JP6744702B2 - Real estate information processing device, calculation method information generation device, real estate information processing, calculation method information generation method, and program - Google Patents

Description

The present invention relates to a real estate information processing device or the like that performs processing such as calculating an assessed amount of real estate.

Conventionally, there has been a system that can calculate an appraisal price without much cost and effort when comparing real estate. Such a system is a case property information recording means in which the evaluation item information and the evaluation price of a case property similar to the assessed property are recorded, an assessed property information recording means in which the evaluation item information of the assessed property is recorded, and the case property information. Evaluation coefficient information of the case property recorded in the recording means, and a correction coefficient group calculation means for calculating a correction coefficient group based on the degree of similarity between the evaluation item information of the assessed property recorded in the assessed property information recording means, An evaluation price calculation means for calculating the evaluation price of the assessed property from the evaluation price of the case property by applying the correction coefficient group to a preset correction arithmetic expression (for example, see Patent Document 1).

JP-A-2003-114924 (page 1, FIG. 1, etc.)

However, in the prior art, since the real estate was not properly classified and the calculation method according to the classification was not adopted, the appraisal price of the real estate could not be calculated appropriately.

The real estate information processing apparatus according to the first aspect of the present invention includes range information indicating a range of each classification parameter that constitutes a classification parameter set, which is a set of one or more parameters used for classifying real estate, and 1 Or calculation method information that can store two or more calculation method information, which is a combination with calculation method specifying information that specifies the calculation method of the assessed amount corresponding to each class specified by the range information of two or more classification parameters A storage unit, an input parameter set receiving unit that receives an input parameter set that is a set of one or more parameters of one real estate, and calculation method specifying information corresponding to a classification parameter set included in the input parameter set. A class deciding unit, a valuation amount obtaining unit that obtains the valuation amount using the calculation method specifying information decided by the class deciding unit, and one or more parameters of the input parameter set; and an output unit that outputs the valuation amount. It is a real estate information processing device comprising.

With this configuration, since the real estate is appropriately classified and the calculation method according to the classification is adopted, the appraisal price of the real estate can be calculated appropriately.

Further, in the real estate information processing device according to the second aspect of the present invention, the calculation method specifying information is a calculation formula in which one or more parameters can be substituted for the first aspect of the invention, and the assessment amount acquisition unit is In the real estate information processing apparatus, one or more parameters of the input parameter set are substituted into a calculation formula that is calculation method specifying information corresponding to the classification parameter set of the above, and the assessed amount is acquired.

With this configuration, the appraisal price of the real estate can be calculated appropriately.

Further, the real estate information processing device of the third aspect of the present invention is the real estate information processing apparatus according to the first or second aspect of the invention, wherein at least two pieces of calculation method identification information out of two or more pieces of calculation method identification information in each of two or more classes are: The real estate information processing device has different types of parameters used.

With this configuration, the appraisal price of the real estate can be calculated appropriately.

Further, the real estate information processing device of the fourth invention is two or more pieces of learning information having two or more parameters and price information with respect to the first invention, and is any one of two or more calculation method specifying information. Further, a learning information storage unit capable of storing two or more pieces of learning information associated with each other is provided, and the appraisal amount acquisition unit is provided for the one or more learning information corresponding to the calculation method identification information determined by the class determination unit. , A real estate information processing apparatus that applies one or more parameters of an input parameter set and acquires an assessed amount.

With this configuration, the appraisal price of the real estate can be calculated appropriately.

The real estate information processing apparatus according to the fifth aspect of the present invention is the real estate information processing apparatus according to any one of the first to fourth aspects, in which the classification parameter set includes a district identifier for identifying an existing district and a use area for identifying a use area. The real estate information processing apparatus is a set of one or more parameters of an identifier, building age information indicating a building age, floor number information indicating a maximum floor number, and walking time information indicating a walking time from a station.

With this configuration, the appraisal price of the real estate can be calculated appropriately.

Further, in the real estate information processing apparatus according to the sixth aspect of the present invention, the appraisal amount acquisition unit calculates and purchases both the purchase price and the rental price of one real estate with respect to any one of the first to fifth inventions. The real estate information processing apparatus is characterized in that a price calculation method and a rental price calculation method are different.

With this configuration, it becomes possible to properly assess the purchase price and rental price of the real estate.

Further, the real estate information processing device according to the seventh invention is different from the sixth invention in that the learning information storage unit is capable of storing two or more pieces of learning information having two or more parameters and rental price information indicating a rental price. The appraisal amount acquisition unit includes an approximate learning information determining unit that determines learning information that is approximate enough to satisfy a predetermined relationship with the input parameter set, and two or more parameters that the learning information that is approximate to the input parameter set has. And a rental price information correction unit that corrects rental price information included in approximate learning information according to the difference between the real estate information processing apparatus and the real estate information processing apparatus.

With this configuration, it becomes possible to properly assess the purchase price and rental price of the real estate.

Further, in the real estate information processing device according to the eighth aspect of the present invention, the learning information is associated with any one of two or more pieces of calculation method specifying information, and the appraisal amount acquisition unit is similar to the seventh aspect. The real estate information processing device corrects the rental price information included in the approximate learning information according to the calculation method specifying information corresponding to the learned information.

With this configuration, it becomes possible to properly assess the purchase price and rental price of the real estate.

The real estate information processing apparatus according to the ninth aspect of the present invention is the real estate information processing apparatus according to any one of the first to eighth aspects, in which the output unit outputs both the selling price and the rental price.

With such a configuration, it is possible to see both the purchase price and the rental price for one real estate.

Further, the calculation method information generation device of the tenth invention is a calculation method information generation device which generates two or more calculation method information with respect to any one of the first to ninth inventions, and has two or more parameters. And a price information, a learning information storage unit that can store two or more pieces of learning information, a parameter identifier receiving unit that receives a parameter identifier that identifies one classification parameter, and a class of n (n is 2 or more) A learning information acquisition unit that acquires from the learning information storage unit one or more pieces of learning information corresponding to each class of the classification parameters that are classified parameters that are identified by the parameter identifier, and learning information acquisition. A calculation formula generation unit that generates a calculation formula that calculates price information by using one or more learning information for each class acquired by the department, and a calculation formula generation unit that generates a calculation formula having a variable that substitutes two or more parameters; The calculation method information generating device further includes a calculation method information output unit that acquires and outputs two or more pieces of calculation method information having calculation method specifying information that is a calculation formula generated by the calculation formula generation unit.

With this configuration, the calculation method information used to calculate the assessed value of the real estate can be automatically generated.

In addition, the calculation method information generation device of the eleventh invention is different from the tenth invention in that the parameter identifier reception unit receives two or more classification parameter identifiers, and the learning information acquisition unit includes two or more classification parameter identifiers. For each metaclass that is a combination of two or more classes of classification parameters identified by the classification parameter identifier, one or more learning information corresponding to each metaclass is acquired from the learning information storage unit, and the calculation formula generation unit A calculation formula for calculating price information by using one or more pieces of learning information acquired by the learning information acquisition unit, and a calculation formula having a variable for substituting two or more parameters, and calculating method information output unit For each metaclass, obtains the calculation method information that is a set of the classification parameter set that is a set of two or more corresponding classification parameters and the calculation method identification information that is the calculation formula generated by the calculation formula generation unit. , A calculation method information generating device for outputting.

With this configuration, the calculation method information used to calculate the assessed value of the real estate can be automatically generated.

Further, the calculation method information generating device according to the twelfth invention is different from the eleventh invention in that the learning information acquisition unit is provided for each of the two or more classification parameters identified by the two or more parameter identifiers. Class classification means for classifying two or more classes, and two or more classes classified by the class classification means for two or more classification parameters identified by two or more parameter identifiers. For the classification, the learning information acquisition unit that acquires one or more learning information for each class from the learning information storage unit, and the calculation formula generation unit include two or more classification parameters identified by two or more parameter identifiers. For each of the two or more classifications of each class, it is a calculation formula for calculating price information using one or more pieces of learning information for each class acquired by the learning information acquisition means. And a calculation formula generation unit for the classification of two or more classes for each of the two or more classification parameters identified by the two or more parameter identifiers. A price calculation means for substituting one or more parameters possessed by one or more learning information belonging to each class into the generated formula of each class to calculate a price and obtain calculated price information indicating the calculated price. For each of the two or more classification parameters identified by the two or more parameter identifiers, for each of the two or more classes, the learning information corresponds to the price information included in the learning information and the price information. Error information acquisition means for acquiring error information indicating the difference from the calculated price information, and for each of two or more classification parameters identified by two or more parameter identifiers, for two or more different classes The learning information acquisition unit includes a class classification determination unit that determines a classification of a class having a smaller error so as to satisfy a predetermined condition by using one or more pieces of error information acquired by the error information acquisition unit. For each metaclass consisting of a combination of one class selected from the above classification parameters, one or more pieces of learning information corresponding to the classification parameters belonging to two or more classes forming each metaclass are acquired from the learning information storage unit. The calculation formula generation means is a calculation formula for calculating price information using one or more pieces of learning information acquired by the learning information acquisition means for each metaclass, and has a variable for substituting two or more parameters. The calculation method information output unit generates, for each metaclass, a classification parameter set, which is a set of two or more corresponding parameters, and a calculation formula generation procedure. The calculation method information generation device acquires and outputs the calculation method information that is a set with the calculation method specifying information that is the calculation formula generated by the step.

With such a configuration, the calculation method information used for calculating the appraisal price of the real estate can be appropriately and automatically generated.

Further, the calculation method information generation device of the thirteenth invention further comprises a class number acceptance unit that accepts the class number (n) for one parameter with respect to any one of the tenth to twelfth inventions. The learning information acquisition unit classifies the parameters identified by the parameter identifiers into the number of classes (n) accepted by the class number acceptance unit, and obtains one or more learning information for each class. It is a device.

With such a configuration, the calculation method information used for calculating the appraisal price of the real estate can be appropriately and automatically generated.

According to the real estate information processing device of the present invention, the appraisal price of the real estate can be calculated appropriately.

The figure which shows the conceptual diagram of the real estate information processing system in Embodiment 1. Block diagram of the real estate information processing system Block diagram of the real estate information processing device Flowchart explaining the operation of the real estate information processing apparatus 1 Flowchart explaining the real estate information collection process Flowchart explaining the aggregation processing Flowchart explaining the same housing diagram information generation process Flowchart explaining the assessment amount accumulation process Flowchart explaining the assessment amount calculation process Figure showing the same real estate information collection rule management table Figure showing the same address normalization rule management table Figure showing the name identification rule management table Diagram showing the real estate information management table Figure showing the same output example Figure showing the same output example Figure showing the same size information classification management table Figure showing the same floor information classification management table Figure showing the same walking fraction information classification management table Figure showing the same age information classification management table Diagram showing the relative position information classification management table for the same floor Figure showing the same rank number information classification management table Diagram showing the same floor plan information classification management table Diagram showing isotropic information classification management table Figure showing the same area identifier classification management table Figure showing the calculation method information management table Figure showing the same output example Block diagram of a calculation method information generation device 4 according to the second embodiment The flowchart explaining the process which determines the class classification of the parameter for the same classification. Flowchart explaining the operation of accumulating the calculation method information Another block diagram of the calculation method information generation device Overview of the computer system in the above embodiment Block diagram of the computer system

Hereinafter, embodiments of a real estate information processing device and the like will be described with reference to the drawings. It should be noted that, in the embodiments, the components denoted by the same reference numerals perform the same operation, and thus the repetitive description may be omitted.

(Embodiment 1)
In the present embodiment, a real estate information processing system including a real estate information processing device capable of automatically calculating a real estate appraisal value will be described.

Further, in the present embodiment, a real estate information processing system capable of outputting real estate information including prices of two or more dwellings in an apartment house in association with the houses in the apartment house will be described.

Further, in the present embodiment, a real estate information processing system capable of outputting price information of a house that is not for sale will be described. The real estate information processing system is a real estate information processing system capable of visually distinguishing a house for sale and a house for sale, and outputting an assessment price and the like.

In addition, a real estate information processing system capable of generating housing diagram information will be described in the present embodiment.

In addition, in the present embodiment, a real estate information processing system capable of performing address normalization processing described later will be described.

Further, in the present embodiment, a real estate information processing system capable of performing a name identification process of a building name described later will be described.

FIG. 1 is a conceptual diagram of the real estate information processing system in this embodiment. The real estate information processing system includes a real estate information processing device 1, one or more server devices 2 and one or more terminal devices 3. The real estate information processing device 1 is a device that processes real estate information and may be of any type such as a so-called cloud server or server device. The server device 2 is a server on the web, and the type of device does not matter. The terminal device 3 is a terminal used by a user who browses real estate information and may be of any type such as a so-called personal computer, tablet terminal, smartphone, or the like.

FIG. 2 is a block diagram of the real estate information processing system in the present embodiment. FIG. 3 is a block diagram of the real estate information processing device 1 that constitutes the real estate information processing system.

The real estate information processing device 1 that constitutes the real estate information processing system includes a storage unit 11, a reception unit 12, a reception unit 13, a processing unit 14, and an output unit 15.

The storage unit 11 includes a housing diagram information storage unit 111, a real estate information storage unit 112, a learning information storage unit 113, and a calculation method information storage unit 114.

The reception unit 13 includes a real estate information reception unit 131 and an input parameter set reception unit 132.

The processing unit 14 includes an apartment house diagram information generation unit 141, a real estate information collection unit 142, an address normalization processing unit 143, a building name processing unit 144, a class determination unit 145, and an assessment amount acquisition unit 146.

The assessed amount acquisition unit 146 includes approximate learning information determination means 1461 and rental price information correction means 1462.

The server device 2 includes a server storage unit 21, a server reception unit 22, and a server transmission unit 23.

The terminal device 3 includes a terminal storage unit 31, a terminal reception unit 32, a terminal processing unit 33, a terminal transmission unit 34, a terminal reception unit 35, and a terminal output unit 36.

The storage unit 11 included in the real estate information processing device 1 can store various kinds of information. The various types of information are, for example, collective housing diagram information, real estate information, learning information, calculation method information, etc., which will be described later.

The housing complex diagram information storage unit 111 can store one or more housing complex diagram information. The collective housing diagram information is information for constructing a collective housing diagram having two or more dwellings. The collective housing map information includes information indicating relative positions of two or more houses. The collective housing diagram information is information for constructing a collective housing diagram. The collective housing diagram information may include a part or all of two or more pieces of real estate information described later. It should be noted that the collective housing map information including real estate information may be referred to as collective housing map information including real estate information. The form of an apartment house may be an apartment, an apartment, or the like. The collective housing diagram information may be a bitmap, vector data, information described in HTML, XML, etc., or information composed of a combination thereof. In other words, the data structure and data format of the housing diagram information does not matter.

The real estate information storage unit 112 can store two or more real estate information. The real estate information is, for example, information on a house in an apartment, information on a single house, and information on a land. Real estate information has one or more parameters. The parameter is, for example, price information that is information about the price of a house. The price information is usually information indicating the assessed price, but may be information indicating the price of the sales result. Further, the parameters are, for example, address information indicating an address, size information indicating a size (for example, 80 m2), floor plan information (for example, 3LDK, 2K, etc.) that is information about a floor plan, and direction information that is a direction for a house. Information (for example, facing south, facing southwest, etc.) and balcony direction information, which is information about the direction of the balcony. In addition, the parameter is, for example, the total number of floors information indicating the total number of floors of a building (usually an apartment complex), the number of minutes walked indicating the number of minutes walked from the nearest station, the information about the number of years built, the relative number of floors belonging to the real estate Belonging position relative position information indicating a specific position, belonging rank information indicating the belonging number, a district identifier for identifying an existing district, a use area identifier for identifying a use area, a management company flag indicating a predetermined management company , A construction company flag indicating that it is a predetermined construction company, a business/management flag indicating that the business company (seller) and the management company are the same or affiliated companies, structural information indicating the structure of the building (for example, SRC , RC, etc.) and building name information indicating the building name of a predetermined brand condominium. In addition, the real estate information may include at-sale price information indicating a price at the time of sale. In addition, it is preferable that the address information includes building name information (a condominium name or the like) indicating the name of the building of the apartment building, room information, and the like. The room information is information indicating the number of the house, such as 501 and 103. In addition, it is preferable that the real estate information has a status flag indicating a sales status indicating whether or not the property is on sale. It is preferable that the parameter is associated with the parameter identifier that identifies the parameter.

The learning information storage unit 113 can store two or more pieces of learning information. The learning information has two or more parameters and price information. The learning information storage unit 113 can store two or more pieces of learning information having two or more parameters and rental price information indicating a rental price. The learning information is usually real estate information. The learning information is usually information about the real estate actually traded.

The parameter here may be called an attribute value of real estate. The parameter is, for example, one or more values among the size information, the total number of floors information, the number of minutes walk information, the age information, the relative position information of the number of floors, the number of floors belonging, and the like. In addition, the parameter may be, for example, an area identifier, a restricted area identifier, or the like.

Further, the price information included in the learning information is usually information indicating the price traded. However, the price information included in the learning information may be information indicating the assessed amount. The price indicated by the price information may be the selling price or the rental price.

Here, the two or more pieces of learning information may be associated with any one of the two or more pieces of calculation method specifying information. That is, the two or more pieces of learning information in the learning information storage unit 113 may be classified into two or more classes.

The calculation method specifying information is information that specifies the method of calculating the assessed amount. The calculation method specifying information is, for example, a calculation formula in which one or more parameters can be substituted. Further, the calculation method specifying information may be, for example, a class identifier that identifies a class to which the learning information belongs. The calculation method specifying information may be, for example, one or more pieces of learning information.

The calculation method information storage unit 114 can store two or more pieces of calculation method information. The calculation method information is a set of range information indicating the range of one or more classification parameters and calculation method specifying information. The classification parameter is a parameter used for classifying real estate. The one or more classification parameters are referred to as a classification parameter set. It should be noted that the class is a classification, and includes a metaclass described later.

The classification parameters include, for example, size information, total floor number information, walking minutes information, building age information, belonging floor relative position information, belonging floor information, and a customer identifier indicating a customer target of real estate. Further, the range information corresponding to the size information is, for example, six, and, for example, "1 to 19,""20 to 29,""30 to 49,""50 to 69,""70 to 89,""90to." (All units are square meters). Further, the range information corresponding to the total floor number information is, for example, seven, and is, for example, “3 to 4”, “5 to 9”, “10 to 14,” “15 to 19,” “20 to 27,” “28 to 39. "40-" (all units are floors). Further, the range information corresponding to the walking fraction information is, for example, six, and for example, “1-2 minutes”, “3-5 minutes”, “6-7 minutes”, “8-10 minutes”, “11-15 minutes”. "15 minutes or more". Further, the range information corresponding to the age information is, for example, three, for example, “1-12 years”, “13-23 years”, and “24 years or more”. Further, the range information corresponding to the belonging floor relative position information is, for example, five, and is, for example, “less than 1/3”, “1/3 or more, 1/2 or less”, “greater than 1/2, 2/3”. "Smaller", "2/3 or more, less than 0.9", "0.9 or more". In addition, the relative position information of the belonging floors is calculated by, for example, “the belonging floors of the real estate/the total floors of the building”. Further, the range information corresponding to the belonging floor number information is, for example, five, and is, for example, “first floor”, “second floor”, “third floor”, “substantially top floor”, and “others”. The “substantially the highest floor” is, for example, the relative floor position information of the belonging floor is 0.9 or more. Moreover, "other than that" is other than "1st floor", "2nd floor", "3rd floor", and "approximately the top floor". Further, the range information corresponding to the customer identifier is, for example, three, and is, for example, “for one person”, “for two persons”, and “for family”.
When the range information corresponding to the customer identifier is used as the classification parameter, for example, in the case of "only for one person living (for one person)", it is particularly important that it is close to the station and the equipment is not so important. However, equipment is important for "family-friendly". That is, since the parameter to be emphasized is different depending on the range information (market) corresponding to the customer identifier, it is preferable that the calculation method specifying information is different for each market.

The receiving unit 12 receives instructions, information and the like from the server device 2 or the terminal device 3. The instruction or information is, for example, all or a part of the real estate information received from the server device 2. Further, the instruction or information is, for example, an instruction to output the housing diagram information received from the terminal device 3. The output instruction of the collective housing diagram information is an instruction to output the collective housing diagram information. The output instruction of the collective housing diagram information usually has a collective housing identifier for identifying the collective housing. The collective housing identifier is, for example, an ID or a collective housing name (for example, an apartment name, an apartment name, etc.). Further, the instruction, information and the like are, for example, an instruction to output real estate information received from the terminal device 3. The real estate information output instruction is one real estate information output instruction.

The reception unit 13 receives instructions, information, and the like. The received instruction or information is, for example, all or part of real estate information, or an input parameter set described later.

The real estate information reception unit 131 receives all or part of one or more real estate information.

The input parameter set reception unit 132 receives an input parameter set that is a set of one or more parameters of one real estate.

The input parameter set reception unit 132 may receive a real estate identifier for identifying a real estate, and may search the input parameter set in the recording medium using the real estate identifier as a key.

The input parameter set includes, for example, the following parameters in addition to the classification parameter set. The input parameter set includes, for example, a management company identifier for identifying a management company, information indicating whether or not a manager is resident, information indicating a management form (whether or not all management companies are entrusted), building structure (for example, , RC, SRC, etc.), information on the number of nearest routes, information on the number of rooms in a housing complex, a consignment company identifier for identifying a consignment company, orientation information, and the like.

Any means such as a keyboard, a mouse, or a menu screen may be used as the input means for the instructions and information. The reception unit 13 and the like can be realized by a device driver of input means such as a keyboard, control software for a menu screen, and the like.

In addition, reception means reception of information input from an input device such as a keyboard, mouse, or touch panel, reception of information transmitted via a wired or wireless communication line, a recording medium such as an optical disk, a magnetic disk, or a semiconductor memory. It is a concept including acceptance of information read from the.

The processing unit 14 performs various kinds of processing. The various types of processing include, for example, the housing diagram information generation unit 141, the real estate information collection unit 142, the address normalization processing unit 143, the building name side processing unit 144, the class determination unit 145, the assessment amount acquisition unit 146, the approximate learning information determination. This is processing performed by the means 1461, rental price information correction means 1462, and the like.

The collective housing diagram information generation unit 141 generates collective housing diagram information using one or more attribute values of each real estate information of two or more houses of two or more houses in one collective housing. Here, the generation may be generation of a part of the collective housing diagram information or generation of the whole.

The collective housing diagram information generation unit 141 generates, for example, the collective housing diagram information in a mode in which the number of floors of the house can be visually determined by using the floor number information included in each real estate information. Here, the mode in which the number of floors of the house can be visually determined is, for example, that the number of floors is displayed. The mode in which the number of floors of a house can be visually determined is, for example, when a plurality of floors of houses are displayed, the house map information is arranged at a position indicating the number of floors. The house map information is information on the area of each house. The house map information usually has information about a line indicating a boundary with another house. The information on the line may be a line or information on points (usually, four points forming a rectangle) indicating a residential area.

The collective housing diagram information generation unit 141 generates, for example, collective housing diagram information in a mode that visually indicates the size of a house according to the size information included in each real estate information. Here, the aspect of visually indicating the size of the house is, for example, displaying the real estate information of each house in the size of the area of the house corresponding to the size of the house. In addition, the collective housing diagram information of a mode that visually indicates the size of the house indicates the area of each house so that the area of the house has a different area according to the size information included in the real estate information. It is the information on the housing diagram.

The collective housing diagram information generation unit 141 arranges the area of each residence using the room information included in each real estate information, and generates the collective housing diagram information, for example. For example, the collective housing diagram information generation unit 141 arranges each residence diagram information (residential area) in the order of the number indicated by the room information included in each real estate information.

The collective housing diagram information generation unit 141 arranges the area of each residence using the direction information included in each real estate information, and generates the collective housing diagram information, for example. The housing diagram information generation unit 141 arranges the housing diagram information and generates the housing diagram information, for example, such that the areas of the houses corresponding to the real estate information having the same direction information are combined. .. In addition, the collective housing diagram information generation unit 141 arranges each house diagram information at a position corresponding to the direction indicated by the direction information of each real estate information, and generates the collective house diagram information, for example.

The real estate information collecting unit 142 acquires all or part of the real estate information of one or more residences from one or more server devices 2 on the web. The real estate information collecting unit 142 usually obtains all or part of real estate information including information matching a predetermined pattern or a predetermined character string from one or more predetermined web pages. .. The real estate information collecting unit 142 usually acquires all or part of the real estate information of one or more dwellings by crawling on the web.

The real estate information collecting unit 142 may receive all or part of the real estate information of one or more residences from one or more server devices 2. In addition, the real estate information collection unit 142 receives one or more web pages from one or more server devices 2, and from the received one or more web pages, information that matches a predetermined pattern or predetermined information. All or part of the real estate information including the obtained character string may be extracted.

The predetermined pattern is, for example, a tag pattern indicated by the tag pattern information or a character string pattern indicated by the character string pattern information.

The address normalization processing unit 143 performs address normalization processing on two or more pieces of address information. The address normalization processing means that when two or more pieces of address information included in two or more pieces of real estate information stored in the real estate information storage unit 112 satisfy a predetermined condition, the two or more pieces of address information are set to the same address. This is the process of setting the information. The process of making the information indicating the same address is the process of replacing the character strings so as to be the same address, for example, the process of replacing the character strings indicating the two or more addresses that can be determined to be the same, and the process of determining the same. A process of establishing a link between two or more addresses that can be made, a process of forming a database (information group) of fluctuations of notations of two or more addresses that can be determined to be the same, and the like.

Here, the predetermined condition is, for example, that the Arabic numeral and the corresponding Chinese numeral are regarded as the same and have the same character string. In addition, the determined condition is, for example, that the half-width number and the same full-width number as the half-width number are considered to be the same and are the same character string. Further, the determined condition is, for example, that the characters between the numbers indicating "chome", "address" and "go" (for example, "-", "no", "chome", etc.) are regarded as the same. The above is the same character string. In other words, "1-2-3", "1-2-3", "1-2-3", "1-2-3", "1-2-3" of "Ding/Address/Go" are the same, respectively. To consider.

Further, the predetermined condition may be that the same character string is obtained after applying the replacement rule of one or more characters. Character replacement rules are, for example, rules for replacing Chinese numerals with Arabic numerals, rules for replacing half-width characters with full-width characters, and rules for replacing "chome", "address" and "go" with "-", etc. Is.

The building name proximity processing unit 144 performs a building name proximity processing on two or more building name information. The building name information is information indicating the name of the building of an apartment house such as an apartment or an apartment. The building name matching process is, when two or more building name information stored in the two or more real estate information stored in the real estate information storage unit 112 satisfies a predetermined condition, sets the two or more building name information to the same building. This is a process of setting information indicating a name. The process of making the information indicating the same building name is a process of replacing a character string so as to make the same building name, for example, unifying two or more building name information that can be judged to be the same, it is judged to be the same A process of establishing a link between two or more building name information that can be performed, a process of forming a database (information group) of fluctuations of notation of two or more building name information that can be determined to be the same, and the like.

Further, the predetermined condition here is, for example, when “e” and “e”, “bu” and “ve”, or “u” and “u” are the same characters. , Are the same character string. Further, the predetermined condition is that the same character string is obtained, for example, when the last "-" is removed from the character string.

The class determination unit 145 determines one calculation method specifying information in the calculation method information storage unit 114. The class determination unit 145 determines the calculation method specifying information corresponding to the classification parameter set included in the input parameter set.

The class determination unit 145 applies, for example, each classification parameter included in the classification parameter set included in the input parameter set to the corresponding range information, and calculates the calculation method specifying information corresponding to one or more matching range information. , Determine the calculation method specific information used to calculate the assessed amount.

The appraisal amount acquisition unit 146 acquires the appraisal amount using the calculation method specifying information determined by the class determination unit 145 and one or more parameters of the input parameter set. The assessed amount is selling price information indicating a selling price and/or rental price information indicating a rental price. Further, obtaining the assessed amount is to obtain price information indicating the price.

The appraisal amount acquisition unit 146, for example, substitutes one or more parameters of the input parameter set into a calculation formula that is the calculation method specifying information corresponding to the classification parameter set of the input parameter set to acquire the appraisal amount. To do. One or more parameters of the input parameter set are parameters that can be substituted into the variables of the calculation formula.

The appraisal amount acquisition unit 146 applies the one or more parameters of the input parameter set to the one or more learning information corresponding to the calculation method specifying information determined by the class determination unit 145 to acquire the appraisal amount, for example. To do. The appraisal amount acquisition unit 146 uses, for example, one or more learning information corresponding to the calculation method specifying information determined by the class determination unit 145 as teacher data, and inputs one or more parameters of the input parameter set as a machine data. Price information corresponding to one or more parameters of the input parameter set is acquired by a learning algorithm. The machine learning algorithm is, for example, SVR, but other algorithms such as a decision tree may be used. The other algorithm may be AROW (Adaptive Regularization of Weight Vectors). For AROW, for example, see "URL: http://webee.technion.ac.il/people/koby/publications/arow_nips09.pdf#search='Adaptive+Regularization+of+Weight+Vectors'".

It is preferable that the assessed amount acquisition unit 146 calculates both the purchase price and the rental price of one real estate.

When calculating the rental price, the appraisal amount acquisition unit 146 modifies the rental price information included in the approximate learning information according to the calculation method specifying information corresponding to the learning information approximate to the real estate information for calculating the rental price, for example. To do. That is, the assessed amount acquisition unit 146 corrects the price information included in the approximate learning information by different methods according to the class corresponding to the approximate learning information. Note that different methods include using different formulas, using different information, and the like.

The appraisal amount acquisition unit 146 may substitute one or more parameters included in the real estate information into a calculation formula, which is calculation method information corresponding to the real estate information, to calculate the rental price of the real estate corresponding to the real estate information.

Further, the appraisal amount acquisition unit 146 inputs one or more parameters of the real estate information of the real estate as one or more learning information as teacher data, and inputs one or more parameters of the real estate information into one or more parameters of the real estate information by the machine learning algorithm. The corresponding rental price information may be acquired. The machine learning algorithm is, for example, SVR, but other algorithms such as a decision tree may be used. Further, the other algorithm may be the AROW described above.

Further, the appraisal amount acquisition unit 146 uses one or more learning information approximate to the real estate information for calculating the rent price as teacher data, and inputs one or more parameters of the real estate information of the real estate, by a machine learning algorithm, Rental price information corresponding to one or more parameters of real estate information may be acquired.

The approximate learning information determination means 1461 determines the learning information that is approximated to the extent that the predetermined relationship with the input parameter set is satisfied. The approximate learning information determination unit 1461, for example, resembles the first vector data, which is a set of input parameters, and the second vector data of two or more, each of which has two or more parameters of each learning information of the learning information storage unit 113. Degree is calculated, and learning information corresponding to the second vector data having the closest similarity to the first vector data is acquired. The algorithm for the approximate learning information determining unit 1461 to determine the learning information that is approximate enough to satisfy a predetermined relationship with the input parameter set is a method based on the k-nearest neighbor method (method of calculating cosine value between vectors, Euclidean distance). Method) and the like.

The rental price information correction unit 1462 corrects the price information (here, usually the rental price information) included in the approximate learning information according to the difference between the input parameter set and the two or more parameters included in the approximate learning information. ..

It is preferable that the rental price information correcting unit 1462 corrects the price information by a different method if the calculation method specifying information corresponding to two or more parameters included in the input parameter set or the approximate learning information is different.

When calculating the selling price of a used property, the appraisal amount acquisition unit 146 determines the class of the real estate information of the real estate whose price is to be calculated, and acquires the sales price information by using the calculation formula corresponding to the class. When calculating the rent price of a real estate by adopting the first method, the approximate learning information is selected, the rent price information contained in the learning information is corrected, and the rent price information of the real estate is acquired. It is preferable to adopt the method.

The output unit 15 outputs the price information included in each of the two or more real estate information in the real estate information storage unit 112 in the diagram of the apartment house indicated by the apartment house map information in association with each residence corresponding to each real estate information. To do. That is, the output unit 15 outputs the collective housing diagram information so that the information such as the price information is included in the area of each of the two or more houses. One or more of the number of floors indicated by the floor number information, the number of the room information, the direction indicated by the direction information, and the size indicated by the size information in the area of each house in the housing diagram information output by the output unit 15. It is preferable that the information of (1) is included in a visually recognizable manner.

The output unit 15 associates the price information included in each of the two or more real estate information items corresponding to the apartment house diagram information in the diagram of the apartment house indicated by the apartment house diagram information with each house corresponding to each real estate information item. Output.

The output unit 15 outputs the collective housing diagram information using the status flag so that the sales status of the residence corresponding to each of the two or more real estate information can be visually recognized. Visually recognizing the sales status means, for example, changing the background of the area displaying the real estate information, changing the character color of the real estate information, etc., according to the status flag.

The output unit 15 outputs the assessed amount. It is preferable that the output unit 15 outputs both the selling price information and the rental price information. The sales price information and the rental price information are usually information indicating the assessed amount, but may be information indicating the actual contract amount.

Here, the output is usually transmission to the terminal device 3. However, output means display on a display, projection using a projector, printing with a printer, sound output, transmission to an external device, storage on a recording medium, processing to another processing device or other program, etc. It is a concept that includes delivery of results.

The server storage unit 21 included in the server device 2 may store one or more web pages. Web pages typically include all or part of one or more real estate information. The definition format of real estate information on the web page does not matter.

The server receiving unit 22 receives a transmission instruction of all or part of real estate information from the real estate information processing device 1. The server receiving unit 22 may also receive a web page transmission instruction from the real estate information processing device 1.

The server transmission unit 23 transmits all or a part of one or more real estate information stored in the server storage unit 21 to the real estate information processing device 1. The server receiving unit 22 may transmit one or more web pages stored in the server storage unit 21 to the real estate information processing device 1. When the server receiving unit 22 transmits the web page to the real estate information processing device 1, the processing unit 14 of the real estate information processing device 1 extracts all or part of one or more real estate information from the web page.

The terminal storage unit 31 included in the terminal device 3 can store various kinds of information. The various information is, for example, a terminal identifier. The terminal identifier is information for identifying the terminal device 3 or information for identifying the user of the terminal device 3.

The terminal reception unit 32 receives instructions, information, and the like. The instructions, information, etc. are instructions for transmitting all or a part of real estate information, instructions for transmitting collective housing diagram information, instructions for transmitting a web page, and the like.

Any means such as a keyboard, a mouse, or a menu screen may be used as the input means for the instructions and information. The terminal reception unit 32 can be realized by a device driver of input means such as a keyboard or control software for a menu screen.

The terminal processing unit 33 performs various kinds of processing. The various processes are, for example, to make the data structure for transmitting the instructions and information received by the terminal receiving unit 32.

The terminal transmission unit 34 transmits various instructions and information to the real estate information processing device 1. The various instructions, information, and the like are, for example, instructions for transmitting collective housing diagram information.

The terminal receiving unit 35 receives from the real estate information processing device 1 real estate information of 2 or more and housing diagram information. It should be noted that the real estate information of 2 or more and the housing diagram information is referred to as housing information including real estate information as appropriate.

The terminal output unit 36 outputs the real estate information-containing housing diagram information received by the terminal receiving unit 35. The terminal output unit 36 normally outputs the price information included in each piece of real estate information of two or more in the diagram of the apartment house indicated by the apartment house diagram information in a manner of associating the price information with each residence corresponding to each real estate information. The output here is usually a display on a display, but projection using a projector, printing by a printer, sound output, transmission to an external device, storage in a recording medium, other processing device or other It is a concept that includes the delivery of processing results to other programs.

The storage unit 11, the housing complex diagram information storage unit 111, the real estate information storage unit 112, the learning information storage unit 113, the calculation method information storage unit 114, the server storage unit 21, and the terminal storage unit 31 are preferably non-volatile recording media. However, a volatile recording medium can also be used.

The process of storing information in the storage unit 11 or the like does not matter. For example, information may be stored in the storage unit 11 or the like via a recording medium, or information transmitted via a communication line or the like may be stored in the storage unit 11, or The information input via the input device may be stored in the storage unit 11 or the like.

Processing unit 14, housing diagram information generation unit 141, real estate information collection unit 142, address normalization processing unit 143, building name processing unit 144, class determination unit 145, assessment amount acquisition unit 146, approximate learning information determination unit 1461, rental The price information correction unit 1462 and the terminal processing unit 33 can be usually realized by an MPU, a memory or the like. The processing procedure of the processing unit 14 and the like is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

The output unit 15, the server transmission unit 23, and the terminal transmission unit 34 are usually realized by wireless or wired communication means, but may be realized by broadcasting means.

The receiving unit 12, the server receiving unit 22, and the terminal receiving unit 35 are usually realized by wireless or wired communication means, but may be realized by means of receiving broadcast.

The terminal output unit 36 may or may not be considered to include an output device such as a display or a speaker. The terminal output unit 36 can be realized by driver software of an output device or driver software of an output device and an output device.

Next, the operation of the real estate information processing device 1 that constitutes the real estate information processing system will be described using the flowchart in FIG.

(Step S401) The real estate information reception unit 131 determines whether or not all or part of the real estate information has been received. If accepted, go to step S402, and if not accepted, go to step S403.

(Step S402) The processing unit 14 accumulates all or part of the real estate information received in Step S401 in the real estate information storage unit 112. It returns to step S401. In addition, it is preferable that the real estate information is accumulated in association with an apartment house identifier for identifying an apartment house.

(Step S403) The real estate information collection unit 142 determines whether or not it is a crawling timing for collecting real estate information. If it is the crawling timing, the procedure proceeds to step S404, and if it is not the crawling timing, the procedure proceeds to step S405.

(Step S404) The real estate information collecting unit 142 collects real estate information. It returns to step S401. The real estate information collection process will be described with reference to the flowchart of FIG.

(Step S405) The receiving unit 12 determines whether or not an output instruction of the housing diagram information is received from the terminal device 3. If the instruction to output the information on the housing diagram is received, the process proceeds to step S406. If the instruction to output the information on the housing diagram is not received, the process proceeds to step S408.

(Step S406) The collective housing diagram information generation unit 141 generates collective housing diagram information of the collective housing corresponding to the output instruction of the collective housing diagram information. The collective housing diagram information generation process will be described with reference to the flowchart of FIG. 7.

(Step S407) The output unit 15 transmits the collective housing diagram information generated in step S406 to the terminal device 3 that has transmitted the output instruction of the collective housing diagram information. It returns to step S401.

(Step S408) The processing unit 14 determines whether or not it is time to calculate the assessed amount of the real estate. If it is the time to calculate the assessed amount, the process proceeds to step S409, and if it is not the time to calculate the assessed amount, the process returns to step S401. It should be noted that the timing of calculating the assessed amount of the real estate does not matter, for example, when a predetermined time comes.

(Step S409) The appraisal amount acquisition unit 146 calculates and accumulates the appraisal amount of one or more real estate. The assessed amount accumulating process will be described with reference to the flowchart of FIG.

In the flowchart of FIG. 4, the collective housing map information generation unit 141 generates the collective housing map information in response to the received output instruction of the collective housing map information. However, the collective housing diagram information generation unit 141 may generate one or more collective housing diagram information in advance and store the information in the collective housing diagram information storage unit 111. In such a case, it is preferable that the collective housing diagram information corresponds to the collective housing identifier.

Further, in the flowchart of FIG. 4, the process is ended by turning off the power or interrupting the process.

Next, the real estate information collection process of step S404 will be described using the flowchart of FIG.

(Step S501) The real estate information collection unit 142 substitutes 1 into the counter i.

(Step S502) The real estate information collection unit 142 determines whether or not there is an i-th web page for which real estate information should be collected. If the i-th web page exists, the procedure proceeds to step S503, and if the i-th web page does not exist, the procedure proceeds to step S510. It should be noted that whether or not the i-th web page exists is determined by, for example, whether or not the i-th URL exists in the storage unit 11. In addition, the real estate information collection unit 142 may determine whether or not the i-th website for which real estate information should be collected exists.

(Step S503) The real estate information collection unit 142 acquires the i-th web page.

(Step S504) The real estate information collection unit 142 substitutes 1 into the counter j.

(Step S505) The real estate information collecting unit 142 determines whether or not the j-th rule for collecting real estate information exists. If the j-th rule exists, the procedure proceeds to step S506, and if the j-th rule does not exist, the procedure proceeds to step S509.

Note that one or more rules for collecting real estate information are normally stored in the storage unit 11. It goes without saying that the one or more rules stored in the storage unit 11 may be embedded in the program. Further, it is preferable that each of the one or more rules is managed in association with a URL of a web page from which real estate information should be collected. Further, the rule is, for example, an appearance pattern of a tag of a description language such as HTML or XML, a pattern of a character string of address information included in real estate information (for example, ".*' city|road|prefect|prefecture'.*' town" '[1-9]' chome|-|'s|No' [1-9][0-9]*' No.|-|'s'[1-9][0-9]*' No.|- |no|no'").

(Step S506) The real estate information collection unit 142 acquires all information that matches the j-th rule from the i-th web page. The acquired information is usually all or part of real estate information.

(Step S507) The real estate information collection unit 142 stores the information acquired in Step S506 in the real estate information storage unit 112. It is preferable that the real estate information collection unit 142 store the information acquired in step S506 in the real estate information storage unit 112 in association with the collective housing identifier.

(Step S508) The real estate information collection unit 142 increments the counter j by 1. It returns to step S505.

(Step S509) The real estate information collection unit 142 increments the counter i by 1. It returns to step S502.

(Step S510) The real estate information collection unit 142 performs a consolidation process of real estate information. The aggregation process will be described with reference to the flowchart of FIG. Further, the aggregation process is a process for handling a plurality of real estate information of the same residence as one real estate information.

Next, the aggregation processing in step S510 will be described using the flowchart in FIG.

(Step S601) The address normalization processing unit 143 substitutes 1 into the counter i.

(Step S602) The address normalization processing unit 143 determines whether or not the i-th real estate information exists in the newly collected real estate information or the real estate information storage unit 112. If the i-th real estate information exists, the procedure goes to step S603, and if the i-th real estate information does not exist, the procedure goes to step S605.

(Step S603) The address normalization processing unit 143 replaces the character to be replaced in the address information of the i-th real estate information according to the replacement rule of one or more characters.

(Step S604) The address normalization processing unit 143 increments the counter i by 1. It returns to step S602.

(Step S605) The address normalization processing unit 143 substitutes 1 into the counter i.

(Step S606) The address normalization processing unit 143 determines whether or not the i-th unprocessed real estate information is present in the newly collected real estate information or the real estate information storage unit 112. If the i-th unprocessed real estate information exists, the process proceeds to step S607, and if the i-th unprocessed real estate information does not exist, the process returns to the upper process.

(Step S607) The address normalization processing unit 143 searches the i-th unprocessed real estate information and other real estate information having address information that is more similar to satisfy a predetermined condition.

(Step S608) The address normalization processing unit 143 substitutes 1 for the counter j.

(Step S609) The address normalization processing unit 143 determines whether or not the j-th other real estate information exists among the other real estate information acquired in step S607. If the j-th other real estate information exists, the procedure goes to step S610, and if it does not exist, the procedure goes to step S610.

(Step S610) When the j-th other real estate information and the i-th unprocessed real estate information have a building name, the building name adjunct processing unit 144 determines the j-th other real estate information or the i-th unprocessed real estate information. Real estate information or building name processing of real estate information of both is performed. Here, the building name matching process is, for example, a process of replacing the characters forming the building name according to the character replacement rule.

(Step S611) The address normalization processing unit 143 determines whether or not the address information included in the i-th unprocessed real estate information and the address information included in the j-th other real estate information are the same address information. To do. If the information is the same address, the procedure goes to step S612. If the information is not the same address, the procedure goes to step S613.

(Step S612) The address normalization processing unit 143 performs processing for collecting the i-th unprocessed real estate information and the j-th other real estate information.

(Step S613) The address normalization processing unit 143 increments the counter j by 1. It returns to step S609.

(Step S614) The address normalization processing unit 143 increments the counter i by 1. It returns to step S606.

Next, the housing diagram information generation process of step S406 will be described with reference to the flowchart of FIG.

(Step S701) The housing diagram information generation part 141 substitutes 1 at the counter i.

(Step S702) The housing diagram information generation unit 141 determines whether or not the i-th housing exists. If the i-th housing complex is present, the process proceeds to step S703, and if the i-th housing complex is not present, the process returns to the upper processing. For example, the collective housing diagram information generation unit 141 determines whether or not the ith collective housing exists depending on whether or not the ith collective housing identifier exists in the real estate information storage unit 112.

(Step S703) The housing complex diagram information generation unit 141 acquires all real estate information of the i-th housing complex from the real estate information storage unit 112. The collective housing diagram information generation unit 141 acquires, for example, all real estate information corresponding to the i-th collective housing identifier from the real estate information storage unit 112.

(Step S704) The housing diagram information generation unit 141 substitutes 1 into the counter j.

(Step S705) The housing diagram information generation unit 141 determines whether or not the jth floor exists in the i-th housing complex. If the jth floor exists, the procedure proceeds to step S706, and if the jth floor does not exist, the procedure proceeds to step S714.

(Step S706) The housing diagram information generation unit 141 inspects information corresponding to the number of floors in each address information corresponding to the i-th housing complex, and acquires one or more address information on the jth floor. Then, the housing diagram information generation unit 141 sorts one or more pieces of address information on the jth floor. Note that the sorting is performed by using the numeric string corresponding to the room of the residence to sort the real estate information in ascending or descending order.

(Step S707) The housing diagram information generation unit 141 substitutes 1 into the counter k.

(Step S708) The housing complex diagram information generation unit 141 determines whether or not the kth real estate information on the jth floor exists. If the k-th real estate information on the j-th floor exists, the procedure proceeds to step S709, and if the k-th real-estate information on the j-th floor does not exist, the procedure proceeds to step S711.

(Step S709) The housing complex diagram information generating unit 141 generates house diagram information having an area of a size corresponding to the size information of the kth real estate information on the jth floor. The collective housing diagram information generation unit 141 adds the price information included in the kth real estate information on the jth floor to the housing diagram information. In addition, the collective housing diagram information generation unit 141 generates house diagram information such that the state flag included in the kth real estate information on the jth floor can be visually shown. Go to step S712.

(Step S710) The housing diagram information generation unit 141 determines whether or not there is unprocessed real estate information on the jth floor. If unprocessed real estate information on the jth floor exists, the process proceeds to step S712, and if not, the process proceeds to step S715.

(Step S711) The housing diagram information generation unit 141 acquires dummy dwelling diagram information. Go to step S710. The dummy house map information is real estate information indicating that there is no information. The dummy house map information may be stored in the storage unit 11 in advance. Further, the collective housing diagram information generation unit 141 may generate a number string indicating the k number on the jth floor corresponding to the kth number and add it to the dummy house diagram information.

(Step S712) The housing diagram information generation unit 141 arranges the housing diagram information generated in step S709 at a position corresponding to the k-th position on the jth floor, which is the position in the housing diagram information. The arrangement at the k-th position on the j-th floor means that the position where the area corresponding to the house map information is arranged is the position indicating the k-th (k-th number) on the j-th floor. It is that you are.

(Step S713) The housing diagram information generation unit 141 increments the counter i by 1. It returns to step S708.

(Step S714) The housing diagram information generation unit 141 increments the counter i by 1. It returns to step S702.

(Step S715) The housing diagram information generation unit 141 increments the counter j by 1. It returns to step S705.

In the flowchart of FIG. 7, the collective housing map information generation unit 141 may generate the collective housing map information also using the floor number information, floor plan information, direction information, and the like included in the real estate information.

Next, the assessed amount accumulation process of step S409 will be described with reference to the flowchart of FIG.

(Step S801) The assessed amount acquisition unit 146 substitutes 1 into the counter i.

(Step S802) The assessment amount acquisition unit 146 determines whether or not the i-th real estate information subject to assessment exists. If the i-th real estate information exists, the process proceeds to step S803, and if the i-th real estate information does not exist, the process returns to the upper processing. Note that, here, for example, the real estate information to be assessed is real estate information in the real estate information storage unit 112, and is real estate information that does not have price information.

(Step S803) The input parameter set reception unit 132 acquires an input parameter set that is one or more parameters included in the i-th real estate information.

(Step S804) The assessed amount acquisition unit 146 acquires a classification parameter set that is one or more predetermined classification parameters from the input parameter set acquired in step S803.

(Step S805) The class determination unit 145 determines the calculation method specifying information corresponding to the classification parameter set included in the input parameter set. The class determination unit 145 usually selects the calculation method specifying information corresponding to the range information in which one or more classification parameters match.

(Step S806) The appraisal amount acquisition unit 146 acquires the appraisal amount using the calculation method specifying information determined by the class determination unit 145 and one or more parameters in the input parameter set. The assessment amount calculation process will be described with reference to the flowchart of FIG. Here, the assessed amount acquisition unit 146 calculates one or more assessed amounts of the assessed amount of the selling price and the assessed amount of the rental price.

(Step S807) The assessed amount acquisition unit 146 accumulates the price information indicating the assessed amount calculated in step S806 in the i-th real estate information. It is preferable that the assessed amount acquisition unit 146 also stores an identifier indicating the selling price or the rental price in association with the price information.

(Step S808) The assessed amount acquisition unit 146 increments the counter i by 1. It returns to step S802.

Next, the assessment amount calculation process of step S806 will be described with reference to the flowchart of FIG.

(Step S901) The assessment amount acquisition unit 146 calculates the assessment amount using the calculation method specifying information determined by the class determination unit 145 and one or more parameters of the input parameter set. The appraisal amount acquisition unit 146 acquires, for example, a calculation formula that is the calculation method specifying information determined by the class determination unit 145 from the calculation method information storage unit 114, and adds the calculation formula of the input parameter set to the calculation formula. Substituting the corresponding parameter for each of the one or more variables that constitute it, and executing the calculation formula. Then, the assessed amount acquisition unit 146 obtains the price information. The price information here is, for example, an appraisal amount of the selling price.

(Step S902) The appraisal amount acquisition unit 146 determines whether or not to calculate the rental price. If the rental price is calculated, the process goes to step S903, and if the rental price is not calculated, the process returns to the upper process. The criteria for determining whether to calculate the rental price does not matter. The rent price may be calculated when the real estate information does not have the rent price, or the rent price may always be calculated.

(Step S903) The appraisal amount acquisition unit 146 determines the learning information having the vector data of the parameter group that is most approximate to the vector data configured by the input parameter set. The determined learning information is learning information in the learning information storage unit 113.

(Step S904) The assessment amount acquisition unit 146 acquires the rental price information included in the learning information determined in step S903.

(Step S905) The appraisal amount acquisition unit 146 acquires a difference information group which is a set of information on the difference between the vector data constituted by the input parameter set and the vector data of the parameter group.

(Step S906) The assessed amount acquisition unit 146 substitutes 1 into the counter i.

(Step S907) The assessed amount acquisition unit 146 determines whether or not the i-th difference information exists in the difference information group acquired in step S905. If the i-th difference information exists, the process returns to the upper process if the i-th difference information does not exist.

(Step S908) The appraisal amount acquisition unit 146 corrects (corrects) the rental price information using the i-th difference information by a correction method corresponding to the class. The correction method corresponding to the class may be referred to as the correction method corresponding to the calculation method specifying information. The different correction methods include different correction expressions and different correction degrees.

(Step S909) The assessed amount acquisition unit 146 increments the counter i by 1. It returns to step S907.

In the flowchart of FIG. 9, only the rental price information may be calculated. The method of calculating the rental price information may be the same method as the method of calculating the selling price, instead of the method shown in FIG. 9 (the method of correcting the price information after determining the approximate real estate information).

Further, the method of calculating the sales price in the flowchart of FIG. 9 may be a method of determining the approximate real estate information and then correcting the price information (the rental price calculating method of FIG. 9). In addition, the method of calculating the price is real estate information that is approximate enough to satisfy a predetermined condition, and when real estate information that has price information exists, determine the approximate real estate information and then correct the price information. If the real estate information does not exist, the method of calculating the selling price in FIG. 9 may be used.

Next, the operation of the server device 2 will be described. The server receiving unit 22 of the server device 2 receives a web page transmission instruction from the real estate information processing device 1. Then, the server transmission unit 23 transmits the web page stored in the server storage unit 21 to the real estate information processing device 1.

Next, the operation of the terminal device 3 will be described. The terminal accepting unit 32 of the terminal device 3 accepts instructions, information, and the like. Next, the terminal processing unit 33 sets the data structure for transmitting the instructions, information, and the like received by the terminal receiving unit 32. The terminal transmission unit 34 transmits various instructions and information to the real estate information processing device 1.

The terminal receiving unit 35 receives one or more real estate information from the real estate information processing device 1. Alternatively, the terminal receiving unit 35 receives, from the real estate information processing device 1, two or more real estate information and housing diagram information. Then, the terminal output unit 36 outputs the one or more real estate information received by the terminal receiving unit 35, or the real estate information-containing housing diagram information. The collective housing map information including real estate information is collective housing map information having two or more real estate information.

Hereinafter, a specific operation of the real estate information processing system according to the present embodiment will be described. A conceptual diagram of the real estate information processing system is shown in FIG.

Now, the storage unit 11 of the real estate information processing apparatus 1 holds the real estate information collection rule management table shown in FIG. The real estate information collection rule management table manages real estate information collection rules for each website or web page. The real estate information collection rule management table stores one or more records having “ID”, “URL”, “item”, and “collection rule information”. "ID" is information for identifying a record. “URL” indicates a web page to be crawled. The “item” is information that constitutes real estate information. The “collection rule information” is information indicating a rule for collecting information (items) that constitutes real estate information.

The “collection rule information” is tag pattern information, character string pattern information, or tag pattern information and character string pattern information. The tag pattern information indicates a tag pattern in a description language such as HTML or XML. In addition, "$" in the tag pattern information indicates a variable and indicates a character string to be acquired. In other words, the item "Address" of "ID=1" is in the place that matches "<DL><DT>Location</DT><DD>$</DD></DL>” in the web page. It indicates that the character string enclosed by <DD> and </DD> of is acquired.

The character string pattern information indicates a character string pattern. The character string pattern information ".*[City|Municipal|Province|Prefecture].*" of the item "Address" of "ID=2" is a character that includes'City' or'Michi' or'Prefecture' or'Prefecture'. Indicates a column. That is, the item “address” of “ID=2” is a character enclosed by <DD> and </DD> in the part matching “<DD>$</DD>” in the web page. Indicates that you are retrieving a string that is a column and contains'city' or'way' or'fu' or'prefecture'. In addition, the character string pattern information “[1-9][0-9]*'m2'” of the item “Exclusive area” of “ID=2” follows the number between “1” and “9”, Indicates a match if one or more numbers between "0" and "9" are followed by the string "m2".

The storage unit 11 also stores the address normalization rule management table shown in FIG. The address normalization rule management table manages one or more address normalization rules. The address normalization rule management table manages one or more records having “ID” and “address normalization rule information”. The “address normalization rule information” has “input” and “output”. The “address normalization rule information” is information indicating a rule of converting a pattern indicated by “input” into a pattern indicated by “output”. The record of “ID=1” in FIG. 11 indicates that the character string “3rd chome” is changed to the character string “3-”, for example. In addition, the record of “ID=6” indicates that the building name is deleted. The building name is, for example, a character string after the address (for example, "3-1-26"). In addition, the record of “ID=9” indicates that the specific character string “bold” is deleted. Further, the record of “ID=10” indicates that the duplicate character string is deleted, and if the address normalization rule is applied, for example, the character string “Tsurugashima City Tsurugaoka Tsurugashima City Tsurugashima Oji Tsurugaoka 74-1” It becomes a character string "74-1, Tsurugaoka, Tsurugashima City, Saitama Prefecture". Further, the record of “ID=11” is the address of Kyoto City, and indicates that if there is a character string other than the numbers between “-town” and “number”, the character string is deleted. .. If this address normalization rule is applied, for example, “3-433 Shinbashi-Dori Yamatooji Higashiiri Higashiyama-cho, Higashiyama-ku, Kyoto-shi, Kyoto” becomes “3-433 Hayashishita-cho, Higashiyama-ku, Kyoto-shi, Kyoto”.

The storage unit 11 also stores the name identification rule management table shown in FIG. The name identification rule management table manages one or more name identification rules, which is information indicating rules for name identification of building names. The name identification rule management table stores one or more records having “ID” and “name identification rule information”. The “name matching rule information” is information indicating a rule of converting a pattern or character string indicated by “input” into a pattern or character string indicated by “output”.

In the above situation, two specific examples will be described below. Specific Example 1 is an example of outputting the housing diagram information. The second specific example is an example of calculating the appraisal amount of the selling price and the rental price.

(Specific example 1)
First, it is assumed that the user inputs an instruction to collect real estate information to the real estate information processing device 1.

Next, the real estate information processing device 1 receives such an instruction, and the real estate information collecting unit 142 determines that it is a crawling timing for collecting real estate information.

Next, the real estate information collection unit 142 collects real estate information as follows. That is, the real estate information collection unit 142 acquires the first web page using the URL “URL1” in FIG. 10. Then, by using the tag pattern information of “ID=1” in FIG. 10, the “address”, the “exclusive area”, and the like that constitute the real estate information are acquired. The real estate information collecting unit 142 applies the tag pattern information corresponding to the items “address”, “occupied area”, etc. to the first web page, and sets the adjacent “address”, “occupied area”, etc. as one real estate information. One piece of real estate information is acquired assuming that it is the "address", "proprietary area", etc. that compose the. Next, the real estate information collection unit 142 acquires the second web page using the URL “URL2” of FIG. Then, by using the collection rule information of “ID=2” in FIG. 10, “address”, “proprietary area”, and the like that compose the real estate information are acquired. After that, the real estate information collecting unit 142 collects a lot of real estate information from the web by using the third and subsequent records in FIG. 10 in the same manner.

Next, the address normalization processing unit 143 performs a process of collecting real estate information. Specifically, the address normalization processing unit 143 uses the address normalization rule management table of FIG. 11 to normalize the character strings that form the address information of the real estate information. Normalization is a process that unifies the fluctuations of characters. Then, for example, the address normalization processing unit 143 uses the address normalization rule information of FIG. 11 to replace the address information “2-39-12 Ikebukuro, Toshima-ku, Tokyo” with “39--12, Ikebukuro, Toshima-ku, Tokyo”. ". In addition, for example, the address normalization processing unit 143 uses the address normalization rule information of FIG. 11 to convert the address information “4-23-33 Terrace Elf Hoya-cho, Nishitokyo-shi, Tokyo” to the address information “West Tokyo, Tokyo. Ichihoya-cho 4-2-33". Further, for example, the address normalization processing unit 143 converts the address information “85-1 Nijo-dori Yanaibaba Nishiiri, Kannon-cho, Nakagyo-ku, Kyoto-shi, Kyoto” to the address information “85-1 Kanon-cho, Nakagyo-ku, Kyoto, Kyoto”. To do. Also, for example, the address normalization processing unit 143 converts the address information “6856-1 Shiba, Shiba, Kawaguchi City, Saitama” to “6856-1, Shiba, Kawaguchi City, Saitama”. Furthermore, for example, “304-1 Takasaka 304-1 Takasaka, Higashimatsuyama City, Saitama Prefecture” is converted to “304-1 Takasaka 304-1, Higashimatsuyama City, Saitama Prefecture”.

Next, the building name approach processing unit 144 unifies the notation of the same building name using the name identification rule management table of FIG. The building name processing unit 144 acquires, for example, one building name from the information collected by the real estate information collection unit 142, applies all the price adjustment rules of the name identification rule management table of FIG. 12 to the building name, and Generate all possible building names from the building names, and create a building name that matches the generated building name. Replace with the name of the first building you obtained. As a result, the building nayoro processing unit 144 causes the “Gloria Hatsuga Sagamihara” and “Gloria Hatsuga Sagamihara” “Gloria Hatsho Sagamihara” “Gloria Hatsho Sagamihara” “Gloria Hatsuga Sagamihara” “Gloria Hatsuga Sagamihara” “Gloria Hatsuga Sagamihara” “Gloria Hatsuga Sagamihara”. "Are the same building name, and are all unified into "Gloria Hatsumi Sagamihara".

As a result of the above, it is assumed that the real estate information collection unit 142 has accumulated a large amount of real estate information shown in FIG. 13 in the real estate information storage unit 112. Needless to say, the real estate information in the real estate information storage unit 112 may be stored manually by the user.

Next, it is assumed that the real estate information processing device 1 determines that it is the generation timing of the housing diagram information.

Then, the collective housing diagram information generation unit 141 generates the collective housing diagram information using the large number of real estate information shown in FIG. 13 as described below. Note that, here, a case will be described in which housing diagram information corresponding to the building name information “ABC condominium” is generated. Further, the generated collective housing diagram information is the collective housing diagram information including real estate information.

First, the collective housing diagram information generation unit 141 acquires all real estate information corresponding to the building name information “ABC condominium” from the real estate information management table of FIG. 13.

Next, the collective housing diagram information generating unit 141 generates the first floor collective housing diagram information from the real estate information including the numbers “101” to “105”. The number is the room information described above. Further, here, the housing complex diagram information generation unit 141 sorts the real estate information in order of the number of issues. In addition, the collective housing diagram information generation unit 141 generates house diagram information having an area having an area corresponding to the area information included in the real estate information. Here, the house map information has a rectangle. In addition, the collective housing map information generation unit 141 adds the “number”, “price information”, and “size information” that each real estate information on the first floor has to a predetermined area of the housing map information. Needless to say, if the “price information” does not exist, the “price information” is not added to the house map information. In addition, the collective housing diagram information generation unit 141 generates house diagram information such that the state flag of the real estate information on the first floor can be visually shown. Here, the background is gray for a house that is “unsold” indicated by the status flag “0”. Then, the background of the dwelling house “on sale” indicated by the status flag “1” is white. Further, the collective housing diagram information generation unit 141 uses the direction information included in the real estate information on the first floor to combine the house diagram information of the houses having the same direction information and separate the house diagram information of the houses having different direction information. Then, the collective housing diagram information is generated so as to be arranged.

Further, the collective housing diagram information generation unit 141 processes the real estate information on the second floor and above on each floor in the same manner as the first floor, and generates the collective housing diagram information.

Through the above processing, the collective housing diagram information generation unit 141 associates the final collective housing map information (real estate information-containing collective housing map information) with the collective housing identifier “ABC condominium” and stores the collective housing map information storage unit. Accumulate in 111.

In the above situation, it is assumed that the user has input to the terminal device 3 an output instruction of the housing diagram information including “ABC Mansion”. Then, the terminal accepting unit 32 of the terminal device 3 accepts the output instruction of the housing complex map information.

Next, the terminal transmission unit 34 transmits an output instruction of the housing complex map information to the real estate information processing device 1.

Next, the receiving unit 12 of the real estate information processing device 1 receives the output instruction of the housing diagram information including “ABC condominium”.

Next, the output unit 15 acquires the collective housing diagram information corresponding to the “ABC condominium” from the collective housing diagram information storage unit 111, and sends the collective housing diagram information to the output instruction of the collective housing diagram information. Send to device 3.

Next, the terminal receiving unit 35 of the terminal device 3 receives the real estate information-included housing diagram information. Then, the terminal output unit 36 outputs the real estate information-included housing diagram information received by the terminal receiving unit 35. An example of such an output is shown in FIG. In FIG. 14, the area of each residence included in the collective housing diagram information reflects the size information, direction information, and status flag of each real estate information.

The collective housing diagram information generation unit 141 may generate the collective housing diagram information for each floor. In such a case, the collective housing diagram information generation unit 141 generates, for example, the collective house diagram information of the first floor of "ABC condominium" as shown in FIG. Then, the collective housing diagram information generation unit 141 stores the generated collective housing diagram information in the collective housing diagram information storage unit 111 in association with the information “ABC condominium” and “first floor”.

In addition, here, the housing complex diagram information generation unit 141 sorts the real estate information in order of, for example, the number of issues. In addition, the house map information having an area having an area corresponding to the area information included in the real estate information is generated. In addition, the collective housing map information generation unit 141 adds the “number”, “price information”, and “size information” that each real estate information on the first floor has to a predetermined area of the housing map information. Needless to say, if the “price information” does not exist, the “price information” is not added to the house map information. In addition, the collective housing diagram information generation unit 141 generates house diagram information such that the state flag of the real estate information on the first floor can be visually shown. Here, the background is gray for a house that is “unsold” indicated by the status flag “0”. Then, the background of the dwelling house “on sale” indicated by the status flag “1” is white. Further, the collective housing diagram information generation unit 141 uses the direction information included in the real estate information on the first floor to combine the house diagram information of the houses having the same direction information and separate the house diagram information of the houses having different direction information. Then, the collective housing diagram information is generated so as to be arranged. Here, the collective housing diagram information generation unit 141 arranges each residence diagram information according to the direction indicated by the direction information.

Then, it is assumed that the user inputs an output instruction of the real estate information group on the “first floor” of “ABC condominium” to the terminal device 3, for example. Then, the terminal receiving unit 32 of the terminal device 3 receives the output instruction. Next, the terminal transmission unit 34 transmits the output instruction to the real estate information processing device 1.

Next, the receiving unit 12 of the real estate information processing device 1 receives the output instruction of the housing diagram information including the "first floor" of the "ABC condominium".

Then, the output unit 15 acquires the collective housing map information corresponding to the “ABC condominium” and the “first floor” from the collective housing map information storage unit 111, and outputs the collective housing map information to output the collective housing map information. It transmits to the terminal device 3 which has transmitted.

Next, the terminal receiving unit 35 of the terminal device 3 receives the real estate information-included housing diagram information. Then, the terminal output unit 36 outputs the real estate information-included housing diagram information received by the terminal receiving unit 35. An example of such an output is shown in FIG.

(Specific example 2)
Next, in the second specific example, a case of calculating the appraisal amount of the selling price and the rental price will be described.

Now, the storage unit 11 stores the size information classification management table shown in FIG. The area information classification management table is a table for managing information for classifying real estate using the area information and information for calculating an assessment amount. The size information classification management table has “ID”, “size information (square meter)”, and “value information”. “ID” is information for identifying a record and is identification information for classification. “Area information (square meters)” is range information indicating the range of the area information. The “value information” indicates the value substituted into the calculation formula.

The storage unit 11 also stores the total floor number information classification management table shown in FIG. The total floor information classification management table is a table that manages information for classifying real estate using total floor information and information for calculating an assessment amount. The total floor information classification management table has “ID”, “total floor information (floor)”, and “value information”. “ID” is information for identifying a record and is identification information for classification. “Total floor number information (floor)” is range information indicating the range of total floor number information. The “value information” indicates the value substituted into the calculation formula. Needless to say, in FIG. 17, the total floor information may include value information corresponding to “1” and “2”. Further, in such a case, for example, the value information corresponding to the total floor number information “1” is “v28”, and the value information corresponding to the total floor number information “2” is “v29”. The value information such as “v21” and “v22” is usually a constant.

The storage unit 11 also stores the walking fraction information classification management table shown in FIG. The walking fraction information classification management table is a table for managing information for classifying real estate using the walking fraction information and information for calculating an assessment amount. The walking fraction information classification management table has “ID”, “walking fraction information (minutes)”, and “value information”. “ID” is information for identifying a record and is identification information for classification. The "walking fraction information (minutes)" is range information indicating the range of the walking fraction information. The “value information” indicates the value substituted into the calculation formula. When the walking fraction information is “15 minutes or more”, since the area is not a walking area but an area where a car is used, the same value information is associated with 15 minutes, 16 minutes, and 20 minutes.

The storage unit 11 also stores the age information classification management table shown in FIG. The age information classification management table is a table that manages information for classifying real estate using age information and information for calculating an assessment amount. The age information classification management table has “ID”, “age information (year)”, and “value information”. “ID” is information for identifying a record and is identification information for classification. The "age information (year)" is range information indicating the range of the age information. The “value information” indicates the value substituted into the calculation formula.

The storage unit 11 also stores the belonging floor relative position information classification management table shown in FIG. The affiliation floor relative position information classification management table is a table for managing information for classifying real estate using affiliation floor relative position information and information for calculating an assessment amount. The affiliation floor relative position information classification management table has “ID”, “affiliation floor relative position information (p=affiliation floor number/total floor number)”, and “value information”. “ID” is information for identifying a record and is identification information for classification. “Affiliation floor relative position information (p=affiliation floor number/total floor number)” is range information indicating a range of belonging floor relative position information. The “value information” indicates the value substituted into the calculation formula. Note that here, the belonging floor relative position information (p) is calculated by “p=the belonging floor/total floor”, but the information indicating the relative position of the belonging floor is calculated by another arithmetic expression. Is also good.

The storage unit 11 also stores the belonging floor number information classification management table shown in FIG. The belonging floor information classification management table is a table that manages information for classifying real estate using the belonging floor information and information for calculating an assessment amount. The affiliation floor information classification management table has “ID”, “affiliation floor information (floor)”, and “value information”. “ID” is information for identifying a record and is identification information for classification. “Affiliation floor information (floor)” is range information indicating a range of belonging floor information. The “value information” indicates the value substituted into the calculation formula.

Further, the storage unit 11 stores the floor plan information classification management table shown in FIG. The floor plan information classification management table is a table that uses the floor plan information and manages information for calculating an assessment amount. The floor plan information classification management table has “ID”, “floor plan information”, and “value information”. “ID” is information for identifying a record and is identification information for classification. “Floor plan information” is information indicating the floor plan information, which may also be referred to as range information. The “value information” indicates the value substituted into the calculation formula.

The storage unit 11 also stores the direction information classification management table shown in FIG. The direction information classification management table is a table that manages information for calculating an assessment amount using direction information. The direction information classification management table has “ID”, “direction information”, and “value information”. “ID” is information for identifying a record and is identification information for classification. The “direction information” is information indicating a direction, which may also be called range information. “Value information” indicates a value (parameter) substituted in the arithmetic expression.

The storage unit 11 also stores the district identifier classification management table shown in FIG. The district identifier classification management table is a table that manages information for calculating an assessment amount using district identifiers. The district identifier classification management table has “ID”, “district identifier”, and “value information”. “ID” is information for identifying a record and is identification information for classification. The “district identifier” is information for identifying a district, which may also be called range information. “Value information” indicates a value (parameter) substituted in the arithmetic expression.

In addition to the floor plan information classification management table, direction information classification management table, and district identifier classification management table, the storage unit 11 is value information corresponding to each parameter value or range information, and is a value that can be substituted into the arithmetic expression. It is assumed to hold information.

Furthermore, it is assumed that the calculation method information storage unit 114 stores the calculation method information management table shown in FIG. The calculation method information management table is a table for managing the calculation method information, and stores one or more records having “class identifier”, “calculation method specifying information”, “range information group”, and “difference coefficient”. The “class identifier” is information that identifies a real estate class determined by the value of one or more classification parameters. Here, the “class identifier” is information for identifying the above-mentioned metaclass. The “calculation method specifying information” is an arithmetic expression for calculating the assessed value of the real estate here. The "calculation method specifying information" is a calculation formula of a linear function here, but may be another kind of calculation formula. The “range information group” is information indicating the range of values of one or more classification parameters. Although the “range information group” here is the “ID” of the various classification management tables of FIGS. 16 to 24, it goes without saying that it may be the “range information”. The “difference coefficient” exists for each parameter and each class. The “difference coefficient” is a coefficient applied to the calculation formula when there is a difference.

Under the above circumstances, it is assumed that the input parameter set reception unit 132 has read the input parameter set (a plurality of parameters forming the real estate information) of the following real estate information R1 from the real estate information storage unit 112. The input parameter set is information between the tag <input parameter set> and the tag </input parameter set>. At this point, the real estate information R1 is one of real estate information that does not have price information.
<Input parameter set>
<Address information> Shibuya-ku, Tokyo...
<Size information> 80m2
<Floor information> 3LDK
<Direction information> Facing south <Total floor information> 10
<Frequency information> 6
<Age information> 9
<Affiliation floor relative position information> 0.8
<Affiliation floor information> 8
<District identifier> Shibuya ward <Restricted area identifier> First-class middle and high-rise residential area </ Input parameter set>

Next, the appraisal amount acquisition unit 146 determines one or more predetermined classification parameters “<size information>80 m2, <total floor information>10, <walking fraction information> from the received input parameter set. 6, <age age information> 9, <affiliation floor relative position information> 0.8, <affiliation floor information> 8”.

Next, the appraisal amount acquisition unit 146 sets the ID “5” corresponding to “<size information>80 m2”, the ID “3” corresponding to “<total floor number information>10”, and the <distance information on foot>6”. Corresponding to ID “3”, ID “1” corresponding to <age age information>9, ID “4” corresponding to <affiliation floor relative position information>0.8”, <affiliation floor information>8” The ID “5” to perform is acquired from each classification management table (FIGS. 16 to 21).

Further, the appraisal amount acquisition unit 146, the value information “v15” corresponding to “<size information>80 m2”, the value information “v23” corresponding to “<total floor number information>10”, and the “walking minutes information>6”. Value information "v33" corresponding to <value information "v33", <value information "v41" corresponding to "age information> 9", value information "v54" corresponding to <relative position information of belonging floor> 0.8, <affiliation floor information> The value information “v65” corresponding to “8” is also acquired from each classification management table.

Next, the class determination unit 145 determines the calculation method specifying information corresponding to the classification parameter set. That is, the class determination unit 145 corresponds to the ID “5” corresponding to “<size information>80 m2”, the ID “3” corresponding to “<total floor number information>10”, and the <walking fraction information>6”. ID “3”, ID “1” corresponding to <age age information>9”, ID “4” corresponding to <affiliation floor relative position information>0.8”, ID corresponding to <affiliation floor information>8” The calculation method specifying information “y=a98+b98x981+c98x982+...” Paired with the range information group that matches all of “5” is acquired from the calculation method information management table of FIG. In the calculation formula that is the calculation method specifying information, “y” is the assessed amount. Further, “a98”, “b98”, “c98” and the like are constants, and “x981” and “x982” and the like are variables, and corresponding parameters are respectively substituted.

Further, the assessed amount acquisition unit 146 also acquires value information corresponding to each parameter that is an input parameter set and is not a classification parameter. That is, for example, the assessed amount acquisition unit 146 acquires the value information “v75” corresponding to “<floor information>3LDK” from the floor plan information classification management table in FIG. Further, for example, the assessed amount acquisition unit 146 acquires the value information “v81” corresponding to “<direction information> southward” from the floor plan information classification management table in FIG. 23. Furthermore, for example, the assessed amount acquisition unit 146 acquires the value information “v902” corresponding to “<district identifier> Shibuya Ward” from the district identifier classification management table of FIG.

Then, the assessed amount acquisition unit 146 associates the value information corresponding to one or more parameters of the input parameter set with each calculation parameter “y=a98+b98x981+c98x982+... ”Acquired by the class determination unit 145. It substitutes into the variable ("x981" "x982" etc.) to perform, and calculates. Then, it is assumed that the assessed amount acquisition unit 146 has obtained the assessed amount of “38 million yen”.

Next, the assessed amount acquisition unit 146 accumulates the price information “38 million yen” indicating the calculated assessed amount (sales price) in the real estate information R1 of the real estate information storage unit 112.

Further, it is assumed that the assessed amount acquisition unit 146 calculates the assessed amount of the rental price of the real estate information R1 as follows.

First, the assessed amount acquisition unit 146 acquires vector data (v15, v23, v33, v41, v54, v65, v75, v81, v902,...) Obtained from the input parameter set of the real estate information R1.

The vector data of real estate information is (value information corresponding to <area information>, value information corresponding to <floor information>, value information corresponding to <direction information>, value information corresponding to <total floor information> , Value information corresponding to <Fractory information>, Value information corresponding to <Age information>, Value information corresponding to <Affiliation floor relative position information>, Value information corresponding to <Affiliation floor information>, <District identifier Value information corresponding to <>, and value information corresponding to <use area identifier>).

Next, the assessed amount acquisition unit 146 acquires vector data (v15, v23, v33, v41, v54, v65, v75, v81, v902, from the learning information in the learning information storage unit 113 from the input parameter set. () is determined to have learning information having vector data of a parameter group that is most approximate to

Then, the assessed amount acquisition unit 146 determines that the learning information having the following real estate information R2 is determined as the most approximate learning information.
<Real estate information> R2
<Address information> Shibuya-ku, Tokyo...
<Area information> 70m2
<Floor information> 3LDK
<Direction information> Facing south <Total floor information> 10
<Frequency information> 6
<Age information> 9
<Affiliation floor relative position information> 0.8
<Affiliation floor information> 8
<District identifier> Shibuya Ward <Restricted area identifier> First-class high-rise residential area <Price information Type = Rental price> 150,000 yen/month </ Real estate information>

Next, the assessed amount acquisition unit 146 acquires the rental price information “150,000 yen/month” included in the determined learning information.

Next, the assessed amount acquisition unit 146 obtains the difference information “10 (square meter)” between the real estate information R1 and the real estate information R2 (difference between “<area information>80 m2” and “<area information>70 m2”). get.

Next, the assessed amount acquisition unit 146 acquires the class identifier “98” indicating the class of the real estate information R1 by referring to the table of FIG. 25 using each parameter of the real estate information R1.

Next, the assessed amount acquisition unit 146 acquires the difference coefficient “2.5” that is paired with the class identifier “98”. Further, it is assumed that the assessed amount acquisition unit 146 holds the basic amount “1000 yen” of the difference in rent per 1 square meter.

Next, the appraisal amount acquisition unit 146 uses the “10 (square meter)”, the basic amount “1000 yen” of the difference in the rent, and the difference coefficient “2.5” to determine the rental price of the real estate in the real estate information R2. The difference from the rental price of the real estate in the real estate information R1 is calculated as “10×1000×2.5=25,000 yen”.

Next, the appraisal amount acquisition unit 146 adds "25,000 yen" to the real estate rental price information "150,000 yen/month" of the real estate information R2 to obtain the real estate rental price "175,000 yen/month" of the real estate information R1. obtain.

Next, the assessed amount acquisition unit 146 accumulates rental price information “175,000 yen/month” indicating the calculated rental price in the real estate information R1 of the real estate information storage unit 112.

From the above, “<price information type=sales price>38 million yen/, <price information type=rent price>175,000 yen/month” is added to the real estate information R1.

In addition, next, it is assumed that the user inputs, to the terminal device 3, an output instruction of output of the housing diagram information on the eighth floor of the condominium including the real estate information R1. Then, the terminal accepting unit 32 of the terminal device 3 accepts the output instruction of the housing complex map information.

Next, the terminal transmission unit 34 transmits an output instruction of the housing complex map information to the real estate information processing device 1.

Next, the reception unit 12 of the real estate information processing device 1 receives the output instruction of the apartment building information on the eighth floor of the condominium containing the real estate information R1.

Next, the output unit 15 acquires, from the collective housing map information storage unit 111, the collective housing map information on the eighth floor of the condominium containing the real estate information R1, and outputs the collective housing map information to output the collective housing map information. Is transmitted to the terminal device 3 which has transmitted. It should be noted that the process of generating the collective housing map information and the like have already been described above, and thus a repetitive description will be omitted.

Next, the terminal receiving unit 35 of the terminal device 3 receives the real estate information-included housing diagram information. Then, the terminal output unit 36 outputs the real estate information-included housing diagram information received by the terminal receiving unit 35. An example of such an output is shown in FIG. It should be noted that R1 in FIG. 26 is a display example of real estate information of the real estate corresponding to the real estate information R1, and includes display of both the selling price and the rental price. Further, R2 in FIG. 26 is a display example of real estate information of real estate corresponding to the real estate information R2.

As described above, according to the present embodiment, since the real estate is appropriately classified and the calculation method according to the class is adopted, the appraisal price of the real estate can be calculated appropriately.

Further, according to the present embodiment, it is possible to appropriately assess both the purchase price and the rental price of the real estate. Then, according to the present embodiment, both the purchase price and the rental price of one real estate can be displayed.

Further, according to the present embodiment, it is possible to output the dwelling information including the prices of two or more dwellings in the housing complex in association with the dwellings in the housing complex.

Further, according to the present embodiment, it is possible to output the residence information of each of the two or more dwellings in the housing complex so that it can be visually distinguished whether the dwelling is for sale or not for sale.

Further, according to the present embodiment, at least a part of the collective housing diagram information can be generated from the housing information of each of two or more houses of one collective housing. It should be noted that according to the present embodiment, it is possible to generate the collective housing diagram information from the residence information of each of the two or more dwellings in a mode showing the layout relationship of the two or more dwellings.

Further, according to the present embodiment, at least a part of the collective housing diagram information including the area of the house corresponding to the size indicated by the size information included in the house information of each of the two or more houses of one collective house is generated. it can.

Further, according to the present embodiment, the residence information can be automatically collected from one or more server devices on the web.

Further, according to the present embodiment, substantially the same address information can be collected. Furthermore, according to this embodiment, the names of substantially the same buildings can be aggregated.

Further, the processing in this embodiment may be realized by software. Then, this software may be distributed by software download or the like. Further, this software may be recorded on a recording medium such as a CD-ROM and distributed. Note that this also applies to other embodiments in this specification. The software that realizes the real estate information processing device 1 according to the present embodiment is the following program. In other words, this program stores range information indicating a range of each classification parameter that constitutes a classification parameter set, which is a set of one or more parameters used for classifying real estate, in a computer-accessible recording medium. Calculation that can store two or more calculation method information that is a combination with calculation method specifying information that specifies the method of calculating the assessed amount corresponding to each class specified by the range information of one or more classification parameters An input parameter set acceptance unit that includes a method information storage unit and that accepts an input parameter set that is a set of one or more parameters of one real estate, and a classification parameter set included in the input parameter set. A class determination unit that determines the calculation method specifying information, a calculation method specifying information that is determined by the class determination unit, and an assessment amount acquisition unit that obtains the assessment amount using one or more parameters of the input parameter set. And a program for functioning as an output unit that outputs the assessed amount.

In the above program, the calculation method specifying information is a calculation formula in which one or more parameters can be substituted, and the assessment amount acquiring unit is the calculation method specifying information corresponding to the classification parameter set of the input parameter set. It is preferable that the program is a program that causes a computer to function as a formula for substituting one or more parameters of the input parameter set into the calculation formula to obtain the assessed amount.

In the above program, it is preferable that at least two calculation method specifying information out of the two or more calculation method specifying information of each of the two or more classes are programs for causing a computer to function as different types of parameters to be used. is there.

In the above program, the recording medium is two or more pieces of learning information having two or more parameters and price information, and stores two or more pieces of learning information associated with any one of the two or more pieces of calculation method specifying information. The assessment amount acquisition unit further includes a learning information storage unit for obtaining, and the appraisal amount acquisition unit, for one or more learning information corresponding to the calculation method specifying information determined by the classification unit, one or more parameters of the input parameter set. It is preferable that the program is a program that causes a computer to function by applying the above method to obtain the assessed amount.

In the above program, the classification parameter set includes a district identifier for identifying an existing district, a use area identifier for identifying a use area, building age information indicating a building age, floor number information indicating a maximum floor number, walking time from a station. It is preferable that the program is a program that causes a computer to function as a set of one or more parameters of the walking time information indicating the.

In the above program, the assessed amount acquisition unit calculates both the purchase price and the rent price of one real estate, and the purchase price calculation method and the rental price calculation method are different, It is preferable that the program is a program that causes a computer to function.

In the above program, the recording medium includes a learning information storage unit capable of storing two or more learning information having two or more parameters and rental price information indicating a rental price, and the assessment amount acquisition unit is the input parameter. The approximate learning information determining means for determining the learning information approximated to the extent that a predetermined relationship with the set is satisfied, and the approximation is performed according to the difference between the input parameter set and two or more parameters included in the approximate learning information. A program that causes a computer to function as a rental price information correction unit that corrects rental price information included in learning information is preferable.

In the above program, the learning information is associated with any one of two or more calculation method specifying information, and the assessment amount acquiring unit is configured to execute the calculation method specifying information corresponding to the approximate learning information. A program that causes a computer to function as a means for correcting rental price information included in approximate learning information is preferable.

(Embodiment 2)
In the present embodiment, a calculation method information generation device that uses learning information to determine an appropriate classification for each parameter of real estate information will be described.

Further, in the present embodiment, a calculation method information generation device will be described in which parameter classification is given by trial and error for each parameter of real estate information and the best classification is determined.

Furthermore, in the present embodiment, the number of classes to be classified is fixedly given or dynamically changed, and an appropriate classification is determined for each parameter of real estate information. The device will be described.

FIG. 27 is a block diagram of the calculation method information generation device 4 in this embodiment. The calculation method information generation device 4 is a device that normally generates the calculation method information in the calculation method information storage unit 114 of the real estate information processing device 1 described in the first embodiment.

The calculation method information generation device 4 includes a storage unit 41, a reception unit 42, and a processing unit 43.

The storage unit 41 includes a learning information storage unit 411 and a calculation method information storage unit 114.

The reception unit 42 includes a parameter identifier reception unit 421 and a class number reception unit 422.

The processing unit 43 includes a learning information acquisition unit 431, a calculation formula generation unit 432, and a calculation method information output unit 433.

The learning information acquisition unit 431 includes a class classification unit 4311 and a learning information acquisition unit 4312.

The calculation formula generation unit 432 includes a calculation formula generation unit 4321, a price calculation unit 4322, an error information acquisition unit 4323, and a class classification determination unit 4324.

The storage unit 41 can store various kinds of information. The various types of information are, for example, learning information and calculation method information.

The learning information storage unit 411 can store two or more pieces of learning information. Here, the learning information has two or more parameters and price information. The two or more parameters include a classification parameter set that is one or more parameters used for classification. The parameter is a parameter that constitutes real estate information. Moreover, it is preferable that the parameter is associated with a parameter identifier for identifying the parameter.

The reception unit 42 receives various information and instructions. The various information and instructions are a parameter identifier, the number of classes, etc., which will be described later.

The input means of various information and instructions may be anything such as a keyboard, a mouse, or a menu screen. The reception unit 42 can be realized by a device driver of input means such as a keyboard or control software for a menu screen.

The parameter identifier receiving unit 421 receives a classification parameter identifier (which may be simply referred to as a parameter identifier) that identifies one classification parameter. Moreover, the parameter identifier receiving unit 421 may receive two or more classification parameter identifiers.

The parameter identifier receiving unit 421 may perform a process of reading one or more classification parameter identifiers from the storage unit 41. The one or more classification parameters are usually predetermined.

The class number receiving unit 422 receives the number of classes (n) for one parameter. The number n of classes is a natural number of 2 or more. The class number receiving unit 422 receives the number of classes (n) for each of one or more parameters. Further, the class number receiving unit 422 may automatically acquire the number of classes. The number-of-classes accepting unit 422 may acquire the number of classes n while incrementing from 2, for example, and terminate when the termination condition is satisfied. The termination condition is, for example, an upper limit threshold value, which may be fixed or dynamically changed. When it is changed dynamically, it may be changed dynamically according to the parameter.

The processing unit 43 performs various kinds of processing. The various processes are, for example, processes performed by the learning information acquisition unit 431, the calculation formula generation unit 432, the calculation method information output unit 433, and the like.

The learning information acquisition unit 431 is a classification parameter classified into n (n is 2 or more) classes, and for each class of classification parameters identified by a parameter identifier, one or more learnings corresponding to each class. Information is acquired from the learning information storage unit 411. The learning information acquisition unit 431 normally searches the learning information storage unit 411 for one or more pieces of learning information that match the range information corresponding to the class of the classification parameter.

It is preferable that the learning information acquisition unit 431 acquires, for each metaclass, one or more pieces of learning information corresponding to each metaclass from the learning information storage unit 411. The metaclass is a combination of two or more classes of classification parameters identified by two or more classification parameter identifiers.

For example, there are six classes of the classification parameter "width information", and for example, "1-19" "20-29" "30-49" "50-69" "70-89" "90-" ( All units are square meters), and the class of the classification parameter "total floor information" is, for example, 7, for example, "3-4" "5-9" "10-14" "15-19". It is assumed to be “20 to 27”, “28 to 39”, and “40 to”. Then, when the classification parameter set is two of “width information” and “total floor information”, the metaclass is one of the classes of the classification parameter “width information” and the classification parameter “ It is a combination of one of the classes of "total floor information". That is, in this case, there are 42 6×7 metaclasses.

The learning information acquisition unit 431 may classify the parameter identified by the parameter identifier into the number of classes (n) accepted by the class number accepting unit 422, and acquire one or more learning information for each class. ..

The learning information acquisition unit 431 classifies the parameter identified by the parameter identifier into n (n is 2 or more) classes, and acquires, for each class, one or more learning information corresponding to each class from the learning information storage unit 411. You may do it. Classifying a parameter into n classes is classifying the value of the parameter into a class. For example, an example of the result of classifying the parameter "width information" into 6 classes is the attribute "width information" in FIG.

The learning information acquisition unit 431 classifies the parameter identified by the parameter identifier into the number of classes (n) received by the class number reception unit 422, and acquires one or more pieces of learning information for each class. Note that n may be determined in advance, or may be 2 or more and m (m is a natural number of 3 or more) or less, and may be sequentially changed.

It is preferable that the class classification unit 4311 classify the class into two or more classes for each of the two or more classification parameters identified by the two or more parameter identifiers. The class classification method performed by the class classification unit 4311 does not matter. For example, when the parameter can take a value of a natural number of 9 from “1” to “9” and classifies the parameter into three classes, the class classification unit 4311 uses “1 to 3” and “4 to 6”. The three classes may be configured such that “7 to 9” and an equal number of parameters are included in each class, and “1”, “2”, “3 to 9”, and “1 to 7” “1”. A class that includes non-uniform parameters such as “8” and “9” may be configured. The class classification means 4311 normally divides the values that the classification parameters can take according to the number of classes.

Here, performing class classification means, for example, acquiring class classification information that is class classification information for each class. The class classification information has, for example, two or more sets of classification parameter identifiers and range information.

The learning information acquisition unit 4312, for each of the two or more classification parameters identified by the two or more parameter identifiers, for each of the two or more classes classified by the class classification unit 4311, One or more pieces of learning information are acquired from the learning information storage unit 411.

The learning information acquisition unit 4312 may acquire, for each metaclass, one or more pieces of learning information corresponding to the range information of the classification parameters belonging to two or more classes forming each metaclass from the learning information storage unit 411. The metaclass is a combination of one class selected from two or more classification parameters.

The calculation formula generation unit 432 is a calculation formula for calculating price information using one or more pieces of learning information for each class, and generates a calculation formula having a variable into which two or more parameters are substituted. The one or more learning information for each class is the learning information acquired by the learning information acquisition unit 431.

The calculation formula generation unit 432 is a calculation formula for calculating price information by using one or more pieces of learning information for each metaclass, and generates a calculation formula having a variable into which two or more parameters are substituted. Variables for substituting two or more parameters are usually variables for substituting parameters other than price information. The one or more pieces of learning information are learning information acquired by the learning information acquisition unit 431.

It is preferable that the calculation formula generation unit 432 generate a linear calculation formula by multiple regression analysis using one or more pieces of learning information.
The calculation formula generation unit 4321 is a calculation formula for calculating price information using one or more pieces of learning information for each metaclass, and generates a calculation formula having a variable into which two or more parameters are substituted. The calculation formula generating means 4321 generates a calculation formula that minimizes an error when calculating price information using one or more learning information and one or more parameters for each metaclass. There may be various algorithms for the calculation formula generation means 4321 to generate a calculation formula, and there is no limitation.

The price calculation unit 4322 substitutes one or more parameters of one or more pieces of learning information belonging to each class into the calculation formula of each class, calculates the price, and acquires the calculated price information indicating the calculated price.

The price calculation means 4322 calculates each class generated by the calculation formula generation means 4321 for two or more classification classes for each of two or more classification parameters identified by two or more parameter identifiers. One or more parameters of one or more pieces of learning information belonging to each class are substituted into the formula to calculate the price, and the calculated price information indicating the calculated price is acquired.

The error information acquisition unit 4323 has, for each of the two or more classification parameters identified by the two or more parameter identifiers, the price information included in the learning information for each of the two or more classes. Error information indicating a difference between (actual price information) and calculated price information corresponding to the price information is acquired. The error information is, for example, the absolute value of the difference between the two prices.

The class classification determination unit 4324 has one or more classes acquired by the error information acquisition unit 4323 with respect to two or more classes of each class for each of the two or more classification parameters identified by the two or more parameter identifiers. The error information is used to determine the classification of the class with less error so that a predetermined condition is satisfied.

It should be noted that the classification of a class in which the error is small enough to satisfy a predetermined condition is usually a classification in which the representative value of one or more pieces of error information is the smallest. The representative value of the error is, for example, the representative value of the one or more pieces of error information is an average value or a median of the errors indicated by the one or more pieces of error information.

The calculation method information output unit 433 acquires and outputs, for each class, two or more pieces of calculation method information having calculation method specifying information that is a calculation formula generated by the calculation formula generation unit 432.

The calculation method information output unit 433 is a combination of a classification parameter set, which is a set of two or more corresponding parameters, and calculation method specifying information, which is a calculation formula generated by the calculation formula generation unit 4321, for each metaclass. Get method information and output.

The calculation method information output unit 433 normally acquires two or more pieces of calculation method information and stores them in a recording medium. The recording medium is usually the calculation method information storage unit 114. However, the calculation method information output unit 433 may transmit the acquired two or more pieces of calculation method information to an external device.

The storage unit 41, the learning information storage unit 411, and the calculation method information storage unit 114 are preferably non-volatile recording media, but can also be realized by volatile recording media.

The process of storing information in the storage unit 41 or the like does not matter. For example, the information may be stored in the storage unit 41 via a recording medium, or the information transmitted via a communication line may be stored in the storage unit 41, or The information input via the input device may be stored in the storage unit 41.

Processing unit 43, learning information acquisition unit 431, calculation formula generation unit 432, calculation method information output unit 433, class classification unit 4311, learning information acquisition unit 4312, calculation formula generation unit 4321, price calculation unit 4322, error information acquisition unit 4323. The class classification determining unit 4324 can be usually realized by an MPU, a memory or the like. The processing procedure of the processing unit 43 is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

It may be considered that the calculation method information output unit 433 is realized by the driver software of the output device or the driver software of the output device and the output device.

Next, the operation of the calculation method information generation device 4 will be described. First, the process in which the calculation method information generation device 4 determines the class classification of one classification parameter will be described with reference to the flowchart of FIG.

(Step S2801) The parameter identifier receiving unit 421 determines whether or not one parameter identifier has been received. If the one parameter identifier is received, the process proceeds to step S2802, and if the one parameter identifier is not received, the process returns to step S2801. The one parameter identifier is a classification parameter identifier. Further, it is assumed that the classification parameter identifier is usually predetermined.

(Step S2802) The class classification means 4311 substitutes 2 for the counter i.

(Step S2803) The class classification unit 4311 determines whether or not the number of classes of i satisfies the first end condition. If the first end condition is satisfied, the process proceeds to step S2819, and if the first end condition is not satisfied, the process proceeds to step S2804. The first termination condition is, for example, that the maximum value in the case of class division is reached, and is fixedly determined, for example, in common or for each parameter. However, the maximum value in the case of dividing into classes may be dynamically determined, or may be the maximum value in the case of dividing into the classes the maximum number of divisions possible.

(Step S2804) The class classification means 4311 substitutes 1 into the counter j.

(Step S2805) The class classification unit 4311 determines whether or not the j-th class classification method of the one parameter satisfies the second end condition. If the second end condition is satisfied, the process proceeds to step S2818, and if the second end condition is not satisfied, the process proceeds to step S2806. The second termination condition may be that the processing in all cases when dividing into the number of classes of i has been completed, or that j has reached a predetermined upper limit number.

(Step S2806) The class classification means 4311 substitutes 1 into the counter k.

(Step S2807) The class classification means 4311 determines whether or not the k-th class in the j-th class classification method exists. If the kth class exists, the process proceeds to step S2808, and if the kth class does not exist, the process proceeds to step S2817.

(Step S2808) The learning information acquisition unit 4312 acquires one or more pieces of learning information belonging to the k-th class of one parameter from the learning information storage unit 411. The learning information belonging to the kth class is learning information having a parameter that matches the range information corresponding to the kth class. The parameter that matches the range information may be the parameter that corresponds to the value information that matches the range information.

(Step S2809) The calculation formula generating means 4321 acquires the calculation formula of the k-th class using the one or more pieces of learning information acquired in step S2808. The calculation formula generation means 4321 is, for example, one or more parameters included in the one or more learning information acquired in step S2808, and is a calculation formula in which one or more parameters excluding price information are variables, and one or more learning is performed. The calculation formula that minimizes the error for calculating the price information included in the information is acquired by multiple regression analysis.

(Step S2810) The price calculation means 4322 substitutes 1 into the counter m.

(Step S2811) The price calculation means 4322 judges whether or not the m-th learning information belonging to the k-th class exists. If the m-th learning information exists, the process proceeds to step S2812, and if the m-th learning information does not exist, the process proceeds to step S2815.

(Step S2812) The price calculation means 4322 substitutes the parameter of the m-th learning information into the calculation formula acquired in step S2809 to calculate the calculated price information.

(Step S2813) The error information acquisition unit 4323 acquires error information indicating the difference between the price information (actual price information) included in the m-th learning information and the calculated price information calculated in step S2812, and stores it in a buffer (not shown). Accumulate temporarily.

(Step S2814) The price calculation means 4322 increments the counter m by 1. The procedure returns to step S2811.

(Step S2815) The error information acquisition means 4323 calculates the representative value of the error information of the kth class using the one or more error information acquired using the one or more learning information belonging to the kth class. The representative value of the error information is, for example, an average value of one or more error information, a median value of one or more error information, or the like. However, the method of acquiring the representative value does not matter. The same applies to other representative values.

(Step S2816) The class classification means 4311 increments the counter k by 1. The procedure returns to step S2807.

(Step S2817) The error information acquisition means 4323 calculates the representative value of the error information of the j-th class classification method using the representative value of the error information of each class in the j-th class classification method. It returns to step S2805.

(Step S2818) The class classification means 4311 calculates the representative value of the error information of the number of classes of i using the representative value of the error information of each class classification method in the number of classes of i. It returns to step S2803.

(Step S2819) The class classification determining unit 4324 determines the number of classes with the smallest error information from the representative values of the error information for all the number of classes. Then, the class classification determining unit 4324 determines the class classification method having the smallest error information of the determined number of classes. Then, the class classification determining unit 4324 acquires the range information of each class of the class classification method and temporarily stores it in a buffer (not shown). The process ends.

Note that, for example, when one parameter is “width information”, for example, the number of classes with the smallest error information is “6”, and the range information of each class of the class classification method is the attribute value of FIG. It is shown in "Area information".

Note that in the flowchart of FIG. 28, one classification parameter identifier is accepted, but it is preferable to accept two or more classification parameter identifiers and execute the above process for each classification parameter identifier. ..

Next, the operation of the calculation method information generation device 4 for accumulating the calculation method information will be described with reference to the flowchart of FIG. Note that it is assumed that the operation described in the flowchart of FIG. 28 is performed for all the classification parameters, and the appropriate classification of all the classification parameters is completed. Further, a diagram showing an example of such classification is a table excluding the attribute “value information” in FIGS. 16 to 21. That is, the classification parameters here are six, for example, size information, total floor number information, walking fraction information, building age information, belonging floor relative position information, and belonging floor information.

(Step S2901) The calculation formula generation means 4321 substitutes 1 into the counter i.

(Step S2902) The calculation formula generation means 4321 determines whether or not the i-th class (here, a metaclass) exists. If the i-th class exists, the process proceeds to step S2903, and if the i-th class does not exist, the process ends. Note that the total number of classes here is the number of combinations of each range information of all classification parameters. That is, when the classification result is the table excluding the "value information" in FIGS. 16 to 21, the number of classifications of the size information is "6", the number of classifications of the total floor information is "7", the number of classifications of the walking fraction information. "6", the number of classes of age information "3", the number of classes of relative floor position information "5", and the class of belonging floor information "5" are multiplied, and the total number of classes is "6x7x6x". 3×5×5=18900”.

(Step S2903) Learning information acquisition means 4312 acquires one or more pieces of learning information belonging to the i-th class from learning information storage unit 411. The learning information acquisition unit 4312 acquires, from the learning information storage unit 411, one or more pieces of learning information that match all the range information of each classification parameter corresponding to the i-th class.

(Step S2904) The calculation formula generating means 4321 uses the one or more learning information acquired in step S2903 and the one or more parameters to calculate the price information so that the error is minimized. Generate an expression. The one or more parameters are usually predetermined. Further, when the calculation formula generating means 4321 generates the calculation formula, the values of the one or more parameters may be used as they are, or the parameter values are converted by using some calculation formula or a correspondence table. It may be used in place of the value (value information). The calculation formula generation unit 4321 may generate the calculation formula by using, for example, multiple regression analysis. It is preferable that the calculation formula generation unit 4321 generate the calculation formula by multiple regression analysis using a data set excluding data outside the predetermined range.

(Step S2905) The calculation method information output unit 433 is a set of the range information of one or more classification parameters corresponding to the i-th class and the calculation method specifying information which is the calculation formula generated in step S2904. Compose calculation method information.

(Step S2906) The calculation method information output unit 433 accumulates the calculation method information configured in Step S2905 in the calculation method information storage unit 114.

(Step S2907) The calculation formula generation means 4321 increments the counter i by 1.

In the flowchart of FIG. 29, the set of accumulated calculation method information is, for example, the calculation method information management table (excluding the difference coefficient) of FIG. 25.

As described above, according to this embodiment, the calculation method information used for calculating the assessed value of the real estate can be automatically generated.

In the present embodiment, the class classification of each classification parameter may be given manually. In such a case, the calculation method information generation device has the configuration shown in FIG. The calculation method information generation device includes a learning information storage unit that can store two or more pieces of learning information having two or more parameters and price information, and a parameter identifier reception unit that receives a parameter identifier that identifies one parameter. , A learning information acquisition unit that classifies parameters identified by the parameter identifier into n (n is 2 or more) classes and acquires, for each class, one or more learning information corresponding to each class from the learning information storage unit. And a calculation formula generation unit for generating a calculation formula for calculating price information having two or more parameters using one or more learning information for each class acquired by the learning information acquisition unit, and corresponding for each class And a calculation method information output unit that acquires two or more pieces of calculation method information, which is a set of the classification parameter set and the calculation method specifying information that is the calculation formula generated by the calculation formula generation unit, and that stores the calculation method information in the recording medium. This is a calculation method information generation device provided.
Furthermore, the software that realizes the calculation method information generation device according to the present embodiment is the following program. In other words, this program has a computer-accessible recording medium provided with a learning information storage section capable of storing two or more learning information having two or more parameters and price information, and a computer is provided with one classification parameter. A parameter identifier accepting unit that accepts a parameter identifier to be identified, and classification parameters that are classified into n (n is 2 or more) classes. Each class of classification parameters identified by the parameter identifier is assigned to each class. A learning information acquisition unit that acquires one or more corresponding learning information from the learning information storage unit, and a calculation formula that calculates price information using one or more learning information for each class acquired by the learning information acquisition unit. And a calculation formula generation unit that generates a calculation formula having a variable that substitutes two or more parameters, and two or more calculations that have, for each class, calculation method specifying information that is the calculation formula generated by the calculation formula generation unit. It is a program that functions as a calculation method information output unit that acquires and outputs method information.

Further, in the above program, the parameter identifier accepting unit accepts two or more classification parameter identifiers, and the learning information obtaining unit recognizes two or more classification parameters identified by the two or more classification parameter identifiers. For each metaclass, which is a combination of classes, one or more pieces of learning information corresponding to each metaclass are acquired from the learning information storage unit, and the calculation formula generation unit acquires, for each metaclass, the learning information acquisition unit 1 A calculation formula for calculating price information by using the above learning information, which generates a calculation formula having a variable for substituting two or more parameters, and the calculation method information output unit corresponds to each metaclass. A computer is used to acquire and output the calculation method information that is a set of the classification parameter set that is a set of the above classification parameters and the calculation method specifying information that is the calculation formula generated by the calculation formula generation unit. It is preferable that the program be a functioning program.

In the above program, the learning information acquisition unit may classify a class into two or more classes for each of the two or more classification parameters identified by the two or more parameter identifiers; For two or more classification parameters identified by two or more parameter identifiers, one or more learning information for each class is provided for each of the two or more classes classified by the class classification means. The learning information acquisition unit that acquires the learning information from the learning information storage unit and the calculation formula generation unit include two or more classes for each of the two or more classification parameters identified by the two or more parameter identifiers. For the classification, a calculation formula for calculating price information by using one or more learning information for each class acquired by the learning information acquisition means, and a calculation formula for generating a calculation formula having two or more parameters as variables. For each of the two or more classification parameters identified by the generation means and the two or more classification parameters identified by the two or more parameter identifiers, calculation of each class generated by the calculation formula generation means A price calculation means for substituting one or more parameters possessed by one or more learning information belonging to each class into the formula to calculate a price, and obtain calculated price information indicating the calculated price; and each of the above two or more. For each of two or more classification parameters identified by the parameter identifier, for each of the two or more classes, the learning information has the price information included in the learning information and the calculation corresponding to the price information. Error information acquiring means for acquiring error information indicating a difference from price information, and for each of the two or more classification parameters for each of the two or more classification parameters identified by the two or more parameter identifiers. And a class classification deciding means for deciding a classification of a class having less error so as to satisfy a predetermined condition by using one or more pieces of error information obtained by the error information obtaining means. For each metaclass consisting of a combination of one class selected from the two or more classification parameters, one or more learning information corresponding to the classification parameters belonging to two or more classes forming each metaclass is learned. The calculation formula generation unit acquires the price information from the information storage unit using one or more pieces of learning information acquired by the learning information acquisition unit for each of the metaclasses, and has two or more parameters. A calculation formula having a variable for substituting for each metaclass. In addition, the calculation method information that is a set of the classification parameter set that is a set of two or more corresponding parameters and the calculation method specifying information that is the calculation formula generated by the calculation formula generating means is acquired and output. It is preferable that the program is a program that causes a computer to function.

In the above program, the computer may further function as a class number receiving unit that receives the number of classes (n) for the one parameter, and the learning information acquisition unit may change the parameter identified by the parameter identifier to the number of classes. It is preferable that the program is a program that causes a computer to classify the classes into the number of classes (n) received by the reception unit and acquire one or more pieces of learning information for each class.

Further, FIG. 31 shows an external appearance of a computer that executes the programs described in this specification to realize the real estate information processing device and the like of the various embodiments described above. The above-described embodiments can be realized by computer hardware and a computer program executed on the computer hardware. FIG. 31 is a general view of the computer system 300, and FIG. 32 is a block diagram of the system 300.

31, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

32, in addition to the CD-ROM drive 3012, the computer 301 includes an MPU 3013, a bus 3014 connected to the MPU 3013 and the CD-ROM drive 3012, a ROM 3015 for storing programs such as a boot-up program, and an MPU 3013. And a hard disk 3017 for temporarily storing the instructions of the application program and providing a temporary storage space, and a hard disk 3017 for storing the application program, the system program, and data. Although not shown here, the computer 301 may further include a network card that provides a connection to a LAN.

A program that causes the computer system 300 to execute the functions of the real estate information processing apparatus and the like of the above-described embodiments may be stored in the CD-ROM 3101, inserted into the CD-ROM drive 3012, and further transferred to the hard disk 3017. .. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored in the hard disk 3017. The program is loaded into the RAM 3016 when it is executed. The program may be loaded directly from the CD-ROM 3101 or the network.

The program does not necessarily have to include the operating system (OS) that causes the computer 301 to execute the functions of the real estate information processing apparatus and the like according to the above-described embodiments, a third-party program, or the like. The program only needs to include a part of an instruction that calls an appropriate function (module) in a controlled manner and obtains a desired result. How the computer system 300 operates is well known and will not be described in detail.

In the above program, in the step of transmitting information, the step of receiving information, etc., the processing performed by hardware, for example, the processing performed by the modem or the interface card in the transmission step (only performed by hardware. Processing) is not included.

Moreover, the computer that executes the program may be a single computer or a plurality of computers. That is, centralized processing may be performed or distributed processing may be performed.

Further, in each of the above-mentioned embodiments, it goes without saying that two or more communication means existing in one device may be physically realized by one medium.

Further, in each of the above-described embodiments, each process may be realized by centralized processing by a single device, or may be realized by distributed processing by a plurality of devices.

Needless to say, the present invention is not limited to the above-described embodiments, and various modifications can be made, which are also included in the scope of the present invention.

As described above, the real estate information processing device according to the present invention has the effect of being able to appropriately calculate the appraisal price of real estate, and is useful as a web server device or the like that realizes a service for presenting real estate information.

1 Real Estate Information Processing Device 2 Server Device 3 Terminal Device 4 Calculation Method Information Generation Device 11, 41 Storage Unit 12 Reception Unit 13, 42 Reception Unit 14, 43 Processing Unit 15 Output Unit 21 Server Storage Unit 22 Server Reception Unit 23 Server Transmission Unit 31 terminal storage unit 32 terminal reception unit 33 terminal processing unit 34 terminal transmission unit 35 terminal reception unit 36 terminal output unit 111 housing diagram information storage unit 112 real estate information storage unit 113, 411 learning information storage unit 114 calculation method information storage unit 131 Real estate information reception unit 132 Input parameter set reception unit 141 Housing diagram information generation unit 142 Real estate information collection unit 143 Address normalization processing unit 144 Building name processing unit 145 Class determination unit 146 Assessment amount acquisition unit 421 Parameter identifier reception unit 422 Number of classes Reception unit 431 Learning information acquisition unit 432 Calculation formula generation unit 433 Calculation method information output unit 1461 Approximate learning information determination unit 1462 Rental price information correction unit 4311 Class classification unit 4312 Learning information acquisition unit 4321 Calculation formula generation unit 4322 Price calculation unit 4323 Error Information acquisition means 4324 Class classification determination means

Claims (13)

A learning information storage unit capable of storing two or more learning information having two or more parameters and price information;
A parameter identifier receiving unit that receives a parameter identifier that identifies two or more classification parameters;
A learning information acquisition unit that acquires from the learning information storage unit one or more pieces of learning information corresponding to each metaclass for each metaclass that is a combination of two or more classes of classification parameters identified by the two or more parameter identifiers. When,
A calculation formula generating a calculation formula for calculating price information using one or more pieces of learning information acquired by the learning information acquisition unit for each metaclass, and generating a calculation formula having a variable for substituting two or more parameters Department,
Obtaining and outputting calculation method information having a classification parameter set that is a set of two or more corresponding classification parameters and calculation method specifying information that is a calculation formula generated by the calculation formula generation unit for each metaclass. And a calculation method information output section
The learning information acquisition unit,
Class classification means for classifying two or more classes for each of the two or more classification parameters identified by the two or more parameter identifiers;
One or more learning information for each class for each of the two or more classes classified by the class classification means for the two or more classification parameters identified by the two or more parameter identifiers. Learning information acquisition means for acquiring from the learning information storage unit,
The calculation formula generation unit,
For each of two or more classification parameters identified by the two or more parameter identifiers, one or more learning information for each class acquired by the learning information acquisition means for the two or more class classifications. Is a calculation formula for calculating price information using, and a calculation formula generating means for generating a calculation formula having two or more parameters as variables.
For each of the two or more classification parameters identified by the two or more parameter identifiers, the calculation formula of each class generated by the calculation formula generation means for each of the two or more classes A price calculation means for substituting one or more parameters possessed by one or more pieces of learning information belonging to each class, calculating a price, and obtaining calculated price information indicating the calculated price,
For each of two or more classification parameters identified by the two or more parameter identifiers, for each of the two or more classes, the price information included in the learning information and the price Error information acquisition means for acquiring error information indicating a difference from the calculated price information corresponding to the information,
For each of the two or more classification parameters identified by the two or more parameter identifiers, the one or more error information acquired by the error information acquisition means is used for the two or more classes. , And a class classification determination means for determining a classification of a class having less error as satisfying a predetermined condition,
The learning information acquisition means,
Two or more constituting each metaclass for each metaclass consisting of a combination of one class selected from the classes included in the classification of the class determined by the class classification determination means for each of the two or more classification parameters Acquiring one or more pieces of learning information corresponding to the classification parameters belonging to the class from the learning information storage unit,
The calculation formula generating means,
Calculation method information for generating a calculation formula for calculating price information by using one or more pieces of learning information acquired by the learning information acquisition unit for each metaclass, and generating a calculation formula having a variable for substituting two or more parameters. Generator. Further comprising a class number receiving unit that receives the number of classes (n) for each of the two or more classification parameters,
The learning information acquisition unit,
The calculation method information generation according to claim 1, wherein the parameter identified by the parameter identifier is classified into the number of classes (n) accepted by the class number accepting unit, and one or more learning information is acquired for each class. apparatus. A calculation method information generating device according to claim 1 or 2;
The range of each classification parameter constituting the classification parameter set, which is two or more calculation method information output by the calculation method information generation device and is a set of one or more parameters used for real estate classification, Two or more pieces of calculation method information, which is a set of the range information shown and the calculation method specifying information specifying the method of calculating the assessed amount corresponding to each class specified by the range information of one or more classification parameters. A calculation method information storage unit that can be stored,
An input parameter set reception unit that receives an input parameter set that is a set of one or more parameters of one real estate;
A class determining unit that determines calculation method specifying information corresponding to a classification parameter set included in the input parameter set,
An assessment amount acquisition unit that obtains an assessment amount using the calculation method specifying information determined by the class determination unit and one or more parameters of the input parameter set;
A real estate information processing apparatus comprising: an output unit that outputs the assessed amount. The calculation method specific information is
A calculation formula that can substitute one or more parameters,
The assessment amount acquisition unit,
The real estate according to claim 3, wherein one or more parameters of the input parameter set are substituted into a calculation formula that is calculation method specifying information corresponding to a classification parameter set of the input parameter set to acquire the assessed amount. Information processing device. The real estate information processing apparatus according to claim 3 or 4, wherein at least two calculation method specifying information among two or more calculation method specifying information of each of two or more classes have different types of parameters to be used. The learning information storage unit further includes two or more pieces of learning information having two or more parameters and price information and capable of storing two or more pieces of learning information associated with any of the two or more pieces of calculation method specifying information. ,
The assessment amount acquisition unit,
The real estate information according to claim 3, wherein one or more parameters of the input parameter set is applied to one or more learning information corresponding to the calculation method specifying information determined by the class determining unit to acquire the assessed amount. Processing equipment. The classification parameter set is
1 or 2 of a district identifier for identifying an existing district, a restricted zone identifier for identifying a restricted zone, building age information indicating a building age, floor number information indicating a maximum floor number, and walking time information indicating a walking time from a station The real estate information processing apparatus according to any one of claims 3 to 6, which is a set of the above parameters. The assessment amount acquisition unit,
Calculate both the purchase price and the rental price of one real estate,
The real estate information processing apparatus according to any one of claims 3 to 7, wherein a method of calculating the purchase price and a method of calculating the rental price are different. A learning information storage unit capable of storing two or more pieces of learning information having two or more parameters and rental price information indicating a rental price;
The assessment amount acquisition unit,
Approximate learning information determining means for determining learning information that has been approximated to satisfy a predetermined relationship with the input parameter set,
9. The rental price information correction means for correcting rental price information included in the approximated learning information according to a difference between the input parameter set and two or more parameters included in the approximated learning information. Real estate information processing equipment. The learning information is
Corresponding to any of the two or more calculation method specific information,
The assessment amount acquisition unit,
The real estate information processing apparatus according to claim 9, wherein the rental price information included in the approximated learning information is corrected according to the calculation method specifying information corresponding to the approximated learning information. The output unit is
The real estate information processing apparatus according to any one of claims 3 to 10, which outputs both the selling price and the rental price. It can be realized by a learning information storage unit capable of storing two or more learning information having two or more parameters and price information, a parameter identifier reception unit, a learning information acquisition unit, a calculation formula generation unit, and a calculation method information output unit. Calculation method Information generation method,
A parameter identifier receiving step in which the parameter identifier receiving unit receives a parameter identifier for identifying two or more classification parameters;
The learning information acquisition unit, for each metaclass that is a combination of two or more classes of classification parameters identified by the two or more parameter identifiers, outputs one or more learning information corresponding to each metaclass from the learning information storage unit. The learning information acquisition step to acquire,
The calculation formula generation unit is a calculation formula for calculating price information for each of the metaclasses, using one or more pieces of learning information acquired in the learning information acquisition step, and has variables for substituting two or more parameters. A calculation formula generation step for generating a calculation formula,
The calculation method information output unit includes, for each metaclass, a classification parameter set that is a set of two or more corresponding classification parameters and calculation method specifying information that is the calculation formula generated in the calculation formula generating step. A calculation method information output step of acquiring and outputting the calculation method information that the user has,
The learning information acquisition step,
To the two or more two or more of each classification parameters identified by the parameter identifier, two types or more, and categorized Busuteppu for classifying the class,
For two or more of each classification parameters identified by the two or more respective parameter identifier for the classification of each class of more the two types classified by the classification sub-step, for each class 1 or more And a learning information acquisition sub-step of acquiring learning information from the learning information storage unit,
The calculation formula generating step,
For each of the two or more classification parameters identified by the two or more parameter identifiers, one or more of each class acquired in the learning information acquisition sub-step for the two or more classes of each class A calculation formula for calculating price information using the learning information, which is a calculation formula generation sub-step for generating a calculation formula having two or more parameters as variables;
For each of the two or more classification parameters identified by the two or more parameter identifiers, the calculation formula of each class generated in the calculation formula generation sub-step for the classification of the two or more classes , A price calculation sub-step of substituting one or more parameters possessed by one or more learning information belonging to each class, calculating a price, and obtaining calculated price information indicating the calculated price,
For each of two or more classification parameters identified by the two or more parameter identifiers, for each of the two or more classes, the price information included in the learning information and the price Error information acquisition substep of acquiring error information indicating a difference from the calculated price information corresponding to the information,
For each of the two or more classification parameters identified by the two or more parameter identifiers, the one or more pieces of error information acquired in the error information acquisition substep for the two or more classes Using a class classification determination sub-step for determining the classification of the class with less error as satisfying a predetermined condition,
In the learning information acquisition sub-step,
For each of the two or more classification parameters, each metaclass is configured for each metaclass consisting of a combination of one class selected from the classes included in the class classification determined in the class classification determination substep. Acquiring one or more pieces of learning information corresponding to classification parameters belonging to two or more classes from the learning information storage unit,
In the calculation formula generation sub-step,
A calculation formula for calculating price information using one or more pieces of learning information acquired in the learning information acquisition sub-step for each metaclass, and generating a calculation formula having a variable for substituting two or more parameters Method Information generation method. A computer accessible to a learning information storage unit capable of storing two or more learning information having two or more parameters and price information,
A parameter identifier receiving unit that receives a parameter identifier that identifies two or more classification parameters;
A learning information acquisition unit that acquires from the learning information storage unit one or more pieces of learning information corresponding to each metaclass for each metaclass that is a combination of two or more classes of classification parameters identified by the two or more parameter identifiers. When,
A calculation formula generating a calculation formula for calculating price information using one or more pieces of learning information acquired by the learning information acquisition unit for each metaclass, and generating a calculation formula having a variable for substituting two or more parameters Department,
Obtaining and outputting calculation method information having a classification parameter set that is a set of two or more corresponding classification parameters and calculation method specifying information that is a calculation formula generated by the calculation formula generation unit for each metaclass. A program for functioning as a calculation method information output unit,
The learning information acquisition unit,
Class classification means for classifying two or more classes for each of the two or more classification parameters identified by the two or more parameter identifiers;
One or more learning information for each class for each of the two or more classes classified by the class classification means for the two or more classification parameters identified by the two or more parameter identifiers. Learning information acquisition means for acquiring from the learning information storage unit,
The calculation formula generation unit,
For each of two or more classification parameters identified by the two or more parameter identifiers, one or more learning information for each class acquired by the learning information acquisition means for the two or more class classifications. Is a calculation formula for calculating price information using, and a calculation formula generating means for generating a calculation formula having two or more parameters as variables.
For each of the two or more classification parameters identified by the two or more parameter identifiers, the calculation formula of each class generated by the calculation formula generation means for each of the two or more classes A price calculation means for substituting one or more parameters possessed by one or more pieces of learning information belonging to each class, calculating a price, and obtaining calculated price information indicating the calculated price,
For each of two or more classification parameters identified by the two or more parameter identifiers, for each of the two or more classes, the price information included in the learning information and the price Error information acquisition means for acquiring error information indicating a difference from the calculated price information corresponding to the information,
For each of the two or more classification parameters identified by the two or more parameter identifiers, the one or more error information acquired by the error information acquisition means is used for the two or more classes. , And a class classification determination means for determining a classification of a class having less error as satisfying a predetermined condition,
The learning information acquisition means,
Two or more constituting each metaclass for each metaclass consisting of a combination of one class selected from the classes included in the classification of the class determined by the class classification determination means for each of the two or more classification parameters Acquiring one or more pieces of learning information corresponding to the classification parameters belonging to the class from the learning information storage unit,
The calculation formula generating means,
As a calculation formula for calculating price information using one or more pieces of learning information acquired by the learning information acquisition means for each metaclass, and generating a calculation formula having a variable for substituting two or more parameters. A program for operating the computer.