JP5064063B2 - Information processing apparatus, information processing method, and program - Google Patents

Description

  The present invention relates to an information processing apparatus or the like that acquires information such as a user's advanced degree and trend transition of a product, etc., using information of an action history such as a user's product purchase.

  Conventionally, there has been a market information analysis device that makes it easy to find a keyword indicating the value of a consumer in order to determine a market trend (see Patent Document 1). The marketing information analysis apparatus includes a market performance value storage unit that stores market performance value data for each product or service, a keyword storage unit that stores a keyword indicating a consumer's value for each product or service, and a predetermined value. A time series totaling unit that totals the market performance value data for each given period in time series, and a total value output unit that outputs the total value data totaled by the time series totaling unit.

  In addition, there is an information processing system that simultaneously realizes both a content recommendation with high accuracy based on an item name and item value that are highly interested by the user, and a content recommendation considering the order of content use (see Patent Document 2). This system stores a content usage history information storage management unit that stores and manages content usage history information of a user, a content usage transition information calculation unit that calculates content usage transition information from content usage history information, and stores content usage transition information Content recommendation information is generated based on the content usage transition information storage management unit to be managed, the content metadata information storage management unit to store and manage content metadata information, content usage history information, content usage transition information and content metadata information A content recommendation information generation unit.

  Further, there is a system that extracts features for each individual item name and recommends content based on the features for each individual item name (see Patent Document 3). This system acquires user-oriented information by user item for the target item name set in advance, and sets the item name in advance by referring to the acquired user-item-oriented information. This is a system that extracts an item value of the number of appearances that is equal to or greater than the threshold value, acquires content information that includes this item value as the value of the target item name, and recommends the acquired content information to the user.

Furthermore, there is a system that improves the possibility of product purchase and realizes a comprehensive recommendation service (see Patent Document 4). In this system, when a user purchases music software, for example, by accessing the server of the music software distribution shop A through a network connection service with a mobile phone, the server of the shop A transmits the purchase information to the center, The center is a system in which concert information by the singer is retrieved from the recommendation rules, and the recommendations are transmitted to the mobile phone via the network connection service. In this system, when a user purchases a concert ticket to the server of the ticket sales shop B by a mobile phone, the server of the shop B transmits the purchase information to the center, and the center transmits the concert information of the purchase information. This is a system that searches for a reservation status such as an airplane on the date of the event from a recommendation rule and sends the recommendation to a mobile phone.
Japanese Patent Laying-Open No. 2005-92721 (first page, FIG. 1 etc.) Japanese Patent Laying-Open No. 2005-293384 (first page, FIG. 1 etc.) JP 2004-362011 A (first page, FIG. 1 etc.) JP 2002-117292 A (first page, FIG. 1 etc.)

  However, in the conventional system, simply by aggregating the market performance value data in time series, the information about the user's advanced level, the trend of product trends, etc. is obtained using the behavior information indicating the behavior of the user's object. I couldn't. In other words, information that is important for marketing, such as trend leaders and product trend transitions, could not be acquired automatically.

  Moreover, in the conventional system, it is related with a user's advanced degree, the fashion transition of goods, etc. using the action information which is the information which shows the log | history by which action is performed with respect to a user's target object. Information could not be acquired, and the system was not enough to contribute to recommendations and marketing.

  The information processing apparatus according to the first aspect of the present invention is information indicating a history of processing of an object by performing an action on the object of the user, and identifies the user identification information for identifying the user and the object The behavior information storage unit storing two or more behavior information having the target object identification information and the timing information indicating the occurrence timing of the behavior, and the two or more behavior information are read from the behavior information storage unit. An action order information acquisition unit that acquires action order information that is information about an action order of two or more users with respect to an object identified by the object identification information from the object identification information and time information included in the information; Using the action order information acquired by the action order information acquisition unit, a leading degree information calculating unit that calculates user leading degree information that is information about a user's leading degree or delay degree, and the leading degree information An information processing apparatus having a leading degree information output section for force.

  With this configuration, it is possible to calculate the leading degree information from the action histories (behavior information) of a plurality of users.

  Further, in the information processing apparatus according to the second aspect of the present invention, in contrast to the first aspect of the invention, the leading degree information calculation unit is configured to obtain a plurality of user order information from two or more action order information acquired by the action order information acquisition unit. A trend leader degree calculating means for calculating a trend leader degree for each of two or more users, which is a degree that is a starting point of an action on the same object, and information indicating a degree of a trend transmission source; From the two or more action order information acquired by the action order information acquisition unit, the degree of following the starting point of action for the same target object of a plurality of users, and the trend follower degree which is information indicating the degree of following the trend, A trend follower degree calculating means for calculating two or more users, wherein the leading degree information output unit includes the trend leader degree and the trend follower degree; Chino is an information processing apparatus for outputting at least one.

  With such a configuration, the trend leader degree and the trend follower degree can be calculated from the action histories (behavior information) of a plurality of users.

  In addition, the information processing apparatus according to the third aspect of the invention accepts the leading degree information output by the leading degree information output unit with respect to either the first or second aspect of the invention, and uses the leading degree information to A trend leader acquisition unit for acquiring user identification information for identifying a trend leader who is an early user who satisfies the time condition of the above, and a trend leader output unit for outputting the user identification information acquired by the trend leader acquisition unit An information processing apparatus.

  With this configuration, a trend leader can be acquired.

  The information processing apparatus according to the fourth aspect of the present invention is the information processing apparatus according to any one of the first to third aspects, wherein the object is a product or service, and the action is purchase of a product or service, or It is an information processing apparatus that is a rental.

  With this configuration, a trend leader or the like can be determined from information such as purchase of goods or services.

  Further, the information processing apparatus according to the fifth aspect of the present invention is information indicating a history of an action on the object of the user, the user identification information for identifying the user, the object identification information for identifying the object, and the generation time of the action Action information storage unit storing two or more action information having time information indicating the time information, and two or more action information are read from the action information storage unit, and the user identification information and the time information possessed by each of the two or more action information From the processing order information acquisition unit that acquires processing order information that is information about the processing order of two or more objects of the user identified by the user identification information, and the processing order acquired by the processing order information acquisition unit Using the information, a leading degree information calculating unit that calculates target leading degree information that is information about a leading degree or a delay degree of a target object, and a leading degree information that outputs the target leading degree information An information processing apparatus having a multi-address output unit.

  With this configuration, it is possible to calculate the object advance degree information from the action histories (action information) of a plurality of users.

  Further, in the information processing apparatus according to the sixth aspect of the present invention, in contrast to the fifth aspect, the object precedence information output unit includes a plurality of pieces of processing order information acquired by the processing order information acquisition unit. Source item degree that calculates the source item degree that is the degree of the target object that is the starting point of the same user's action on the target object and that indicates the hub degree of the target object for each of two or more target objects The derived item degree, which is a degree of following the starting object of the same user's action with respect to a plurality of objects, from the calculating means and the two or more processing order information acquired by the processing order information acquiring unit is 2 or more Derived item degree calculation means for calculating each object, and the object leading degree information output unit is an information processing apparatus that outputs at least one of the source item degree and the derived item degree That.

  With this configuration, the source item degree and the derived item degree can be calculated from action histories (behavior information) of a plurality of users.

  In addition, the information processing apparatus according to the seventh aspect of the invention accepts the object leading degree information output by the object leading degree information output unit with respect to any of the fifth and sixth aspects of the invention, Using the information, the trend transition information acquisition unit that acquires the trend transition information that is the information of the trend transition that is the flow of action on the target object, and the trend transition information acquired by the trend transition information acquisition unit are output. The information processing apparatus further includes a trend transition information output unit.

  With this configuration, trend transition information can be acquired.

  The information processing apparatus according to the eighth aspect of the present invention is the information processing apparatus according to any one of the fifth to seventh aspects, wherein the object is a product or a service, and the action is a purchase of a product or a service, or a product It is an information processing apparatus that is a rental.

  With such a configuration, it is possible to obtain trend transition information on products and the like from information such as purchases of products or services.

  According to the information processing apparatus of the present invention, using the behavior information that is information indicating a history of processing of the target object by performing the action on the target object of the user, the degree of advancement of the user or the trend of the product is changed. You can get information about.

Hereinafter, embodiments of an information processing apparatus and the like will be described with reference to the drawings. In addition, since the component which attached | subjected the same code | symbol in embodiment performs the same operation | movement, description may be abbreviate | omitted again.
(Embodiment 1)

  In this Embodiment, it is the information which shows the log | history by which a target object is processed by performing action with respect to a user's target object, Comprising: The user identification information which identifies a user, The target object identification information which identifies a target object, An information processing apparatus that manages behavior information having time information indicating the occurrence time of behavior and outputs information related to the characteristics (preceding degree or delay degree) of the user with respect to other users using the behavior information will be described.

  FIG. 1 is a conceptual diagram of an information processing system in the present embodiment. The information processing system includes one information processing apparatus 11 and two or more information terminals 12. Here, it is assumed that one or more users operate the information terminal 12 and access the information processing apparatus 11. The information processing device 11 is a server device on the Web, for example. The information terminal 12 may be a so-called laptop computer or a mobile phone. The information terminal 12 may be any terminal that can communicate with the information processing apparatus 11.

  FIG. 2 is a block diagram of the information processing system in the present embodiment. The information processing apparatus 11 includes a server-side receiving unit 1101, a behavior information storage unit 1102, a behavior information storage unit 1103, a behavior order information acquisition unit 1104, a leading degree information calculation unit 1105, a leading degree information output unit 1106, and a trend leader acquisition unit 1107. The trend leader output unit 1108 is provided.

  The leading degree information calculating unit 1105 includes a trend leader degree calculating unit 11051 and a trend follower degree calculating unit 11052.

  The information terminal 12 includes a reception unit 1201, a terminal side transmission unit 1202, a terminal side reception unit 1203, and a terminal side output unit 1204.

  The server-side receiving unit 1101 receives behavior information, various instructions, data, and the like from the information terminal 12. The behavior information is information indicating a history of processing the target object by performing the action on the target object of the user. The behavior information includes user identification information, object identification information, and time information. The user identification information is information for identifying a user. Actions include, for example, purchase of goods or services, or rental of goods, entry to places (eg, amusement park attractions), visits to places, regions, countries, etc., comments on articles, hyperlinks to information And trackbacks, voting for your favorite movie (or political party / politician, popular talent). The object identification information is information for identifying the object, such as an object ID and an object name. The target object is, for example, information such as products, services, places, scenic spots, regions, countries, articles, people, and the like, and includes objects that are targets of all actions. The time information is information indicating the occurrence time of the action. The time information may be provided by the information processing apparatus 11 or the information terminal 12. The date information may be a date alone or information having a date and time. The format of the timing information is not limited. The user identification information is, for example, a user ID, name, mail address, user information terminal ID (IP address, telephone number, MAC address, etc.). Further, examples of the above instructions include a leading degree information output instruction that is an instruction to output leading degree information, a trend leader output instruction that is an instruction to output a trend leader, and the like. Note that the behavior information received by the server-side receiving unit 1101 may not have time information. In such a case, the information processing apparatus 11 acquires time information indicating time (such as the time when the server-side receiving unit 1101 receives the information) by means (not shown) (acquired from a clock in its own apparatus or an external apparatus) Write as time information of action information. The server-side receiving unit 1101 is preferably a wireless or wired communication means, but can also be realized by a means for receiving a broadcast.

  The behavior information accumulation unit 1102 accumulates the behavior information in the behavior information storage unit 1103 when the server side reception unit 1101 receives the behavior information. The behavior information storage unit 1102 can usually be realized by an MPU, a memory, or the like. The processing procedure of the behavior information storage unit 1102 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 behavior information storage unit 1103 stores two or more behavior information. The behavior information storage unit 1103 is preferably a nonvolatile recording medium, but can also be realized by a volatile recording medium.

  The action order information acquisition unit 1104 reads two or more pieces of action information from the action information storage unit 1103, and the object identified by the object identification information from the object identification information and the time information included in the two or more pieces of action information. Action order information, which is information about the action order of two or more users for an object, is acquired and placed on a memory. The action order information is information of a directed graph constructed from the context of the time indicated by the time information included in the action information, and the format does not matter. The format may be a matrix or link information. The link information is information in which action information is connected by links in the order of times indicated by the time information. When the behavior information is connected by a link, the link may be a link connecting the behavior information in ascending order or a link connecting the descending order. A specific example of the action order information will be described later. The action order information acquisition unit 1104 can be usually realized by an MPU, a memory, or the like. The processing procedure of the action order information acquisition unit 1104 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 precedence level information calculation unit 1105 uses the behavior order information acquired by the behavior order information acquisition unit 1104, substitutes the behavior order information into a predetermined calculation formula, and uses information about the user's precedence level or delay level. Certain user precedence information is calculated and placed on the memory. The user precedence information includes, for example, one or both of the trend leader degree and the trend follower degree. The trend leader degree is a degree that is a starting point of action for the same target object of a plurality of users, and is information indicating a degree of being a user's fashion transmission source. The trend follower degree is a degree of following a starting point of an action with respect to the same target object of a plurality of users, and is information indicating a degree of following the trend. Specific examples of the information on the user precedence information, the trend leader degree, or the trend follower degree will be described later. The leading degree information calculation unit 1105 can usually be realized by an MPU, a memory, or the like. The processing procedure of the leading degree information calculation unit 1105 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The trend leader degree calculating unit 11051 substitutes the two or more action order information acquired by the action order information acquiring unit 1104 into a predetermined calculation formula, and calculates the trend leader degree for each of two or more users. Place it on the memory. A specific example of the method for calculating the trend leader degree will be described later. The trend leader degree calculating means 11051 can be usually realized by an MPU, a memory, or the like. The processing procedure of the trend leader degree calculating means 11051 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The trend follower degree calculation means 11052 substitutes the two or more action order information acquired by the action order information acquisition unit 1104 into a predetermined calculation formula, and calculates the trend follower degree for each of the two or more users. Place it on the memory. A specific example of the method for calculating the trend follower degree will be described later. The trend follower degree calculating unit 11052 can be realized usually by an MPU, a memory, or the like. The processing procedure of the trend follower degree calculating unit 11052 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 leading degree information output unit 1106 outputs the leading degree information calculated by the leading degree information calculating unit 1105. The leading degree information output unit 1106 outputs at least one of a trend leader degree and a trend follower degree, for example. Here, output is a concept including display on a display, printing on a printer, sound output, transmission to an external device, passing data to other processing, and the like. The other processes include a process for recommending products and services, a process for outputting rankings of trend leader degrees and trend follower degrees, and the like. The process of recommending a product or service is, for example, reading information on a product or service recently purchased by a user with the highest trend leader degree from the behavior information storage unit 1103, and obtaining information on the product or service as an information terminal 12 is a process to transmit to 12. Alternatively, the process of recommending a product or service is, for example, a user with a higher trend leader degree than a certain user reads information on the purchased product or service from the behavior information storage unit 1103, and information on the product or service is The process etc. which transmit to the information terminal 12 may be sufficient. When recommending a product or service, there are various possible types of user to purchase a product or the like. In other words, when recommending a product or service, one or more pieces of information of the trend leader degree or the trend follower degree may be used. The process of outputting the ranking of the trend leader degree and the trend follower degree is a process of sorting the user identification information using the trend leader degree and the trend follower degree as a key and transmitting the sorting result to the information terminal 12. The precedence information output unit 1106 may or may not include an output device such as a display or a speaker. The leading degree information output unit 1106 can be realized by driver software of an output device or driver software of an output device and an output device. Note that here, the leading degree information output unit 1106 will mainly be described as passing the leading degree information to the trend leader acquisition unit 1107.

  The trend leader acquisition unit 1107 receives the leading degree information output by the leading degree information output unit 1106, and uses the leading degree information to identify a trend leader who is a user who acts early on satisfying a certain period of time. Get identification information. The trend leader acquisition unit 1107 may acquire user identification information paired with a value having the highest trend leader degree, may acquire top three user identification information having the highest trend leader degree, or may be determined in advance. User identification information paired with a trend leader degree higher than a given threshold value may be acquired. In addition, the trend leader acquisition unit 1107 determines the ability to create a user's trend using both the trend leader degree and the trend follower degree, and meets a predetermined condition (for example, determines that the ability to create a trend is the highest). The user identification information of the user may be acquired. The trend leader acquisition unit 1107 can usually be realized by an MPU, a memory, or the like. The processing procedure of the trend leader acquisition unit 1107 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 trend leader output unit 1108 outputs the user identification information acquired by the trend leader acquisition unit 1107. Here, the output is a concept including display, printing, audio output, transmission to an external device, passing data to other processing, and the like. The other processing includes processing for recommending a product or service, processing for notifying the user identified by the user identification information, and the like. The process of recommending a product or service refers to information on the product or service purchased by the user (trend leader) identified by the user identification information from the behavior information storage unit 1103, and information on the product or service as information This is a process of transmitting to the terminal 12. The trend leader output unit 1108 may or may not include an output device such as a display or a speaker. The trend leader output unit 1108 can be implemented by output device driver software, or output device driver software and an output device.

  The accepting unit 1201 accepts various instructions from the user, behavior information, various data, and the like. The input means such as various instructions and action information may be anything such as a numeric keypad, a keyboard, a mouse, or a menu screen. The accepting unit 1201 can be realized by a device driver for input means such as a numeric keypad or a keyboard, control software for a menu screen, and the like.

  The terminal side transmission unit 1202 transmits the behavior information received by the reception unit 1201 and various data to the information processing apparatus 11 in accordance with the received instruction. The terminal-side transmitting unit 1202 is usually realized by a wireless or wired communication unit, but may be realized by a broadcasting unit.

  The terminal side receiving unit 1203 receives user identification information from the information processing apparatus 11. In addition, the terminal-side receiving unit 1203 may receive user precedence information (such as a trend leader degree and a trend follower degree) from the information processing apparatus 11.

  The terminal side output unit 1204 outputs the user identification information and the precedence information received by the terminal side receiving unit 1203, information input by the user, and the like. The terminal side output unit 1204 may be considered as including or not including an output device such as a display or a speaker. The terminal-side output unit 1204 can be implemented by output device driver software, or output device driver software and an output device.

  Next, the operation of the information processing system will be described. First, the operation of the information processing apparatus 11 will be described using the flowcharts of FIGS.

  (Step S301) The server-side receiving unit 1101 determines whether or not behavior information has been received. If the behavior information is received, the process goes to step S302, and if the behavior information is not received, the process goes to step S303.

  (Step S302) The behavior information accumulation unit 1102 adds the behavior information received in step S301 to the behavior information storage unit 1103. Go to step S301.

  (Step S303) The server-side receiving unit 1101 determines whether or not a leading degree information output instruction that is an instruction to output leading degree information is received. If a leading degree information output instruction is received, the process proceeds to step S304, and if a leading degree information output instruction is not received, the process proceeds to step S306.

  (Step S304) The leading degree information calculating unit 1105 calculates leading degree information. Details of the leading degree information calculation process will be described with reference to the flowcharts of FIGS.

  (Step S305) The leading degree information output unit 1106 transmits the leading degree information calculated in Step S304 to the information terminal 12 that has transmitted the leading degree information output instruction. The process returns to step S301.

  (Step S306) The server-side receiving unit 1101 determines whether or not a trend leader output instruction that is an instruction to output a trend leader has been received. If the trend leader output instruction is received, the process goes to step S307, and if the trend leader output instruction is not received, the process returns to step S301.

  (Step S307) The leading degree information calculating unit 1105 calculates leading degree information. Details of the leading degree information calculation process will be described with reference to the flowcharts of FIGS.

  (Step S308) The trend leader acquisition unit 1107 reads a trend leader condition, which is information indicating a condition for extracting user identification information as a trend leader. Here, it is assumed that the trend leader acquisition unit 1107 stores, for example, trend leader conditions in advance. Note that the trend leader acquisition unit 1107 may dynamically determine the trend leader condition.

  (Step S309) The trend leader acquisition unit 1107 acquires user identification information of a user that matches the trend leader condition read in step S308. A specific example of the user identification information acquisition process will be described later. The trend leader acquisition unit 1107 normally applies each user's leading degree information (information of one or more of the trend leader degree and the trend leader follower degree) to the trend leader condition and matches the trend leader condition. Determine whether or not. Then, the trend leader acquisition unit 1107 reads the user identification information that is paired with the leading degree information that matches the trend leader condition.

  (Step S310) The trend leader output unit 1108 transmits the user identification information acquired in step S309 to the information terminal 12. The process returns to step S301.

  In the flowchart of FIG. 3, processing corresponding to an instruction other than the leading degree information output instruction and the trend leader output instruction may be performed.

  In the flowchart of FIG. 3, the process ends when the power is turned off or the process is terminated.

  Next, details of the leading degree information calculation processing will be described with reference to the flowcharts of FIGS.

  (Step S401) The action order information acquisition unit 1104 reads out all two or more pieces of action information from the action information storage unit 1103, and obtains user identification information and time information corresponding to the object identification information indicating one or more objects. The information of the directed graph which links two or more user identification information in the order of the time when the action occurred is acquired from the acquired two or more time information. An example of the algorithm for configuring the directed graph information will be described with reference to the flowchart of FIG. The directed graph information here has the same meaning as the action order information. Further, the “order of the time when the action occurred” may be either the order of the old action to the new action, or the order of the new action to the old action.

  (Step S402) The trend leader degree calculating means 11051 initializes a trend leader degree vector. The trend leader degree vector is vector data having the trend leader degree corresponding to each user identification information as an element. The trend follower degree calculation unit 11052 initializes a trend follower degree vector. The rend follower degree vector is vector data having a lend follower degree corresponding to each user identification information as an element.

  (Step S403) The trend follower degree calculating means 11052 substitutes the directed graph information (matrix) obtained in step S401 and the current trend leader degree vector into a predetermined calculation formula, and the next trend follower degree vector is obtained. obtain.

  (Step S404) The trend leader degree calculating means 11051 substitutes the directed graph information (matrix) obtained in step S401 and the current trend follower degree vector into a predetermined calculation formula, and obtains the next trend leader degree vector. obtain.

  (Step S405) The trend leader degree calculating unit 11051 and the trend follower degree calculating unit 11052 determine whether the trend leader degree and the trend follower degree have converged. Specifically, it is determined whether or not “| trend leader degree vector−next trend leader degree vector | <ε” and “| trend follower degree vector−next trend follower degree vector | <ε” are satisfied. Here, ε is preferably a very small number such as “0.0001”. If it has converged, go to step S406, and if it has not converged, go to step S407.

  (Step S406) The trend leader degree calculating unit 11051 and the trend follower degree calculating unit 11052 use the elements of the next trend leader degree vector and the next trend follower degree vector as the trend leader degree and the trend follower degree of each user, respectively. Accumulate on a storage medium. Return to upper process.

  (Step S407) The trend leader degree calculating unit 11051 substitutes the next trend leader degree vector as a trend leader degree vector into a variable in which the trend leader degree vector is stored.

  (Step S408) The trend follower degree calculating unit 11052 substitutes the next trend follower degree vector as a trend follower degree vector into a variable in which the trend follower degree vector is stored. The process returns to step S403.

  In the flowchart of FIG. 4, the trend leader degree is calculated after calculating the trend leader degree (steps S403 and S404). However, it goes without saying that the order of calculating the trend leader degree and the trend follower degree does not matter. That is, in the flowchart of FIG. 4, the trend leader degree may be calculated after the trend follower degree is calculated. The same applies to other embodiments.

  Next, an example of the algorithm for the configuration of the directed graph information in step S401 will be described using the flowchart of FIG.

  (Step S501) The action order information acquisition unit 1104 substitutes 1 for a counter i.

  (Step S502) The action order information acquisition unit 1104 determines whether the i-th object identification information exists from the object identification information included in the action information of the action information storage unit 1103. If the i-th object identification information exists, the process proceeds to step S503, and if the i-th object identification information does not exist, the process returns to the upper level. Note that the i-th object identification information is i-th type object identification information, and behavior information having the same object identification information is not determined as having different object identification information. Therefore, when one object identification information is managed separately as one record by means not shown, it is preferable that the action order information acquisition unit 1104 reads the i-th object identification information from the management information. It is.

  (Step S503) The action order information acquisition unit 1104 acquires all the user identification information of the user who has acted on the object identified by the i-th object identification information from the action information storage unit 1103. The data are temporarily stored in a memory or the like in the order shown. The stored information is a set of user identification information.

  (Step S504) The action order information acquisition unit 1104 substitutes 1 for a counter j.

  (Step S505) The action order information acquisition unit 1104 determines whether or not the “j + 1” -th user identification information exists in the set of user identification information stored in Step S503. If the “j + 1” th user identification information exists, the process goes to step S506, and if the “j + 1” th user identification information does not exist, the process goes to step S509.

  (Step S506) The action order information acquisition unit 1104 acquires the jth and “j + 1” th user identification information in the set of user identification information stored in Step S503.

  (Step S507) The action order information acquisition unit 1104 sets the value of the element corresponding to the jth and “j + 1” th user identification information, which is an element in the directed graph information and acquired in Step S506, to “1”. " That is, the meaning that the network link is extended is “1”.

  (Step S508) The action order information acquisition unit 1104 increments j by 1. The process returns to step S505.

  (Step S509) The action order information acquisition unit 1104 increments i by 1. The process returns to step S502.

  Next, the operation of the information terminal 12 will be described. The reception unit 1201 of the information terminal 12 receives various instructions from the user, behavior information, various data, and the like. And the terminal side transmission part 1202 transmits the action information, various data, etc. which the reception part 1201 received to the information processing apparatus 11 according to the received instruction | indication. Next, the terminal-side receiving unit 1203 receives user identification information and leading degree information from the information processing apparatus 11, for example, according to various instructions transmitted by the terminal-side transmitting unit 1202. Then, the terminal-side output unit 1204 outputs the user identification information and the leading degree information received by the terminal-side receiving unit 1203. The operation of the information terminal 12 described above is a well-known technique and will not be described in detail.

  Hereinafter, a specific operation of the information processing apparatus according to the present embodiment will be described. FIG. 1 is a conceptual diagram of the information processing system.

  Now, it is assumed that the action order information acquisition unit 1104 or a unit (not shown) holds the object management table shown in FIG. The object management table is a table for managing objects. Here, the object is a product, particularly an article to be worn such as clothes or shoes. The target object management table is a table that stores one or more target object records that are information on products or services that are targets of electronic commerce. The object management table has “ID”, “object identification information”, and “object attribute”. “ID” is information for identifying a table record and exists for table management. “Object identification information” is information for identifying an object, and here is an object ID. However, the “object identification information” may be a product name or the like, and may be considered as information including an object attribute described later. The “object attribute” stores one or more attribute values of the object. The attribute value includes “product name”, “product type”, “size”, and the like. “Product type” indicates the type of product.

  The behavior information storage unit 1103 stores a behavior information management table shown in FIG. Here, the behavior information management table stores behavior information which is information indicating purchase history of past products and the like. That is, here, the behavior information is information indicating that the user has generated the behavior of purchasing a product or the like, and includes user identification information, object identification information, and time information. The behavior information management table stores one or more records having “ID” and “behavior information”. The “behavior information” includes “user identification information”, “object identification information”, and “time information”.

  The behavior information stored in the behavior information storage unit 1103 is accumulated by, for example, the operation described below. In other words, it is assumed that the user logs in to a site that conducts certain electronic commerce and displays, for example, a home page as shown in FIG.

  Then, the user purchases a favorite product (presses the “Add to shopping cart” button and performs electronic payment processing). Then, the reception unit 1201 of the information terminal 12 receives “object identification information” indicating a product to be purchased. The information terminal 12 constitutes behavior information (object identification information, user identification information, time information), and the terminal-side transmission unit 1202 transmits the behavior information to the information processing apparatus 11. Note that the user identification information is input by the user, for example, when logging in to the site of FIG. 8 or when making electronic payment. In addition, it is assumed that the time information is acquired from its own clock when the information terminal 12 accepts pressing of a purchase decision button (not shown). The time information is preferably acquired when the information processing apparatus 11 receives the behavior information.

  Next, the server side receiving unit 1101 of the information processing apparatus 11 receives behavior information. Then, the behavior information accumulation unit 1102 adds the received behavior information to the behavior information storage unit 1103. The action information is accumulated by the above processing.

  Next, it is assumed that the user inputs a leading degree information output instruction using the input unit of the information terminal 12. Then, the receiving unit 1201 of the information terminal 12 receives a leading degree information output instruction. Next, the terminal-side transmission unit 1202 transmits the leading degree information output instruction received by the receiving unit 1201 to the information processing apparatus 11.

  Next, the server-side receiving unit 1101 of the information processing apparatus 11 receives a leading degree information output instruction. Then, the leading degree information calculating unit 1105 and the like calculate leading degree information as follows. That is, first, the behavior order information acquisition unit 1104 reads out all the two or more behavior information from the behavior information management table of FIG. 7, and the user identification information and time corresponding to the object identification information indicating each of the one or more objects. Information is acquired, and information of a directed graph that links two or more pieces of user identification information in the order of the time when an action has occurred is configured from the acquired two or more pieces of time information. Here, it is assumed that the behavior order information acquisition unit 1104 obtains the network information of the user identification information for each target identification information by paying attention to the order of purchase of products and the like as conceptually shown in FIG. . Furthermore, the object identification information is deleted from the conceptual diagram of FIG. 9, and the action order information acquisition unit 1104 configures directed graph information that links purchaser identification information as shown in FIG. In FIG. 10, the directed graph (arrow) is directed from the user identification information (node) of the user who purchased late to the user identification information (node) of the user who purchased earlier. This directed graph information is expressed as matrix (M) information as shown in FIG. In FIG. 11, the matrix (M) indicates the link source and the column indicate the link destination, and for example, “E → B” is expressed as an element value “1” of 5 rows and 2 columns. The action order information acquisition unit 1104 writes the information shown in FIG. 11 in an array of 5 rows and 5 columns to obtain directed graph information. Note that the initial value of the 5 × 5 array is “0” in all elements.

Next, the trend leader degree calculation unit 11051 initializes the trend leader degree vector, and obtains the trend leader degree vector (TL) “(1 1 1 1 1) ^T ”. The vector “T” is transpose. Also, the trend follower degree calculating means 11052 initializes a trend follower degree vector (TF) to obtain “(1 1 1 1 1) ^T ”.

Next, the trend follower degree calculation means 11052 obtains the next trend follower degree vector using the directed graph information (matrix (M)) and the current trend leader degree vector (TL). Here, for example, the trend follower degree calculating means 11052 obtains the next trend follower degree vector (TF) by “TF = M · TL, TF = TF / | TF |”. Specifically, the trend follower degree calculation means 11052 multiplies the directed graph information (matrix (M)) and the trend leader degree vector (TL) by a matrix multiplication circuit, and the next trend follower leader degree vector “(2 1 1 2 2) ^T ”is obtained and placed on the memory (FIG. 12 (1)).

Next, the trend leader degree calculating means 11051 obtains the next trend follower degree vector using the directed graph information (matrix (M)) and the current trend follower degree vector (TF). Here, for example, the trend leader degree calculating means 11051 obtains the next trend leader degree vector (TL) by “TL = M ^T · TF, TL = TL / | TL |”. Specifically, the trend leader degree calculation means 11051 multiplies the directed graph information (matrix (M ^T )) and the trend follower degree vector (TF) by a matrix multiplication circuit, and the next trend leader degree vector “(1 7 2 4 0) ^T ”is obtained and placed on the memory (FIG. 12 (2)). The “current trend follower degree vector (TF)” is the same as the previously calculated “next trend follower degree vector (TF)”.

Then, the trend follower degree calculation means 11052 divides the trend follower leader degree vector “(2 1 1 2 2) ^T ” (TF) by the absolute value (| TF |) to obtain the next trend follower degree vector (TF). ) The next trend follower vector (TF) is “(0.53 0.27 0.27 0.53 0.53) ^T ” ((3) in FIG. 12).

Then, the trend leader degree calculating means 11051 divides the vector “(1 7 2 4 0) ^T ” (also referred to as TL) by its absolute value (| TL |), and the next trend leader degree vector “( 0.12 0.84 0.24 0.48 0.0) ^T ”((4) in FIG. 12).

Next, similarly, the trend follower degree calculating unit 11052 further calculates the next trend follower degree vector ((5) and (7) in FIG. 12). Then, the trend follower degree calculating means 11052 further arranges the next trend follower degree vector “(0.57 0.052 0.36 0.47 0.57) ^T ” on the memory ((7) in FIG. 12). ).

  Then, the trend follower degree calculating means 11052 calculates | previous trend follower degree vector−current trend follower degree vector |, and whether the value is smaller than a predetermined value (ε “ε is, for example, 0.001”). Determine whether. That is, the trend follower degree calculating unit 11052 determines whether or not the trend follower degree vector has converged.

  If it is determined that the trend follower degree calculation unit 11052 has converged, the process ends. If the trend follower degree calculation unit 11052 determines that the trend follower degree calculation unit 11052 has not converged, the trend follower degree calculation unit 11052 continues the same process as described above until the convergence. In this case, it is assumed that the trend follower degree vector has converged when the value becomes the value shown in (9) of FIG.

The trend leader degree calculating means 11051 also calculates the next trend leader degree vector ((6) and (8) in FIG. 12). Then, the trend leader degree calculating means 11051 further arranges the next trend leader degree vector “(0.022 0.85 0.20 0.49 0.0) ^T ” on the memory ((8) in FIG. 12). ).

  Then, the trend leader degree calculating means 11051 calculates | previous trend leader degree vector-current trend leader degree vector |, and whether or not the value is smaller than a predetermined value (ε “ε is, for example, 0.001”). Determine whether. That is, the trend leader degree calculating unit 11051 determines whether or not the trend leader degree vector has converged.

  If it is determined that the trend leader degree calculation unit 11051 has converged, the process ends. If the trend leader degree calculation unit 11051 determines that the trend leader degree calculation unit 11051 has not converged, it continues the same process as described above until the convergence. In this example, it is assumed that the trend leader degree vector has converged when it reaches the value shown in (10) of FIG.

  By the above calculation, the leading degree information calculation unit 1105 obtains the trend leader degree and the trend follower degree of each user shown in FIG.

  In the above description, the action order information acquisition unit 1104 configures the directed graph information considering only the connection of the user identification information using the time information without considering the purchase order and the purchase time. This is apparent from the fact that the network structure in FIG. 10 is configured from the network in the “user identification information” in FIG.

  However, the action order information acquisition unit 1104 may configure the directed graph information in consideration of the order of purchase. For example, when the product [1] is purchased in the order of “A → B → C → D”, the action order information acquisition unit 1104 performs weighting considering the order (for example, by multiplying by a constant 0.9), The weight of A ← B may be “1”, the weight of “B ← C” may be “0.9”, and the weight of “C ← D” may be “0.81”. “1”, “0.9”, and “0.81” constitute element values of the directed graph information (matrix).

In addition, the action order information acquisition unit 1104 may configure the directed graph information in consideration of the purchase time (operation occurrence time). For example, when the product [1] is purchased in the order of “A (time t ₁ ) → B (time t ₃ ) → C (time t ₁₀ ) → D (time t ₃₀ )”, the forgetting factor “e ^{− (T−tx)} ”may be weighted to calculate the value of the element of the directed graph information (matrix). The subscripts “1” and “3” at the times t ₁ and t ₃ are the same as the ID of the behavior information management table in FIG.

  In addition, there can be various algorithms for the action order information acquisition unit 1104 to configure the information of the directed graph. The behavior order information acquisition unit 1104 reads two or more behavior information from the behavior information storage unit 1103, acquires user identification information and time information corresponding to the target identification information indicating one or more target objects, and acquires the acquired 2 What is necessary is just to comprise the information of the directed graph which links two or more user identification information in order of the generation | occurrence | production time of an operation | movement from the above time information. This directed graph information may be information having a weighted value as described above.

  Next, the leading degree information output unit 1106 transmits the leading degree information (one or more pieces of information of the trend leader degree or the trend follower degree) in FIG. 13 to the information terminal 12. Here, for example, it is preferable that the leading degree information output unit 1106 slightly processes the leading degree information of FIG. 13 and transmits it to the information terminal 12. That is, the leading degree information output unit 1106 sorts the user identification information in descending order of the trend leader degree in the leading degree information of FIG. 13, ranks the users, and “1st place: B, 2nd place: D, 3”. Information of “rank: C, 4th place: A, 5th place: E” is acquired. Then, the leading degree information output unit 1106 transmits information of “first place: B, second place: D, third place: C, fourth place: A, fifth place: E” to the information terminal 12.

  Through the above processing, the user of the information terminal 12 can know his / her trend leader degree. In such a case, it is preferable that the leading degree information output unit 1106 determines (ranks) the order of the advanced degree of the user in consideration of the trend follower degree.

  For example, when the leading degree information output unit 1106 selects trend leaders up to the top five, an algorithm that the trend follower degree does not select user identification information that is paired with a value larger than a predetermined threshold is also used. good. In such a case, the leading degree information output unit 1106 selects the user identification information of the top five users of the trend leader degree from the user identification information whose trend follower degree is less than a predetermined threshold, and the rank It is preferable to transmit to the information terminal 12 together.

  Next, it is assumed that the user inputs a trend leader output instruction using the input unit of the information terminal 12.

  Then, it is assumed that the trend leader degree and the trend follower degree of each user shown in FIG. 13 are calculated by the same process as described above.

  Next, the trend leader acquisition unit 1107 is a trend leader condition (here, “trend follower degree <= 0.5 and trend leader degree> 0.0) which is information indicating a condition for extracting user identification information as a trend leader. 5 ") is read out.

  Next, the trend leader acquisition unit 1107 displays the user identification information (B, D) of the user that matches the read trend leader condition (trend follower degree <= 0.5 and trend leader degree> 0.5) as shown in FIG. Get from the processing result of.

  Then, the trend leader output unit 1108 transmits the acquired user identification information (B, D) to the information terminal 12.

  Next, the terminal-side receiving unit 1203 of the information terminal 12 receives the user identification information (B, D), and the terminal-side output unit 1204 outputs the user identification information (B, D) as a trend leader to the display. To do.

  As described above, according to the present embodiment, it is possible to calculate the leading degree information (the trend leader degree and the trend follower degree) from the action histories (behavior information) of a plurality of users. In addition, by using the leading degree information, it is possible to calculate a ranking of the degree of trend leader or to detect a trend leader.

  In the present embodiment, the information processing apparatus 11 receives behavior information from the information terminal 12. However, the information processing apparatus 11 cannot communicate with the information terminal 12 and may store the behavior information via manual input or a storage medium. That is, the information processing apparatus 11 may process the stored behavior information standalone. At that time, the information processing apparatus 11 may transmit a processing result (such as precedence information) to an external apparatus such as the information terminal 12.

  Further, in the present embodiment, the leading degree information is calculated with the reception unit 1201 receiving a leading degree information output instruction as a trigger. However, the trigger for calculating the leading degree information does not matter. That is, it is preferable that the information processing apparatus 11 calculates the leading degree information in the background without a user instruction.

  As a specific example of the present embodiment, the information terminal 12 outputs the trend leader to the display. However, as described above, the information on the trend leader (user identification information) may be passed to another process. Then, other processes such as a process of recommending a product or service, a process of notifying the user identified by the user identification information, or the like may be performed.

  Furthermore, the processing in the present embodiment may be realized by software. Then, this software may be distributed by software download or the like. Further, this software may be recorded and distributed on a recording medium such as a CD-ROM. This also applies to other embodiments in this specification. Note that the software that implements the information processing apparatus according to the present embodiment is the following program. In other words, the program reads out two or more pieces of behavior information stored in a storage medium, and is identified by the subject identification information from the subject identification information and the timing information included in each of the two or more pieces of behavior information. The action order information acquisition unit that acquires action order information that is information about the action order of two or more users with respect to the target object, and the action order information acquired by the action order information acquisition unit, Alternatively, it is a program for functioning as a leading degree information calculating unit that calculates user leading degree information that is information about the degree of delay, and a leading degree information output unit that outputs the leading degree information.

  Further, in the above program, the leading degree information calculation unit is a degree that acts as a starting point of an action on the same object of a plurality of users from two or more action order information acquired by the action order information acquisition unit. The trend leader degree calculating means for calculating the trend leader degree, which is information indicating the degree of being a fashion transmission source, for two or more users, and the two or more action order information acquired by the action order information acquiring unit The trend follower degree calculating means for calculating a trend follower degree, which is a degree of following a starting point of an action on the same object of a plurality of users and indicating a degree of following the trend, for each of two or more users The leading degree information output unit outputs at least one of the trend leader degree and the trend follower degree As shall, it is preferred to cause a computer to function.

Further, in the above program, the user identification that accepts the leading degree information output by the leading degree information output unit and uses the leading degree information to identify a trend leader who is an early user who satisfies a certain temporal condition A trend leader acquisition unit that acquires information;
It is preferable to further cause the computer to function as a trend leader output unit that outputs the user identification information acquired by the trend leader acquisition unit.
(Embodiment 2)

  In this Embodiment, it is the information which shows the log | history by which a target object is processed by performing action with respect to a user's target object, Comprising: The user identification information which identifies a user, The target object identification information which identifies a target object, An information processing apparatus that manages behavior information having time information indicating the occurrence timing of the behavior, and outputs information related to characteristics (advanced degree, follow-up degree) of the target object such as a product with respect to another target object using the behavior information. Will be described. The conceptual diagram of the information processing system in the present embodiment is the same as FIG.

  FIG. 14 is a block diagram of the information processing system in the present embodiment. The information processing system includes one information processing apparatus 141 and two or more information terminals 12. The information processing apparatus 141 includes a server-side receiving unit 1101, a behavior information storage unit 1102, a behavior information storage unit 1103, a processing order information acquisition unit 14104, a leading degree information calculating unit 14105, a target leading degree information output unit 14106, and trend transition information. An acquisition unit 14107 and a trend transition information output unit 14108 are provided.

  The leading degree information calculating unit 14105 includes a source item degree calculating unit 141051 and a derived item degree calculating unit 141052.

  The processing order information acquisition unit 14104 reads two or more pieces of behavior information from the behavior information storage unit 1103, and from the user identification information and the time information that each of the two or more pieces of behavior information has, the user identified by the user identification information Processing order information which is information about processing order for two or more objects is acquired. The processing order information is information about the processing order of a certain user for two or more objects. The processing order information is information of a directed graph constructed from the context of the time indicated by the time information included in the behavior information, and the format does not matter. The format may be a matrix or link information. For example, when a user purchases a product “disposable camera → APS camera → compact digital camera → digital single lens reflex camera” in this order, the processing order information includes, for example, “ID for identifying disposable camera, ID for identifying APS camera, compact This is an information string of “ID for identifying digital camera, ID for identifying digital single lens reflex camera”. Further specific examples of the processing order information will be described later. The processing order information acquisition unit 14104 can be usually realized by an MPU, a memory, or the like. The processing procedure of the processing order information acquisition unit 14104 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The leading degree information calculating unit 14105 uses the processing order information acquired by the processing order information acquiring unit 14104, substitutes the processing order information into a predetermined calculation formula, and information about the leading degree or the delay degree of the target object. The object leading degree information is calculated. The degree of advance or delay of an object is information about the degree of advance and the degree of delay for the time when the object is processed (purchase, rental, visit, etc.). More specifically, the leading degree information calculation unit 14105 includes the object leading degree information “ID for identifying a disposable camera, ID for identifying an APS camera, ID for identifying a compact digital camera, and ID for identifying a digital single lens reflex camera”. From the object advance information of a plurality of users, the object advance information that is information on the degree of purchase of each object (for example, a disposable camera, an APS camera, etc.) earlier or later is calculated. To do. A specific example of the calculation method of the object leading degree information will be described later. Further, the object advance degree information is, for example, information of one or more of a source item degree and a derived item degree described later. The leading degree information calculation unit 14105 can be usually realized by an MPU, a memory, or the like. The processing procedure of the leading degree information calculation unit 14105 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 source item degree calculation means 141051 substitutes the processing order information for two or more pieces of processing order information acquired by the processing order information acquisition unit 14104 into a predetermined calculation formula, and sets the source item degree to each of two or more targets. Calculate for objects. The source item degree is information indicating the degree of an object that is the starting point of the action of the same user with respect to a plurality of objects, and is information indicating the hub degree of the object. The source item degree calculation unit 141051 can be usually realized by an MPU, a memory, or the like. The processing procedure of the source item degree calculation unit 141051 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The derived item degree calculation means 141052 substitutes the processing order information for two or more pieces of processing order information acquired by the processing order information acquisition unit 14104 into a predetermined calculation formula, and determines the derived item degree for each of two or more targets. Calculate for objects. Derived item degree is information which shows the degree of following (derived) the target object of the same user's action with respect to a plurality of target objects. Derived item degree calculation means 141052 can usually be realized by an MPU, a memory, or the like. The processing procedure of the derived item degree calculation means 141052 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The object leading degree information output unit 14106 outputs the object leading degree information. Here, the output is a concept including display on a display, printing on a printer, sound output, transmission to an external device, passing object leading degree information to another processing unit, and the like. The object leading degree information output unit 14106 may or may not include an output device such as a display or a speaker. The object leading degree information output unit 14106 can be realized by driver software of an output device or driver software and an output device of an output device.

  The trend transition information acquisition unit 14107 receives the target leading degree information output by the target leading degree information output unit 14106, and uses the target leading degree information to cause a trend in which a behavior is caused to the target. The trend transition information that is transition information is acquired. The trend transition information acquisition unit 14107 can be usually realized by an MPU, a memory, or the like. The processing procedure of the trend transition information acquisition unit 14107 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The trend transition information output unit 14108 outputs the trend transition information acquired by the trend transition information acquisition unit 14107. Here, output is a concept including display on a display, printing on a printer, sound output, transmission to an external device, passing trend transition information to other processing units, and the like. The trend transition information output unit 14108 may or may not include an output device such as a display or a speaker. The trend transition information output unit 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 information processing system will be described. First, the operation of the information processing apparatus will be described with reference to the flowcharts of FIGS. In the flowchart of FIG. 15, description of the same steps as those in the flowchart of FIG. 3 is omitted.

  (Step S1501) The server-side receiving unit 1101 determines whether or not an object leading degree information output instruction, which is an instruction to output the object leading degree information, has been received. If an object leading degree information output instruction is received, the process proceeds to step S1502, and if an object leading degree information output instruction is not received, the process proceeds to step S1504.

  (Step S1502) The leading degree information calculating unit 1105 calculates target leading degree information. Details of the leading degree information calculation process will be described with reference to the flowcharts of FIGS.

  (Step S1503) The target advance degree information output unit 1106 transmits the target advance degree information calculated in step S1502 to the information terminal 12 that has transmitted the target advance degree information output instruction. The process returns to step S301.

  (Step S1504) The server-side receiving unit 1101 determines whether or not a trend transition information output instruction that is an instruction to output a trend transition of an object such as a product has been received. If a trend transition information output instruction is received, the process proceeds to step S1505. If a trend transition information output instruction is not received, the process returns to step S301.

  (Step S1505) The leading degree information calculating unit 14105 calculates target leading degree information. Details of the object leading degree information calculation processing will be described using the flowcharts of FIGS. 16 and 17.

  (Step S1506) The target precedence information output unit 14106 passes the subject precedence information calculated in step S1505 to the trend transition information acquisition unit 14107.

  (Step S1507) The trend transition information acquisition unit 14107 configures trend transition information from the object advance degree information passed in Step S1506. An example of the configuration method of the trend transition information will be described later.

  (Step S1508) The trend transition information output unit 14108 transmits the trend transition information configured in step S1507 to the information terminal 12. The process returns to step S301.

  Note that the processing is ended by powering off or interruption for aborting the processing in the flowchart in FIG.

  Next, details of the object leading degree information calculation processing in steps S1502 and S1505 will be described using the flowcharts of FIGS.

  (Step S1601) The processing order information acquisition unit 14104 reads out all two or more pieces of behavior information from the behavior information storage unit 1103, and obtains user identification information and time information corresponding to the item identification information indicating one or more items. The information of the directed graph which links two or more user identification information in the order of the time when the action occurred is acquired from the acquired two or more time information. An example of the algorithm for configuring the directed graph information will be described with reference to the flowchart of FIG. The directed graph information here has the same meaning as the processing order information.

  (Step S1602) Source item degree calculation means 141051 initializes a source item degree vector. The source item degree vector is vector data having a source item degree corresponding to each object identification information as an element. Derived item degree calculation means 141052 initializes a derived item degree vector. The derived item degree vector is vector data having a derived item degree corresponding to each object identification information as an element.

  (Step S1603) Derived item degree calculation means 141052 substitutes the directed graph information (matrix) obtained in step S1601 and the current source item degree vector into a predetermined calculation formula to obtain the next derived item degree vector. .

  (Step S1604) The source item degree calculation means 141051 substitutes the directed graph information (matrix) obtained in step S1601 and the current derived item degree vector into a predetermined calculation formula to obtain the next source item degree vector. .

  (Step S1605) The source item degree calculating unit 141051 and the derived item degree calculating unit 141052 determine whether the source item degree and the derived item degree have converged. Specifically, it is determined whether or not “| source item degree vector−next source item degree vector | <ε” and “| derived item degree vector−next derived item degree vector | <ε” are satisfied. Here, ε is preferably a very small number such as “0.0001”. If it has converged, go to step S1606, and if it has not converged, go to step S1607.

  (Step S1606) The source item degree calculating unit 141051 and the derived item degree calculating unit 141052 use the elements of the next source item degree vector and the next derived item degree vector as the source item degree and the derived item degree of each user, respectively. Accumulate on a storage medium. Return to upper process.

  (Step S1607) The source item degree calculation unit 141051 substitutes the next source item degree vector as a source item degree vector into a variable in which the source item degree vector is stored.

  (Step S1608) The derived item degree calculation unit 141052 substitutes the next derived item degree vector as a derived item degree vector into a variable in which the derived item degree vector is stored. The process returns to step S1603.

  In the flowchart of FIG. 16, after calculating the derived item degree, the source item degree is calculated (steps S1603 and S1604). However, it goes without saying that the order of calculation of the derived item degree and the source item degree is not limited. That is, in the flowchart of FIG. 16, after calculating the source item degree, the derived item degree may be calculated. The same applies to other embodiments.

  Next, an example of the algorithm for the configuration of the directed graph information in step S1601 will be described using the flowchart of FIG.

  (Step S1701) The processing order information acquisition unit 14104 substitutes 1 for a counter i.

  (Step S1702) The processing order information acquisition unit 14104 determines whether the i-th user identification information exists from the user identification information included in the behavior information of the behavior information storage unit 1103. If i-th user identification information exists, it will go to step S1703, and if i-th user identification information does not exist, it will return to a high-order process. The i-th user identification information is the i-th type of user identification information, and action information having the same user identification information is not determined as having different user identification information. Therefore, when user management is performed separately by means not shown, with one user identification information as one record, the processing order information acquisition unit 14104 can read the i-th user identification information from the user management information. Is preferred.

  (Step S1703) The processing order information acquisition unit 14104 acquires all the target object identification information for identifying the target object on which the user identified by the i-th user identification information has taken action from the behavior information storage unit 1103. The information is temporarily stored in a memory or the like in the order indicated by the information. The stored information is a set of object identification information.

  (Step S1704) The processing order information acquisition unit 14104 substitutes 1 for a counter j.

  (Step S1705) The processing order information acquisition unit 14104 determines whether or not the “j + 1” th object identification information exists in the set of object identification information stored in step S1703. If the “j + 1” th object identification information exists, the process proceeds to step S1706, and if the “j + 1” th object identification information does not exist, the process proceeds to step S1709.

  (Step S1706) The processing order information acquisition unit 14104 acquires the j-th and “j + 1” -th object identification information in the set of object identification information stored in Step S1703.

  (Step S1707) The processing order information acquisition unit 14104 obtains values of elements corresponding to the j-th and “j + 1” -th object identification information, which are elements in the directed graph information, acquired in step S1706. 1 ”. That is, the meaning that the network link is extended is “1”.

  (Step S1708) The processing order information acquisition unit 14104 increments j by 1. The process returns to step S1705.

  (Step S1709) The processing order information acquisition unit 14104 increments i by 1. The process returns to step S1702.

  Hereinafter, a specific operation of the information processing system in the present embodiment will be described. Similarly to the description of the specific operation of the first embodiment, the behavior information storage unit 1103 stores the behavior information management table shown in FIG. Since the example of the operation until the behavior information management table is configured has been described in the first embodiment, description thereof is omitted here.

  In such a situation, it is assumed that the user uses the input unit of the information terminal 12 to input an object precedence degree information output instruction. Then, the receiving unit 1201 of the information terminal 12 receives an object advance degree information output instruction. Next, the terminal-side transmission unit 1202 transmits the object precedence degree information output instruction received by the reception unit 1201 to the information processing apparatus 11.

  Next, the server-side receiving unit 1101 of the information processing apparatus 11 receives an object precedence degree information output instruction. Then, the leading degree information calculating unit 1105 and the like calculate the target leading degree information as follows. That is, first, the processing order information acquisition unit 14104 reads out all two or more pieces of behavior information from the behavior information management table of FIG. 7, and object identification information and time information corresponding to user identification information indicating one or more users. And the information of the directed graph that links the two or more object identification information in the order of the time when the action occurred (the time of the action with the object identification information as the object) from the acquired two or more time information. Here, as shown conceptually in FIG. 18, the processing order information acquisition unit 14104 pays attention to the order of actions (for example, purchase) on objects such as products of each user, and for each user identification information, It is assumed that network information of identification information is obtained. Furthermore, the user identification information is deleted from the conceptual diagram of FIG. 18, and the processing order information acquisition unit 14104 configures directed graph information that links the object identification information as shown in FIG. In FIG. 19, the directed graph (arrow) is directed from the object identification information (node) of a product whose purchase time is late to the object identification information (node) of a product whose purchase time is early. This directed graph information is expressed as matrix (M) information as shown in FIG. In FIG. 20, a matrix (M) indicates a link source in a row and a link destination in a column. For example, “[4] → [3]” is expressed as an element value “1” in 4 rows and 3 columns. Yes. The action order information acquisition unit 1104 writes the information shown in FIG. 20 in an array of 5 rows and 5 columns to obtain directed graph information. Note that the initial value of the 5 × 5 array is “0” in all elements. Needless to say, the directed graph (arrow) in FIG. 19 may be reversed. When the directed graph (arrow) is reverse, the matrix (M) in FIG. 20 may be transposed.

Next, the source item degree calculation means 141051 initializes the source item degree vector, and obtains the source item degree vector (SI) “(1 1 1 1 1) ^T ”. The vector “T” is transpose. Also, the derived item degree calculation means 141052 initializes the derived item degree vector (DI) to obtain “(1 1 1 1 1) ^T ”.

Next, the derived item degree calculation unit 141052 substitutes the directed graph information (matrix (M)) and the current source item degree vector (SI) into a predetermined calculation formula to obtain the next derived item degree vector. . Here, for example, the derived item degree calculation means 141052 obtains the next source item degree vector (DI) by the calculation formula “DI = M · SI, DI = DI / | DI |”. Specifically, the derived item degree calculation unit 141052 multiplies the directed graph information (matrix (M)) and the source item degree vector (SI) by a matrix multiplication circuit, and obtains the next derived item degree vector “(1 0 2). 2 1) Obtain ^T ”and place it on the memory.

Then, the derived item degree calculation means 141052 divides the vector “(1 0 2 2 1) ^T ” (DI) by the absolute value (| DI |) to obtain the next derived item degree vector (DI). The next derived item degree vector (DI) is “(0.32 0.0 0.63 0.63 0.32) ^T ” ((1) and (3) in FIG. 21).

  Then, the derived item degree calculation unit 141052 calculates | previous derived item degree vector−current derived item degree vector | and whether the value is smaller than a predetermined value (ε “ε is, for example, 0.001”). Determine whether. That is, the derived item degree calculation means 141052 determines whether or not the trend leader degree vector has converged.

  The derived item degree calculation unit 141052 terminates the process if it is determined that it has converged, and continues to perform the same process as described above if it is determined that it has not converged. In this case, it is assumed that the derived item degree vector has converged when it reaches the value shown in (9) of FIG.

Next, the source item degree calculation unit 141051 obtains a source item degree vector (SI) using the directed graph information (matrix (M)) and the derived item degree vector “(1 0 2 2 1) ^T ”. Specifically, here, the source item degree calculating unit 141051 is ^{"SI = M T · DI, SI} = SI / | SI | " gives the next source item degree vector. The source item degree calculation means 141051 multiplies the directed graph information (matrix (M ^T )) and the derived item degree vector “(1 0 2 2 1) ^T ” by a matrix multiplication circuit, and the source item degree vector “(2 3 2 1 2) ^T ”is obtained ((2) in FIG. 12).

Then, the source item degree calculation means 141051 divides the source item degree “(2 3 2 1 2) ^T ” (also referred to as SI) by its absolute value (| SI |), and the next source item degree vector “(0.43 0.64 0.43 0.21 0.43) ^T ” is obtained ((4) in FIG. 12).

Then, the source item degree calculation unit 141051 similarly calculates the next source item degree vector ((6) and (8) in FIG. 12). Then, the source item degree calculation means 141051 further arranges the next source item degree vector “(0.45 0.72 0.36 0.089 0.36) ^T ” on the memory ((8) in FIG. 12). ).

  Then, the source item degree calculation means 141051 calculates | previous source item degree vector-current source item degree vector | and whether the value is smaller than a predetermined value (ε “ε is, for example, 0.001”). Determine whether. That is, the source item degree calculation unit 141051 determines whether or not the trend leader degree vector has converged.

  If it is determined that the source item degree calculation unit 141051 has converged, the process ends. If it is determined that the source item degree calculation unit 141051 has not converged, the same process as described above is continued until the convergence. In this case, it is assumed that the source item degree vector has converged when it reaches the value shown in (10) of FIG.

  Through the above calculation, the leading degree information calculating unit 14105 obtains the source item degree and the derived item degree of each object shown in FIG.

  In the above, the processing order information acquisition unit 14104 configures the directed graph information in consideration of only the connection of the object identification information using the time information without considering the order of the actions for the object and the time information. . This is apparent from the fact that the network structure in FIG. 19 is configured from the network in “object identification information” in FIG.

  However, the processing order information acquisition unit 14104 may configure the directed graph information in consideration of the order of actions with respect to the object. For example, when the user “B” purchases a product (object) in the order of “[1] → [3] → [4] → [5]”, the processing order information acquisition unit 14104 performs weighting considering the order. (For example, multiply by a constant 0.9), the weight of “[1] ← [3]” is “1”, the weight of “[3] ← [4]” is “0.9”, “[4 ] ← [5] ”may be set to“ 0.81 ”. “1”, “0.9”, and “0.81” constitute element values of the directed graph information (matrix).

Further, the processing order information acquisition unit 14104 may configure the directed graph information in consideration of the purchase time (operation occurrence time). For example, when the user “A” purchases a product at the time in the order of “1 (time t ₁ ) → 3 (time t ₆ ) → 4 (time t ₂₁ ) → 5 (time t ₃₄ )”, the forgetting factor “ Weighting using “e− ^(t−tx) ” may be performed to calculate element values of the directed graph information (matrix). The subscripts “1” and “3” at the times t ₁ and t ₃ are the same as the ID of the behavior information management table in FIG.

  Further, the processing order information acquisition unit 14104 uses the weight of the multiple links (for example, the link [1] ← [3] in FIG. 19) (in the case of [1] ← [3] in FIG. 19), there are three links. In consideration of “3”), the elements of the directed graph information (matrix) may be calculated. In such a case, the value of the third row and the first column in FIG. 20 is “3”.

  In addition, there can be various algorithms for the processing order information acquisition unit 14104 to configure the information of the directed graph. The processing order information acquisition unit 14104 reads two or more pieces of behavior information from the behavior information storage unit 1103, and from the user identification information and the time information that each of the two or more pieces of behavior information has, the user identified by the user identification information What is necessary is just to comprise the processing order information (directed graph information), which is information about the processing order for two or more objects. This directed graph information may be information having a weighted value as described above.

  Then, the object advance degree information output unit 14106 transmits the advance degree information (one or more information items of the source item degree or the derived item degree) of FIG. 22 to the information terminal 12. Here, for example, it is preferable that the leading degree information calculating unit 14105 slightly processes the leading degree information in FIG. 22 and transmits it to the information terminal 12. In other words, the object precedence information output unit 14106 sorts the object identification information in ascending order of the source item degree in the precedence information of FIG. 22, and displays “[4] − [3] − [5] − [1”. ]-[2] "is acquired. Then, the leading degree information output unit 1106 transmits information of “[4] − [3] − [5] − [1] − [2]” to the information terminal 12.

  As described above, according to the present embodiment, it is possible to calculate the object advance degree information (source item degree and derived item degree) from the action histories (behavior information) of a plurality of users. Moreover, the trend transition information which shows the transition of the trend of goods etc. can be output using leading degree information.

  In the present embodiment, the information processing apparatus 141 receives behavior information from the information terminal 12. However, the information processing apparatus 141 may not communicate with the information terminal 12 and may store behavior information via manual input or a storage medium. That is, the information processing apparatus 141 may process the stored behavior information standalone. At that time, the information processing apparatus 141 may transmit a processing result (such as object leading degree information) to an external apparatus such as the information terminal 12.

  In the present embodiment, the object leading degree information is calculated with the reception unit 1201 receiving a leading degree information output instruction as a trigger. However, the trigger for calculating the object precedence information is not limited. That is, it is preferable that the information processing apparatus 141 calculates the object leading degree information in the background without a user instruction.

  The software that realizes the information processing apparatus according to the present embodiment is the following program. That is, this program reads out two or more pieces of behavior information stored in the storage medium from the computer, and identifies the user identified by the user identification information from the user identification information and the time information included in the two or more pieces of behavior information. A processing order information acquisition unit that acquires processing order information that is information about processing order for two or more objects, and a calculation formula that is determined in advance using the processing order information acquired by the processing order information acquisition unit In order to function as a leading degree information calculating unit that calculates target leading degree information that is information about a leading degree or a delay degree of a target, and a target leading degree information output unit that outputs the target leading degree information. Program.

  In the above program, the object precedence information output unit is a target that is the starting point of the same user's action on a plurality of objects from two or more pieces of processing order information acquired by the processing order information acquisition unit. Source item degree calculation means for calculating the source item degree that is the degree of the object and indicates the hub degree of the object for each of the two or more objects, and two or more acquired by the processing order information acquisition unit Derived item degree calculation means for calculating, for each of two or more objects, a derived item degree that is a degree to follow the object of the starting point of the same user's action for a plurality of objects Then, the object leading degree information output unit causes the computer to function as outputting at least one of the source item degree and the derived item degree. It is preferred.

Further, in the above program, the object leading degree information output unit receives the object leading degree information, and using the target leading degree information, the trend transition which is a flow in which an action is caused to the target. A trend transition information acquisition unit for acquiring trend transition information as information;
It is preferable that the trend transition information output unit that outputs the trend transition information acquired by the trend transition information acquisition unit is a program that causes a computer to function.

  FIG. 23 shows the external appearance of a computer that executes the programs described in this specification to realize the information processing apparatuses and information terminals of the various embodiments described above. The above-described embodiments can be realized by computer hardware and a computer program executed thereon. FIG. 23 is an overview diagram of the computer system 340, and FIG. 24 is a block diagram of the computer system 340.

  In FIG. 23, the computer system 340 includes a computer 341 including an FD (Flexible Disk) drive and a CD-ROM (Compact Disk Read Only Memory) drive, a keyboard 342, a mouse 343, and a monitor 344.

  24, in addition to the FD drive 3411 and the CD-ROM drive 3412, the computer 341 includes a CPU (Central Processing Unit) 3413, a bus 3414 connected to the CPU 3413, the CD-ROM drive 3412, and the FD drive 3411, and a boot. A ROM (Read-Only Memory) 3415 for storing a program such as an up program, and a RAM (Random Access Memory) connected to the CPU 3413 for temporarily storing instructions of an application program and providing a temporary storage space 3416 and a hard disk 3417 for storing application programs, system programs, and data. Although not shown here, the computer 341 may further include a network card that provides connection to the LAN.

  A program that causes the computer system 340 to execute the functions of the information processing apparatus according to the above-described embodiment is stored in the CD-ROM 3501 or the FD 3502, inserted into the CD-ROM drive 3412 or the FD drive 3411, and further stored in the hard disk 3417. May be forwarded. Alternatively, the program may be transmitted to the computer 341 via a network (not shown) and stored in the hard disk 3417. The program is loaded into the RAM 3416 at the time of execution. The program may be loaded directly from the CD-ROM 3501, the FD 3502, or the network.

  The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 341 to execute the functions of the information processing apparatus according to the above-described embodiment. The program only needs to include an instruction portion that calls an appropriate function (module) in a controlled manner and obtains a desired result. How the computer system 340 operates is well known and will not be described in detail.

  In each of the above embodiments, each process (each function) may be realized by centralized processing by a single device (system), or by distributed processing by a plurality of devices. May be.

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

  Further, the computer that executes the program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

  Further, in each of the above embodiments, it goes without saying that two or more communication means (such as an information transmission unit) existing in one apparatus may be physically realized by one medium.

  The present invention is not limited to the above-described embodiments, and various modifications are possible, and it goes without saying that these are also included in the scope of the present invention.

  As described above, the information processing apparatus according to the present invention uses the action information, which is information indicating the history of processing of the object by performing the action on the object of the user, It has the effect of being able to acquire information related to trends in products, and is useful as an information processing device that supports marketing and recommends products.

Conceptual diagram of information processing system in Embodiment 1 Block diagram of the information processing system Flow chart for explaining the operation of the information processing apparatus A flowchart for explaining the operation of the leading degree information calculation process A flowchart for explaining the configuration operation of the directed graph information Figure showing the object management table Figure showing the behavior information management table The figure which shows the example of the homepage which is displayed on the same information terminal The figure which shows the example of information which paid its attention to the order of purchase of the goods etc. Diagram showing an example of the directed graph The figure which shows the example of the directed graph information The figure explaining the procedure of the precedence information calculation Diagram showing the degree of trend leader and trend follower Block diagram of an information processing system in the second embodiment Flow chart for explaining the operation of the information processing apparatus Flowchart for explaining the operation of the object preceding degree information calculation process A flowchart for explaining the configuration operation of the directed graph information The figure which shows the example of information which paid its attention to the order of purchase of the goods etc. Diagram showing an example of the directed graph The figure which shows the example of the directed graph information The figure explaining the procedure of the same object precedence information calculation The figure which shows the source item degree and derivative item degree which are acquired External view of the computer that realizes the information processing apparatus and the information terminal Block diagram of the computer system

Explanation of symbols

DESCRIPTION OF SYMBOLS 11,141 Information processing apparatus 12 Information terminal 1101 Server side receiving part 1102 Action information storage part 1103 Action information storage part 1104 Action order information acquisition part 1105 Precedence information calculation part 1106 Precedence information output part 1106 Object precedence degree information output part DESCRIPTION OF SYMBOLS 1107 Trend leader acquisition part 1108 Trend leader output part 1201 Reception part 1202 Terminal side transmission part 1203 Terminal side reception part 1204 Terminal side output part 11051 Trend leader degree calculation means 11052 Trend follower degree calculation means 14104 Processing order information acquisition part 14105 Precedence degree information Calculation unit 14106 Target precedence information output unit 14107 Trend transition information acquisition unit 14108 Trend transition information output unit 141051 Source item degree calculation means 141052 Derived item degree calculation means

Claims (12)

Information indicating the history of processing of an object by performing an action on the object of the user, the user identification information for identifying the user, the object identification information for identifying the object, and the generation time of the action An action information storage unit storing two or more action information having time information;
Two or more pieces of behavior information are read out from the behavior information storage unit, and two or more users of the subject identified by the subject identification information are detected from the subject identification information and time information included in the two or more pieces of behavior information. An action order information acquisition unit that acquires action order information that is information about the action order;
Using the action order information acquired by the action order information acquisition unit, a leading degree information calculating unit that calculates user leading degree information that is information about the leading degree or delay degree of the user;
Using the user precedence information, a trend leader acquisition unit that acquires user identification information for identifying a trend leader who is an early user that satisfies a certain temporal condition;
A trend leader output unit that outputs the user identification information acquired by the trend leader acquisition unit;
The leading degree information calculation unit
A trend that is a degree that is a starting point of an action on the same target object of a plurality of users from two or more action order information acquired by the action order information acquisition unit, and indicates a degree that is a trend transmission source Trend leader degree calculating means for calculating the leader degree for each of two or more users;
From the two or more action order information acquired by the action order information acquisition unit, the degree of following the starting point of action for the same target object of a plurality of users, and the trend follower degree which is information indicating the degree of following the trend, A trend follower degree calculating means for calculating two or more users;
The trend leader acquisition unit
An information processing apparatus that acquires user identification information for identifying the trend leader using the trend leader degree and the trend follower degree . The action order information acquisition unit
Obtaining action order information which is information of a directed graph constructed from the context of the time indicated by the time information included in the two or more action information stored in the action information storage unit;
The trend leader degree calculating means includes:
Two or more trend leader degrees, which are information indicating the degree of being the origin of a trend and the degree of being the source of the trend, from the action order information which is information of the directed graph. For each user of
The trend follower degree calculating means includes:
It is a degree to follow the starting point of action for the same object of a plurality of users from the action order information which is information of the directed graph, and a trend follower degree which is information indicating a degree to follow the trend is given to each of two or more users The information processing apparatus according to claim 1, wherein the information processing apparatus calculates the information. Until the trend leader degree and the trend follower degree converge,
The trend leader degree calculating means includes:
Using the action order information that is the information of the directed graph and the trend follower degree calculated immediately before, a new trend leader degree is obtained,
And, by judging whether the difference between the new trend leader degree and the original trend leader degree is within a threshold, it is judged whether the trend leader degree has converged,
The trend follower degree calculating means includes:
Using the action order information that is information of the directed graph and the trend leader degree calculated immediately before, a new trend follower degree is obtained,
The information processing system according to claim 2, wherein it is determined whether or not the trend follower degree has converged by determining whether or not a difference between the new trend follower degree and the original trend follower degree is within a threshold value. The action order information acquisition unit
The information of the directed graph constructed from the context of the time indicated by the time information included in the two or more behavior information stored in the behavior information storage unit is acquired, and the link source in the information of the directed graph is set as a row or a column. Get a matrix M with the column or row as the destination,
The trend leader degree calculating means includes:
Calculate a trend leader degree vector, which is a vector indicating the trend leader degree,
The trend follower degree calculating means includes:
Calculate the trend follower degree vector, which is a vector indicating the trend follower degree,
The trend leader degree calculating means includes:
A new trend leader degree is obtained using the product of the matrix M obtained by the action order information obtaining unit and the trend follower degree vector calculated immediately before,
The trend follower degree calculating means includes:
Using the product of the matrix M acquired by the action order information acquisition unit and the trend leader degree vector calculated immediately before, a new trend follower degree is obtained,
The trend leader acquisition unit
The information processing apparatus according to claim 3, wherein user identification information having the largest trend leader degree after convergence is acquired. Two or more pieces of behavior information including user identification information for identifying the user, target identification information for identifying the target, and timing information indicating the occurrence timing of the behavior are stored. A behavior information storage unit,
Two or more pieces of behavior information are read from the behavior information storage unit, and the processing order for the two or more objects of the user identified by the user identification information from the user identification information and the time information that each of the two or more pieces of behavior information has A processing order information acquisition unit that acquires processing order information that is information about;
Using the processing order information acquired by the processing order information acquisition unit, a leading degree information calculating unit that calculates target leading degree information that is information about the leading degree or the delay degree of the target object;
A trend transition information acquisition unit that acquires trend transition information that is trend transition information that is a flow in which an action is caused on a target using the target precedence information;
A trend transition information output unit that outputs the trend transition information acquired by the trend transition information acquisition unit,
The leading degree information calculation unit
This is information indicating the degree of the object that is the starting point of the action of the same user for a plurality of objects from the two or more process order information acquired by the processing order information acquisition unit, and indicates the hub degree of the object. Source item degree calculation means for calculating a source item degree for each of two or more objects;
From two or more pieces of processing order information acquired by the processing order information acquisition unit, a degree of a derived item, which is a degree of following a starting point of the same user's action for a plurality of targets, is set to each of the two or more targets. A derived item degree calculating means for calculating
The trend transition information acquisition unit
An information processing apparatus that acquires the trend transition information using the source item degree and the derived item degree . The processing order information acquisition unit
Obtaining processing order information which is information of a directed graph constructed from the user's identification information included in each of the two or more pieces of behavior information stored in the behavior information storage unit and the context of the time indicated by the time information;
The source item degree calculation means includes:
From the processing order information that is information of the directed graph, the source item degree that is the degree of the object that is the starting point of the action of the same user with respect to a plurality of objects and that indicates the hub degree of the object is 2 Calculate for each of these objects,
The derived item degree calculation means includes:
From the processing order information that is information of the directed graph, a derived item degree that is information indicating a degree of following the target object of the same user's action with respect to a plurality of target objects is calculated for each of two or more target objects The information processing apparatus according to claim 5. Until the source item degree and the derived item degree converge,
The source item degree calculation means includes:
Using the action order information that is information of the directed graph and the derived item degree calculated immediately before, a new source item degree is obtained,
And determining whether or not the source item degree has converged by determining whether or not a difference between the new source item degree and the original source item degree is within a threshold,
The derived item degree calculation means includes:
Using the action order information that is the information of the directed graph and the source item degree calculated immediately before, a new derived item degree is obtained,
The information processing apparatus according to claim 6, wherein it is determined whether or not the derived item degree has converged by determining whether or not a difference between the new derived item degree and the original derived item degree is within a threshold. The action order information acquisition unit
Obtain processing order information that is information of a directed graph constructed from the user identification information included in each of the two or more pieces of behavior information stored in the behavior information storage unit and the time relationship indicated by the time information, and information on the directed graph To obtain a matrix M in which the link source in is a row or column and the link destination is a column or row,
The source item degree calculation means includes:
Calculate a source item degree vector, which is a vector indicating the source item degree,
The derived item degree calculation means includes:
Calculate a derived item degree vector, which is a vector indicating the derived item degree,
The source item degree calculation means includes:
Using the product of the matrix M acquired by the action order information acquisition unit and the derived item degree vector calculated immediately before, a new source item degree is obtained,
The derived item degree calculation means includes:
The information processing apparatus according to claim 7, wherein a new derived item degree is obtained using a product of the matrix M obtained by the action order information obtaining unit and the source item degree vector calculated immediately before. Computer
Two or more users with respect to the object identified by the object identification information from the object identification information and the timing information included in each of the two or more action information are read out from the two or more action information stored in the storage medium An action order information acquisition unit for acquiring action order information which is information about the action order of
Using the action order information acquired by the action order information acquisition unit, by using a predetermined calculation formula, a leading degree information calculating unit that calculates user leading degree information that is information about the leading degree or the delay degree of the user;
Using the user precedence information, a trend leader acquisition unit that acquires user identification information for identifying a trend leader who is an early user that satisfies a certain temporal condition;
A program for functioning as a trend leader output unit that outputs user identification information acquired by the trend leader acquisition unit,
The leading degree information calculation unit
A trend that is a degree that is a starting point of an action on the same target object of a plurality of users from two or more action order information acquired by the action order information acquisition unit, and indicates a degree that is a trend transmission source Trend leader degree calculating means for calculating the leader degree for each of two or more users;
From the two or more action order information acquired by the action order information acquisition unit, the degree of following the starting point of action for the same target object of a plurality of users, and the trend follower degree which is information indicating the degree of following the trend, A trend follower degree calculating means for calculating two or more users;
The trend leader acquisition unit
A program for causing a computer to function as one that acquires user identification information for identifying the trend leader using the trend leader degree and the trend follower degree . Computer
Processing for two or more objects of the user identified by the user identification information from the user identification information and the time information included in the two or more pieces of behavior information, by reading two or more pieces of behavior information stored in the storage medium A processing order information acquisition unit that acquires processing order information that is information about the order;
Using the processing order information acquired by the processing order information acquisition unit, a leading degree information calculating unit that calculates target leading degree information that is information about the leading degree or the delay degree of the target object;
A trend transition information acquisition unit that acquires trend transition information that is trend transition information that is a flow in which an action is caused on a target using the target precedence information;
A program for functioning as a trend transition information output unit that outputs trend transition information acquired by the trend transition information acquisition unit,
The leading degree information calculation unit
This is information indicating the degree of the object that is the starting point of the action of the same user for a plurality of objects from the two or more process order information acquired by the processing order information acquisition unit, and indicates the hub degree of the object. Source item degree calculation means for calculating a source item degree for each of two or more objects;
From two or more pieces of processing order information acquired by the processing order information acquisition unit, a degree of a derived item, which is a degree of following a starting point of the same user's action for a plurality of targets, is set to each of the two or more targets. A derived item degree calculating means for calculating
The trend transition information acquisition unit
The program for functioning a computer as what acquires the said fashion transition information using the said source item degree and the said derived item degree. An information processing method for outputting a trend leader using an action order information acquisition unit, a leading degree information calculation unit, a trend leader acquisition unit, and a trend leader output unit ,
The action order information acquisition unit reads two or more action information stored in a storage medium, and is identified by the object identification information from the object identification information and time information included in the two or more action information. An action order information acquisition step for acquiring action order information that is information about the action order of two or more users with respect to the object;
The preceding degree information calculating unit calculates user leading degree information that is information about the leading degree or the delay degree of the user by using a predetermined calculation formula using the action order information acquired in the action order information acquiring step. A leading degree information calculating step,
The trend leader acquisition unit acquires user identification information for identifying a trend leader who is a user who acts early at a certain time using the user precedence information, and a trend leader acquisition step,
The trend leader output unit comprises a trend leader output step for outputting the user identification information acquired in the trend leader acquisition step,
The preceding degree information calculating step includes:
It is information indicating the degree of being a starting point of action for the same object of a plurality of users from two or more action order information acquired in the action order information acquisition step, and indicating the degree of being a trendy transmission source. A trend leader degree calculating step for calculating a trend leader degree for each of two or more users;
A trend follower degree, which is a degree of following a starting point of action on the same target object of a plurality of users from two or more action order information acquired in the action order information acquisition step, and is information indicating a degree of chasing the trend. A trend follower degree calculating step for calculating two or more users,
In the trend leader acquisition step,
An information processing method for acquiring user identification information for identifying the trend leader using the trend leader degree and the trend follower degree . An information processing method for outputting trend transition information using a processing order information acquisition unit, a leading degree information calculation unit, a trend transition information acquisition unit, and a trend transition information output unit ,
The processing order information acquisition unit reads two or more pieces of behavior information stored in a storage medium, and from the user identification information and the time information that each of the two or more pieces of behavior information has, the user identified by the user identification information A processing order information acquisition step for acquiring processing order information that is information about the processing order for two or more objects;
Using the processing order information acquired in the processing order information acquisition step, the preceding degree information calculating unit uses information about the degree of advance or delay of the object according to a predetermined calculation formula. A leading degree information calculating step for calculating
The trend transition information acquisition unit acquires trend transition information, which is trend transition information that is a flow of action on the target, using the target leading degree information,
The trend transition information output unit comprises a trend transition information output step for outputting the trend transition information acquired in the trend transition information acquisition step,
The preceding degree information calculating step includes:
Information indicating the degree of hub of an object, which is the degree of the object that is the starting point of the action of the same user for a plurality of objects from two or more process order information acquired in the process order information acquisition step. A source item degree calculating step for calculating a certain source item degree for each of two or more objects;
Each of the two or more object items is a derived item degree that is a degree of following the object of the starting point of the same user's action with respect to a plurality of objects from the two or more process order information acquired in the process order information acquiring step. A derived item degree calculating step for calculating
In the trend transition information acquisition step,
An information processing method for acquiring the trend transition information using the source item degree and the derived item degree .