JP7671085B2 - Program, method, information processing device, and system - Google Patents

Description

This disclosure relates to a program, a method, an information processing device, and a system.

A system for managing information related to real estate is known (see, for example, Patent Document 1). In Patent Document 1, for example, OCR is used to generate text information with line information (for example, HTML, XML files) from various certificate documents, image data, etc. Next, each item of the certificate of all details (purpose of registration, ranking number, etc.) is extracted based on the line information.

JP 2002-373197 A

In Patent Document 1, document items are extracted based on text information, which is vulnerable to exception processing and requires human judgment to make corrections. This means that there is a high possibility of processing errors occurring and may also impose a burden on the person in charge. The purpose of this disclosure is to obtain information from real estate certified copies with a high degree of accuracy and efficiently manage information related to real estate certified copies.

The present disclosure provides a program for causing a computer having a processor and a memory to execute a process, the program causing the processor to execute an acquisition step of acquiring registration data related to real estate registration, a generation step of generating shaped data based on the registration data using a trained model, a first storage step of extracting property data, which is data related to a property, from the shaped data and storing the extracted property data in a storage unit, a second storage step of extracting owner data, which is data related to the owner of the property, from the shaped data and storing the extracted owner data in a storage unit, and an association step of associating the owner data stored in the storage unit with the property data.

According to the present disclosure, information can be obtained from real estate certified copies with high accuracy, and information related to real estate certified copies can be efficiently managed.

FIG. 2 is a block diagram showing the functional configuration of the system 1. FIG. 2 is a block diagram showing the functional configuration of the server 10. FIG. 2 is a block diagram showing the functional configuration of a user terminal 20. FIG. 13 is a diagram showing the data structure of an owner database 1012. FIG. 10 is a diagram showing the data structure of a property database 1013. FIG. 13 is a diagram showing the data structure of a debt database 1015. FIG. 13 is a diagram showing the data structure of a creditor database 1016. 4 is a flowchart showing the first half of the processing flow of the system 1. 13 is a flowchart showing the second half of the processing flow of the system 1. FIG. 11 is a diagram illustrating a portion of shaping data. 11 is a flowchart showing the first half of the processing flow of the analysis process (S300). 13 is a flowchart showing the latter half of the processing flow of the analysis process (S300). 13 is a flowchart showing the latter half of the processing flow of the analysis process (S300). FIG. 2 is a block diagram showing the basic hardware configuration of a computer 90.

Embodiments of the present disclosure will be described below with reference to the drawings. In all figures describing the embodiments, common components are given the same reference numerals, and repeated explanations will be omitted. Note that the following embodiments do not unduly limit the contents of the present disclosure described in the claims. Furthermore, not all components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, each figure is a schematic diagram, and is not necessarily a precise illustration.

<1. Configuration of System 1>
The system 1 in the present disclosure is an information processing system that manages information related to real estate registration. As shown in Fig. 1, the system 1 in the present disclosure includes a server 10 and a user terminal 20. The server 10, the user terminal 20, and an external server S are communicatively connected via a network N. Note that, although the example shown in Fig. 1 has one server 10 and one user terminal 20, either or both of the server 10 and the user terminal 20 may be configured as a plurality of units.

The server 10 and the user terminal 20 are configured by a computer 90 equipped with a calculation device and a storage device. The basic hardware configuration of the computer 90 and the basic functional configuration of the computer realized by the hardware configuration will be described later. For the server 10 and the user terminal 20, descriptions that overlap with the basic hardware configuration and basic functional configuration of the computer 90 described later will be omitted.

The external server S provides access to a large-scale language model M. The large-scale language model M is an example of a trained model, and is a natural language model trained using a large number of parameters (e.g., billions to hundreds of billions) and high levels of computational resources. A natural language model refers to a computer program or algorithm designed to perform natural language processing tasks. As an example, natural language processing involves processes such as morphological analysis, syntactic analysis, information extraction, and sentence generation, allowing a computer to analyze language used by humans (i.e., natural language) and perform specified processing.

Examples of large-scale language models M include the GPT series (Generative Pre-trained Transformer) developed by OPEN AI and BERT (Bidirectional Encoder Representations from Transformers) developed by Google. Large-scale language models M tend to have high training costs because they are trained using a very large number of parameters and computational resources. In this embodiment, training costs are reduced by using trained models that are publicly available from an external server S. Note that a certified copy of a real estate property's registration (certificate of registered details) is not, by definition, written. For this reason, the GPT series is more preferable than BERT. In this embodiment, for example, a definition is passed to GPT, and the GPT is made to understand the context before generating information.

2. Configuration of Server 10
2, the server 10 is an information processing device that manages information related to real estate registration. The server 10 includes a storage unit 101 and a control unit 104.

<2.1. Configuration of the storage unit 101 of the server 10>
The memory unit 101 of the server 10 includes an application program 1011 , an owner database 1012 , a property database 1013 , a debt database 1015 , a creditor database 1016 , and a shaping request 1014 .

The application program 1011 is a program for causing the control unit 104 of the server 10 to function as each functional unit. By executing the application program 1011, the control unit 104 provides various applications such as a web browser application.

The owner database 1012 is a database that stores information (hereinafter also referred to as owner data) regarding the owner of a specific real estate property (hereinafter also simply referred to as property). As shown in FIG. 4, as an example, the owner database 1012 has the items "Owner ID", "Name", "Address", "Owned Real Estate", and "Debt Information". Note that the owner database 1012 may have items other than these, or may not have any of these.

The item "Owner ID" is an item for storing an identifier for uniquely identifying an owner registered in the owner database 1012. The item "Owner ID" functions as the primary key of the owner database 1012. The item "Owner ID" may also be referred to as a reception number.

The "Name" item is used to store information about the owner's name.

The "Address" item is used to store information about the owner's address.

The "Owned Real Estate" item is an item for storing information about real estate (properties) owned by an owner. The "Owned Real Estate" item stores, for example, information for identifying an owned property, such as a property ID or a property number. The "Owned Real Estate" item may also store a ranking indicating changes in ownership. The "Owned Real Estate" item may also store the share of an owned property. The share is information indicating the owner's share ratio when an owned property is shared. As an example, the share holds the share ratio calculated as a percentage.

The "Debt Information" item is an item for storing identification information that represents debt information. For example, a debt ID is stored in the "Debt Information" item.

A user of the system 1 (a real estate agent, for example) can add and register a new record in the owner database 1012 or update the contents of a record registered in the owner database 1012 by operating the user terminal 20. Alternatively, the server 10 can execute the analysis process (S400/FIG. 9) described below to add a new record to the owner database 1012 or update the contents of an existing record. The analysis process will be described in detail later.

The property database 1013 is a database that stores information about a specific property (hereinafter also referred to as property data). As shown in FIG. 5, as an example, the property database 1013 has the items "Property ID", "Real Estate Number", "Address", "Land Use", "Registration Date", "Land Area", and "Cause". Note that the property database 1013 may have items other than these, or may not have any of these.

The item "Property ID" is an item for storing an identifier for identifying a property registered in the property database 1013. The item "Property ID" may also be referred to as a reception number.

The "Real Estate Number" item is used to store a real estate number that uniquely identifies a property. Real estate numbers are 13-digit numbers managed by the Legal Affairs Bureau.

The "Address" item is used to store information about the address of the property. The "Address" item may be separated into the location and the lot number.

The "land use" item is used to store the main use of the land. For example, the "land use" item stores the use, such as residential land.

The "Registration Date" item is used to record the date the property was registered.

The "land area" item is used to store the area of land.

The "Cause" item is used to record the reason for the registration and the date on which it occurred.

A user of the system 1 can add and register a new record in the property database 1013 or update the contents of a record registered in the property database 1013 by operating the user terminal 20. Alternatively, the server 10 can execute the analysis process (S400) described below to add a new record to the property database 1013 or update the contents of an existing record. The analysis process will be described in detail later.

The debt database 1015 is a database that stores information about debts related to a specified property (hereinafter also referred to as debt data). As shown in FIG. 6, as an example, the debt database 1015 has the items "Debt ID", "Borrowing date", "Amount of claim", "Damage", "Interest rate", "Debtor", "Creditor", and "Expected balance". Note that the debt database 1015 may have items other than these, or may not have any of these.

The "Debt ID" item is an item for storing an identifier for identifying a debt registered in the debt database 1015. The "Borrowing Date" item is an item for storing the date on which the debt was borrowed. The "Claims Amount" item is an item for storing the amount of the debt registered in the debt database 1015. The "Damage" item is an item for storing interest on damages incurred when a debtor fails to make payments.

The "interest rate" item is an item that stores interest on a debt. The "debtor" item is an item that stores a party who owes a debt. The "debtor" item stores, for example, an owner ID. The "creditor" item is an item that stores a party that has the right to request a specific action from a debtor. The "creditor" item stores, for example, a creditor ID. The "expected balance" item is an item that stores the balance of a debt.

A user of the system 1 can add and register new records in the debt database 1015 or update the contents of records registered in the debt database 1015 by operating the user terminal 20. Alternatively, the server 10 can execute the analysis process (S400) described below to add new records to the debt database 1015 or update the contents of existing records. The analysis process will be described in detail later.

The creditor database 1016 is a database that stores information about debtors (hereinafter also referred to as creditor data). As shown in FIG. 7, as an example, the creditor database 1016 has the items "Creditor ID" and "Address". Note that the creditor database 1016 may have items other than these, or may not have any of these.

The item "Creditor ID" is an item for storing an identifier for identifying a creditor registered in the creditor database 1016. The item "Address" is an item for storing information regarding the creditor's address.

A user of the system 1 can add and register new records in the creditor database 1016 or update the contents of records registered in the creditor database 1016 by operating the user terminal 20. Alternatively, the server 10 can execute the analysis process (S400) described below to add new records to the creditor database 1016 or update the contents of existing records. The analysis process will be described in detail later.

The shaping request 1014 is a request to have the large-scale language model M provided by the external server S output shaping data for a property described in the registry data based on the specified registry data. The shaping data is, for example, data in which information about a property described in the registry data is arranged in a specified order. The shaping data may also be, for example, data in which information about a property described in the registry data is arranged in an order according to the type of data and described in a specified data format. The shaping data may also be, for example, data in which information about a property is arranged in an order according to data corresponding to a database and described in a specified data format. More specifically, the shaping data is, for example, data in which information about a property is arranged in an order according to data corresponding to a database and data described in Jason format is converted into a data type called a dictionary type, object type, or the like. However, the format and data type of the shaping data are not limited to this example and can be set appropriately by the user.
The registry data also includes the history of ownership of the property. In other words, the registry data includes the past and present owners. Therefore, the real estate data also includes information about the past and present owners.

The shaping request 1014 is, for example, a prompt (command sentence) input to the large-scale language model M, and can be specified in natural language. Specifically, for example, the shaping request 1014 may be specified in the form of a sentence requesting a person, such as "Organize the information in the registration data by title section (land description), rights section (area A), and rights section (area B), and output it in Jason format." The format of the shaping data is an example, and can be set appropriately by the user changing the shaping request. In this embodiment, the shaping request 1014 is stored in the storage unit 101, but is not limited to this example, and the server 10 may receive the shaping request 1014 input by the user to the user terminal 20.

<2.2. Configuration of the control unit 104 of the server 10>
The control unit 104 of the server 10 includes, as functional units, a transmission/reception module 1041, an acquisition module 1042, a generation module 1043, and a data management module 1045. The control unit 104 executes an application program 1011 stored in the storage unit 101 to operate as each functional unit.

The transmission/reception module 1041 controls the process in which the server 10 transmits and receives signals to and from external devices (e.g., the user terminal 20) in accordance with a communication protocol.

The acquisition module 1042 acquires registration data related to real estate registration. The registration data is data having information such as the address, identification information (e.g., real estate number), land area, owner, and share of the real estate property. As an example, the registration data holds information corresponding to each item of the property database 1013 in the storage unit 101. As another example, the registration data holds information corresponding to each item of the owner database 1012 in the storage unit 101. As another example, the registration data holds information corresponding to each item of the debt database 1015 in the storage unit 101. The format of the registration data may be a document format such as PDF, or may be an image format. The registration data may not have the items themselves as long as it has information related to each item. As an example, the registration data may be a certified copy of the registration (certificate of registered matters) related to the real estate property. The registration data may be a data file obtained by scanning the certified copy of the registration book. One piece of registration data may include information about one or more properties. The acquisition module 1042 acquires one or more pieces of registration data specified by the user.

The generation module 1043 generates shaping data based on the registration data using the large-scale language model M provided by the external server S. Specifically, the generation module 1043 transmits the registration data acquired by the acquisition module 1042 and the shaping request 1014 stored in the storage unit 101 to the transmission/reception module 1041 by transferring them to the external server S. In the external server S, the received registration data and the shaping request are input to the large-scale language model, and shaping data based on the registration data is output. The large-scale language model M does not analyze characters related to items in the registration data, understand what the items are, and then shape the information. The large-scale language model M estimates what the information is from the arrangement of character strings in the registration data, and generates shaping data based on the estimated information. The transmission/reception module 1041 receives the generated shaping data from the external server S.

The generation module 1043 may encrypt the registration data acquired by the acquisition module 1042 before transmitting the registration data to the external server S. As the encryption method, a shared key encryption method such as the Advanced Encryption Standard (AES) algorithm, a public key encryption method such as the Rivest-Shamir-Adleman (RSA) algorithm, or a hybrid encryption method using both of these may be appropriately adopted. In this case, the transmission/reception module 1041 transmits the encrypted registration data to the external server S. The external server S outputs the encrypted shaping data by inputting the encrypted registration data and a shaping request to the large-scale language model M. The generation module 1043 decrypts the encrypted shaping data. With such specifications, the registration data to be transmitted to the external server S and the shaping data to be output based on the registration data are encrypted, and when an external learning model is used, it is possible to prevent leakage of personal information described in the registration data.

The data management module 1045 stores data included in the shaping data in the storage unit 101. Specifically, the data management module 1045 stores, for example, property data, which is data related to a specific property, included in the shaping data, in the property database 1013 of the storage unit 101 (corresponding to the "first storage step" in the claims). The data management module 1045 also stores, for example, owner data, which is data related to the owner of a specific property, included in the shaping data, in the owner database 1012 of the storage unit 101 (corresponding to the "second storage step" in the claims). The data management module 1045 also stores debt data, which is data related to debts related to a specific property, included in the shaping data, in the debt database 1015 of the storage unit 101. The data management module 1045 also stores creditor data, which is data related to creditors, in the creditor database 1016 of the storage unit 101. Furthermore, the data management module 1045 associates the property data stored in the property database 1013, the owner data stored in the owner database 1012, the debt data stored in the debt database 1015, and the creditor data stored in the creditor database 1016. The processing of the data management module 1045 is executed by an analysis process (S400/FIG. 9). The analysis process will be described in detail later.

3. Configuration of user terminal 20
As shown in FIG. 3, the user terminal 20 is an information processing device operated by a user who uses the service. The user terminal 20 may be, for example, a mobile terminal such as a smartphone or a tablet, a stationary PC (Personal Computer), or a laptop PC. The user terminal 20 may also be a wearable terminal such as an HMD (Head Mount Display) or a wristwatch-type terminal. The user terminal 20 may also be a multifunction device capable of performing at least one of the functions of copying, printing, scanning, and facsimile. The user terminal 20 may also be connectable to the multifunction device. The user terminal 20 includes a storage unit 211, a control unit 214, an input device 216, and an output device 218.

<3.1. Configuration of the storage unit 211 of the user terminal 20>
The storage unit 211 of the user terminal 20 includes an application program 2111. The application program 2111 may be stored in advance in the storage unit 201, or may be configured to be downloaded from a web server operated by a service provider via a communication IF. The application program 2111 includes an application such as a web browser application. The application program 2111 includes an interpreter-type programming language such as JavaScript (registered trademark) that is executed on the web browser application stored in the user terminal 20.

<3.2. Configuration of the control unit 214 of the user terminal 20>
The control unit 214 of the user terminal 20 includes, as functional units, an operation reception unit 2141, a transmission/reception unit 2142, and a notification control unit 2143. The control unit 214 executes an application program 2111 stored in the storage unit 211 to realize each functional unit.

The operation reception unit 2141 performs processing for receiving a user operation input from the input device 216. For example, the operation reception unit 2141 determines the type of operation, such as whether the operator's operation is a flick operation, a tap operation, or a drag (swipe) operation, based on information about the coordinates where the user touches the touch device 2165 with a finger or the like, and receives the operation.

The transmission/reception unit 2142 performs processing to enable the user terminal 20 to transmit and receive data to and from external devices such as the server 10 in accordance with a communication protocol.

The notification control unit 2143 notifies the user of various information by outputting various data to the output device 218. Specifically, the notification control unit 2143 causes the display 2181 to display data such as images, videos, and text to be notified to the user. The notification control unit 2143 also causes the speaker 2182 to output an audio signal of the data to be notified to the user.

<3.3. Configuration of the input device 216 of the user terminal 20>
The input device 216 of the user terminal 20 includes a camera 2161 , a microphone 2162 , a position information sensor 2163 , a motion sensor 2164 , and a touch device 2165 .

3.4. Configuration of the output device 218 of the user terminal 20
The output device 218 of the user terminal 20 includes a display 2181 and a speaker 2182 .

<4. Operation of System 1>
Each process of the system 1 will be described below.

<4.1. Overall operation>
8 and 9 are flowcharts showing an overall view of the processing flow of the system 1. In step S110 shown in Fig. 8, the operation acceptance unit 2141 of the user terminal 20 accepts registration data from a user. As an example, the operation acceptance unit 2141 accepts a selection operation by the user to accept a selection of one or more pieces of registration data that have been downloaded to the user terminal 20 in advance.

In step S120, the transmission/reception unit 2142 of the user terminal 20 transmits the registration data selected by the user via the operation reception unit 2141 to the server 10. In step S210, the transmission/reception module 1041 of the server 10 receives the registration data transmitted from the user terminal 20. Next, the acquisition module 1042 acquires the registration data received by the transmission/reception module 1041. The acquisition module 1042 further acquires the shaping request 1014 stored in the memory unit 101. As an example, the shaping request 1014 is a request to generate shaped data in which information about the property described in the registration data is organized in an order according to the database.

In step S220, the generation module 1043 encrypts the registration data acquired by the acquisition module 1042. As an example, the generation module 1043 generates encrypted registration data using the AES algorithm.

In step S230, the generation module 1043 transmits the encrypted registration data and the formatting request to the external server S by handing them over to the transmission/reception module 1041. In step S310, the external server S receives the encrypted registration data and the formatting request.

In step S320, the external server S inputs the encrypted registration data and the shaping request into the large-scale language model M as a trained model, and causes the large-scale language model M to output the shaping data. In step S330, the external server S transmits the shaping data output by the large-scale language model M to the server 10. In step S240, the transmission/reception module 1041 of the server 10 receives the shaping data from the external server S.

In step S250, the generation module 1043 decrypts the registry data received from the external server S. As an example, the generation module 1043 decrypts the shaping data using the AES algorithm. FIG. 10 is a diagram illustrating a concept of a portion of the decrypted shaping data D in the form of a table. In FIG. 10, the shaping data D organizes information about a specific property in an order according to the database. In addition, the shaping data D associates, for example, property data, owner data of the property, debt data, and creditor data. In the shaping data D, for example, a record is generated for each registry data. Note that the shaping data shown in FIG. 10 is only a portion, and may include information other than that shown in FIG. 10.

In step S400 of FIG. 9, an analysis process of the shaped data is performed. In the analysis process (S400), the data management module 1045 executes a step of storing the property data, owner data, debt data, and creditor data in a database, and a step of associating the property data, owner data, debt data, and creditor data described in the same record in the shaped data. The analysis process will be described in detail later.

In step S260, the transmission/reception module 1041 of the server 10 transmits the results of the registration of the property data, owner data, debt data, and creditor data in the memory unit 101 by the analysis process (S400) to the user terminal 20. In step S130, the transmission/reception unit 2142 of the user terminal 20 receives the registration results of the property data, owner data, debt data, and creditor data from the server 10. In step S140, the notification control unit 2143 of the user terminal 20 notifies the user of the registration results of the property data, owner data, debt data, and creditor data. As an example, the notification control unit 2143 displays the registration results on the display 2181.

<4.2. Analysis process flow>
The flow of the analysis process (S400) will be described with reference to Figures 11 to 13. Figures 11 to 13 show an example in which the data management module 1045 stores the property data in the property database 1013 and stores the owner data in the owner database 1012.

In step S405 shown in FIG. 11, the data management module 1045 extracts property data and owner data from the decrypted formatted data. In the formatted data, data corresponding to, for example, property data, owner data, debt data, and creditor data are organized so that they can be distinguished by data position. The data management module 1045 repeats the processing of steps S410 to S480 shown below as many times as there are records in the formatted data.

In step S410, the data management module 1045 determines whether the owner data extracted from a specific record (hereinafter referred to as the record) of the shaping data has already been registered in the owner database 1012 of the storage unit 101 (i.e., whether a record corresponding to the owner data extracted from the shaping data exists in the owner database 1012), for example, based on the owner's name and address. If the owner data extracted from the shaping data has already been registered in the owner database 1012 (Yes in step S410), step S420 shown in FIG. 12 is executed. On the other hand, if the owner data has not been registered in the owner database 1012 (No in step S410), step S450 shown in FIG. 13 is executed.

Below, with reference to Figure 12, we will explain a case where the owner data extracted from the corresponding record of the shaping data has already been registered in the owner database 1012.

In step S420 shown in FIG. 12, the data management module 1045 determines whether the property data in the record has already been registered in the property database 1013 of the storage unit 101 (i.e., whether a record corresponding to the property data in the record exists in the property database 1013). If the property data included in the formatted data has already been registered in the property database 1013 (Yes in step S420), S430 is executed. On the other hand, if the property data has not been registered in the property database 1013 (No in step S420), step S425 is executed.

In step S430, the data management module 1045 determines whether the owners of the extracted properties match. Specifically, for example, the data management module 1045 refers to the owner database 1012 for the owners included in the bent data, and determines whether the properties stored in the "Owned Real Estate" item match the properties included in the bent data. If the properties match (Yes in step S430), step S435 is executed. On the other hand, if the owner information does not match (No in step S430), step S440 is executed.

In step S435, the data management module 1045 updates the information in the property database 1013 and terminates the analysis process for the record.

In step S440, the data management module 1045 changes the owner of the property based on the owner information in the corresponding record of the shaping data. Specifically, the data management module 1045 stores the property information included in the shaping data in the "Owned Real Estate" item in the owner database 1012 for the corresponding owner. This makes the corresponding owner the current final owner. Note that the property information is maintained as past owner information in the owner database 1012 of the owner who previously owned the property.

In the process of determining whether the owners match in step S430, if the property is shared, the data management module 1045 also checks the owner's share. The data management module 1045 references the owner database 1012 for the owner included in the bent data, and determines whether the property and share stored in the item "Owned Real Estate" match the property and share included in the bent data. The data management module 1045 executes step S435 if both the property and the share match. On the other hand, if at least one of the property and the share does not match, the data management module 1045 executes step S440.

In step S425, the data management module 1045 registers the property data in the corresponding record of the shaped data in the property database 1013. Specifically, the data management module 1045 adds and stores a record related to the property data in the property database 1013.

In step S445, the data management module 1045 associates the record added to the property database 1013 with the owner data stored in the owner database 1012 based on the owner data in that record of the shaped data. Specifically, the data management module 1045 adds the item "Property ID" of the record added to the property database 1013 in step S425 to the item "Owned Real Estate" in the owner database 1012 of the corresponding owner. This associates the property data and owner data stored in the memory unit 101.

Next, referring to FIG. 13, we will explain a case where the owner data extracted from the corresponding record of the shaping data is not registered in the owner database 1012.

In step S450 shown in FIG. 13, the data management module 1045 registers the owner data in the record in the owner database 1012. Specifically, the data management module 1045 adds and stores a record related to the owner data in the record in the owner database 1012. The data management module 1045 may perform a name matching process based on the owner data added to the owner database 1012. For example, if there is information that represents the same owner but has a different owner name, address, or both, the data management module 1045 may match the information registered in the owner database 1012 with the newly registered information so that the information is unified with the latest information. The data management module 1045 determines, for example, based on information obtained from other registration data, that the newly stored information represents the same owner as the registered information, and performs a name matching process.

In FIG. 13, the data management module 1045 determines whether the property data in the record of the shaped data has already been registered in the property database 1013 of the storage unit 101. If the property data has already been registered in the property database 1013 (Yes in step S460), step S470 is executed. On the other hand, if the property data has not been registered in the property database 1013 (No in step S460), step S475 is executed.

In step S470, the data management module 1045 updates the owner of the property stored in the property database 1013 based on the owner information in the corresponding record of the shaping data. Specifically, the data management module 1045, for example, extracts the owner associated with the property stored in the property database 1013, and updates the information about the property stored in the "Owned Real Estate" item in the owner database 1012 for that owner. In addition, if the property is shared, the share in the "Owned Real Estate" item in the owner database 1012 is updated.

In step S475, the data management module 1045 registers the property data in the record in the property database 1013. Specifically, the data management module 1045 adds and stores a record related to the property data in the property database 1013.

In step S480, the data management module 1045 associates the record added to the property database 1013 with the owner data stored in the owner database 1012 based on the owner data in the record. Specifically, the data management module 1045 adds the item "Property ID" of the record added to the property database 1013 in step S475 to the item "Owned real estate" in the owner database 1012 of the corresponding owner. This associates the property data and owner data stored in the memory unit 101.

The data management module 1045 performs an analysis process similar to that shown in Figures 11 to 13, extracts debt data from the formatted data, and stores the extracted debt data in the debt database 1015. The data management module 1045 also performs an analysis process similar to that shown in Figures 11 to 13, extracts creditor data from the formatted data, and stores the extracted creditor data in the creditor database 1016. The data management module 1045, for example, associates debtors in the debt data managed in the debt database 1015 with owners managed in the owner database 1012. The data management module 1045, for example, associates creditors in the debt data managed in the debt database 1015 with creditor data managed in the creditor database 1016.

5. Basic Hardware Configuration of Computer 90
14 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 901, a main storage device 902, an auxiliary storage device 903, and a communication IF 991 (interface). These are electrically connected to each other by a communication bus 921.

The processor 901 is hardware for executing a set of instructions written in a program. The processor 901 is composed of an arithmetic unit, registers, peripheral circuits, etc.

The main memory device 902 is used to temporarily store programs and data processed by the programs. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

The auxiliary storage device 903 is a storage device for saving data and programs. For example, it is a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, a semiconductor memory, etc.

The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using a wired or wireless communication standard. The network is composed of the Internet, LAN, various mobile communication systems constructed by wireless base stations, etc. For example, the network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks (e.g., Wi-Fi (registered trademark)) that can be connected to the Internet via a specified access point. In the case of a wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), Bluetooth (registered trademark), etc. In the case of a wired connection, the network also includes one that is directly connected by a USB (Universal Serial Bus) cable, etc.

The computer 90 can be realized virtually by distributing all or part of each hardware configuration across multiple computers 90 and connecting them together via a network. In this way, the concept of computer 90 includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.

6. Basic Functional Configuration of Computer 90
A description will now be given of the functional configuration of the computer realized by the basic hardware configuration of the computer 90. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.

The functional units of the computer 90 can also be realized by distributing all or part of each functional unit across multiple computers 90 that are connected to each other via a network. The concept of computer 90 includes not only a single computer 90 but also a virtualized computer system.

The control unit is realized by the processor 901 reading out various programs stored in the auxiliary storage device 903, expanding them in the main storage device 902, and executing processing in accordance with the programs. The control unit can realize functional units that perform various information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

The storage unit is realized by a main storage device 902 and an auxiliary storage device 903. The storage unit stores data, various programs, and various databases. Furthermore, the processor 901 can secure a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 in accordance with a program. Furthermore, the control unit can cause the processor 901 to execute processes for adding, updating, and deleting data stored in the storage unit in accordance with various programs.

The term "database" refers to a relational database, which is used to manage sets of data called masters and tables in a tabular format structurally defined by rows and columns, by relating them to each other. In a database, a table is called a master, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables and masters can be set and associated.

Usually, a column that serves as a primary key for uniquely identifying a record is set in each table and each master, but setting a primary key in a column is not essential. The control unit can cause the processor 901 to add, delete, or update records in a specific table or master stored in the storage unit according to various programs.
Furthermore, by storing data, various programs, and various databases in the storage unit, it can be considered that the information processing device and information processing system according to the present disclosure have been manufactured.

In addition, the databases and masters in this disclosure may include any data structure (such as a list, dictionary, associative array, or object) in which information is structurally defined. Data structures also include data that can be considered as data structures by combining data with functions, classes, methods, etc. written in any programming language.

The communication unit is realized by the communication IF 991. The communication unit realizes the function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 901 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.

<7. Summary>
As described above, in this embodiment, the system 1 executes the following steps: an acquisition step (S110, S210) for acquiring registration data related to real estate registration; a generation step (S320) for generating shaped data based on the registration data using a trained model; a first storage step (S425, S475) for extracting property data, which is data related to the property, from the shaped data (S405) and storing the extracted property data in a memory; a second storage step (S450) for extracting owner data, which is data related to the owner, from the shaped data (S405) and storing the extracted owner data in a memory; and an association step (S440, S445, S470, S480) for associating the owner data and property data stored in the memory. With this configuration, the "context" of the registration data is determined by machine learning, the information is classified, and shaped data is generated, so that information can be acquired from the real estate certified copy with high accuracy, and information on the real estate certified copy can be efficiently managed.

In addition, in the first storage step and the second storage step, the control unit 104 stores the property data and the owner data in separate databases. This further improves the efficiency of data management.

The control unit 104 also executes a third storage step of extracting debt data, which is data related to debts, from the shaped data and storing the extracted debt data in memory, and a fourth storage step of extracting creditor data, which is data related to creditors, from the shaped data and storing the extracted creditor data in memory. In an association step, the control unit 104 associates the owner data, debt data, and creditor data stored in memory. This makes it possible to manage debt information and creditor information as well, making it possible to manage information obtained from the real estate certified copy even more efficiently.

In addition, in the first storage step, the second storage step, the third storage step, and the fourth storage step, the control unit 104 stores the property data, the owner data, the debt data, and the creditor data in separate databases. This further improves the efficiency of data management.

In addition, in the generation step, a shaping request for generating shaped data may be input to a large-scale language model M as a trained model, and the large-scale language model M may be caused to output the shaped data. With this configuration, it is possible to manage registration data using a large-scale language model trained using a large amount of parameters and high-level computational resources, thereby improving the efficiency of management operations.

The formatting request may also be a request to have the large-scale language model M generate formatted data in which data included in the acquired registration data is organized in an order according to the type of data. This configuration makes it possible to create a data structure that is easy to store in a database.

The shaped data generated by the shaping step may have a record in which a specific property is associated with the current and past owners of the property, and in the associating step, the owner data of the owner and the property data of the property may be associated in the same record. With this configuration, it is possible to efficiently associate the owner data and the property data based on the shaped data generated by the generating step.

The shaped data generated by the shaping step may have records in which a specific property, a current or past owner of the property, a debt related to the property, and a creditor of the debt are associated with each other, and in the associating step, the owner data of the owner, the debt data of the debt, and the creditor data of the creditor, all of which are listed in the same record, may be associated. This makes it possible to efficiently associate the owner data, debt data, and creditor data based on the shaped data generated by the generating step.

In addition, in the generation step, the acquired registration data may be encrypted, the encrypted registration data may be input to a trained model as a trained model, and the formatted data output from the trained model may be decrypted. By adopting such specifications, it is possible to prevent personal information described in the registration data from being leaked when using a trained model provided by an external server such as a publicly available large-scale language model M.

8. Other embodiments
Although the embodiments to which the technical scope of the present application is applied have been described above, the present invention is not limited to the above contents.

For example, in the above embodiment, a large-scale language model M that is publicly available through an external server S is used to generate formatting data based on registration data, but the present invention is not limited to this embodiment. For example, a trained model that a user trains himself/herself may be stored in the memory unit 101 of the server 10, and the technical idea of the present disclosure may be implemented using the trained model. With such specifications, it is possible to obtain the same effect as the above embodiment using the server 10 and user terminal 20 provided in the system 1.

In addition, in the above embodiment, the registration data is encrypted (S220 in FIG. 8) and the shaping data is decrypted (S250 in FIG. 9), but encryption and decryption are not necessarily required. For example, as described above, when implementing the technical idea of the present disclosure using a trained model stored in the memory unit 101 of the server 10, specifications may be made such that the registration data is not encrypted and the shaping data is not decrypted. By adopting such specifications, it becomes possible to simplify the processing of the system 1 and manage the registration data more efficiently. Furthermore, in the case where the large-scale language model M is designed such that input information is not used for learning, encryption and decryption are not necessarily required.

In addition, in the above embodiment, the shaping request 1014 is stored in the memory unit 101 of the server 10, but this is not limited to the above. For example, in step S210 of FIG. 8, the user terminal 20 may accept the registration data and at the same time accept the shaping request from the user. By adopting such specifications, it becomes easy to generate generated data based on the shaping request that reflects the detailed needs of the user.

In addition, in the above embodiment, the owner data is managed by the owner database 1012, and the property data is managed by the property database 1013, but this is not limited to the above. That is, the property data and the owner data may be managed in one database, or may be managed in three or more databases. As an example, a new database may be added to define the association between the owner database 1012 and the property database 1013.

In addition, in the above embodiment, owner data is managed by the owner database 1012, property data is managed by the property database 1013, debt data is managed by the debt database 1015, and creditor data is managed by the creditor database 1016, but this is not limited to the above. In other words, these data may be managed in one database, or in three or more databases. As an example, a new database may be added to define the association between the owner database 1012, debt database 1015, and creditor database 1016.

In addition, in the above embodiment, an example was described in which owner data, property data, debt data, and creditor data were registered in the storage unit 101, but one or a combination of at least two or more of these may be registered in the storage unit 101.

In addition, in the above embodiment, the technical ideas of the present disclosure are applied to the management of real estate properties and owners based on registration data such as real estate certified copies, but the present invention is not limited to this example. In other words, the technical ideas of the present disclosure can be applied to the management of objects that are the subject of specific rights and that are uniquely identified, and the owners of those rights. In this case, instead of registration data, right holder data indicating the person who owns the rights to the uniquely identified object can be acquired by the acquisition module 1042 of the server 10. In this way, the technical ideas of the present disclosure can be applied to situations other than the management of real estate properties, and the same effects as those of the above embodiment can be obtained.

In addition, in the above embodiment, an example of a form in which each function is provided by the user terminal 20 or the server 10 is described, but this is not limited to this form, and some functions may be provided by the user terminal 20, the server 10, or both the user terminal 20 and the server 10 in a form different from the above embodiment.

For example, each step described in the above embodiment as being executed by the user terminal 20 may be executed by the server 10, and each step described as being executed by the server 10 may be executed by the user terminal 20.

In addition, the sharing of specific information via a communication line is mainly performed via a WAN such as the Internet, but between information processing devices, the sharing may be performed only via short-range wireless communication such as Bluetooth (registered trademark) and infrared communication without using a WAN.

Furthermore, the present invention may be realized as a computer-readable non-transitory recording medium that stores the above-mentioned program.

Although various embodiments of the present invention have been described above, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the gist of the invention. The embodiments and their modifications are included within the scope and gist of the invention, and are included in the scope of the invention and its equivalents as set forth in the claims.

<9. Notes>
The matters described in the above embodiments will be supplemented below.

(Appendix 1)
A program for causing a computer having a processor and a memory to execute processing, the program causing the processor to execute the following steps: an acquisition step for acquiring registration data related to real estate registration; a generation step for generating shaped data based on the registration data using a trained model; a first storage step for extracting property data, which is data related to a property, from the shaped data and storing the extracted property data in a memory unit; a second storage step for extracting owner data, which is data related to the owner of the property, from the shaped data and storing the extracted owner data in a memory unit; and an association step for associating the owner data stored in the memory unit with the property data.
(Appendix 2)
The program according to claim 1, wherein in the first storage step and the second storage step, the property data and the owner data are stored in separate databases.
(Appendix 3)
A program described in Appendix 2, which causes a processor to execute a third storage step of extracting debt data, which is data regarding debts, from the formatted data and storing the extracted debt data in the memory unit, and a fourth storage step of extracting creditor data, which is data regarding creditors, from the formatted data and storing the extracted creditor data in the memory unit, and in an association step, associates the owner data, debt data, and creditor data stored in the memory unit.
(Appendix 4)
A program described in Appendix 3, in which in the first storage step, the second storage step, the third storage step, and the fourth storage step, property data, owner data, debt data, and creditor data are stored in separate databases.
(Appendix 5)
A program described in any one of (Appendix 1) to (Appendix 4), in which, in the generation step, a shaping request for generating shaping data is input to a large-scale language model as a trained model, and the large-scale language model is caused to output the shaping data.
(Appendix 6)
The formatting request is a request to the large-scale language model to generate formatted data in which the data contained in the acquired registration data is organized in an order according to the type of data (program described in Appendix 6).
(Appendix 7)
A program described in any one of (Appendix 1) to (Appendix 6), in which the formatted data has a record in which a specific property is associated with the current and past owners of the property, and in the association step, the owner data of the owner and the property data of the property are associated in the same record.
(Appendix 8)
The formatted data has records in which a specific property, the current or past owner of the property, the debt related to the property, and the creditor of the debt are correspondingly recorded, and in an association step, the owner data of the owner, the debt data of the debt, and the creditor data of the creditor are associated with each other in the same record (Appendix 3).
(Appendix 9)
A program described in any one of (Appendix 1) to (Appendix 8), in which, in the generation step, the acquired registration data is encrypted, the encrypted registration data is input into a trained model, and the shaped data output from the trained model is decrypted.
(Appendix 10)
A method executed by a computer having a processor and a memory, wherein the processor executes all of the steps performed in any of the inventions according to (Appendix 1) to (Appendix 9).
(Appendix 11)
An information processing device comprising a control unit and a memory unit, wherein the control unit executes all of the steps executed in the invention according to any one of (Supplementary Note 1) to (Supplementary Note 9).
(Appendix 12)
A system comprising means for executing all the steps performed in any of the inventions according to (Appendix 1) to (Appendix 9).

1: System, 10: Server, 20: User terminal, 90: Computer, 101: Memory unit, 104: Control unit, 201: Memory unit, 211: Memory unit, 214: Control unit, 216: Input device, 218: Output device, 901: Processor, 902: Main memory unit, 903: Auxiliary memory unit, 921: Communication bus, 1011: Application program, 1012: Owner database, 1013: Property database, 1014: Shaping request , 1041: transmission/reception module, 1042: acquisition module, 1043: generation module, 1045: data management module, 2111: application program, 2141: operation reception unit, 2142: transmission/reception unit, 2143: notification control unit, 2161: camera, 2162: microphone, 2163: position information sensor, 2164: motion sensor, 2165: touch device, 2181: display, 2182: speaker.

Claims (10)

A program for causing a computer having a processor and a memory to execute a process,
The processor,
An acquisition step of acquiring registration data relating to real estate registration;
a generation step of inputting the registry data and a command statement for outputting information about properties described in the registry data in an order corresponding to the type of data into a large-scale language model, which is a natural language model designed to execute multiple tasks of natural language processing, thereby causing the large-scale language model to generate formatted data in which information about properties described in the registry data is organized in an order corresponding to the type of data ;
a first storage step of extracting property data, which is data related to a property, from the shaped data and storing the extracted property data in a storage unit;
a second storage step of extracting owner data relating to an owner of the property from the shaped data and storing the extracted owner data in the storage unit;
an associating step of associating the owner data and the property data stored in the storage unit;
A program that executes the following. The program according to claim 1, wherein in the first storage step and the second storage step, the property data and the owner data are stored in separate databases. a third storage step of extracting debt data, which is data related to debt, from the shaped data and storing the extracted debt data in the storage unit;
a fourth storage step of extracting creditor data, which is data related to creditors, from the shaped data and storing the extracted creditor data in the storage unit;
3. The program according to claim 2, wherein in said associating step, said owner data, said debt data and said creditor data stored in said storage unit are associated with each other. The program according to claim 3, wherein in the first storage step, the second storage step, the third storage step, and the fourth storage step, the property data, the owner data, the debt data, and the creditor data are stored in separate databases. The said formatting data has a record in which a specific property is associated with the current and past owners of the property,
2. The program according to claim 1, wherein said associating step associates owner data of an owner and property data of a property described in the same record. The formatted data includes a record in which a specific property, a current or past owner of the property, a debt related to the property, and a creditor of the debt are described in association with each other;
4. The program according to claim 3, wherein said associating step associates owner data of an owner, debt data of a debt, and creditor data of a creditor, all of which are described in the same record. The program according to claim 1, wherein in the generating step, the acquired registration data is encrypted, the encrypted registration data is input to the large-scale language model, and the formatted data output from the large-scale language model is decrypted. A method executed by a computer having a processor and a memory, the processor executing all of the steps executed in the invention according to any one of claims 1 to 7. An information processing device comprising a control unit and a storage unit, the control unit executing all steps executed in the invention according to any one of claims 1 to 7. A system having means for executing all steps performed in any of the inventions according to claims 1 to 7.