JP2019091355A - Determination device, determination method and determination program - Google Patents

Abstract

To provide a device, a method and a program for determining credibility for a business operator from various viewpoints.SOLUTION: In a determination system, a determination device comprises an acquisition part and a determination part. The acquisition part acquires information relating to a user using a predetermined commerce site on a network. The determination part determines credibility of a first business operator on the basis of an action history on the network of a first user being a user having a transaction history with the first business operator performing commercial transaction in the commerce site, out of the information related to the user acquired by the acquisition part.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a determination apparatus, a determination method, and a determination program.

  Generally, when a financial institution such as a bank determines the available credit limit, business data provided by a data provider specializing in collection and analysis of business (company) information is referred to. Such business entity data is generated, for example, based on a business statement (for example, financial statements, profit and loss statement, etc.) of the business entity. That is, the financial institution utilizes the enterprise data provided by the vendor to determine the credit information for determining whether the amount of loans to each enterprise is appropriate.

  Here, a model is created in which not only data with a long update interval (static data) such as financial data published in the fiscal year but also data with a short update interval (dynamic data) such as stock prices etc. A system has been proposed that can perform the latest company evaluation in a timely manner (eg, Patent Document 1). Also, with the rapid spread of the Internet in recent years, in addition to the information based on the financial statements etc. of the conventional business operators, information users share information on business operators on the Internet and unify the shared information There is known a technology for improving the objectivity of business entity data by performing integrated management (for example, Patent Document 2).

JP 2000-348015 A Unexamined-Japanese-Patent No. 2010-26602

  However, in the above-mentioned prior art, it is not always possible to determine the credit to the business from various points of view. Specifically, in the above-mentioned prior art, the financial information of the public company, the business results of the business which the information user can know, the information of the industry news and the like are only shared, It is difficult to properly assess the creditworthiness of a business (for example, the growth potential or stability of the business over the future) even if In addition, since data such as stock prices are not disclosed to unlisted companies, in some cases, there is a shortage of data for conducting company evaluations, making it difficult to determine the creditworthiness of a business.

  This application is made in view of the above, and an object of the present invention is to provide a judgment device, a judgment method, and a judgment program which can judge credit to a business from various viewpoints.

  The determination apparatus according to the present application is a first business performing a commercial transaction at the commerce site among an acquisition unit for acquiring information on a user who uses a predetermined commerce site on the network and information on the user acquired by the acquisition unit A determination unit that determines the creditworthiness of the first business operator based on an action history of the first user who is a user who has a transaction history with a person.

  According to one aspect of the embodiment, it is possible to determine the credit to the business with high accuracy.

FIG. 1 is a diagram illustrating an example of determination processing according to the embodiment. FIG. 2 is a diagram illustrating an exemplary configuration of a determination system according to the embodiment. FIG. 3 is a diagram showing an example of the configuration of the determination apparatus according to the embodiment. FIG. 4 is a diagram illustrating an example of a business entity information storage unit according to the embodiment. FIG. 5 is a diagram showing an example of a usage history table according to the embodiment. FIG. 6 is a diagram showing an example of a browsing history table according to the embodiment. FIG. 7 is a diagram showing an example of a payment information table according to the embodiment. FIG. 8 is a diagram showing an example of an attribute information table according to the embodiment. FIG. 9 is a diagram illustrating an example of a model storage unit according to the embodiment. FIG. 10 is a flowchart showing a generation processing procedure by the determination apparatus according to the embodiment. FIG. 11 is a flowchart illustrating the determination processing procedure by the determination apparatus according to the embodiment. FIG. 12 is a diagram illustrating an example of the determination process according to the modification. FIG. 13 is a hardware configuration diagram showing an example of a computer that implements the function of the determination apparatus.

  Hereinafter, a determination apparatus, a determination method, and a mode for implementing a determination program according to the present application (hereinafter, referred to as “embodiment”) will be described in detail with reference to the drawings. In addition, the determination apparatus, the determination method, and the determination program which concern on this application by this embodiment are not limited. Moreover, the same code | symbol is attached | subjected to the site | part same in each following embodiment, and the overlapping description is abbreviate | omitted.

[1. Example of determination processing]
First, an example of the determination process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of determination processing according to the embodiment. Specifically, in FIG. 1, an example will be described in which the determination apparatus 100 according to the embodiment performs processing of determining the creditworthiness of a business operator who is opening a store at a predetermined commerce site on the network.

  In the example shown in FIG. 1, the determination device 100, the user terminal 10, and the web server 30 are communicably connected via a communication network (for example, the Internet) not shown.

  The determination device 100 illustrated in FIG. 1 is a server device that performs a process of determining the creditworthiness of a business entity. In the embodiment, the determination apparatus 100 determines the creditworthiness of a company who opens a store in a shopping mall, which is a predetermined commerce site on the network provided by the web server 30.

  In the embodiment, a business operator who is opening a store in a shopping mall and is a target whose creditworthiness is determined in the determination process according to the embodiment is referred to as a “first business operator”. Further, in the embodiment, among businesses operating in a shopping mall, a business that is different from the first business and can be learning data of a model for determining credit in the determination process according to the embodiment. It is written as "2nd company". In addition, when the first enterprise and the second enterprise are not particularly distinguished from one another, the first enterprise and the second enterprise are simply referred to as "the enterprise".

The user terminal 10 ₁ and 10 ₂ shown in FIG. 1 is an information processing device used by a user. Specifically, the user terminal 10 ₁ and 10 _2, and for the user to browse the various web pages, or to purchase goods in the web site (for example, a shopping mall on the network), evaluation of product information (the so-called review) It is used to post and. In the example of FIG. 1, the user terminal 10 ₁ is utilized by the user U01 which is an example of a user, the user terminal 10 ₂ is used by the user U02 is an example of a user. Also, unless otherwise identified and the user terminal 10 ₁ and 10 ₂ are collectively referred to as "user terminal 10". In the example of FIG. 1, the user terminal 10 is, for example, a smartphone or a tablet terminal.

  Furthermore, in the embodiment, among the users, a user who has a transaction history with the first business (for example, a user who has a history of having purchased a product at a store where the first business has opened) is referred to as a “first user”. write. Further, among users, a user who has a transaction history with the second business entity is referred to as a "second user". In addition, when the same user has a transaction history for both the first business operator and the second business operator, the user can be the “first user” or the “second user” depending on the processing status. Moreover, when not distinguishing the 1st user and the 2nd user in particular, it only describes with a "user."

  The web server 30 illustrated in FIG. 1 is a server device that provides various web pages when accessed from the user terminal 10. In the example shown in FIG. 1, the web server 30 is assumed to provide a shopping mall site on the network. In the shopping mall provided by the web server 30, each business opens a store that handles products of various categories.

  In addition, the web server 30 acquires information on the user who uses the shopping mall through the provided website. Information on the user is stored, for example, in a storage unit provided in the web server 30 or in a predetermined external storage device. The information on the user means, for example, information transmitted from the user terminal 10 according to the operation of the user when using the service provided from the web server 30. Specifically, information on the user includes user attribute information (age, gender, etc.), purchase behavior in the shopping mall, payment information in the shopping mall, rank of the user in the shopping mall (for example, the user is a good member) Or not).

  In addition, the information regarding a user may be acquired via services other than a shopping mall. For example, the web server 30 provides various services such as a portal service, a news distribution service, a schedule management service, and a restaurant reservation service as services other than the shopping mall. And the web server 30 may acquire the information regarding a user through utilization of these services. Specifically, the web server 30 can acquire, as information on the user, information on news content browsed by the user, information on a schedule registered in the service by the user, and the like.

  By the way, the business owner who opens a commerce site on a network such as a shopping mall provided by the web server 30 has a small business configuration, is relatively new in establishment, is unlisted, and has an individual legal personality. Even if you are a business owner, you may not have enough funds. For this reason, there is a demand for obtaining a loan to these businesses, and there is a demand for obtaining an opportunity to give a loan to these businesses for a financial institution or the like.

  Generally, when a financial institution provides a loan, it is decided based on the creditworthiness (credit) of the business operator whether the loan can be made and how much the amount of the loan should be. The creditworthiness of such a business is measured, for example, by the financial institution itself or a specialized organization that evaluates the business. However, since small businesses often do not disclose quarterly or semi-annual financial information or capital relationships, there are cases where specialized institutions or financial institutions can not measure the creditworthiness of businesses. In this case, the business can not receive a loan, and the financial institution also loses the opportunity of the loan, which causes both sides to be disadvantaged.

  Therefore, the determination apparatus 100 according to the embodiment determines the creditworthiness of the business owner who opens the store based on the information about the user who has a transaction history in the store that opened the shopping mall.

  This is a steady and reliable user who uses the store where the first business entity is open (for example, a user who has not yet made a payment, a user who browses a relatively large number of economic news, etc.) The reason is that it is assumed that the first company is also a credible company. That is, the determination apparatus 100 determines a store having a relatively large number of trusted customers as a store having a high credit rating, and further determines a first business operator who operates the store as a business operator having a high credit rating.

  In this determination process, the determination apparatus 100 has information on the second business operator who is a business operator whose credit rating is set in advance (for example, some credit rating information is given by a financial institution, a specialized organization, or a shopping mall). You may use For example, the determination apparatus 100 learns the correlativity between the second enterprise and the information on the second user having the transaction history with the second enterprise. Thus, the determination apparatus 100 learns what kind of information the user who has a high credit rating (or low credit) store and a transaction has. Specifically, the determination apparatus 100 generates a model in which the correlation between the second provider and the information on the second user is learned. Then, the determination apparatus 100 determines the credit of the first business using the generated model. As a result, the determination apparatus 100 can accurately determine the credit rating even for a relatively small-sized first business operator who has not released information such as financial status and stock price. Hereinafter, the determination process according to the embodiment will be described along the flow with reference to FIG.

  In the example shown in FIG. 1, the shopping mall provided by the web server 30 is operated by a business operator A01 (an example of a first business operator) who is a business enterprise to which creditworthiness information is not given from a financial institution or a specialized organization. There is a store page 61 which is a web page of the store AAA. In addition, in the shopping mall, there is a store page 71 which is a web page of a store BBB operated by a business operator A02 (an example of a second business operator) who is a business having a credit rating (having credit information). Do. In the example of FIG. 1, it is assumed that the credibility is indicated by a score (index value) having a maximum of 100 and a minimum of 0. In the example of FIG. 1, a credit rating indicating a relatively high score of "85" is set for the business operator A02, and such a value indicates that the business operator A02 is evaluated as a business operator having a relatively high credit rating. It shows. Although not illustrated in FIG. 1, the second mall 30 provides a shopping mall provided by the web server 30 with a sufficient number of second businesses that can obtain a sufficient amount of information for performing the determination process according to the embodiment. Shall exist.

The user takes an action such as browsing a product or purchasing a product from the store of the shopping mall. For example, the user terminal 10 ₁ in accordance with operation by the user U01, accesses the shopping mall web server 30 is provided, utilizing a shopping mall (step S11). For example, the user U01 purchases a product from the store AAA. In the example of FIG. 1, the user U01 corresponds to the first user because the user U01 is a user having the business history with the business operator A01, which is the first business operator.

Similarly, the user terminal 10 ₂ in accordance with operation by the user U02, accesses the shopping mall web server 30 is provided, utilizing a shopping mall (step S12). For example, the user U02 purchases a product from the store BBB. In the example of FIG. 1, the user U02 corresponds to the second user because the user U02 is a user who has a transaction history with the business operator A02, which is the second business operator. Although not illustrated in the example of FIG. 1, a plurality of users U01 and U02 exist, and a considerable number of accesses are obtained such that a sufficient amount of information can be obtained to perform the determination process according to the embodiment. It shall be done.

  In addition, it is assumed that the user U01 and the user U02 appropriately use services other than the shopping mall provided by the web server 30. For example, it is assumed that the user U01 and the user U02 use a news service distributed via a network, a schedule service provided by the web server 30, and the like. The action history and the like of these users are all included in the information on the user according to the embodiment.

  Here, the determination apparatus 100 acquires, from the web server 30, the degree of credit of the second business operator set in advance and information on the user U02 (the second user) who has made a transaction with the second business company (step S13). ).

  Then, based on the acquired information, the determination apparatus 100 generates a model in which the correlation between the degree of credit of the second enterprise and the information on the second user is learned (step S14). The model is a model for indicating the correlation between the degree of credit of the enterprise and the information on the user, and, for example, when the information on the first user is input to the model, the first model corresponding to the first user 1 Creditworthiness of the business is output. The details of the model generation process will be described later, but the determination device 100 uses, for example, the credit of the business operator A02 as correct answer data (teacher data, objective variable), and various information on the second user corresponding to the business operator A02 as a feature (explanatory variable Generating a regression learning model such as Support Vector Machine.

  Thereafter, the determination apparatus 100 acquires information on the user U01 (first user) who has made a transaction with the business operator A01, which is the first business operator to be processed (step S15).

  Then, the determination apparatus 100 outputs a score (index value) indicating the credit of the business entity A01 by inputting the information on the business object A01 to be processed and the user U01 having the transaction history into the generated model. The determination apparatus 100 determines the credit of the first enterprise based on the output score (step S16).

  That is, the model generated by the determination apparatus 100 outputs a score indicating the credit of the business entity A01 based on the information regarding the first user when the information regarding the first user who has a transaction with the business enterprise A01 is input. . For example, if the information on the user U01 is very similar to the information on the user U02, the model outputs a score similar to "85", which is the credit of the business operator A02, as the credit of the business operator A01. The determination apparatus 100 does not acquire information such as the financial status of the business operator A01 according to the determination process, and based on the information (for example, various behavior histories of the user U01) of the business user U01, the business operator A01. You can determine the credit rating of

  Thus, the determination apparatus 100 according to the embodiment acquires information on a user who uses a predetermined commerce site on the network. Then, based on the action history on the network of the first user who is the user who has a transaction history with the first enterprise who performs a commercial transaction on the commerce site among the information related to the acquired user, the determination apparatus 100 determines the first enterprise. Determine the credit rating of

  That is, the determination apparatus 100 according to the embodiment not only uses financial information generally used to measure the creditworthiness of a business, but also information of a user who has a transaction with a store opened at a commerce site such as a shopping mall. Use to determine the creditworthiness of the business. Thereby, the determination apparatus 100 can determine the credit to the business from various points of view regardless of the business financial information and sales amount. Hereinafter, the configuration and the like of the determination device 100 that performs the above-described processing, the determination system 1 including the determination device 100, and the like will be described in detail.

[2. Configuration of judgment system]
The configuration of the determination system 1 including the determination apparatus 100 according to the embodiment will be described using FIG. 2. FIG. 2 is a view showing a configuration example of the determination system 1 according to the embodiment. As illustrated in FIG. 2, the determination system 1 according to the embodiment includes the user terminal 10, the business operator terminal 20, the web server 30, and the determination apparatus 100. These various devices are communicably connected by wire or wireless via a network N (for example, the Internet). The determination system 1 illustrated in FIG. 2 may include a plurality of user terminals 10, a plurality of business operator terminals 20, and a plurality of web servers 30.

  The user terminal 10 is, for example, an information processing apparatus such as a smartphone, a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), a wearable device (Wearable Device), etc. It is. The user terminal 10 accesses the web server 30 according to the operation by the user, thereby providing various contents from the service provided from the web server 30 (for example, the store page 61 of the store AAA or the store BBB shown in FIG. Get page 71). Then, the user terminal 10 displays the acquired content on a display device (for example, a liquid crystal display). In the present specification, the user and the user terminal 10 may be regarded as identical. For example, "providing content to the user" may actually mean "providing content to the user terminal 10 used by the user".

  The provider terminal 20 is an information processing apparatus used by a provider. Specifically, the business operator terminal 20 performs the procedure of opening a store in the shopping mall, the procedure of exhibition of the product in the store, and the like according to the operation of the business operator. In the embodiment, a business operator is a concept broadly including a person who carries out a business, and is not limited to a corporation etc., but may be an individual business owner or an organization having a legal personality.

  The web server 30 is a server device that provides various contents such as a web page when accessed from the user terminal 10. In the example of FIG. 1, while the web server 30 provides the website corresponding to a shopping mall, the example which provides the web page of entrepreneur A01 and entrepreneur A02 which are opening a store in the said shopping mall was shown. However, the service provided by the web server 30 is not limited to this, and the web server 30 may be, for example, a news site, a weather forecast site, a shopping site, a finance (stock price) site, a route search site, a map providing site, a travel site, eating and drinking You may provide various web pages about a store introduction site, a web blog, etc.

  In addition, the web server 30 may acquire information on each web site and information on users that can be acquired on the network. The information on the user is, for example, information transmitted from the user terminal 10 in accordance with the operation of the user when using services provided from various websites. For example, the information on the user includes attribute information (sex, age, address, occupation, annual income, etc.) registered by the user when using the service. Also, the information on the user includes action information of the user. For example, the user's action information may be browsing information in which the user browses the news content, information on a search query sent on the search site, information on purchasing behavior on the shopping site or a review from the user, SNS posted by the user ( Contains information related to messages on the Social Networking Service site.

  In the embodiment, a plurality of web servers 30 may exist. In this case, the web server 30 for providing the shopping mall to the user terminal 10 may be different from the web server 30 for acquiring information on the user.

  The determination apparatus 100 acquires information on a user who uses a predetermined commercial transaction site (a shopping mall or the like shown in FIG. 1) on the network, and among the acquired information on the user, performs the commercial transaction at the commercial site. It is a server apparatus which determines the credit of a 1st enterprise based on the action history on the network of the 1st user who is a user who has a transaction history. Note that the determination apparatus 100 may double as the above-described web server 30. That is, the determination apparatus 100 itself may provide a shopping mall, and the determination apparatus 100 may obtain information from the user terminal 10 that has accessed the shopping mall.

  In addition, the determination apparatus 100 evaluates the creditworthiness of a business by examining, acquiring, and managing information processing terminals installed in a financial institution that actually provides financing to the business and financial information on the business. It may communicate with an information processing terminal or the like installed in a specialized organization. For example, the determination apparatus 100 may acquire rating information (corresponding to “credit” in the embodiment) of the second business entity from an information processing terminal installed in a financial institution or a specialized institution. In addition, when the financial information of the company A01 or the company A02 is announced, the determination apparatus 100 may appropriately acquire the financial information from an information processing terminal installed in a financial management company or the like. In addition, when financial information on the business entity A01 and the business enterprise A02 can be acquired from a public organization or the like, the determination apparatus 100 may appropriately access the public organization or the like to acquire information. These processes may be performed using, for example, a predetermined program that crawls on a network to acquire information.

[3. Configuration of determination device]
Next, the configuration of the determination apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a view showing a configuration example of the determination apparatus 100 according to the embodiment. As shown in FIG. 3, the determination apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The determination apparatus 100 includes an input unit (for example, a keyboard or a mouse) that receives various operations from a manager or the like who uses the determination apparatus 100, and a display unit (for example, a liquid crystal display or the like) for displaying various information. You may have.

(About communication unit 110)
The communication unit 110 is realized by, for example, a network interface card (NIC). The communication unit 110 is connected to a communication network by wire or wireless, and transmits and receives information to and from the user terminal 10 and the like through the communication network.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 according to the embodiment includes a business entity information storage unit 121, a feature information storage unit 122, and a model storage unit 127. Hereinafter, each storage unit will be described in order.

(About company information storage unit 121)
The business entity information storage unit 121 stores information on business entities that open stores on a predetermined commerce site. The information stored in the business entity information storage unit 121 is acquired from, for example, the web server 30 via a network. Here, FIG. 4 illustrates an example of the business entity information storage unit 121 according to the embodiment. As shown in FIG. 4, the business entity information storage unit 121 has items such as “business entity ID”, “store”, “legal personality”, “credit degree”, and “customer information”.

  “Business ID” indicates identification information that identifies a business that has a store at a commerce site. In the present specification, identification information may be used as a reference code used in the description. For example, a business operator whose business operator ID is "A01" may be described as "business operator A01".

  "Store" indicates the name of a store where a business entity has opened a commerce site. Note that the business operator may open a plurality of stores instead of opening only one store at one commerce site. "Moral personality" indicates the legal personality of the business.

  "Credit" indicates the credit to the business. The credit rating is stored in the business entity information storage unit 121 after the credit rating is determined by the determination unit 134 described later. For example, for a business whose credit quality is not currently determined (in the embodiment, the first business operator; in FIG. 4, the business operator A01 corresponds in FIG. 4), the credit quality of the business operator A01 who received the loan Is a blank (indicated as "none" in the example of FIG. 4) is stored. Also, for example, a business whose credit rating has already been determined or whose credit rating has been set by a specialized organization (the second business operator in the embodiment. In FIG. 4, the business operator A02, the business operator A03 and the business operator A04 are relevant) The value of 0 to 100 is stored in the item of credibility).

  The “customer information” stores information on a user who is a customer of a store where the business operates. In the example shown in FIG. 4, the information stored in "customer information" is indicated by a concept such as "B01", but in fact, in the item of customer information, information identifying a user who has a transaction history Also, various information such as the number of users who are customers, the details of the transaction, the transaction amount and the like are stored.

  That is, in FIG. 4, as one example of data stored in the company information storage unit 121, the company A01 identified by the company ID "A01" has opened a store "AAA", and the legal personality is " It shows that "It is a corporation", the credit rating is "none", and the customer information is "B01".

  Although not shown in FIG. 4, the business operator may open a plurality of stores instead of opening one store at one commerce site.

(About the feature information storage unit 122)
The feature information storage unit 122 stores information on features used in the model generation process. Specifically, the feature information storage unit 122 stores various pieces of information about the user on the network as the feature information. As shown in FIG. 3, the feature information storage unit 122 has data tables such as a usage history table 123, a browsing history table 124, a payment information table 125, and an attribute information table 126. Each data table will be described in order below.

(About usage history table 123)
The usage history table 123 stores usage history of the store by the user as an example of the information regarding the user. Here, FIG. 5 shows an example of the usage history table 123 according to the embodiment. As shown in FIG. 5, the usage history table 123 has items such as "user ID", "usage store", and "number of transactions".

  "User ID" indicates identification information for identifying a user or a user terminal 10 used by the user. "Use store" indicates the name of the store used by the user. The “number of transactions” indicates the number of times the user has made a transaction with each store (for example, purchase of goods, use of service, etc.).

  That is, in FIG. 5, as an example of data stored in the usage history table 123, the user U01 identified by the user ID “U01” uses “store AAA”, “store EEE”, “store FFF”, etc. It has a history, and the number of transactions with store AAA is “16”, the number of transactions with store EEE is “7”, and the number of transactions with store FFF is “5” It shows.

(About browsing history table 124)
The browsing history table 124 stores the history of browsing of the content by the user. In the embodiment, the content widely includes a web page provided with various information and application content provided via a network. In the example of FIG. 6, news content is taken as an example among the contents provided to the user. The news content includes, for example, news content at a news site provided by the web server 30, news content provided via a news dedicated application, and the like. Here, FIG. 6 shows an example of the browsing history table 124 according to the embodiment. As shown in FIG. 6, the browsing history table 124 has items such as “user ID”, “counting period”, and “browsing history”. Also, "browsing history" has a middle item "news content". Furthermore, "news content" has small items such as "category", "number of browsing times", and "browsing time".

  "User ID" corresponds to the same item shown in FIG. The "aggregation period" indicates a period in which the browsing history of the user is aggregated. The “browsing history” indicates the browsing history of the user. "News content" indicates information on browsing of news content in browsing history.

  "Category" indicates a category of individual news content. The categories are tagged with individual news content, for example by the person providing the news distribution service. The “number of browsing times” indicates the number of times the news content has been browsed by category. The "browsing time" indicates the time at which the news content was viewed (in the example of FIG. 6, the unit is "minute") by category.

  That is, in FIG. 6, as an example of data stored in the browsing history table 124, the browsing history of the news content in the aggregation period up to "Oct. 1, 2017-October 31, 2017" of the user U01 is " The number of browsing times for the 'economy' category is' 21 'and the browsing time is' 110' minutes, and the number of browsing times for the 'sports' category is' 5' times and the browsing time is' 40 'minutes,' It indicates that the number of browsing times for the "entertainment" category is "3" times and the browsing time is "20 minutes".

  Although FIG. 6 shows an example in which the browsing history is stored as “one month” in the aggregation period, the aggregation period is not limited to this example, and is appropriately changed according to the model generation processing and the credit determination processing described later. It may be done.

(About payment information table 125)
The settlement information table 125 stores information on settlement at the commerce site among the information on the user. Here, FIG. 7 shows an example of the payment information table 125 according to the embodiment. As shown in FIG. 7, the settlement information table 125 has items such as “user ID”, “counting period”, and “transaction history”. Further, the “transaction history” has small items such as “the number of settlements”, “the number of unpaid bills”, and “the number of divided payment users”.

  The "user ID" and the "total period" correspond to the same items shown in FIG. "Trading history" indicates the history of the user's trading. The “number of payments” indicates the number of times the user has made a payment at the commerce site. The “number of unpaid bills” indicates the number of unpaid transactions, for example, because the user has made a transaction on the commerce site but the payment is not properly made. “Number of installment payments” indicates the number of times the installment payment method is adopted in settlement.

  That is, in FIG. 7, as an example of data stored in the settlement information table 125, the number of settlements is “30” as the transaction history in the aggregation period from “Oct. 1, 2017 to October 31, 2017” of user U01. "There are 2 times of unpaid times and unpaid times, which indicates that the number of installments used was" 5 times ".

(About the attribute information table 126)
The attribute information table 126 stores attribute information of the user among the information related to the user. Here, FIG. 8 shows an example of the attribute information table 126 according to the embodiment. As shown in FIG. 8, the attribute information table 126 has items such as “user ID” and “attribute information”. Further, the “attribute information” has small items such as “age”, “sex”, “address”, “occupation”, “language used”, and “user rank”.

  "User ID" corresponds to the same item shown in FIG. "Attribute information" indicates user attribute information. "Age" indicates the age of the user. "Gender" indicates the gender of the user. "Address" indicates the address of the user. “Occupation” indicates the occupation of the user. "Language used" indicates a language available to the user. In the example of FIG. 8, the information stored in the items of “profession” and “language used” is indicated by a concept such as “E01” or “F01”, but in actuality, a specific occupation name or , Names of languages (Japanese, English, etc.) are stored.

  "User rank" indicates the rank of the user at the commerce site. The rank of the user at the commerce site is the rating information of the user based on the commerce site's own standard, and for example, the transaction amount exceeding a predetermined amount, or the user is a member (paying member) paying a fixed amount monthly It is a ranking that is performed by various information, such as being an excellent member who pays In the example of FIG. 8, the information stored in the item of “user rank” is indicated by the concept of “G01” or the like, but in actuality, a specific rank name (rank corresponding to excellent members, ordinary members, etc.) The name of etc.) is stored.

  That is, in FIG. 8, as an example of data stored in the attribute information table 126, the attribute information of the user U01 is the age "30's", the sex is "female", and the address "A prefecture ..." It indicates that the occupation is "E01", the language used is "F01", and the user rank is "G01".

(About the model storage unit 127)
The model storage unit 127 stores information related to the model generated by the determination device 100. Here, FIG. 9 illustrates an example of the model storage unit 127 according to the embodiment. As shown in FIG. 9, the model storage unit 127 has items such as “model ID”, “information update date”, and “learning data”. In addition, “learning data” has small items such as “company ID of second company” and “second user information”.

  "Model ID" indicates identification information for identifying a model. "Information update date" indicates the date when the model was updated. "Learning data" indicates data used for model generation (learning). The “business ID of the second business operator” indicates the business operator ID of the second business operator used to generate the model. The business operator ID shown in FIG. 9 is the same as the business operator ID shown in FIG. "2nd user information" shows the information of the 2nd user corresponding to each 2nd provider. In the example of FIG. 9, the information stored in the “second user information” is indicated by the concept of “H01” or the like, but in practice, the information identifying the second business person and the user who has a transaction history Also, various information such as the number of second users as customers of each second enterprise, the details of the transaction, the transaction amount, and the like are stored.

  That is, in FIG. 9, as an example of data stored in the model storage unit 127, the model M01 identified by the model ID “M01” has its information updated on “November 1, 2017”, and the model M01 is updated. For example, the second operator who has become the learning data of is the one identified by the enterprise ID “A02” or “A03”, the second user information corresponding to the enterprise A02 is “H01”, and the enterprise It indicates that the second user information corresponding to the person A03 is "H02".

(About the control unit 130)
The control unit 130 is a controller, and for example, various programs (for example, a determination program stored in a storage device in the determination device 100 by a central processing unit (CPU), a micro processing unit (MPU), etc. (Equivalent) is realized by executing the RAM as a work area. The control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As shown in FIG. 3, the control unit 130 according to the embodiment includes an acquisition unit 131, a generation unit 132, a reception unit 133, and a determination unit 134, and functions and operations of the information processing described below. Realize or execute. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 3, and may be another configuration as long as it performs the information processing described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship illustrated in FIG. 3, and may be another connection relationship.

(About acquisition unit 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires information on a user who uses a predetermined commerce site on the network. Specifically, the acquisition unit 131 acquires an action history and the like on the network of the first company who is conducting a commercial transaction on the commerce site and a first user who is a user who has a transaction history on the network.

  For example, the acquisition unit 131 acquires, as the action history of the first user on the network, a browsing history in which the first user browsed the content. Specifically, the acquisition unit 131 acquires information on the web page browsed by the user and information on the application content.

  More specifically, the acquisition unit 131 acquires the number of times or time the first user browsed the news content in a predetermined period (for example, the aggregation period illustrated in FIG. 5) and the category of the browsed news content.

  In addition, the acquisition unit 131 acquires information on the transaction and settlement of the user at the commerce site. Specifically, the acquisition unit 131 acquires information on at least one of the number of settlements at the commerce site of the first user, the number of unpaid settlements, and the number of uses of installments.

  The acquisition unit 131 also acquires attribute information of the first user. For example, the acquisition unit 131 acquires information on the rank of the first user's commerce site. In addition, the acquisition unit 131 acquires information on at least one of the age, gender, address, occupation, and language of the first user.

  In addition, when model generation processing by the generation unit 132 described later is performed, the acquisition unit 131 acquires not only the information on the first user but also the information on the second user.

  Further, the acquiring unit 131 may acquire various types of information on information that can be acquired via a network, in addition to the above-described behavior history and attribute information.

  For example, the acquisition unit 131 may acquire information on the evaluation of the business entity at the commerce site from the user. The commerce site has, for example, a system for receiving an evaluation (for example, a score indicated by a numerical value of 5 levels) from the user for each business entity (for each store), or a score or a review for each product. In this case, the acquisition unit 131 may acquire information such as the content of the evaluation performed by each user, the number of times of evaluation, and the content of the specific review.

  In addition, the acquisition unit 131 acquires information on the transition of the number of responses from the user to the store or product opened by the business, or the transition of the evaluation value scored by the user for the store or commodity opened by the business You may That is, the acquisition unit 131 acquires the change in the number of reviews posted in a predetermined period and the change in the increase or decrease in the score.

  In addition, the acquisition unit 131 may acquire a word included in a store opened by a business or a review of a product with respect to a product as information on the evaluation of the business from the user. For example, the acquisition unit 131 morphologically analyzes the review from the user, extracts a word included in the review, and acquires information on the extracted word. In addition, the acquiring unit 131 may acquire only a word with a high weight using an algorithm for scoring each word appearing in a review, such as tf-idf (Term Frequency-Inverse Document Frequency). In addition, the acquisition unit 131 may acquire a comment (that is, a word included in the comment) sent by the business owner in response to a review from a user of a store or a product opened by the business owner.

  In addition, the acquisition unit 131 may acquire information related to the credit rating set in advance for the second business entity. For example, the acquisition unit 131 acquires the credit rating of the business entity set by the specialization period of a rating company or the like. Alternatively, the acquisition unit 131 may acquire the credit rating that is uniquely set in the commerce site (shopping mall or the like). In this case, the credit rating may be set using various methods such as store evaluation (five-step numerical value as described above) at the commerce site or numerical values set corresponding to store rankings in the shopping mall. It may be done. In addition, the degree of credit may be indicated not only by a numerical value, but also simply by a binary value such as "whether or not the business operator has credit."

  The acquisition unit 131 appropriately stores the acquired information in the storage unit 120. For example, the acquisition unit 131 stores information on a transaction on a commerce site in the usage history table 123 and the payment information table 125. In addition, the acquisition unit 131 stores information on the browsing behavior of the user on the network in the browsing history table 124. In addition, the acquisition unit 131 stores the attribute information of the user in the attribute information table 126. In addition, the acquisition unit 131 stores information on the creditworthiness of the enterprise in the enterprise information storage unit 121. Further, the acquisition unit 131 may appropriately acquire information required for processing from the storage unit 120.

  Note that the acquisition unit 131 may randomly acquire information on various users and businesses without specifying a user and a business enterprise acquiring the information. For example, the acquisition unit 131 can obtain information about the user or the provider at any time, or update the acquired information by crawling the Internet using a program such as a search robot used for a search engine or the like. You may

  In addition, for example, when the financial information of the business entity can be acquired from a financial institution, a financial management company, or the like, the acquisition unit 131 may acquire such information. When financial information is acquired by the acquisition unit 131, the determination unit 134 described later may determine the degree of credit for the first business operator in consideration of the financial information.

(About the generation unit 132)
The generation unit 132 generates a model for determining the creditworthiness of the first business entity. Specifically, the generation unit 132 is a business that is a business that is different from the first business among business businesses that perform commerce on a commerce site, and is a business of a second business whose creditworthiness is determined in advance. And a model for determining the creditworthiness of a business operator based on the correlation between the second business operator and information about the second user who is a user who has a transaction (hereinafter, such a model is referred to as “first model” Generate).

  For example, the generation unit 132 may be configured to calculate the second number based on the correlation between the number of settlements at the second user's commerce site, the number of unpaid settlements, or at least one of the numbers of usage of installments 1 Generate a model.

  In addition, the generation unit 132 generates the first model based on the correlation between the number of times the second user browsed the news content in a predetermined period or time and the category of the browsed news content and the credit of the second business operator. May be generated. In addition, the generation unit 132 may generate the first model using various pieces of information about the second user acquired by the acquisition unit 131 as well as the information described above.

  For example, the generation unit 132 generates, as a first model, a learning model in which each piece of information about the second user acquired by the acquisition unit 131 is a feature, and the credit rating of a second business operator set in advance is correct data. Specifically, the generation unit 132 generates a first model in which a weight is given to what kind of information among the pieces of information about the second user who is a feature and is learned recursively. In other words, in the determination of the creditworthiness of the second business entity acquired as correct data among the information on the second user, the generation unit 132 determines which feature has a greater influence for judging the creditworthiness. Generate a first model showing

  Below, an example of the 1st model which generation part 132 generates is shown. Note that the first model generated by the generation unit 132 is not limited to the following, and is a model generated based on the credit rating of the second business operator set in advance, and when information related to the first user is input In addition, any model may be used as long as it outputs a score indicating the creditworthiness of the first enterprise.

  For example, the generation unit 132 sets the credit of the second enterprise as a target variable in machine learning. Then, the generation unit 132 sets each piece of information about the second user acquired by the acquisition unit 131 as an explanatory variable (feature). Then, using the target variable and the explanatory variable, the generation unit 132 generates a first model for determining the degree of credit of the business. That is, when the information of the first user is input to the first model, a score indicating the credit of the first enterprise whose customer is the first user is output. For example, the generation unit 132 can use any information stored in the feature information storage unit 122 as an explanatory variable.

  First, the generation unit 132 generates a formula indicating the relationship between the credit level of the second enterprise and the information on the second user who is a customer of the second enterprise. Such a formula is generated as many as the number of second businesses serving as learning data. Furthermore, the generation unit 132 learns and determines what weight each piece of information about the second user has with respect to the event of the creditworthiness of the second enterprise. Thereby, the generation unit 132 can obtain information such as how much each feature contributes in the determination of the creditworthiness of the second business entity. For example, the generation unit 132 generates the following equation (1).

y = ω ₁ · x ₁ + ω ₂ · x ₂ + ω ₃ · x ₃ ... + ω _N · x _N (1) (N is an arbitrary number)

  The above equation (1) is created, for example, for each second operator. In the said Formula (1), "y" shows "the credit of 2nd operator preset." In the learning, if the business operator A02 shown in FIG. 4 is used as the correct data, “y” takes a value of “85”. Further, if the business operator A03 shown in FIG. 4 is used as the correct data, “y” takes a value of “45”.

Moreover, in the said Formula (1), "x" respond | corresponds to each explanatory variable which is the information (feature) regarding a 2nd user. Moreover, in said Formula (1), "(omega)" is a coefficient of "x" and shows a predetermined | prescribed weight value. Specifically, "ω ₁ " is a weight value of "x ₁ ", "ω ₂ " is a weight value of "x ₂ ", and "ω ₃ " is a weight value of "x ₃ " It is. Thus, the above equation (1) is a variable including the explanatory variable “x” corresponding to the feature information extracted from the information on the second user and the predetermined weight value “ω” (for example, “ω ₁ ··· It is created by combining x ₁ ").

For example, in the above equation (1), it is temporarily assumed that “x ₁ ” is “the number of settlements of the second user”. Further, it is assumed that “x ₂ ” is “the number of unpaid payments of the second user”. Further, it is assumed that “x ₃ ” is “the number of times the second user browsed the news content of the economic category”. In this case, the above equation (1) corresponding to the business operator A01 can be expressed as the following equation (2).

y _{(Operator A02)} (= 1) = ω ₁ · (Number of settlements for the second user) + ω ₂ · (Number of unpaid accounts for the second user) + ω ₃ · (The second user browses the news content of the economic category Number of times) ... + ω _N · x _N ... (2) (N is an arbitrary number)

The generation unit 132 generates Equation (2) for each second operator and for each second user of the second operator. Then, the generation unit 132 sets the generated expression as a sample of machine learning. Then, the generation unit 132 derives a value corresponding to a predetermined weight value “ω” by performing arithmetic processing (regression learning) of an expression serving as a sample. That is, the generation unit 132 determines a predetermined weight value “ω” that satisfies the above equation (2). In other words, the generation unit 132 can determine the weight value “ω” indicating the influence of the predetermined explanatory variable on the target variable “y”. For example, if "the number of unpaid payments of the second user" significantly contributes to "the creditworthiness of the second company" compared to other variables, this corresponds to "the number of unpaid payments of the second user". The value of the weight value “ω ₂ ” is calculated to be larger than other variables.

  Also, for example, if “the number of times the second user browsed the news content of the economic category” contributes to the numerical value of the correct data as compared with other variables, for example, the customer “news content of the economic category A business operator who has many users who have a large number of "visits" may have a relatively high credit rating.

  In the above example, although the number of times of settlement, the number of unpaid times, and the number of browsing of news content of the economic category are shown as features, these numerical values may be converted to be used as explanatory variables by predetermined processing. . For example, the generation unit 132 may normalize and use these numerical values by a known method. Alternatively, the generation unit 132 divides the number of settlements of the second user into, for example, “high”, “middle”, and “low” in three stages as compared with the average value of all users who use the commerce site, and explains each of them as explanatory variables It may be used as In this case, the generation unit 132 can determine, for example, a weight value given to the objective variable (= credit) by the explanatory variable that the number of unpaid bills is “high”. As a result, the generation unit 132 can generate a first model that outputs a result such as “the higher the business owner who has the second user who has a large number of unpaid bills, the lower the degree of credit is determined”.

  As described above, the generation unit 132 determines the relationship between the tendency of the score indicating “the creditworthiness of the second enterprise” and the information (the identity) of the second user who is the customer of the second enterprise. Generate the first model of.

  It should be noted that the above equation (2) does not set the left side as the credit rating value (such as “85”), and “credits (= 1) businesses whose credit rating exceeds a predetermined number (for example,“ 70 ”). It may be regressive expression which makes a business person whose numerical value of a degree of credit does not have a predetermined number or less “no credit (= 0)”. In addition, the generation unit 132 assumes a predetermined error in learning, and uses a method such as the least squares method or the like to approximate the value obtained by squaring the difference with the error to a minimum value, and to optimize “ω”. The solution may be calculated.

  In addition, although description is abbreviate | omitted in said example, the production | generation part 132 may produce | generate a 1st model using all the features regarding a 2nd user. In addition, the generation unit 132 may add information on the second business entity as a feature. For example, the generation unit 132 may use, as a feature, financial information in a store operated by the second business or sales information of a product handled by the store. In addition, the generation unit 132 may use the legal person of the second enterprise as a feature. After such learning, the generation unit 132 determines that, for example, the legal personality such as “Individual Business Owner” or “Limited Company” is judged to have low credit, and “Corporate” is judged to have relatively high credit. There is a possibility to generate 1 model. In this case, "attributes" such as a stock company or an individual business owner have a weight with respect to the event of the credit of the business. In addition, depending on the result of learning, there may be a result that a certain feature has little influence on the event of credibility. In this case, it is assumed that the weight (ω) corresponding to the feature in the above equation (2) approaches “0”.

  Note that the illustrated first model is an example, and the first model generated by the generation unit 132 is not limited to the above example. That is, the generation unit 132 is a model generated based on the credit rating of the second business operator set in advance, and when information on the first user is input, a score indicating the credit business of the first business operator is obtained. As long as it is an output model, a first model different from the above example may be generated as appropriate by combining known methods. For example, in the above example, although the example which produces | generates a 1st model by regression analysis was shown, the production | generation part 132 may produce | generate a 1st model by other statistical processing, and also uses a neural network. The first model may be generated. Further, in the learning process (machine learning), various techniques such as linear regression, logistic regression, support vector machine, decision tree, hazard analysis and the like may be used.

  As described above, the generation unit 132 determines the creditworthiness of the business based on the degree of credit of the second business and the correlation with the information on the second user who is a user who has a transaction with the second business. Generate a first model for In other words, the generation unit 132 includes information on the customer (second user) of the second enterprise whose credit rating is already set, and information on the customer (first user) of the first enterprise whose credit rating is not determined. The first model for determining the creditworthiness of the first business entity is generated from the correlation of That is, the generation unit 132 can generate a model that determines the creditworthiness of the business entity from the viewpoint of information on the customer held by the business entity, unlike the viewpoints of the financial status, sales proceeds, and the like. The generation unit 132 stores the generated model in the model storage unit 127.

(About reception part 133)
The accepting unit 133 accepts a request related to the determination of the creditworthiness of the first business entity. Specifically, the reception unit 133 according to the embodiment receives, for example, a request from a financial institution or the like to determine the creditworthiness of the first business entity. The reception unit 133 may specify a first business entity to be processed, and cause the acquisition unit 131 to acquire information on a first user corresponding to the first business enterprise, upon receiving the request as a trigger.

(Regarding the determination unit 134)
The determination unit 134 determines, based on the action history on the network of the first user who is a user who has a transaction history with the first business person who performs a commercial transaction on the commerce site among the information about the user acquired by the acquisition unit 131. 1 Determine the creditworthiness of the business.

  For example, the determination unit 134 determines the credit of the first enterprise based on the tendency of the browsing history of the first user. Specifically, the determination unit 134 determines the creditworthiness of the first enterprise based on the number or time of the first user browsing the news content in a predetermined period, and the tendency of the category of the browsed news content.

  For example, the determination unit 134 determines the number of times and the time to browse the news content categorized into “economy”, “finance” or the like among the categories of the news content relatively to all the users of the commerce site. To be a highly trusted user. Then, the determination unit 134 has a high rate of the user having a high credit rating as a customer (for example, the ratio of the first business category to all customers exceeds 50%, etc.). Determined relatively high.

  Alternatively, the determination unit 134 may determine the creditworthiness of the first business operator based on at least one of the information on the number of settlements at the first user's commerce site, the number of unpaid settlements, or the number of uses of installments.

  For example, the determination unit 134 estimates that the user having a smaller number of unpaid payments in the settlement is a user with higher credibility with respect to the number of payments at the first user's commerce site. Then, the determination unit 134 determines the credibility relatively high for the first business entity in which the ratio of the user having the high credibility to the customer is high. In addition, the determination unit 134 estimates that the user having a smaller number of installments in the settlement is a user with higher credibility with respect to the number of settlements at the first user's commerce site. Then, the determination unit 134 determines the credibility relatively high for the first business entity in which the ratio of the user having the high credibility to the customer is high.

  Further, the determination unit 134 may determine the creditworthiness of the first enterprise based on the information on the rank of the first user's commerce site. For example, the determination unit 134 estimates that the user who is a paid member of the commerce site has a high degree of credit compared to other users. Alternatively, the determination unit 134 estimates that the user who is determined to be the excellent member according to the sales amount of the commerce site or the like has a high credit rating as compared with other users. Then, the determination unit 134 determines the credibility relatively high for the first business entity in which the ratio of the user having the high credibility to the customer is high.

  In addition, the determination unit 134 may determine the credit of the first enterprise based on the information of at least one of the age, gender, address, occupation, and language of the first user. For example, the determination unit 134 sets, for each attribute information of the user, a numerical value serving as a reference for determining the degree of credit. Specifically, the determination unit 134 sets the degree of credit for each age, gender, address, occupation, or language used, and based on the attribute information of all the first users corresponding to the first enterprise, 1 Determine the creditworthiness of the business.

  As described above, the determination unit 134 establishes a predetermined standard for the creditworthiness of the user's information, statistically compares the information on the first user corresponding to the first business entity, and based on the compared information The credit rating of the first enterprise may be calculated. Furthermore, the determination unit 134 may perform the determination using the model generated by the generation unit 132. Specifically, based on the result output from the first model generated by the generation unit 132, the determination unit 134 determines the credit of the first business entity.

  As described above, the first model generated by the generation unit 132 indicates the correlation between the existing credibility set by a specialized organization or the like and the information on the second user corresponding to the second enterprise. For this reason, the determination unit 134 can output the credit corresponding to the first business by inputting the information on the first user to be processed into the first model. That is, the determination unit 134 determines the credit of the first business based on the output score.

  In addition, the determination unit 134 may set the output score itself as the credit of the first business operator, or may perform processing such as normalizing the output score, and calculate the value calculated after the processing as the first business operator's It may be a credit.

[4. Processing procedure]
Next, a procedure of generation processing by the determination apparatus 100 according to the embodiment will be described using FIG. FIG. 10 is a flowchart showing a generation processing procedure by the determination apparatus 100 according to the embodiment.

  As shown in FIG. 10, in order to generate a model, the determination apparatus 100 acquires, from the web server 30, a specialized organization, and the like, the credit rating set in advance for the second business (step S101). Subsequently, the determination apparatus 100 acquires information on a user (second user) who has a transaction with the second operator (step S102).

  Then, the determination apparatus 100 generates a first model based on the credit of the second enterprise and the information on the second user (step S103). Subsequently, the determination apparatus 100 stores the generated first model in the model storage unit 127 (step S104).

  Next, the procedure of the determination process by the determination apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 11 is a flowchart illustrating the determination processing procedure by the determination apparatus 100 according to the embodiment. The determination apparatus 100 starts the determination process according to the embodiment, for example, when a request for determining the degree of credit is transmitted from a financial institution or the like.

  First, the determination apparatus 100 determines whether or not the information regarding the first provider to be processed and the user (first user) who has a transaction is acquired (step S201). If the information has not been acquired, the determination apparatus 100 stands by until acquisition (step S201; No).

  On the other hand, when the information on the first user is acquired (step S201; Yes), the determination apparatus 100 inputs the acquired information on the first user to the first model (step S202).

  Then, the determination apparatus 100 outputs a score indicating the credit of the first business using the first model. Furthermore, the determination unit 134 determines the credit of the first business based on the output score (step S204).

[5. Modified example]
The determination apparatus 100 according to the above-described embodiment may be implemented in various different forms other than the above-described embodiment. So, below, other embodiment of said determination apparatus 100 is described.

[5-1. User credit rating judgment model]
In the above embodiment, the determination apparatus 100 generates the first model based on the correlation between the credit of the second business and the information on the second user, and determines the credit of the first business using the first model. The process has been described. Here, in the case where the “credibility of the user” is acquired in advance, the determination apparatus 100 may determine the creditworthiness of the business having a transaction with the user based on the creditworthiness of the user. In this case, the determination apparatus 100 is different from the first model based on the correlativity between the information on the second user and the credit rating set for the second user (hereinafter referred to as “user credit rating”). A model (hereinafter, referred to as a “second model”) for determining the credibility of the user, which is a model, is generated. Then, the determination apparatus 100 uses the second model to determine the degree of credit of the first enterprise to be processed. This point will be described with reference to FIG.

  FIG. 12 is a diagram illustrating an example of the determination process according to the modification. FIG. 12 shows an example in which the user U01 and the user U02 use the store AAA and the store BBB opened in the shopping mall, as in FIG.

Similar to FIG. 1, the user terminal 10 ₁ in accordance with operation by the user U01, accesses the shopping mall web server 30 is provided, utilizing a shopping mall (step S21). For example, the user U01 purchases a product from the store AAA. Similarly, the user terminal 10 ₂ in accordance with operation by the user U02, accesses the shopping mall web server 30 is provided, utilizing a shopping mall (step S22).

  Here, in the example of FIG. 12, it is assumed that a predetermined user credit degree is set for the user U02 which is the second user. For example, in the user U02, a user credit rating set according to the shopping mall transaction and the attribute of the user U02 is set. Specifically, user U 02 has a user credit rating indicated by a numerical value of 0 to 100 according to a rating performed to each user from each store having a transaction with user U 02, an amount of money used for a shopping mall, etc. In the example of 12, "70" is set.

  In the example of FIG. 12, the determination apparatus 100 acquires the user credibility of the user U02 as well as information such as the action history of the user U02 (step S23). Then, the determination apparatus 100 generates a model (second model) for determining the creditworthiness of the user (step S24).

  For example, the determination apparatus 100 stores the user credit rating preset for the user U02 on the right side, and the features described in the embodiment (the number of settlements, the browsing history of news contents, user rank and other attribute information, etc.) Generate an expression. The determination apparatus 100 is assumed to acquire information from a sufficient number of users U02 required for learning. Then, the determination apparatus 100 generates the second model indicating the correlation between each feature and the user credit by recursively learning the expression generated for each user U02, as in the generation process of the first model. .

  Thereafter, the determination apparatus 100 acquires information on the user U01 (first user) who is the user who has made a transaction with the business operator A01 which is the processing target (step S25). The determination apparatus 100 inputs the acquired information on the first user into the second model, and determines the user credit of each first user (step S26).

  Then, the determination apparatus 100 determines the credit of the first enterprise based on the credit of the first user (step S27). For example, the determination apparatus 100 determines the average value or the like of the creditworthiness determined for the user U01 with the creditworthiness of the first enterprise who has a transaction with the user U01.

  Thus, the second model for determining the creditworthiness of the user based on the correlation between the information on the second user and the user credit degree set for the second user, according to the modification. Generate Then, the determination apparatus 100 determines the credit of the first enterprise based on the output result when the information on the first user is input to the second model.

  That is, the determination apparatus 100 according to the modification determines the credit of the user itself, and further determines the credit of a business having a transaction with the user. As a result, the determination apparatus 100 can determine the credibility of the enterprise from various points of view, such as determining the higher the credibility of the enterprise having more users with high user credibility as customers, for example. Moreover, according to such a method, the determination apparatus 100 can determine the credit of the first business based on the credit of the user itself, even if the credit of the second business is not set in advance.

  The determination apparatus 100 can use the same features as the first model as the features of the second model. For example, the determination apparatus 100 may determine whether the number of settlements at the second user's commerce site, the number of unpaid settlements, or the number of uses of the installment is correlated with the user credit of the second user. 2 Generate a model. Alternatively, the determination apparatus 100 determines the second model based on the number of times or time that the second user browsed the news content in a predetermined period, and the correlation between the category of the browsed news content and the credit of the second user. It may be generated.

5-2. Information to use]
In the above embodiment, an example has been shown in which the determination apparatus 100 determines the credit of the business using the information on the user who has a transaction with the business. Here, the determination apparatus 100 may calculate the credit of the business using a known model in addition to the information on the user. As an example, the determination apparatus 100 may use any known enterprise evaluation model. For example, as a company evaluation model for obtaining a score indicating a bankruptcy probability of a business based on financial information, Z value of Altman (Edward Altman) or the like is widely known. The determination apparatus 100 may adopt a score indicating the bankruptcy probability of the business operator as one of the elements for determining the credit using such an existing model.

  In addition, the determination apparatus 100 may, for example, access number (Page View) of the store where the business operates, the number of reviews, customer unit price of the user (for example, purchase amount per user in a predetermined period), store in a predetermined period The credit rating of the business may be determined using information such as the name of the business, the number of times the product has been searched, and the increase rate of the number of searches.

[5-3. Amount of information]
In the above embodiment, an example has been shown in which the determination apparatus 100 generates a model based on various information that can be acquired on the network. Here, the determination apparatus 100 may perform the process using only information obtained from general users who use various websites, which exceeds a certain threshold.

  For example, a review on a product in a store, a user's evaluation, etc. may show a biased tendency if not based on a certain number or more of data. In this case, since the influence of the data biased to the regression equation is exerted, the determination apparatus 100 may generate a model that can not accurately determine the creditworthiness of the business. For this reason, the determination apparatus 100 can use only data in which the total number of scores and reviews transmitted from the user exceeds a certain number for a predetermined store as data handled in the model determination process. Thus, the determination apparatus 100 can generate a model that outputs a highly reliable score.

[5-4. correction〕
The determination apparatus 100 may generate a model that can correct the output score according to the actual economic condition. For example, the determination apparatus 100 classifies a business entity whose business condition is improved when the yen tends to appreciate, a business owner who has no influence, and a business enterprise whose business condition is deteriorated. Then, when generating the model, the determination apparatus 100 adopts the trend of the value of the circle in a predetermined period as a feature, and outputs the corrected score in consideration of the trend of the value of the circle. Generate The determination apparatus 100 reflects such correction information in the model by, for example, acquiring information of a business entity in the long run and accumulating information related to the movement of the value of the yen and the like.

  The above correction may be performed, for example, by limiting the type of business of the second business operator to be input to the model to an importer, or to an exporter.

[6. Other]
Further, among the processes described in the above embodiment, all or part of the process described as being automatically performed may be manually performed, or the process described as being manually performed. All or part of them can be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified.

  Further, each component of each device illustrated is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of the distribution and integration of each device is not limited to the illustrated one, and all or a part thereof may be functionally or physically dispersed in any unit depending on various loads, usage conditions, etc. It can be integrated and configured.

  For example, the information in the storage unit 120 illustrated in FIG. 3 may be held by an external storage server or the like without being held by the determination apparatus 100. In this case, the determination apparatus 100 acquires various types of stored information by accessing the storage server.

  Further, for example, the determination apparatus 100 described above acquires the various information, receives the determination request of the credit rating of the business entity, etc., the front end server side mainly executing the exchange with the external device, the generation process, It may be distributed to the back end server side which executes the determination process and the like. In this case, for example, the front end server includes at least an acquisition unit 131. In addition, the back end server includes at least a determination unit 134.

[7. Hardware configuration]
Further, the determination apparatus 100, the user terminal 10, the provider terminal 20, and the web server 30 according to the embodiment described above are realized by, for example, a computer 1000 configured as shown in FIG. Hereinafter, the determination device 100 will be described as an example. FIG. 13 is a hardware configuration diagram showing an example of a computer 1000 for realizing the function of the determination apparatus 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 to control each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from another device via the communication network 500 (corresponding to the network N shown in FIG. 2) and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 via the communication network 500 to other devices. Send to the device of

  The CPU 1100 controls an output device such as a display or a printer and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from an input device via the input / output interface 1600. The CPU 1100 also outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the CPU 1100 with the program via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a digital versatile disc (DVD) or a phase change rewritable disc (PD), a magneto-optical recording medium such as a magneto-optical disk (MO), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the determination device 100, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing the program loaded on the RAM 1200. In addition, each data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from the other device via the communication network 500.

[8. effect〕
As described above, the determination apparatus 100 according to the embodiment includes the acquisition unit 131 and the determination unit 134. The acquisition unit 131 acquires information on a user who uses a predetermined commerce site on the network. The determination unit 134 determines, based on the action history on the network of the first user who is a user who has a transaction history with the first business person who performs a commercial transaction on the commerce site among the information about the user acquired by the acquisition unit 131. 1 Determine the creditworthiness of the business.

  As described above, the determination apparatus 100 according to the embodiment is not only used for financial information generally used to measure the creditworthiness of a business, but also for a user who has a transaction with a store opened at a commerce site such as a shopping mall. Use the information to determine the creditworthiness of the business. Thereby, the determination apparatus 100 can determine the credit to the business from various points of view regardless of the business financial information and sales amount.

  In addition, the acquisition unit 131 acquires, as the action history of the first user on the network, a browsing history in which the first user browsed the content. The determination unit 134 determines the creditworthiness of the first enterprise based on the tendency of the browsing history of the first user.

  As described above, the determination apparatus 100 according to the embodiment can determine the creditworthiness of the business from various points of view by using the browsing history of the content, which is one of the daily activities of the user.

  Further, the acquisition unit 131 acquires the number of times or the time in which the first user browsed the news content in a predetermined period, and the category of the browsed news content. The determination unit 134 determines the creditworthiness of the first enterprise based on the number or time of the first user browsing the news content in a predetermined period, and the tendency of the category of the browsed news content.

  Thus, the determination apparatus 100 according to the embodiment uses the browsing history of the news content, for example, a store (business company) with many users who often browse the economic news among the customers has a high credit rating For example, it is possible to evaluate a business using an index that is difficult to be assumed as a general business evaluation index, such as evaluation.

  In addition, the acquisition unit 131 acquires information on at least one of the number of settlements at the commerce site of the first user, the number of unpaid settlements, and the number of uses of installments. The determination unit 134 determines the creditworthiness of the first business operator based on at least one of information of the number of settlements at the commerce site of the first user, the number of unpaid settlements, and the number of times of use of installments.

  As described above, the determination apparatus 100 according to the embodiment determines the credit rating to be high for a business that has a firm customer and a transaction such as steady payment, for example, by using the action relating to the user's payment for processing. , Etc., and can evaluate the business operator from various points of view.

  In addition, the acquisition unit 131 acquires information on the rank of the first user's commerce site. The determination unit 134 determines the creditworthiness of the first enterprise based on the information on the rank of the first user's commerce site.

  As described above, the determination apparatus 100 according to the embodiment can evaluate the business from various viewpoints, such as determining the creditworthiness of the business based on the rank of the customer on the commerce site.

  In addition, the acquisition unit 131 acquires information on at least one of the age, gender, address, occupation, and language of the first user. The determination unit 134 determines the creditworthiness of the first enterprise based on the information of at least one of the age, gender, address, occupation, and language of the first user.

  As described above, the determination apparatus 100 according to the embodiment can perform company evaluation based on the tendency of being hard to appear in financial information or the like by determining the creditworthiness of the enterprise according to the attribute of the user who is the customer. .

  In addition, the determination apparatus 100 according to the embodiment is a second business operator who is a business who is different from the first business operator among business businesses who perform commerce on the commerce site and whose business credit is determined in advance. The generator 132 further includes a generation unit 132 that generates a first model for determining the creditworthiness of the business based on the degree of credit and the correlation between the second business and information about the second user who is a user who has a transaction. The determination unit 134 determines the creditworthiness of the first enterprise based on the result output from the first model generated by the generation unit 132.

  As described above, the determination apparatus 100 according to the embodiment performs the determination process by generating a model based on the correlation between the credit degree of the business and the information about the user, thereby performing the determination process with higher accuracy. it can.

  In addition, the acquisition unit 131 acquires information on at least one of the number of settlements at the commerce site of the second user, the number of unpaid settlements, and the number of times the installments are used. The generation unit 132 generates the first model based on the correlation between the second user's creditworthiness and at least one of the information on the number of settlements at the second user's commerce site, the number of unpaid settlements, or the number of uses of installments. Generate

  As described above, the determination apparatus 100 according to the embodiment adjusts the credit information to be determined to be high for a business that has a firm customer and a transaction such as performing payment steadily by using payment information for generation processing. It is possible to further improve the accuracy of the credibility determination, such as being able to generate the generated model.

  Further, the acquiring unit 131 acquires the number of times or the time in which the second user browsed the news content in a predetermined period, and the category of the browsed news content. The generation unit 132 generates a first model based on the number of times or time the second user browsed the news content in a predetermined period, and the correlation between the category of the browsed news content and the credit of the second business operator. Do.

  As described above, the determination apparatus 100 according to the embodiment uses the browsing history for the generation process, and is a model adjusted so that the credit rating is determined to be high for a customer who browses economic news frequently and a business having a transaction. Can be generated, and the accuracy of the credit determination can be further improved.

  In addition, the generation unit 132 generates a second model for determining the user credit based on the correlation between the information on the second user and the user credit degree set for the second user. The determination unit 134 determines the creditworthiness of the first enterprise based on the output result when the information on the first user is input to the second model.

  As described above, the determination apparatus 100 according to the embodiment may determine the credit of the user itself, and may further determine the credit of a business having a transaction with the user. As a result, the determination apparatus 100 can determine the credibility of the enterprise from various points of view, such as determining the higher the credibility of the enterprise having more users with high user credibility as customers, for example. Moreover, according to such a method, the determination apparatus 100 can determine the credit of the first business based on the credit of the user itself, even if the credit of the second business is not set in advance.

  In addition, the acquisition unit 131 acquires information on at least one of the number of settlements at the commerce site of the second user, the number of unpaid settlements, and the number of times the installments are used. The generation unit 132 generates the second model based on the correlation between the number of settlements at the commerce site of the second user, the number of unpaid settlements, or the number of uses of the installment, and the user credit of the second user. Generate

  As described above, the determination apparatus 100 according to the embodiment uses the payment information for the generation process, and a model based on the actual situation such that a solid user who performs payment steadily is determined to have a high credit rating. Can be generated.

  Further, the acquiring unit 131 acquires the number of times or the time in which the second user browsed the news content in a predetermined period, and the category of the browsed news content. The generation unit 132 generates a second model based on the number of times or time the second user browsed the news content in a predetermined period, and the correlation between the category of the browsed news content and the user confidence of the second user. Do.

  As described above, the determination apparatus 100 according to the embodiment evaluates the user from various viewpoints such that the user who frequently browses the economic news is determined to have high credibility by using the browsing history for the generation process. Can generate models that can

  Although the embodiments of the present application and some of the modifications of the embodiments have been described in detail based on the drawings, these are only examples, and it is to be understood by those skilled in the art that the embodiments described in the section of the description of the invention are included. It is possible to implement the present invention in other forms based on various modifications and improvements.

  In addition, the above-described determination apparatus 100 may be realized by a plurality of server computers, and may be realized by calling an external platform or the like by API (Application Programming Interface) or network computing depending on the function. It can be changed flexibly.

  Further, "section, module, unit" described in the claims can be read as "means", "circuit" or the like. For example, the generation unit can be read as a generation unit or a generation circuit.

DESCRIPTION OF SYMBOLS 1 judgment system 10 user terminal 20 provider terminal 30 web server 100 determination apparatus 110 communication part 120 storage part 121 provider information storage part 122 feature information storage part 123 usage history table 124 browsing history table 125 payment information table 126 attribute information table 127 Model storage unit 130 Control unit 131 Acquisition unit 132 Generation unit 133 Reception unit 134 Determination unit

Claims (14)

An acquisition unit for acquiring information on a user who uses a predetermined commerce site on the network;
Among the information on the user acquired by the acquisition unit, the first enterprise based on the activity history on the network of the first user who is the user who has a transaction history with the first enterprise who performs a commercial transaction on the commerce site A determination unit that determines the credit rating of
The determination apparatus characterized by having. The acquisition unit
As the action history of the first user on the network, a browsing history in which the first user browsed the content is acquired,
The determination unit is
Determining the credit of the first business based on the tendency of the browsing history of the first user;
The determination apparatus according to claim 1, characterized in that: The acquisition unit
Acquiring the number of times or time the first user browsed the news content in a predetermined period, and the category of the browsed news content;
The determination unit is
The credit rating of the first business operator is determined based on the number of times or time that the first user browsed the news content in a predetermined period, and the tendency of the category of the browsed news content.
The determination apparatus according to claim 2, characterized in that: The acquisition unit
Acquiring at least one of information on the number of settlements at the commerce site of the first user, the number of unpaid settlements, and the number of usage of installments,
The determination unit is
The creditworthiness of the first business entity is determined based on information on at least one of the number of settlements at the commerce site of the first user, the number of unpaid settlements, and the number of uses of installments.
The determination apparatus according to any one of claims 1 to 3, characterized in that: The acquisition unit
Obtaining information on the rank of the first user at the commerce site,
The determination unit is
The credit rating of the first business is determined based on the information on the rank of the first user at the commerce site,
The determination apparatus according to any one of claims 1 to 4, characterized in that: The acquisition unit
Acquiring at least one of the age, gender, address, occupation, and language of the first user;
The determination unit is
The credit rating of the first business is determined based on information of at least one of the age, gender, address, occupation, and language of the first user.
The determination apparatus according to any one of claims 1 to 5, characterized in that: The degree of credit of the second business operator who is a business that is different from the first business operator among businesses operating in the commerce site, and whose creditworthiness is determined in advance; A generation unit that generates a first model for determining the creditworthiness of the business based on the correlation with the information on the second user who is the user who has a transaction,
And further
The determination unit is
Determining the creditworthiness of the first business entity based on the result output from the first model generated by the generation unit;
The determination apparatus according to any one of claims 1 to 6, characterized in that: The acquisition unit
Acquiring at least one of information on the number of settlements at the commerce site of the second user, the number of unpaid settlements, and the number of usage of installments,
The generation unit is
The first model is determined based on the correlation between the number of settlements at the commerce site of the second user, the number of unpaid settlements, or the number of uses of installments, and the credit of the second business operator. Generate,
The determination apparatus according to claim 7, characterized in that: The acquisition unit
Acquiring the number of times or the time when the second user browsed the news content in a predetermined period, and the category of the browsed news content,
The generation unit is
The first model is generated based on the number of times or time that the second user browsed the news content in a predetermined period, and the correlation between the category of the browsed news content and the credit of the second business operator.
The determination apparatus according to claim 7 or 8, wherein The generation unit is
Generating a second model for determining the user credit based on the correlation between the information on the second user and the user credit set for the second user,
The determination unit is
The credit rating of the first enterprise is determined based on the output result when the information on the first user is input to the second model.
The determination apparatus according to any one of claims 7 to 9, characterized in that: The acquisition unit
Acquiring at least one of information on the number of settlements at the commerce site of the second user, the number of unpaid settlements, and the number of usage of installments,
The generation unit is
The second model is determined based on the correlation between the number of settlements at the commerce site of the second user, the number of unpaid settlements, or the number of uses of installments, and the user credit of the second user. Generate,
The determination apparatus according to claim 10, characterized in that: The acquisition unit
Acquiring the number of times or the time when the second user browsed the news content in a predetermined period, and the category of the browsed news content,
The generation unit is
The second model is generated based on the correlation between the number of times the second user browsed the news content in a predetermined period or time and the category of the browsed news content and the user credit of the second user.
The determination apparatus according to claim 10 or 11, characterized in that: It is a judgment method executed by a computer, and
An acquiring step of acquiring information on a user who uses a predetermined commerce site on the network;
Among the information on the user acquired by the acquisition step, the first enterprise based on the activity history on the network of the first user who is the user who has a transaction history with the first enterprise who carries out a commercial transaction at the commerce site A determination step of determining the credit rating of
A determination method comprising: An acquisition procedure for acquiring information on a user who uses a predetermined commerce site on the network;
Among the information on the user acquired by the acquisition procedure, the first enterprise based on the activity history on the network of the first user who is the user who has a transaction history with the first enterprise who carries out a commercial transaction at the commerce site A determination procedure for determining the credit rating of
A determination program that causes a computer to execute.

Images