Information processing device, information processing method, and program

Abstract

To provide an information processing device, an information processing method and a program capable of properly evaluating a user.SOLUTION: In a user evaluation system in which the information processing device, an analysis server, a user terminal, an affiliated server and a financial institution server are mutually connected for communication via a network such as Internet, a first user DB 141 of a server 1 which is the information processing device stores transaction information indicating a transaction history of a first user and action history information indicating an action history of the first user on the network. A control section 11 executes a program P to acquire identification information provided to a second user due to a session to a Web site, acquires action history information of the second user on the basis of the acquired identification information, and evaluates the second user on the basis of the transaction information and the action history information of the first user and the action history information of the second user.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program.

Background Art

[0002] When conducting commercial transactions, financial transactions, etc. with customers, the credit of the customers is evaluated. Along with this, various methods for evaluating the credit of customers have been proposed.

[0003] For example, in Patent Document 1, based on the asset information of a user and the behavior history of the user on the network, the asset information of a second user having a behavior history similar to that of the first user is estimated, and a determination apparatus for determining the creditworthiness of the second user is disclosed.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The invention according to Patent Document 1 extracts another user (first user) similar to the user to be evaluated (second user) from the behavior history on the network, and uses, as the behavior history, a search query input to a search engine, a posted article on an SNS (Social Networking Service), etc. However, in order to collect these behavior histories, it is necessary to register in advance the information of the user (such as the terminal used by the user and the SNS account), which is not easy.

[0006] In one aspect, an object is to provide an information processing apparatus or the like that can suitably evaluate a user.

Means for Solving the Problems

[0007] An information processing apparatus according to one aspect stores transaction information indicating the transaction history of a first user and behavior history information indicating the behavior history of the first user on a network, the behavior history information including access information that can be obtained when the first user accesses a website, and a storage unit; A generation unit that generates a learned model for determining an evaluation value of a user when the action history information is input based on the transaction information and the action history information of the first user; a first acquisition unit that acquires identification information assigned to a second user through a session to a website, and a second acquisition unit that acquires the behavior history information including the access information of the second user based on the identification information; , the stores the behavior history information of the second user By inputting into the model for the second user To determine the evaluation value of and an evaluation unit.

Effect of the Invention

[0008] In one aspect, a user can be suitably evaluated.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Mode for Carrying Out the Invention

[0010] Hereinafter, the present invention will be described in detail based on the drawings showing its embodiments. (Embodiment) FIG. 1 is a schematic diagram showing a configuration example of the user evaluation system. In the present embodiment, a user evaluation system for evaluating the creditworthiness of an arbitrary second user based on the financial transaction history of a large number of first users (other users) who are customers of a financial institution and the behavior history of each first user on the Internet will be described. The user evaluation system includes an information processing device 1, an analysis server 2, a user terminal 3, a partnering server 4, and a financial institution server 5. Each device is communicatively connected to each other via a network N such as the Internet.

[0011] The information processing device 1 is an information processing device capable of various information processing and information transmission and reception, and is, for example, a server computer, a personal computer, or the like. In the present embodiment, it is assumed that the information processing device 1 is a server computer, and hereinafter, it will be read as server 1 for simplicity. Preferably, the server 1 determines (evaluates) the creditworthiness of an arbitrary second user based on transaction information (for example, the transaction history of financial products) showing the transaction history of a first user who is a customer of a financial institution (such as a bank) and behavior history information (for example, words in a website browsed by the first user) showing the behavior history of the first user on the network N.

[0012] In addition, in this embodiment, the user serving as the basis for credit evaluation is referred to as the "first user", and the user to be evaluated is referred to as the "second user" for distinction. However, this nomenclature is for the convenience of distinguishing the two, and for example, the first user and the second user may be the same person. Also, when not distinguishing between the two, they are simply referred to as "users". Further, the user is not limited to an individual and may be a corporation.

[0013] Also, in this embodiment, the creditworthiness of the second user is determined from the transaction history of financial products and the like. However, this embodiment is not limited thereto. For example, the server 1 may determine the creditworthiness from the purchase history (commercial transaction history) of products in a physical store or an EC site. That is, the transaction information is not limited to the history of financial transactions.

[0014] Also, in this embodiment, mainly the creditworthiness in credit extension is determined. However, this embodiment is not limited thereto. For example, as will be described later, the server 1 may determine the purchase probability or the like of the second user purchasing a product. The server 1 only needs to be able to evaluate the user based on the transaction information and the action history information, and the evaluation criteria are not particularly limited.

[0015] The analysis server 2 is a server computer that analyzes the action history of users on the network N, and is a server computer that analyzes the web pages browsed by users on a plurality of affiliated web sites (hereinafter referred to as "affiliated sites"). In this embodiment, the analysis server 2 uses a method called DMP (Data Management Platform) to collect the data of the browsed pages and analyze the action history information. The analysis server 2 stores the analyzed action history information in the action history DB (Database) 201.

[0016] DMP is a platform for integrating and managing data accumulated in various web servers and performing optimizations such as advertisement delivery. In this embodiment, DMP is applied to credit extension evaluation, and the creditworthiness is determined using the analysis result by the analysis server 2, that is, the action history information of the user.

[0017] The user terminal 3 is a terminal device operated by the user, such as a personal computer, a smartphone, a tablet terminal, etc. The analysis server 2 analyzes the web page of the partner site accessed by the user terminal 3.

[0018] The partner server 4 is a server computer of the operator who operates the partner site, and is a server computer that functions as a web server. Examples of the partner site include an EC (Electronic Commerce) site, a news article site, a search site, etc., but the content is not particularly limited.

[0019] The financial institution server 5 is a server computer of the financial institution used by the first user as a customer, and provides the server 1 with the transaction information of the customer stored in the customer DB 501. Also, in the present embodiment, the financial institution server 5 is also partnered with the analysis server 2 and provides a financial institution web site (for example, an electronic money transfer site, a credit statement confirmation site, etc.). In the following description, for convenience, it is called a "financial institution site" to distinguish it from other partner sites.

[0020] In the present embodiment, the analysis server 2 centrally manages the identification information given to the user at each partner site, collects the data of the web pages browsed by the user associated with the identification information, and analyzes the behavior history.

[0021] Generally, in a web site, when a session is received from a user, a session ID is assigned for each session to manage the data. The ID is stored in the user terminal 3 as the value of the cookie data, and the web server (partner server 4) identifies the terminal of the session source based on the ID.

[0022] However, since each website assigns IDs separately, even if one attempts to associate session data across multiple websites for a single user, it is impossible to identify which session data on one website corresponds to which session data on another website.

[0023] Therefore, for example, on partner sites AA, BB, CC... that cooperate with the analysis server 2, a program called a DMP tag is embedded. When the user terminal 3 accesses a certain partner site AA, it executes the DMP tag to access the analysis server 2 and receives the issuance of a common ID that is shared among partner sites AA, BB, CC.... When accessing other partner sites BB, CC..., the user terminal 3 sends the said ID to conduct a session, thereby enabling the association of session data on each partner site.

[0024] In the following description, the ID assigned by the analysis server 2 is referred to as the "common ID".

[0025] Note that the above association method is just an example, and the method is not limited to what is called DMP. As long as the analysis server 2 can collect data based on the identification information (such as the above-mentioned common ID) assigned to the user on a certain partner site, the specific method is not particularly limited. Also, the data collection method is not limited to the method using cookies. For example, it may be a method using access information such as IP addresses and user agents.

[0026] A DMP tag is also embedded in the financial institution website. When the user terminal 3 of the first user accesses the financial institution website, the common ID assigned to the first user is sent to the analysis server 2. Thereby, it is possible to associate the transaction information of the first user held by the financial institution with the behavior history information of the first user analyzed by the analysis server 2.

[0027] Server 1 determines the creditworthiness of User 2 based on the transaction information and behavior history information of User 1. Then, Server 1 provides the determination result (evaluation result) to the partnering server 4 of the merchant who conducts transactions with User 2. For example, when a merchant accepts a purchase application from User 2 via a partnering site such as an e-commerce site, Server 1 receives application information indicating the purchased goods, payment amount, etc. and the common ID of User 2 from the partnering server 4, and accepts a request for output of the creditworthiness. Server 1 makes a determination of the creditworthiness in response to the request and outputs the determination result.

[0028] In the following, the explanation will mainly be given assuming the case of purchasing goods on an e-commerce site. However, the services (transactions) provided on the partnering site are not limited to the purchase of goods, and may be, for example, financial loans, insurance, real estate sales, etc. Also, Server 1 does not necessarily need to provide the determination result of the creditworthiness to all merchants (partnering servers 4) of the partnering sites, and it may only provide it to some of the merchants. Also, the partnering site that collects the behavior history information and the partnering site of the merchant who conducts transactions with User 2 may be different.

[0029] Also, although Server 1 that performs the creditworthiness determination process, analysis server 2 that analyzes the user's behavior history, and financial institution server 5 that holds the user's transaction information will be described as separate server computers, each device may be the same server computer.

[0030] Also, in the following explanation, it is assumed that the user's creditworthiness is provided to the merchant (partnering server 4) of the partnering site, but of course, it may also be provided to a financial institution (financial institution server 5).

[0031] Figure 2 is a block diagram showing a configuration example of Server 1. Server 1 includes a control unit 11, a main memory unit 12, a communication unit 13, and an auxiliary storage unit 14. The control unit 11 has an arithmetic processing device such as one or more CPUs (Central Processing Units), MPUs (Micro-Processing Units), GPUs (Graphics Processing Units), etc., and reads and executes the program P stored in the auxiliary storage unit 14 to perform various information processing, control processing, etc. The main storage unit 12 is a temporary storage area such as SRAM (Static Random Access Memory), DRAM (Dynamic Random Access Memory), flash memory, etc., and temporarily stores the data necessary for the control unit 11 to execute arithmetic processing. The communication unit 13 is a communication module for performing communication-related processing, and transmits and receives information to and from the outside.

[0032] The auxiliary storage unit 14 is a non-volatile storage area such as a large-capacity memory, hard disk, etc., and stores the program P and other data necessary for the control unit 11 to execute processing. Further, the auxiliary storage unit 14 stores the first user DB 141 and the determination table 142. The first user DB 141 is a database that stores the transaction information and behavior history information of the first user. The server 1 stores the transaction information of the first user who is a customer of the financial institution and the behavior history information obtained by analyzing the web pages of the affiliated sites browsed by the first user in association with each other in the first user DB 141. The determination table 142 is a table used to determine the creditworthiness of the second user, and is a table that stores keywords (reference strings) to be referred to during the determination process.

[0033] Note that the auxiliary storage unit 14 may be an external storage device connected to the server 1. Further, the server 1 may be a multi-computer composed of a plurality of computers, or may be a virtual machine virtually constructed by software.

[0034] Also, in this embodiment, the server 1 is not limited to the above configuration. For example, it may include an input unit that receives operation inputs, a display unit that displays images, etc. Further, the server 1 may be provided with a reading unit that reads a portable storage medium 1a such as a CD (Compact Disk)-ROM or a DVD (Digital Versatile Disc)-ROM, and reads and executes the program P from the portable storage medium 1a. Alternatively, the server 1 may read the program P from the semiconductor memory 1b.

[0035] FIG. 3 is an explanatory diagram showing an example of the record layout of the action history DB 201 and the customer DB 501. The action history DB 201 includes a common ID column and a word column. The common ID column stores the common ID assigned to the first user. The word column stores the words (character strings) described in the web pages viewed by the first user in association with the common ID.

[0036] The customer DB 501 includes a customer ID column, a name column, a common ID column, a deposit balance column, a card balance column, and a transaction column. The customer ID column is an ID for identifying the first user who is a customer of the financial institution. The name column, the common ID column, the deposit balance column, the card balance column, and the transaction column store the name of the first user, the common ID assigned to the first user, the deposit balance, the available balance of the credit card, and the transaction history of the financial products, respectively, in association with the customer ID.

[0037] FIG. 4 is an explanatory diagram showing an example of the record layout of the first user DB 141 and the determination table 142. The first user database 141 includes a data number column, a deposit balance column, a card balance column, a transaction column, and a word column. The data number column stores data numbers for associating transaction information and behavior history information. The deposit balance column, the card balance column, the transaction column, and the word column respectively store, in association with the data number, the deposit balance of the first user, the remaining balance of the credit card, the transaction history of financial products, and the words on the viewed page. The data stored in the deposit balance column, the card balance column, and the transaction column corresponds to the transaction information, and the data stored in the word column corresponds to the behavior history information.

[0038] The determination table 142 includes a transaction type column and a keyword column. The transaction type column stores the types of financial transactions. The keyword column stores, in association with the transaction type, the keywords to be referred to when determining the creditworthiness.

[0039] Figure 5 is a timing chart showing the procedure of the behavior history analysis process. Based on Figure 5, the behavior history analysis process using the common ID will be described. The user terminal 3 of the first user accesses the partner site in response to an operation input from the first user (step S101). The partner server 4 responds to the access from the user terminal 3 and transmits the data (HTML file) of the Web page of the partner site (step S102). The data transmitted in step S102 includes a DMP tag for assigning a common ID.

[0040] The user terminal 3 calls the DMP tag and redirects to the analysis server 2, and transmits the data of the Web page of the partner site accessed in step S101 to the analysis server 2 (step S103). For example, the user terminal 3 transmits text data such as the title and the body of the Web page. If the common ID has not been assigned to the user terminal 3, the analysis server 2 assigns the common ID and stores the data of the Web page in association with the common ID (step S104). The user terminal 3 saves the common ID assigned from the analysis server 2.

[0041] The user terminal 3 accesses the partner site in response to an operation input from the first user (step S105). Note that the partner site accessed in step S105 may be the same as or different from the partner site accessed in step S101. The partner server 4 transmits data of the partner site including the DMP tag in response to the access from the user terminal 3 (step S106). The user terminal 3 calls the DMP tag and transmits the stored common ID and the data of the web page accessed in step S105 to the analysis server 2 (step S107). The analysis server 2 stores the data of the web page in association with the common ID.

[0042] The analysis server 2 analyzes the behavior history of the first user from the data of the web page collected based on the common ID, for example, by batch processing (step S108). For example, the analysis server 2 extracts words included in the web page viewed by the user, such as the title of the viewed page, meta keywords (keywords specified as important words by tags in the HTML file), and the like.

[0043] FIG. 6 is an explanatory diagram regarding the analysis process of the behavior history information. As described above, when the user terminal 3 accesses the partner site, a common ID is assigned from the analysis server 2 by calling the DMP tag. When the user terminal 3 accesses the partner site, it transmits the common ID and the data of the viewed page to the analysis server 2.

[0044] The analysis server 2 extracts words described in the page, such as the title, meta keywords, etc., from the viewed page collected based on the common ID. The analysis server 2 accumulates (stores) the extracted words in the database in association with the common ID assigned to the user terminal 3.

[0045] In addition, in this embodiment, although the browsing history information is the extraction of words in the browsing page, this embodiment is not limited thereto. For example, the analysis server 2 analyzes the session data between the user terminal 3 and the partner server 4, and extracts the URL of the page of the partner site browsed by the first user, the referrer (the page of the link source when the first user accesses the partner site from an external site link), the advertisement clicked by the first user, etc. Alternatively, when the partner site is a search site, the search query input by the first user may be analyzed. Thus, the behavior history information is not limited to the words in the page browsed by the first user.

[0046] Also, in the above, as the behavior history information, words, URLs, referrers, etc. in the page browsed by the user are exemplified, but this embodiment is not limited thereto. For example, when the page browsed by the user is a product listing page of an EC site, the information of the products listed may be extracted as the behavior history information. Thus, the behavior history information may be data indicating the user's behavior on the network N, and its content is not particularly limited.

[0047] Also, in the above, the character string of the browsing page is extracted in word units, but the character string may be extracted in units such as phrases and sentences.

[0048] Also, in the above, the text data of the browsing page is directly sent from the user terminal 3 to the analysis server 2. However, for example, when the analysis server 2 accesses the partner site by the user terminal 3, only the URL and session ID of the browsing page are recorded, and later, it accesses the partner server 4 to obtain the text data of the page browsed by the first user from the partner server 4.

[0049] Returning to FIG. 5, the description will be continued. The user terminal 3 accesses the financial institution site according to the operation input from the first user (step S109). The financial institution server 5 responds to the access from the user terminal 3 and transmits the data of the Web page of the financial institution site (step S110). The data transmitted in step S110 includes DMP tags.

[0050] The user terminal 3 calls the DMP tag and transmits the common ID to the financial institution server 5 (step S111). The financial institution server 5 stores the common ID in association with the customer ID. Through the above processing, the behavior history information of the first user is accumulated in the analysis server 2, and in the financial institution server 5, the first user who is a customer is associated with the common ID.

[0051] In the above description, it has been explained that when accessing the financial institution site, the first user already has a common ID assigned. However, when the partner site accessed for the first time is the financial institution site, it goes without saying that the common ID is assigned at the timing of accessing the financial institution site.

[0052] Based on the common ID obtained in step S111, the financial institution server 5 requests the analysis server 2 to output the behavior history information of the first user corresponding to the common ID (step S112). The analysis server 2 transmits the behavior history information of the first user to the financial institution server 5 (step S113). Specifically, as described above, the analysis server 2 transmits the word data extracted from the browsing pages of the first user to the financial institution server 5. The financial institution server 5 transmits the behavior history information received from the analysis server 2 and the transaction information of the corresponding first user to the server 1 (step S114).

[0053] The transaction information is data indicating the transaction history of the first user at the financial institution as described above. In addition to the deposit balance of the first user, the available balance of the credit card, etc., it is data indicating the presence or absence of contracts, cancellations, etc. for each type of transaction (for example, the type of financial product) (see FIG. 3). The financial institution server 5 provides the server 1 with the transaction information and the behavior history information of the corresponding first user as a series of data sets used as a basis for evaluating the second user. The server 1 stores the transaction information of the first user and the behavior history information associated with the common ID of the first user in the first user DB141 in association with each other.

[0054] When transmitting transaction information from the financial institution server 5, anonymized data is transmitted so that an individual cannot be identified from the transaction history. For example, the financial institution server 5 does not transmit data that can identify an individual, such as a common ID or the name of the first user, but only transmits the transaction details. Also, only a part of the various data included in the transaction information is transmitted to the server 1 so that an individual cannot be identified from the transaction history. Alternatively, when the financial institution server 5 transmits numerical values such as deposit balances, it transmits rounded numerical values instead of the raw numerical values. This prevents the first user from being identified from the transaction information.

[0055] In this embodiment, anonymized data that cannot identify an individual is transmitted to the server 1. However, it goes without saying that raw data including personal information may be provided to the server 1.

[0056] Also, in this embodiment, the transaction information and behavior history information of the first user are collectively transmitted from the financial institution server 5 to the server 1. However, this embodiment is not limited to this. For example, the financial institution server 5 may provide the transaction information of the first user to the analysis server 2, and the analysis server 2 may transmit the transaction information and behavior history information to the server 1. Alternatively, when the server 1 can obtain the common ID of the first user, the server 1 may request the analysis server 2 and the financial institution server 5 to output the behavior history information and transaction information respectively based on the common ID, and obtain data from each. Thus, the acquisition path when the server 1 obtains the transaction information and behavior history information is not particularly limited.

[0057] The server 1 extracts keywords (reference strings) to be referred to when evaluating the second user from the transaction information and behavior history information of the first user (step S115). The server 1 stores the extracted keywords in the determination table 142.

[0058] FIG. 7 is an explanatory diagram regarding the keyword extraction process. Based on FIG. 7, the processing content when extracting keywords in step S115 will be described. As described above, the action history information and transaction information of the first user are associated based on the common ID assigned to the first user. The server 1 extracts keywords used when determining the creditworthiness of the second user from the action history information based on the transaction information associated with the action history information based on the common ID.

[0059] For example, as shown in the lower left of FIG. 7, the server 1 extracts words in the page viewed by the first user as keywords and stores them in the determination table 142. Specifically, the server 1 extracts keywords according to the presence or absence of the transaction for each type of transaction (for example, the type of financial product) and stores them in the determination table 142. For example, when there is a "delay" in the "card loan" for a certain first user, the server 1 associates the words extracted from the page viewed by the first user with "card loan" and "delay" and stores them in the determination table 142.

[0060] The server 1 extracts keywords for each type of transaction as described above. When determining the creditworthiness of the second user, the server 1 compares the words in the page viewed by the second user with the keywords to determine the creditworthiness of the user when conducting various types of transactions.

[0061] FIG. 8 is a timing chart showing the procedure of the user evaluation process. Based on FIG. 8, the processing content when determining the creditworthiness of the second user will be described. The user terminal 3 of the second user accesses a partnering site (for example, an EC site) that conducts commercial transactions, financial transactions, etc. according to an operation input from the second user (step S201). The partnering server 4 responds to the access from the user terminal 3 and transmits the data of the Web page of the partnering site (step S202). The data transmitted in step S202 includes a DMP tag in addition to information related to the transaction (for example, product information). The user terminal 3 calls the DMP tag and transmits the common ID to the analysis server 2 (step S203).

[0062] In accordance with the operation input from the second user, the user terminal 3 transmits application information for applying for a transaction from the second user to the partner server 4 to the partner server 4 (step S204). When the partner site is an EC site, the user terminal 3 transmits an application for purchasing a product. In step S204, in addition to the application information, the user terminal 3 transmits a common ID to the partner server 4.

[0063] When the partner server 4 acquires the application information from the user terminal 3, the partner server 4 transmits the application information and the common ID to the server 1 and requests an output of the credit rating (step S205). When receiving the request for output of the credit rating, the server 1 transmits the common ID acquired from the partner server 4 to the analysis server 2 and requests an output of the behavior history information of the second user corresponding to the common ID (step S206). In response to the request from the server 1, the analysis server 2 outputs the behavior history information of the second user (step S207).

[0064] The server 1 determines (evaluates) the credit rating of the second user based on the behavior history information of the second user acquired from the analysis server 2, the transaction information and the behavior history information of the first user, and outputs the determination result (evaluation result) to the partner server 4 (step S208). The partner server 4 determines the approval or disapproval of the transaction based on the credit rating output from the server 1 and notifies the user terminal 3 of the determination result (step S209).

[0065] For example, the server 1 compares the words in the page viewed by the second user with the keywords of various types of transactions stored in the determination table 142, and determines the credit rating for each type of transaction. For example, in the case of a "housing loan", the server 1 collates the words in the viewed page with the keywords such as "contract", "cancellation", and "bankruptcy" related to the "housing loan", and determines the credit rating when the second user conducts a transaction related to the housing loan.

[0066] Although the specific method for determining (calculating) the credit rating is not particularly limited, for example, positive and negative scores are determined for each keyword, and the credit rating is calculated by accumulating these scores. The server 1 calculates the overall credit rating of the second user by summing up the credit ratings determined for each type of transaction.

[0067] Note that the above determination method is just an example. For example, in addition to the words in the browsing page, the URL of the page viewed by the second user, the referrer, etc. may also be referred to for determining the creditworthiness.

[0068] Also, for example, server 1 may refer to the deposit balance of the first user whose browsing page is the same as or similar to that of the second user, the available balance of the credit card, etc., and perform weighting of the creditworthiness. The similarity of the browsing pages may be determined according to, for example, the appearance frequency of common words (keywords).

[0069] Also, for example, server 1 may refer to the action history information for each predetermined period (for example, every month) to determine the creditworthiness for each period, etc. Thereby, it becomes possible to output the change in the creditworthiness of the second user.

[0070] Also, for example, server 1 may also output the breakdown of the creditworthiness determination factors (for example, the scores for each transaction type) based on the scores of the action history information used as the basis for creditworthiness determination (calculation). Thereby, external operators can grasp the creditworthiness determination factors.

[0071] Also, in the above, the creditworthiness was determined based on rules. However, as in Modification Example 2 described later, machine learning based on the action history information and transaction information accumulated in the customer DB501 and the action history DB201 may be performed, and a model (for example, a neural network) that takes the action history information as input and outputs the creditworthiness may be constructed. Thereby, without the need for the system administrator to set rules, the creditworthiness can be determined by inputting the user's action history information into the model.

[0072] FIG. 9 is an explanatory diagram showing a processing example of the user evaluation system. In FIG. 9, an assumed example of the processing described in the timing chart of FIG. 8 is illustrated. As described above, the business operator related to the cooperation server 4 conducts transactions with the second user via the cooperation site. In the example of FIG. 9, assuming that the cooperation site is an EC site, a case is assumed where the second user pays the purchase price to the business operator later by a payment means such as a credit card.

[0073] When the application information is acquired from the user terminal 3, the cooperation server 4 transmits the application information indicating the content of the transaction applied for by the second user and the common ID of the second user to the server 1, and requests an output of the credit rating. The application information includes, for example, information such as the product that the second user wishes to purchase, the purchase price, and information on the payment means (such as a credit card) of the second user.

[0074] When the application information is acquired, the server 1 transfers the common ID to the analysis server 2 to acquire the action history information of the second user. Then, the server 1 refers to the determination table 142 and determines the credit rating of the second user from the action history information.

[0075] In this embodiment, the credit rating of the second user is determined from the history of the first user's financial transactions. However, the server 1 may also refer to the history of commercial transactions that each business operator of each cooperation site has conducted with the first user in the past to determine the credit rating of the second user. Specifically, when the server 1 acquires the common ID and application information of the first user from each business operator (cooperation server 4), the acquired application information is stored in the first user DB 141 as transaction information. In addition, the server 1 requests an output of the action history information of the first user based on the common ID, acquires the action history information from the analysis server 2, and stores it in the first user DB 141 in association with the transaction information of the first user.

[0076] When Server 1 receives a request to output the creditworthiness of a second user from a certain business operator, in addition to the transaction information on the financial transactions of the first user obtained from the financial institution server 5, it also refers to the transaction information on the commercial transactions of the first user obtained from the partner server 4 to determine the creditworthiness. In the example of Fig. 9, when receiving a request to output the creditworthiness from "EC Site XX", Server 1 determines the creditworthiness by referring to the transaction history of the first user on "EC Site XX". Note that Server 1 may use the transaction history of other partner sites different from the partner site where the second user applied for the transaction for the creditworthiness determination of the second user. By referring to the transaction history of the first user who has used the same partner site in the past, the creditworthiness of the second user can be suitably determined based on the characteristics of the users of that partner site.

[0077] The method for determining the creditworthiness including the commercial transaction history on the partner site is not particularly limited. For example, a first user with a similar transaction tendency is identified from the purchased goods, purchase amount, etc. applied for by the second user. If there is a history of non-payment transactions for the first user similar to the second user, a method such as determining that the probability of default (bad debt) is high and lowering the creditworthiness can be considered. In this way, Server 1 may determine the creditworthiness by referring to the commercial transaction history of the first user conducted in the past with the business operator of the partner site.

[0078] Also, for example, when Server 1 obtains application information from the same second user from a plurality of partner sites (EC sites), it may lower the creditworthiness of the second user. Specifically, when the occurrence times of the transactions (post-payment) indicated by the application information obtained from each partner site are in the same period, Server 1 lowers the creditworthiness of the second user. Thereby, the creditworthiness can be suitably determined in consideration of the current transaction status (application status) on a plurality of partner sites.

[0079] Server 1 outputs the creditworthiness determination result to the partnering server 4. It is preferable that the creditworthiness be output as a numerical value (for example, a value between 0 and 1), but it may also be output as a ranked result in the form of, for example, Rank A, Rank B, or Rank C. The partnering server 4 determines whether to approve the application based on the creditworthiness output from Server 1, and notifies the user terminal 3 of the determination result.

[0080] Note that in the above, the creditworthiness of the second user in commercial transactions and financial transactions was determined, but the present embodiment is not limited to this. For example, Server 1 may estimate (evaluate) the purchase probability of the second user purchasing a product on the EC site based on the action history information and transaction information of the first user, and provide the estimation result to the EC site. In this case, for example, Server 1 determines the similarity between the first user and the second user from the action history information of the first user and the second user, and extracts the first user similar to the second user. Server 1 estimates the purchasing power and products of interest of the second user from the transaction information of the extracted first user, and outputs the estimation result to the partnering server 4. Thus, Server 1 only needs to be able to evaluate the second user based on action history information, transaction information, etc., and the evaluation scale is not limited to the creditworthiness in transactions.

[0081] Figure 10 is a flowchart showing the processing procedure executed by Server 1. Based on Figure 10, the processing content executed by Server 1 will be described. The control unit 11 of Server 1 acquires, from the partnering server 4 of the merchant, application information indicating the content of the transaction applied for by the second user to the merchant, and the common ID (identification information) assigned to the second user by the session to the partnering site (step S11).

[0082] The control unit 11 transmits the common ID acquired in step S11 to the analysis server 2, and requests the output of action history information indicating the action history of the second user on the network N (step S12). For example, the control unit 11 requests the output of, in addition to the words (character strings) described on the pages of the partnering site viewed by the second user, the URL, referrer, click ads, etc. The control unit 11 acquires the action history information from the analysis server 2 (step S13).

[0083] The control unit 11 determines the creditworthiness of the second user based on the action history information of the second user acquired in step S13, the action history information and transaction information of the first user who is a customer of the financial institution (step S14). Specifically, keyword (reference string) is stored in the determination table 142 for each type of transaction. The control unit 11 compares the words in the page viewed by the user with the keyword for each type of transaction to determine the creditworthiness. In addition, the control unit 11 refers to the transaction history (transaction information) of each transaction type to determine the creditworthiness. In addition, the control unit 11 may determine the creditworthiness from the URL, referrer, click advertisement, etc. Further, the control unit 11 may also refer to the business transaction history (transaction information) of the first user already acquired from each business operator to determine the creditworthiness. The control unit 11 outputs the determination result to the cooperation server 4 (step S15) and ends the series of processes.

[0084] Note that in the above, the transaction information and action history information of each user are associated based on the common ID (DMP tag), but the present embodiment is not limited to this, and may be associated based on other identification information that can be a user identifier. The other identification information is, for example, the access information of the user terminal 3 that can be acquired when accessing the website, specifically, the IP address, user agent, timestamp, etc.

[0085] For example, when analyzing the behavior history information of each user, the analysis server 2 associates the access information when the user accesses the partner site with the behavior history information and stores it in the behavior history DB 201. When the analysis server 2 receives a request to output the behavior history information of the second user from the server 1 and / or the financial institution server 5, in addition to or instead of the common ID, it acquires this access information. The analysis server 2 compares the acquired access information with the access information of each user stored in the behavior history DB 201, estimates the same or similar users, and outputs the behavior history information of the user. In this way, it is sufficient to be able to associate the behavior history information and the transaction information based on the identification information related to the user that can be acquired when accessing the website (partner site), and the identification information serving as the basis is not limited to the common ID.

[0086] As described above, according to the present embodiment, the behavior history information of the second user is acquired based on the identification information assigned according to the session to the partner site (website), and by referring to the behavior history information and the transaction information of the first user, the second user can be appropriately evaluated (preferably, credit evaluation).

[0087] Further, according to the present embodiment, by acquiring the behavior history information from the analysis server 2 (management device) that manages the identification information (common ID) of the second user in each partner site, the behavior history of the second user on the network N can be preferably grasped.

[0088] Further, according to the present embodiment, by acquiring or assigning the identification information according to the session to the financial institution site (first website), the behavior history information of the first user can be preferably acquired from the analysis server 2.

[0089] Further, according to the present embodiment, the second user can be more preferably evaluated by comparing the words (character strings) described on the page of the partner site browsed by the second user with the keywords (reference character strings).

[0090] In addition, according to the present embodiment, by referring to keywords and transaction histories for each type of transaction, it is possible to more suitably perform user evaluation by combining action history information and transaction information.

[0091] In addition, according to the present embodiment, the evaluation result (for example, credit rating) of the second user can be provided to an external business operator.

[0092] In addition, according to the present embodiment, by referring to the transaction details (application information) that the first user has conducted with a business operator in the past, it is possible to more suitably evaluate the second user.

[0093] (Modification Example 1) In the above-described embodiment, the case of mainly determining (evaluating) the credit rating in lending to the second user has been described. On the other hand, the evaluation measure for the second user does not have to be the credit rating in lending.

[0094] FIG. 11 is an explanatory diagram showing an application example of the user evaluation system. FIG. 11 schematically illustrates the case where this system is applied to various uses. Specifically, it conceptually illustrates keywords (action history information) that serve as criteria when evaluating a target second user, classified into a target user (individual or corporation), a target service ("finance", "non-finance", etc.), and a use ("lending", "sales promotion", "fraud detection", "others"). In the above-described embodiment, the case of determining the credit rating in lending (the "lending" column in FIG. 11) has been described. However, as shown in FIG. 11, the server 1 may evaluate the second user for uses such as "sales promotion", "fraud detection", and "others".

[0095] "Sales promotion" is a case of promoting the sale of an object such as a product to the second user. Here, the "product" mentioned here is not limited to physical products, and may also include financial products, insurance products, etc. Also, the "object" is not limited to products, and may also include the provision of services.

[0096] For example, server 1 stores the transaction history (such as the presence or absence of transactions) of various objects by the first user as transaction information in the first user DB 141. Then, server 1 acquires the keywords of the web pages viewed by each first user from analysis server 2, and stores them in determination table 142 in association with the transaction history of the objects. When server 1 receives a request to output the behavior history information of the second user from cooperation server 4, it acquires the behavior history information (keywords) of the second user from analysis server 2, compares them with the keywords stored in determination table 142, and identifies the first user whose keywords are the same as or similar to those of the second user. Then, based on the transaction history of the first user, server 1 determines the objects for which sales to the second user should be promoted, and outputs the determination result to cooperation server 4.

[0097] Explaining with reference to FIG. 11, for example, in the case of promoting the sale of objects (financial products) related to "finance" to users of "individuals" ("grasping necessary products"), server 1 stores keywords such as "introduction to investment" and "new construction" in determination table 142. Server 1 compares the keywords of the web pages viewed by the second user with these keywords, and determines the objects (financial products) for which sales to the second user should be promoted.

[0098] "Illegality detection" is a case where, at the time of a transaction, it is detected (determined) that the second user may perform an illegal act such as false declaration. Server 1 may determine the possibility of an illegal act (hereinafter referred to as "illegal risk") from the behavior history information of the user on network N.

[0099] For example, the server 1 stores in the first user database 141 whether there is any illegal act of the first user at the time of transaction as the transaction information of the first user. Then, the server 1 obtains from the analysis server 2 the action history information of the first user who has committed an illegal act, and stores keywords in the determination table 142 for each type of illegal act (such as false declaration, multiple contracts with a false user name from the same terminal, illegal use of borrowed money, etc.). When the server 1 receives a request from the partner server 4 to output the action history information of the second user, the server 1 obtains the action history information of the second user from the analysis server 2, compares it with the keywords stored in the determination table 142, and determines the risk of illegal acts by the second user. The server 1 outputs the determination result to the partner server 4 and issues a warning.

[0100] As "others", cases where it is used for predicting the defection of the second user (customer), making a call to the second user (such as sales by phone, email, etc.), predicting a move, etc. are assumed. As a case of using it for predicting defection, for example, when the second user is a customer of a financial institution, the server 1 stores in the determination table 142 the keywords related to the first user who has defected from the financial institution (such as a user who has canceled an account), and determines the possibility that the second user will defect. As a case of using it for making a call, for example, when the server 1 conducts a call to introduce financial products, etc. to the second user in the case where the second user is a customer of a financial institution, the server 1 extracts from the access information the time zone when each user accesses the web page (browser), and determines the time zone when a call should be made to the second user. As a case of using it for predicting a move, for example, the server 1 determines the change of the residence (move) of the second user from the change of the access information (IP address, user agent, etc.) of the second user (customer) at multiple time points.

[0101] In this way, it is sufficient that the server 1 can evaluate the second user based on the action history information of the second user. In addition to the determination of the creditworthiness in credit granting, various evaluation uses such as sales promotion and fraud detection are assumed. As a result, in addition to credit evaluation, this system can be applied to various measures such as narrowing down the targets for sales promotion, strengthening identity verification, implementing a defection prevention campaign, and creating a customer call list.

[0102] Note that the server 1 may combine these evaluation methods. For example, when the second user accesses the partner site, the server 1 first determines the fraud risk posed by the second user. If it is determined that there is no fraud risk, the server 1 then determines the creditworthiness of the second user. If it is determined that there is no problem with the creditworthiness (for example, the creditworthiness is equal to or higher than a predetermined threshold), the server 1 further determines the object to be promoted for sales. The server 1 outputs each determination result to the partner server 4. In this case, for example, the server 1 stores the keywords for each determination in a plurality of determination tables 142, 142, 142... and may use the corresponding determination table 142 when performing each determination. Thus, the evaluation methods may be combined. Also, for example, the server 1 may make it possible for the partner merchant, which is the output destination of the creditworthiness, to select any of these evaluation methods.

[0103] Since the evaluation method of the second user is the same as that of the above-described embodiment except for the difference, detailed description such as a flowchart is omitted in this modification example.

[0104] As described above, according to the first modification example, the second user can be evaluated by various methods.

[0105] (Modification Example 2) In the above-described embodiment, the form of evaluating the second user based on rules has been described. On the other hand, a machine learning model may be constructed using the behavior history information and transaction information of the first user as teacher data, and the second user may be evaluated using the model.

[0106] FIG. 12 is a block diagram showing a configuration example of the server 1 according to Modification 2. The auxiliary storage unit 14 of the server 1 according to this modification stores a determination model 50 instead of the determination table 142. The determination model 50 is a machine learning model that has learned the behavior history information and transaction information of the first user, and is a model that determines the evaluation value of the second user regarding credit granting or the like when the behavior history information of the second user is input. The determination model 50 is assumed to be used as a program module that constitutes a part of artificial intelligence software.

[0107] For example, the determination model 50 is a neural network generated by deep learning using the behavior history information and transaction information of the first user as teacher data. Note that the determination model 50 may be a model based on other learning algorithms such as decision trees, random forests, and SVM (Support Vector Machine) in addition to neural networks.

[0108] The evaluation value output from the determination model 50 is, for example, the creditworthiness of the second user regarding credit granting (for example, the probability of delay in post-payment settlement, etc.). Note that the evaluation value is not limited to the creditworthiness, and may be the purchase probability of the promotion target product, the probability of fraud risk, the probability of defection, etc. described in Modification 1. Further, the evaluation value may be a continuous regression estimate value (for example, a value between 0 and 1), or a classification value (for example, a rank obtained by grading the creditworthiness).

[0109] The server 1 generates the determination model 50 by learning the behavior history information of the first user collected based on the common ID and the transaction information of the first user. Specifically, the server 1 assigns a correct value of the creditworthiness to each first user according to the behavior history information of each first user. For example, the server 1 refers to the first user DB 141 (see FIG. 4), adds or subtracts the creditworthiness according to the presence or absence of a contract, delay, cancellation, etc. with each first user, and assigns a correct value. The server 1 creates teacher data by labeling the correct value of the creditworthiness assigned to each first user with the behavior history information of each first user. The server 1 generates the determination model 50 using the created teacher data.

[0110] Note that the correct value of the credit rating (evaluation value) may be manually assigned instead of being automatically assigned by Server 1.

[0111] Server 1 inputs the behavior history information for the teacher into the determination model 50 and obtains the credit rating as the output from the determination model 50. Server 1 compares the credit rating output from the determination model 50 with the correct value, and updates parameters such as the weights between neurons so that the two are approximated. Server 1 learns the teacher data for each first user, and finally generates a determination model 50 with optimized parameters.

[0112] Here, in the present embodiment, the behavior history information input to the determination model 50 includes access information that can be obtained when accessing the partner site, in addition to the keywords extracted from the partner sites viewed by the first user. The access information is log data when the user terminal 3 accesses the partner site, and is, for example, an IP address, a user agent, or the like. Server 1 gives the access information other than the keywords to the determination model 50 as teacher data for learning.

[0113] In particular, in the present embodiment, the access information to be learned includes the domain of the web page viewed by the user, the language setting in the user terminal 3, the user agent, and the IP address. According to the development of the inventor of the present application, by including these access information in the feature amount, the determination accuracy of the credit rating can be improved.

[0114] When determining the credit rating of the second user, Server 1 inputs the behavior history information (including access information) of the second user obtained from the partner server 4 into the determination model 50 to determine the credit rating of the second user. Server 1 outputs the determined credit rating to the partner server 4.

[0115] FIG. 13 is a flowchart showing the procedure of the generation process of the determination model 50. Based on FIG. 13, the processing content when generating the determination model 50 by machine learning will be described. The control unit 11 of server 1 acquires the action history information and transaction information of each first user from the first user DB 141 (step S21). The action history information includes access information in addition to the keywords extracted from the partner sites (Web sites) accessed by the first user. The access information is log data when the user terminal 3 accesses the partner site, and includes the domain of the Web page browsed (accessed) by the user, the language setting in the user terminal 3, the IP address, and the user agent.

[0116] Based on the transaction information of the first user, the control unit 11 assigns the correct value of the creditworthiness of the first user (step S22). Note that the correct value may be automatically assigned by server 1 or may be assigned manually.

[0117] Based on the action history information of the first user and the correct value of the creditworthiness assigned in step S202, the control unit 11 generates a determination model 50 that determines the creditworthiness when the action history information is input (step S23). For example, the control unit 11 generates a neural network as the determination model 50. The control unit 11 inputs the action history information of the first user into the determination model 50 to obtain the creditworthiness of the first user from the determination model 50. The control unit 11 optimizes parameters such as the weights between neurons so that the obtained creditworthiness approximates the correct value. Thereby, the control unit 11 generates the determination model 50. The control unit 11 ends a series of processes.

[0118] Since it is the same as the above-described embodiment except for determining the creditworthiness of the second user using the determination model 50, detailed descriptions such as the flowchart at the time of creditworthiness determination (see FIG. 10) are omitted in this modification example.

[0119] Incidentally, access information such as the domain of the browsing page, language settings, IP address, and user agent may also be used when evaluating (judging the creditworthiness) the second user based on rules as in the above-described embodiments. For example, when the server 1 stores the keywords of the web pages viewed by the first user in the determination table 142, the server 1 simultaneously stores the domain of the browsing page, language settings, IP address, and user agent of the first user. Then, the server 1 acquires each address information together with the keyword as the action history information of the second user, and determines the creditworthiness by comparing it with the keyword and address information stored in the determination table 142. In this way, it is sufficient that the server 1 can evaluate the second user based on the action history information including each access information, and the evaluation method based on the access information is not limited to the evaluation by the machine learning model.

[0120] From the above, according to this Modification 2, the second user can also be evaluated using the machine learning model.

[0121] The embodiments disclosed this time should be considered as illustrative in all respects and not restrictive. The scope of the present invention is shown not by the above meaning but by the claims, and it is intended that all modifications within the meaning and scope equivalent to the claims are included.

Explanation of Reference Numerals

[0122] 1 Server (information processing device) 11 Control unit 12 Main memory unit 13 Communication unit 14 Auxiliary storage unit P Program 2 Analysis server 3 User terminal 4 Partner server 5 Financial institution server

Claims

1. A storage unit that stores transaction information indicating the transaction history of a first user and behavior history information indicating the behavior history of the first user on a network, the behavior history information including access information that can be obtained when the first user accesses a website; A generation unit that generates a learned model for determining an evaluation value of a user when the behavior history information is input based on the transaction information and the behavior history information of the first user; A first acquisition unit that acquires identification information assigned to a second user through a session to a website; A second acquisition unit that acquires the behavior history information including the access information of the second user based on the identification information; An evaluation unit that determines an evaluation value of the second user by inputting the behavior history information of the second user into the model An information processing apparatus characterized by comprising.

2. The access information includes a user's browsing domain, language setting, user agent, or IP address The information processing apparatus according to claim 1, characterized in that.

3. The evaluation unit determines the creditworthiness of the second user in terms of credit. The information processing apparatus according to claim 1 or 2, characterized in that.

4. The transaction information includes the transaction history of a predetermined object by the first user, The evaluation unit determines the object to be promoted for sale to the second user. The information processing apparatus according to any one of claims 1 to 3, characterized in that.

5. The transaction information includes the presence or absence of fraud by the first user at the time of transaction, The evaluation unit determines the possibility of fraud by the second user at the time of transaction. The information processing apparatus according to any one of claims 1 to 4, characterized in that.

6. A request unit that requests the output of the behavior history information based on the identification information acquired by the first acquisition unit to a management device that manages the identification information commonly assigned to a plurality of the websites; The second acquisition unit acquires the behavior history information indicating the behavior history of the second user on the plurality of websites. The information processing apparatus according to any one of claims 1 to 5, characterized in that.

7. The transaction information includes information indicating the financial transaction history of the first user who is a customer of a financial institution. a third acquisition unit that acquires, in response to a session from the first user to the website of the financial institution, the transaction information of the first user and the behavior history information of the first user on the plurality of websites linked to the identification information of the first user; The storage unit stores the transaction information and the behavior history information of the first user in association with each other.

7. The information processing apparatus according to claim 6,

8. The behavior history information includes data indicating character strings written on pages of the website.

8. The information processing device according to claim 1, wherein the information processing device is a computer.

9. the first acquisition unit acquires the identification information of the second user from a business that conducts a transaction with the second user via the website; an output unit that outputs the evaluation result of the second user to the business operator; 9. The information processing device according to claim 1, wherein the information processing device is a computer.

10. A trained model is generated to determine a user's evaluation value when the behavioral history information is input, based on transaction information indicating the transaction history of a first user stored in a memory unit and behavioral history information indicating the first user's behavioral history on a network, the behavioral history information including access information obtainable when the first user accesses a website; acquiring identification information assigned to the second user through a session to the website; acquire the behavior history information including the access information of the second user based on the identification information; The behavior history information of the second user is input into the model to determine an evaluation value of the second user. An information processing method characterized in that the processing is executed by a computer.

11. A trained model is generated to determine a user's evaluation value when the behavioral history information is input, based on transaction information indicating the transaction history of a first user stored in a memory unit and behavioral history information indicating the first user's behavioral history on a network, the behavioral history information including access information obtainable when the first user accesses a website; acquiring identification information assigned to the second user through a session to the website; acquire the behavior history information including the access information of the second user based on the identification information; The behavior history information of the second user is input into the model to determine an evaluation value of the second user. A program characterized by causing a computer to execute processing.

12. A storage unit that stores transaction information indicating the transaction history of a first user and behavior history information indicating the behavior history of the first user on a network, the behavior history information including access information that can be acquired when the first user accesses a website; A generation unit that generates a learned model for determining an evaluation value of a user when the behavior history information is input based on the transaction information and the behavior history information of the first user; A first acquisition unit that acquires identification information related to a second user who has accessed when accessing a website; A second acquisition unit that acquires the behavior history information including the access information of the second user based on the identification information; An evaluation unit that determines an evaluation value of the second user by inputting the behavior history information of the second user into the model An information processing apparatus characterized by comprising the above.

13. A storage unit that stores transaction information indicating the transaction history of a first user and behavior history information indicating the behavior history of the first user on a network, the behavior history information including data indicating a character string described on a page of a website browsed by the first user; An extraction unit that extracts a reference character string to be referred to when evaluating a second user from the behavior history information of the first user; A table generation unit that stores the extracted reference character string in a table in association with the type of transaction performed by the first user in the past based on the transaction information; A first acquisition unit that acquires identification information assigned to the second user by a session to a website; A second acquisition unit that acquires the behavior history information of the second user, which includes data indicating a character string described on a page of a website browsed by the second user, based on the identification information; An evaluation unit that evaluates the second user for each type of transaction by comparing the character string indicated by the behavior history information of the second user with the reference character string stored in the table for each type of transaction An information processing apparatus characterized by comprising the above.

Images