JP2020204979A - Estimation device, estimation method, and estimation program - Google Patents

Abstract

To improve estimation accuracy of user credibility.SOLUTION: An estimation device of the present invention comprises an identification unit and an estimation unit. The identification unit identifies a predetermined action related to self management from among actions taken by a user. The estimation unit estimates credibility of the user on the basis of the action identified by the identification unit.SELECTED DRAWING: Figure 2

Description

The present invention relates to an estimation device, an estimation method and an estimation program.

Conventionally, there have been provided techniques for forecasting various demands and providing information according to the forecast results. As an example of such a technology, for example, using a model that learns the relationship between user information obtained from a social network and creditworthiness such as credit related to financial services, the user to be estimated A technique for estimating creditworthiness from behavior is known.

Japanese Unexamined Patent Publication No. 2014-206792

However, it may not be possible to say that the above-mentioned technology accurately estimates the creditworthiness of the user.

For example, in the above-mentioned technology, the creditworthiness of the user is estimated from the information posted on the social network by the user. Therefore, if the user posts false information, the accuracy of the creditworthiness may deteriorate. ..

The present application has been made in view of the above, and an object of the present application is to provide an estimation device, an estimation method, and an estimation program capable of improving the estimation accuracy of the creditworthiness of a user.

The estimation device according to the present application estimates the creditworthiness of the user based on the specific unit that specifies a predetermined action related to self-management among the actions performed by the user and the action specified by the specific unit. It is characterized by having an estimation unit.

According to one aspect of the embodiment, there is an effect that the estimation accuracy of the creditworthiness of the user can be improved.

FIG. 1 is a diagram showing an example of an estimation process executed by the estimation device according to the embodiment. FIG. 2 is a diagram showing a configuration example of an estimation system according to an embodiment. FIG. 3 is a diagram showing an example of a management behavior database according to the embodiment. FIG. 4 is a diagram showing an example of a user database according to the embodiment. FIG. 5 is a flowchart showing an example of a flow of estimation processing executed by the estimation device according to the embodiment. FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the function of the estimation device.

Hereinafter, a mode for carrying out the estimation device, the estimation method, and the estimation program according to the present application (hereinafter, referred to as “the embodiment”) will be described in detail with reference to the drawings. The estimation device, estimation method, and estimation program according to the present application are not limited by this embodiment. In addition, each embodiment can be appropriately combined as long as the processing contents do not contradict each other. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[1. An example of estimation processing indicated by an estimation device]
An example of the estimation process executed by the estimation device 100 according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of estimation processing executed by the estimation device 100 according to the embodiment. Specifically, the estimation device 100 estimates the creditworthiness of the user based on a predetermined action related to self-management among the actions performed by the user. The credit rating here is a value used as an index of the credit of the user when conducting a credit transaction such as a loan, and is information called a so-called credit score.

Further, the embodiment is not limited to the credit score, and in addition to the credit score, it is the credit rating of the user who is the service provider, and is a score that can be used as an index when determining whether or not the service can be provided. If so, any score can be adopted.

Hereinafter, an example of the estimation process by the estimation device 100 will be described along the flow with reference to FIG. In the following, an example of using the management application AP for the user to self-manage will be described. The management application referred to here is, for example, an application for managing a user's schedule, health, disaster prevention, and the like. In the following, the application may be referred to as an application.

First, as shown in FIG. 1, the management service providing server 20 receives information regarding a schedule registered by the user TU via the management application AP from the user terminal 10 used by the user TU (step S1). ). For example, an example in which the user TU registers the "scheduled consultation time of the dental clinic" using the management application AP will be described. In this case, the management service providing server 20 receives the information regarding the "scheduled consultation time of the dental clinic" registered by the user TU from the user terminal 10.

For example, an example in which the user TU registers the "wake-up time" using the management application AP will be described. In this case, the management service providing server 20 receives the information regarding the "wake-up time" registered by the user TU from the user terminal 10.

Subsequently, the estimation device 100 acquires information regarding the schedule of the user TU from the management service providing server 20 (step S2). For example, an example in which the user TU registers the "scheduled consultation time of the dental clinic" using the management application AP will be described. In this case, the estimation device 100 acquires information regarding the "scheduled consultation time of the dental clinic" from the management service providing server 20.

For example, an example in which the user TU registers the "wake-up time" using the management application AP will be described. In this case, the estimation device 100 acquires information regarding the "wake-up time" from the management service providing server 20.

Then, the estimation device 100 acquires the behavior information, which is the information about the behavior of the user TU, from the user terminal 10 (step S3). The action information referred to here may be any action as long as it is an action performed by the user. For example, the behavior information is a search history, a browsing history of contents, a purchase history in an electronic commerce service, or the like.

For example, the behavior information includes a history of sending and receiving e-mails, behavior information regarding e-mail settings, information regarding communication regarding application and receipt of courier services, and behavior information regarding reservations to accommodation facilities and restaurants.

For example, the behavior information includes behavior information related to application installation, behavior information related to application startup, behavior information related to application settings, behavior information related to application push notification settings, and the like.

For example, in the example of FIG. 1, the estimation device 100 acquires behavioral information regarding the activation of the application of the user TU. Further, for example, in the example of FIG. 1, the estimation device 100 acquires information regarding communication regarding application and receipt regarding courier service as action information.

Subsequently, the estimation device 100 identifies an action related to self-management, which is an action performed by the user (step S4). That is, in order to identify the behavior related to self-management among the behaviors performed by the user, the estimation device 100 selectively identifies the behavior that easily affects the reliability of the user itself, such as the behavior related to the user's self-management. be able to.

The self-management behavior referred to here may be any self-management behavior performed by the user. For example, the behavior related to self-management is an action related to the management of the user's schedule or an action related to the management of the user's health.

For example, actions related to self-management include actions for registering future plans, actions for requesting redelivery of TA-Q-BIN (registered trademark) addressed to users, and automatic mail received by the user terminal 10 used by the user. It is an action to set the distribution or an action to reserve the use of a predetermined facility.

For example, behaviors related to self-management include actions to set the delivery mode of push notifications to users, actions to install disaster prevention-related applications on the user's user terminal 10, actions to enter health-related search queries, or health-related actions. This is the behavior of purchasing the transaction target of.

For example, behaviors related to self-management include actions to set the delivery mode of push notifications to users, actions to install disaster prevention-related applications on the user's user terminal 10, actions to enter health-related search queries, or health-related actions. This is the behavior of purchasing the transaction target of.

For example, actions related to self-management are entered in an action related to schedule management, an action related to health management, an action related to disaster prevention, an action related to pedometer, or a questionnaire related to health management. Action etc.

Specifically, the estimation device 100 identifies a predetermined action related to self-management among the actions performed by the user. More specifically, the estimation device 100 specifies an action related to schedule management as a predetermined action related to self-management. For example, the estimation device 100 specifies an action in which the user installs an application for managing the schedule on the user's terminal as an action related to schedule management.

For example, the estimation device 100 specifies an action in which the user registers the schedule in the application that manages the schedule as an action related to the schedule management. For example, the estimation device 100 specifies an action in which the user purchases a transaction target for managing the schedule as an action related to the management of the schedule.

Further, more specifically, the estimation device 100 specifies an action of requesting redelivery of Takkyubin addressed to the user as a predetermined action related to self-management. More specifically, the estimation device 100 specifies an action for setting automatic distribution of received emails as a predetermined action related to self-management.

Further, more specifically, the estimation device 100 specifies an action of reserving the use of a predetermined facility as a predetermined action related to self-management. Further, more specifically, the estimation device 100 specifies an action of setting a delivery mode of the push notification to the user as a predetermined action related to self-management.

More specifically, the estimation device 100 specifies an action of installing a disaster prevention-related application on a user's terminal as a predetermined action related to self-management. More specifically, the estimation device 100 specifies an action related to the management of the user's health as a predetermined action related to self-management.

For example, the estimation device 100 identifies an action of inputting a health-related search query as an action related to health management. For example, the estimation device 100 identifies an action of purchasing a health-related transaction target as an action related to health management.

For example, in the example of FIG. 1, the estimation device 100 identifies an action related to schedule management and an action related to health management as actions related to self-management among the actions performed by the user. For example, in the example of FIG. 1, the estimation device 100 identifies an action in which the user activates the schedule management application as an action related to schedule management.

For example, when the user activates the management application AP and registers that he / she will visit the dental clinic in the schedule managed by the management application AP, the estimation device 100 identifies the behavior in which the user activates the management application AP. For example, in the example of FIG. 1, the estimation device 100 identifies an action requested by the user for redelivery as an action related to schedule management.

For example, in the example of FIG. 1, the estimation device 100 identifies an action in which the user sets the distribution of e-mails as an action related to schedule management. For example, the estimation device 100 identifies the behavior of the user who has set the distribution of e-mails when the user has set the distribution of e-mails in order to organize the e-mails received for each customer.

For example, in the example of FIG. 1, the estimation device 100 specifies a period from the reservation made by the user to the actual use by the user as an action related to schedule management. For example, in the estimation device 100, when the user reserves "Restaurant A" and the user visits "Restaurant A" two weeks after the reservation and uses it, the period from the reservation to the use is two weeks. To identify. For example, in the example of FIG. 1, the estimation device 100 identifies an action in which the user has set the management setting of the push notification as an action related to schedule management. For example, in the estimation device 100, when the user sets the push notification of the management application AP and sets the push notification to be performed when the preset schedule is approaching, the user sets the management setting of the push notification. Identify the behavior you have taken. For example, in the example of FIG. 1, the estimation device 100 identifies an action in which the user activates the disaster prevention application as an action related to schedule management. For example, the estimation device 100 identifies the behavior in which the user activates the management application AP when the user activates the management application AP and sets to automatically notify the family of the whereabouts at the time of disaster prevention.

For example, in the example of FIG. 1, the estimation device 100 identifies an action in which a user inputs a health-related search query as an action related to health management. For example, when the user inputs a search query such as "muscle training method", the estimation device 100 identifies an action in which the user inputs "muscle training method" as a search query. For example, in the example of FIG. 1, the estimation device 100 identifies an action in which a user purchases a health management transaction target as an action related to health management. For example, the estimation device 100 identifies the behavior of the user who purchased the "exercise equipment" when the user purchased the "exercise equipment".

For example, in the example of FIG. 1, the estimation device 100 identifies an action in which the user activates the health management application as an action related to health management. For example, when the user activates the management application AP and confirms the number of steps per day, the estimation device 100 identifies the behavior in which the user activates the management application AP. For example, in the example of FIG. 1, the estimation device 100 identifies a user's regular behavior as an behavior related to health management. For example, in the estimation device 100, when the user sets the daily wake-up time and bedtime via the management application AP, the user wakes up at the set wake-up time and goes to bed at the set bedtime. Identify regular behavior.

Then, the estimation device 100 calculates the creditworthiness of the user based on the specified behavior (step S5). That is, the estimation device 100 pays attention to an action that easily affects the reliability of the user itself, such as an action related to the user's self-management, and calculates the creditworthiness of the user with high accuracy based on the action related to the self-management. it can.

Specifically, the estimation device 100 estimates the creditworthiness of the user based on the specified behavior. Specifically, the estimation device 100 estimates the creditworthiness of the user based on whether or not the user manages himself / herself.

More specifically, the estimation device 100 was performed by the target user to be the credit rating estimation target using a model that learned the relationship between the credit rating of the user and the predetermined action among the actions performed by the user. Estimate the creditworthiness of the target user from the prescribed behavior.

For example, the estimation device 100 calculates a higher credit rating when the user has the application installed than when the user has not installed the application. For example, the estimation device 100 calculates the credit rating of the user to a value "10" higher when the user installs the management application AP. For example, the estimation device 100 calculates a higher credit rating when the user has registered the schedule than when the user has not registered the schedule. For example, when the user activates the management application AP and registers that he / she will visit the dental clinic in the schedule managed by the management application AP, the estimation device 100 calculates the credit rating of the user to a value "10" higher.

For example, the estimation device 100 calculates a higher credit rating when the user has purchased the transaction target than when the user has not purchased the transaction target. For example, the estimation device 100 calculates the credit rating of the user to a value "10" higher when the user purchases the supplement as an example of the transaction target. For example, the estimation device 100 calculates a credit rating of a lower value when the user requests the redelivery of TA-Q-BIN than when the user does not request the redelivery of TA-Q-BIN. For example, when the user requests the redelivery of TA-Q-BIN, the estimation device 100 calculates the creditworthiness of the user to a value "10" higher.

For example, the estimation device 100 calculates a higher credit rating when the user has set automatic mail sorting than when the user has not set automatic mail sorting. For example, the estimation device 100 calculates the credit rating of the user to a value "10" higher when the automatic distribution setting of the e-mail is set in order to organize the e-mails received by the user for each customer. For example, when the period from the reservation for the use of the facility to the use of the facility exceeds a predetermined threshold value, the estimation device 100 calculates a higher credit rating than when the period does not exceed the predetermined threshold value. For example, it is assumed that the predetermined threshold value is "1 week". In this case, in the estimation device 100, when the user reserves "Restaurant A" and the user visits "Restaurant A" two weeks after the reservation and uses it, the period from the reservation to the use. Is 2 weeks and exceeds a predetermined threshold value, so the credit rating of the user is calculated to be "10" higher.

For example, when the user sets the delivery mode of the push notification, the estimation device 100 calculates a higher credit rating than when the delivery target of the push notification is not set. For example, when the user sets the push notification of the management application AP and sets the push notification to be performed when the preset schedule is approaching, the estimation device 100 sets the credit rating of the user to a value "10" higher. Calculate to. For example, the estimation device 100 calculates a higher credit rating when the user has installed the disaster prevention-related application than when the user has not installed the disaster prevention-related application.

For example, the estimation device 100 calculates a higher credit rating when the user has entered a health-related search query than when the user has not entered a health-related search query. For example, when the user inputs a search query such as "muscle training method", the estimation device 100 calculates the credit rating of the user to a value "10" higher. For example, the estimation device 100 calculates a higher credit rating when the user has purchased a health-related transaction target than when the user has not purchased a health-related transaction target. For example, the estimation device 100 calculates the credit rating of the user to a value "10" higher when the user purchases the "exercise equipment".

For example, a predetermined type of behavior performed by a target user whose credit rating is to be estimated using a model that learns the relationship between a user's creditworthiness and a predetermined type of behavior among the behaviors performed by the user. An example of estimating the creditworthiness of the target user from the above will be described. In this case, in the example of FIG. 1, the estimation device 100 uses a conventional technique such as machine learning to provide information on a credit score indicating the credit of the user as an example of the creditworthiness of the user, and an action related to self-management of the user. Learn the relationship with.

For example, in the example of FIG. 1, the estimation device 100 learns the relationship between the information regarding the score indicating the credit of the user and the presence / absence of activation of the reservation management application. For example, when the score indicating the credit of the user U1 who started the reservation management application is "0.9", the estimation device 100 makes a reservation with the score "0.9" indicating the credit of the user U1. Learn the relationship with the behavior that launched the management app. On the other hand, when the score indicating the credit of the user U2 who did not start the reservation management application is "0.3", the estimation device 100 reserves the score "0.3" indicating the credit of the user U2. Learn the relationship with behaviors that do not launch the management app.

For example, in the example of FIG. 1, the estimation device 100 learns the relationship between the information regarding the score indicating the credit of the user and the presence / absence of the request for redelivery. For example, when the score indicating the credit of the user U1 who requested the redelivery is "0.9", the estimation device 100 sets the score "0.9" indicating the credit of the user U1 and the redelivery. Learn the relationship with the behavior that requested. On the other hand, when the score indicating the credit of the user U2 who did not request the redelivery is "0.3", the estimation device 100 redelivers the score "0.3" indicating the credit of the user U2. Learn the relationship with the behavior that did not make the request.

For example, in the example of FIG. 1, the estimation device 100 learns the relationship between the information regarding the score indicating the credit of the user and the presence / absence of schedule management. For example, when the score indicating the credit of the user U1 who has performed the schedule management is "0.9", the estimation device 100 performs the schedule management with the score "0.9" indicating the credit of the user U1. Learn the relationship with the behavior. On the other hand, when the score indicating the credit of the user U2 who did not perform the schedule management is "0.3", the estimation device 100 performs the schedule management with the score "0.3" indicating the credit of the user U2. Learn the relationship with behaviors that did not exist.

In this way, the estimation device 100 learns the relationship between the information regarding the credit of the user and the behavior regarding the self-management of the user, and generates a model. Then, the estimation device 100 estimates the creditworthiness of the target user from the predetermined action performed by the target user using such a model.

The above model may be any model. For example, the estimation device 100 may learn, as a positive example, that the action of activating the reservation management application has a score of "1.0" indicating the credit of the user. On the other hand, for example, the estimation device 100 may learn, as a negative example, that the score indicating the credit of the user is "0.0" for the action in which the reservation management application is not started. In this way, the estimation device 100 may generate a model that learns the relationship between the creditworthiness of the user and the behavior of a predetermined type among the behaviors performed by the user. Then, the estimation device 100 may estimate the creditworthiness of the target user by using such a model.

Further, for example, the estimation device 100 may recalculate the weight of the model generated in the above embodiment according to the behavior related to self-management of the user whose credit rating is equal to or higher than a predetermined threshold value. For example, the estimation device 100 calculates the degree of contribution that contributes to the creditworthiness of the behavior related to schedule management and the behavior related to health management among the behaviors related to self-management of the user whose credit rating is equal to or higher than a predetermined threshold value. Then, the estimation device 100 recalculates the weight of the model from the relationship of each contribution. For example, in the estimation device 100, when the contribution corresponding to the behavior related to schedule management is equal to or higher than a predetermined threshold value and the contribution corresponding to the behavior related to health management is equal to or higher than the predetermined threshold value, the weight of the model becomes more reliable. Recalculate as follows. For example, in the estimation device 100, when the contribution corresponding to the behavior related to schedule management is less than the predetermined threshold value and the contribution corresponding to the behavior related to health management is equal to or more than the predetermined threshold value, the weight of the model becomes less reliable. Recalculate as follows.

For example, in the estimation device 100, when the contribution corresponding to the behavior related to schedule management is equal to or more than a predetermined threshold value and the contribution corresponding to the behavior related to health management is less than the predetermined threshold value, the weight of the model becomes less reliable. Recalculate as follows. For example, in the estimation device 100, when the contribution corresponding to the behavior related to schedule management is less than the predetermined threshold value and the contribution corresponding to the behavior related to health management is less than the predetermined threshold value, the weight of the model becomes less reliable. Recalculate as follows. Then, the estimation device 100 may estimate the creditworthiness of the target user by using the recalculated model.

Then, the estimation device 100 notifies the financial service providing server 30 of the creditworthiness of the user TU (step S6). For example, it is assumed that the credit rating of the user TU is "85". In this case, in the example of FIG. 1, the estimation device 100 notifies the financial service providing server 30 of the credit rating “85” of the user TU.

Subsequently, the financial service providing server 30 provides the user TU with a service according to the credit rating (step S7). For example, in the example of FIG. 1, the financial service providing server 30 provides a service related to a credit card application having a high limit when the credit rating is equal to or higher than a predetermined threshold. On the other hand, the financial service providing server 30 provides a service related to a credit card application having a low limit amount when the credit rating is less than a predetermined threshold value. The service provided by the financial service providing server 30 may be any service, for example, services related to loans, installment payments, insurance, stocks, financial products, and the like.

As described above, the estimation device 100 according to the embodiment identifies a predetermined action related to self-management among the actions performed by the user. The estimation device 100 estimates the creditworthiness of the user based on the identified behavior. As a result, the estimation device 100 according to the embodiment estimates the creditworthiness of the user based on the predetermined behavior related to self-management among the actions performed by the user, so that the estimation accuracy of the creditworthiness of the user is improved. can do.

This point will be described. Explaining using the example of FIG. 1, the estimation device 100 identifies the behavior related to self-management of the user TU, and uses a model that learns the relationship between the creditworthiness of other users and the behavior related to self-management. Estimate the creditworthiness of the user TU. In this way, the estimation device 100 focuses on behaviors that easily affect the user's own credibility, such as behaviors related to the user's self-management, and estimates the user's creditworthiness based on such behaviors, so that the user's creditworthiness Can be estimated with high accuracy. As a result, the estimation device 100 can encourage the user to provide appropriate financial services.

[2. Configuration of estimation system]
Next, the configuration of the estimation system according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of an estimation system according to an embodiment. As shown in FIG. 2, the estimation system includes a user terminal 10, a management service providing server 20, a financial service providing server 30, and an estimating device 100. The user terminal 10, the management service providing server 20, the financial service providing server 30, and the estimation device 100 are connected to each other via a network N so as to be communicable by wire or wirelessly. The estimation system shown in FIG. 2 includes a plurality of user terminals 10, a plurality of management service providing servers 20, a plurality of financial service providing servers 30, and a plurality of estimating devices 100. May be good.

The user terminal 10 according to the embodiment is an information processing device used by a user who accesses contents such as a web page displayed on a browser and contents for an application. For example, the user terminal 10 is a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), or the like.

The management service providing server 20 according to the embodiment is an information processing device that provides various services related to user self-management, and is realized by, for example, a server device or the like. For example, the management service providing server 20 provides a management service for the user to self-manage. For example, the management service providing server 20 provides a service for managing a user's schedule. Further, for example, the management service providing server 20 provides a service for managing the health of the user.

The service referred to here may be a service provided in any form of provision. For example, the service is a service provided on a web page displayed on a browser, a service provided by an application installed on a user terminal 10 used by a user, or the like.

The financial service providing server 30 according to the embodiment is a server device of a financial institution or the like, and is an information processing device that provides financial services to users or the like, and is realized by, for example, a server device or the like. For example, the financial service providing server 30 examines a loan, a credit card, an installment payment, etc. using the credit rating, and provides a service according to the examination result to the user.

The estimation device 100 according to the embodiment is realized by, for example, a server device or the like. Specifically, the estimation device 100 identifies a predetermined action related to self-management among the actions performed by the user. The estimation device 100 estimates the creditworthiness of the user based on the identified behavior.

[3. Configuration of estimation device]
Further, the configuration of the estimation device 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of the estimation device 100 according to the embodiment. As shown in FIG. 2, the estimation device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

(About communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 110 is connected to the network N by wire or wirelessly, and transmits / receives information between the user terminal 10, the management service providing server 20, and the financial service providing server 30.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. The storage unit 120 has a management behavior database 121 and a user database 122.

(About management behavior database 121)
The management behavior database 121 according to the embodiment stores information on management behavior, which is an behavior related to self-management, among the actions performed by the user. Here, FIG. 3 shows an example of the management behavior database 121 according to the embodiment. In the example shown in FIG. 3, the management action database 121 has items such as "user ID (Identifier)", "action type", "action content", and "date and time".

The "user ID" is an identifier that identifies a user. The "action type" is information indicating the type of management action associated with the "user ID". The "action content" is information indicating the content of the management action associated with the "user ID". The "date and time" is information related to the date and time when the management action is performed in association with the "user ID".

For example, in FIG. 3, the action type of "user # 1" identified by the user ID is "schedule management", the action content is "launch of the schedule management application", and the date and time is "date and time # 1". ". In the example shown in FIG. 3, the date and time are represented by an abstract code such as "date and time # 1", but the date and time may be a specific numerical value or the like.

(About user database 122)
The user database 122 according to the embodiment stores information about the user. Here, FIG. 4 shows an example of the user database 122 according to the embodiment. In the example shown in FIG. 4, the user database 122 has items such as "user ID", "user information", and "credibility".

The "user ID" is an identifier that identifies a user. The "user information" is information about the user associated with the "user ID". For example, the user information referred to here is attribute information or the like indicating the attributes of the user such as the gender and age of the user.

The "credit" is information about the credit associated with the "user ID". For example, in FIG. 4, the "user # 1" identified by the user ID has the user information "user information # 1" and the credit rating "85".

(About control unit 130)
The control unit 130 is a controller, and for example, various programs (as an example of an estimation program) stored in a storage device inside the estimation device 100 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. (Equivalent) is realized by executing RAM as a work area. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 2, the control unit 130 includes an acquisition unit 131, a specific unit 132, an estimation unit 133, and a provision unit 134, and realizes or executes an information processing function or operation described below. .. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 2, and may be another configuration as long as it is a configuration for performing 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 shown in FIG. 2, and may be another connection relationship.

(About acquisition unit 131)
The acquisition unit 131 acquires various types of information. Specifically, the acquisition unit 131 acquires information on self-management registered by the user from the management service providing server 20. Further, specifically, the acquisition unit 131 acquires behavior information, which is information on the behavior of the user, from the user terminal 10.

For example, an example in which the user TU registers the "scheduled consultation time of the dental clinic" using the management application AP will be described. In this case, the acquisition unit 131 acquires information regarding the "scheduled consultation time of the dental clinic" from the management service providing server 20.

For example, an example in which the user TU registers the "wake-up time" using the management application AP will be described. In this case, the acquisition unit 131 acquires information regarding the "wake-up time" from the management service providing server 20.

For example, in the example of FIG. 1, the acquisition unit 131 acquires the action information regarding the activation of the application of the user TU. Further, for example, in the example of FIG. 1, the acquisition unit 131 acquires information regarding communication regarding application and receipt regarding courier service as action information.

(About specific part 132)
The identification unit 132 identifies a predetermined action related to self-management among the actions performed by the user. Then, the specific unit 132 stores the specified action in the management action database 121. For example, the specific unit 132 specifies a predetermined type of action related to self-management as a predetermined action.

Specifically, the specific unit 132 specifies an action related to scheduled management as a predetermined action related to self-management. For example, the specific unit 132 specifies an action in which the user installs an application for managing the schedule on the user's terminal as an action related to schedule management.

For example, the specific unit 132 specifies an action in which the user registers a schedule in an application that manages the schedule as an action related to schedule management. For example, the specific unit 132 specifies an action in which the user purchases a transaction target for managing the schedule as an action related to schedule management.

Further, specifically, the specific unit 132 specifies an action of requesting redelivery of Takkyubin addressed to the user as a predetermined action related to self-management. Further, specifically, the specific unit 132 specifies an action for setting automatic distribution of received emails as a predetermined action related to self-management.

Further, specifically, the specific unit 132 specifies an action of reserving the use of a predetermined facility as a predetermined action related to self-management. Further, specifically, the specific unit 132 specifies an action for setting the delivery mode of the push notification to the user as a predetermined action for self-management.

Specifically, the specific unit 132 specifies an action of installing a disaster prevention-related application on a user's terminal as a predetermined action related to self-management. In addition, specifically, the specific unit 132 specifies an action related to the health management of the user as a predetermined action related to self-management.

For example, the identification unit 132 identifies an action of inputting a health-related search query as an action related to health management. For example, the specific unit 132 specifies an action of purchasing a health-related transaction target as an action related to health management.

For example, in the example of FIG. 1, the specific unit 132 specifies an action related to schedule management and an action related to health management as actions related to self-management among the actions taken by the user. For example, in the example of FIG. 1, the specific unit 132 specifies an action in which the user activates the schedule management application as an action related to schedule management.

For example, when the user activates the management application AP and registers that he / she will visit the dental clinic in the schedule managed by the management application AP, the specific unit 132 identifies the behavior in which the user activates the management application AP. For example, in the example of FIG. 1, the specific unit 132 specifies an action for which the user has requested redelivery as an action related to schedule management.

For example, in the example of FIG. 1, the specific unit 132 specifies an action in which the user has set the distribution of e-mails as an action related to schedule management. For example, when the user sets the distribution of e-mails in order to organize the e-mails received by the customer for each customer, the specific unit 132 specifies the behavior of the user who has set the distribution of the e-mails.

For example, in the example of FIG. 1, the specific unit 132 specifies the period from the reservation made by the user to the actual use by the user as an action related to schedule management. For example, in the specific unit 132, when the user makes a reservation for "Restaurant A" and the user visits "Restaurant A" two weeks after the reservation and uses it, the period from the reservation to the use is two weeks. To identify. For example, in the example of FIG. 1, the specific unit 132 specifies an action in which the user has set the management setting of the push notification as an action related to schedule management. For example, in the specific unit 132, when the user sets the push notification of the management application AP and sets the push notification to be performed when the preset schedule is approaching, the user sets the management setting of the push notification. Identify the behavior you have taken. For example, in the example of FIG. 1, the estimation device 100 identifies an action in which the user activates the disaster prevention application as an action related to schedule management. For example, the estimation device 100 identifies the behavior in which the user activates the management application AP when the user activates the management application AP and sets to automatically notify the family of the whereabouts at the time of disaster prevention.

For example, in the example of FIG. 1, the specific unit 132 specifies an action in which the user activates the disaster prevention application as an action related to health management. For example, when the user activates the management application AP and sets to automatically notify the family of the whereabouts at the time of disaster prevention, the specific unit 132 specifies the behavior in which the user activates the management application AP. For example, in the example of FIG. 1, the specific unit 132 identifies an action in which a user inputs a health-related search query as an action related to health management. For example, when the user inputs a search query such as "muscle training method", the specific unit 132 identifies an action in which the user inputs "muscle training method" as a search query. For example, in the example of FIG. 1, the specific unit 132 specifies an action in which a user purchases a health management transaction target as an action related to health management. For example, the specific unit 132 identifies the behavior of the user who purchased the "exercise article" when the user purchased the "exercise article".

For example, in the example of FIG. 1, the specific unit 132 specifies an action in which the user activates the health management application as an action related to health management. For example, when the user activates the management application AP and confirms the number of steps per day, the specific unit 132 identifies the behavior in which the user activates the management application AP. For example, in the example of FIG. 1, the specific unit 132 identifies a user's regular behavior as an behavior related to health management. For example, when the user sets the daily wake-up time and bedtime via the management application AP, the specific unit 132 wakes up at the set wake-up time and goes to bed at the set bedtime. Identify regular behavior.

(About estimation unit 133)
The estimation unit 133 estimates the creditworthiness of the user based on the behavior specified by the specific unit 132. Then, the estimation unit 133 stores the creditworthiness of the user in the user database 122. Specifically, the estimation unit 133 estimates the creditworthiness of the user based on whether or not the user manages himself / herself.

More specifically, the estimation unit 133 was performed by the target user to be the credit rating estimation target using a model that learned the relationship between the credit rating of the user and the predetermined action among the actions performed by the user. Estimate the creditworthiness of the target user from the prescribed behavior.

For example, the estimation unit 133 calculates a higher credit rating when the user has the application installed than when the user has not installed the application. For example, the estimation unit 133 calculates the credit rating of the user to a value "10" higher when the user installs the management application AP. For example, the estimation unit 133 calculates a higher credit rating when the user has registered the schedule than when the user has not registered the schedule. For example, when the user activates the management application AP and registers that he / she will visit the dental clinic in the schedule managed by the management application AP, the estimation unit 133 calculates the credit rating of the user to a value "10" higher.

For example, the estimation unit 133 calculates a higher credit rating when the user has purchased the transaction target than when the user has not purchased the transaction target. For example, the estimation unit 133 calculates the credit rating of the user to a value "10" higher when the user purchases the supplement as an example of the transaction target. For example, the estimation unit 133 calculates the credit rating of a value lower when the user requests the redelivery of TA-Q-BIN than when the user does not request the redelivery of TA-Q-BIN. For example, when the user requests the redelivery of TA-Q-BIN, the estimation unit 133 calculates the creditworthiness of the user to a value "10" higher.

For example, the estimation unit 133 calculates a higher credit rating when the user has set automatic mail sorting than when the user has not set automatic mail sorting. For example, the estimation unit 133 calculates the credit rating of the user to a value "10" higher when the automatic distribution setting of the e-mail is set in order to organize the e-mails received by the user for each customer. For example, when the period from the reservation for the use of the facility to the use of the facility exceeds a predetermined threshold value, the estimation unit 133 calculates a higher credit rating than when the period does not exceed the predetermined threshold value. For example, it is assumed that the predetermined threshold value is "1 week". In this case, the estimation unit 133 indicates that when the user reserves "Restaurant A" and the user visits "Restaurant A" two weeks after the reservation and uses it, the period from the reservation to the use. Is 2 weeks and exceeds a predetermined threshold value, so the credit rating of the user is calculated to be "10" higher.

For example, when the user has set the delivery mode of the push notification, the estimation unit 133 calculates a higher credit rating than when the delivery target of the push notification is not set. For example, when the user sets the push notification of the management application AP and sets the push notification to be performed when the preset schedule is approaching, the estimation unit 133 sets the credit rating of the user to a value "10" higher. Calculate to. For example, the estimation unit 133 calculates a higher credit rating when the user has installed the disaster prevention-related application than when the user has not installed the disaster prevention-related application.

For example, the estimation unit 133 calculates a higher credit rating when the user has entered a health-related search query than when the user has not entered a health-related search query. For example, when the user inputs a search query such as "muscle training method", the estimation unit 133 calculates the credit rating of the user to a value "10" higher. For example, the estimation unit 133 calculates a higher credit rating when the user has purchased a health-related transaction target than when the user has not purchased a health-related transaction target. For example, the estimation unit 133 calculates the credit rating of the user to a value "10" higher when the user purchases the "exercise article".

For example, a predetermined type of behavior performed by a target user whose credit rating is to be estimated using a model that learns the relationship between a user's creditworthiness and a predetermined type of behavior among the behaviors performed by the user. An example of estimating the creditworthiness of the target user from the above will be described. In this case, in the example of FIG. 1, the estimation unit 133 uses the conventional technology such as machine learning to obtain information on the score indicating the credit of the user as an example of the creditworthiness of the user and the behavior related to the self-management of the user. Learn the relationships between.

For example, in the example of FIG. 1, the estimation unit 133 learns the relationship between the information regarding the score indicating the credit of the user and whether or not the reservation management application is started. For example, when the score indicating the credit of the user U1 who started the reservation management application is "0.9", the estimation unit 133 sets the score "0.9" indicating the credit of the user U1 and makes a reservation. Learn the relationship with the behavior that launched the management app. On the other hand, when the score indicating the credit of the user U2 who did not start the reservation management application is "0.3", the estimation unit 133 sets the score "0.3" indicating the credit of the user U2 and makes a reservation. Learn the relationship with behaviors that do not launch the management app.

For example, in the example of FIG. 1, the estimation unit 133 learns the relationship between the information regarding the score indicating the credit of the user and the presence or absence of the request for redelivery. For example, when the score indicating the credit of the user U1 who requested the redelivery is "0.9", the estimation unit 133 sets the score "0.9" indicating the credit of the user U1 and the redelivery. Learn the relationship with the behavior that requested. On the other hand, when the score indicating the credit of the user U2 who did not request the redelivery is "0.3", the estimation unit 133 sets the score "0.3" indicating the credit of the user U2 and the redelivery. Learn the relationship with the behavior that did not make the request.

For example, in the example of FIG. 1, the estimation unit 133 learns the relationship between the information regarding the score indicating the credit of the user and the presence / absence of schedule management. For example, when the score indicating the credit of the user U1 who has performed the schedule management is "0.9", the estimation unit 133 manages the schedule with the score "0.9" indicating the credit of the user U1. Learn the relationship with the behavior. On the other hand, when the score indicating the credit of the user U2 who did not manage the schedule is "0.3", the estimation unit 133 manages the schedule with the score "0.3" indicating the credit of the user U2. Learn the relationship with behaviors that did not exist.

In this way, the estimation unit 133 learns the relationship between the information regarding the credit of the user and the behavior regarding the self-management of the user, and generates a model. Then, the estimation unit 133 estimates the creditworthiness of the target user from the predetermined action performed by the target user using such a model.

(About the provider 134)
The providing unit 134 provides various information. Specifically, the providing unit 134 notifies the financial service providing server 30 of the creditworthiness of the user. More specifically, the providing unit 134 refers to the user database 122 and notifies the financial service providing server 30 of the creditworthiness of the user. For example, it is assumed that the credit rating of the user TU is "85". In this case, in the example of FIG. 1, the providing unit 134 notifies the financial service providing server 30 of the credit rating “85” of the user TU.

[4. Processing procedure]
Next, the procedure of the estimation process executed by the estimation device 100 according to the embodiment will be described with reference to FIG. FIG. 5 is a flowchart showing an example of a flow of estimation processing executed by the estimation device 100 according to the embodiment.

As shown in FIG. 5, the acquisition unit 131 determines the estimation timing (step S101). Then, when the acquisition unit 131 does not determine the estimation timing (step S101; No), the acquisition unit 131 waits until the estimation timing is determined.

On the other hand, when the acquisition unit 131 determines that the timing is estimated (step S101; Yes), the specific unit 132 specifies an action related to self-management, which is an action executed by the user (step S102).

Then, the acquisition unit 131 acquires the user's behavior information (step S103). Then, the specific unit 132 specifies the action actually executed among the actions input by the user (step S104).

Then, the estimation unit 133 estimates the creditworthiness of the user according to whether or not there is an action related to self-management and whether or not the schedule is actually executed (step S105). Then, the providing unit 134 provides the credit rating to the server that provides the service based on the credit rating estimated by the estimating unit 133 to the user (step S106).

[5. Modification example]
The estimation device 100 described above may be implemented in various different forms other than the above embodiment. Therefore, another embodiment of the estimation device 100 will be described below.

[5-1. Estimating process (1) Estimating process based on regular life patterns]
In the above embodiment, the estimation device 100 has described an example of an estimation process for estimating the creditworthiness of the user based on a predetermined action related to self-management among the actions performed by the user. Not limited. Specifically, the estimation device 100 determines whether or not the user's life pattern is regular based on the specified behavior, and if the user's life pattern is regular, the life pattern is determined. May calculate a higher credit rating than if is not regular.

For example, an example will be described in which the user TU wakes up at 7 am and goes to bed at 11 pm, which is a regular life pattern. In this case, the estimation device 100 identifies the behavior related to the life pattern such as waking up at 7 am and going to bed at 11 pm among the behaviors of the user TU. Then, the estimation device 100 determines whether or not the specified life pattern is regular. For example, the estimation device 100 has a life pattern of the user TU, such as waking up at 7 am and going to bed at 11 pm, based on a predetermined criterion for determining behavior such as waking up at a predetermined time and going to bed as regular. Judge as regular. Then, the estimation device 100 may calculate the credit rating as a credit rating of "20" higher than that in the case where the life pattern is not regular.

As a result, the estimation device 100 according to the embodiment determines whether or not the user's life pattern is regular based on the specified behavior, and if the user's life pattern is regular, the estimation device 100 determines whether or not the user's life pattern is regular. Since the credit rating of a higher value is calculated than when the life pattern is not regular, the estimation accuracy of the credit rating of the user can be improved.

[5-2. Estimating process (2) Estimating process based on whether or not the schedule was actually executed]
In the above embodiment, the estimation device 100 has described an example of an estimation process for estimating the creditworthiness of the user based on a predetermined action related to self-management among the actions performed by the user. Not limited. Specifically, the estimation device 100 identifies an action for registering a future schedule and an action corresponding to the schedule as predetermined actions, and the user registers the schedule and performs an action corresponding to the schedule. If so, a higher credit rating may be calculated than if no action was taken in response to the schedule.

For example, an example in which a user TU registers "visiting a dental clinic" as a future plan and visits the dental clinic as scheduled will be described. In this case, the estimation device 100 identifies the behavior registered as "visiting the dental clinic" and the behavior corresponding to the schedule. Then, the estimation device 100 registers that the user TU "visits the dental clinic" and visits the dental clinic as scheduled, so that the credit rating is "20" compared to the case where the user does not take the action corresponding to the schedule. It may be calculated as a high credit rating.

As a result, the estimation device 100 according to the embodiment identifies an action for registering a future schedule and an action corresponding to the schedule as predetermined actions, and the user registers the schedule and acts corresponding to the schedule. When the above is performed, the credit rating of a higher value is calculated than when the action corresponding to the schedule is not performed, so that the estimation accuracy of the credit rating of the user can be improved.

[6. Hardware configuration]
Further, the user terminal 10, the management service providing server 20, the financial service providing server 30, and the estimation device 100 according to the above-described embodiment are realized by, for example, a computer 1000 having a configuration as shown in FIG. Hereinafter, the estimation device 100 will be described as an example. FIG. 6 is a hardware configuration diagram showing an example of a computer 1000 that realizes the function of the estimation device 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) Has 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program that depends on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via the network N and sends it to the CPU 1100, and the CPU 1100 transmits the data generated by the CPU 1100 via the network N to the other device.

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 the input device via the input / output interface 1600. Further, the CPU 1100 outputs the data generated via the input / output interface 1600 to the output device.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the 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 DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the estimation device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. Further, the data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the network N.

[7. Others]
Further, among the processes described in the above-described embodiments and modifications, all or part of the processes described as being automatically performed may be manually performed, or may be described as being manually performed. It is also possible to automatically perform all or part of the processed processing by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically distributed / physically in any unit according to various loads and usage conditions. It can be integrated and configured.

In addition, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not contradict each other.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the estimation unit can be read as an estimation means or an estimation circuit.

[8. effect〕
As described above, the estimation device 100 according to the embodiment has a specific unit 132 and an estimation unit 133. The identification unit 132 identifies a predetermined action related to self-management among the actions performed by the user. The estimation unit 133 estimates the creditworthiness of the user based on the behavior specified by the specific unit 132.

As a result, the estimation device 100 according to the embodiment estimates the creditworthiness of the user based on the predetermined behavior related to self-management among the actions performed by the user, so that the estimation accuracy of the creditworthiness of the user is improved. can do.

Further, in the estimation device 100 according to the embodiment, the estimation unit 133 estimates the creditworthiness of the user based on whether or not the user manages himself / herself.

As a result, the estimation device 100 according to the embodiment estimates the creditworthiness of the user based on whether or not the user is self-managing, so that the estimation accuracy of the creditworthiness of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the estimation unit 133 uses a model that learns the relationship between the creditworthiness of the user and a predetermined behavior among the behaviors performed by the user, and is a target for which the creditworthiness is estimated. The creditworthiness of the target user is estimated from the predetermined actions taken by the user.

As a result, the estimation device 100 according to the embodiment is performed by the target user whose credit rating is to be estimated by using a model that learns the relationship between the credit rating of the user and the predetermined action among the actions performed by the user. Since the creditworthiness of the target user is estimated from the predetermined behavior, the estimation accuracy of the creditworthiness of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action related to scheduled management as a predetermined action related to self-management.

As a result, the estimation device 100 according to the embodiment identifies the action related to the schedule management as a predetermined action related to self-management, so that the estimation accuracy of the creditworthiness of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action of installing an application for managing the schedule on the user's terminal as an action related to schedule management, and the estimation unit 133 indicates that the behavior is related to the schedule management. If the user has the application installed, a higher credit rating is calculated than if the user did not have the application installed.

As a result, the estimation device 100 according to the embodiment identifies an action in which the user installs an application for managing the schedule on the user's terminal as an action related to schedule management, and the user installs the application. In this case, since the credit rating of a higher value is calculated than when the user does not install the application, the estimation accuracy of the credit rating of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action of registering the schedule in the application for managing the schedule as an action related to the schedule management, and the estimation unit 133 is used by the user. When the schedule is registered, the credit rating of a higher value is calculated than when the user does not register the schedule.

As a result, the estimation device 100 according to the embodiment specifies an action for registering the schedule in the application for managing the schedule as an action related to the schedule management, and when the user registers the schedule, Since the credit rating of a higher value is calculated than when the user does not register the schedule, the estimation accuracy of the credit rating of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action for the user to purchase a transaction target for managing the schedule as an action related to the schedule management, and the estimation unit 133 is the user. Calculates a higher credit rating than if the user has not purchased the transaction target.

As a result, the estimation device 100 according to the embodiment specifies an action of the user to purchase a transaction target for managing the schedule as an action related to schedule management, and the user purchases the transaction target. Calculates the credit rating of a higher value than when the user does not purchase the transaction target, so that the estimation accuracy of the credit rating of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action of requesting the redelivery of TA-Q-BIN destined for the user as a predetermined action related to self-management, and the estimation unit 133 is the user. When requesting the redelivery of TA-Q-BIN, the credit rating is calculated to be lower than when the user has not requested the redelivery of TA-Q-BIN.

As a result, the estimation device 100 according to the embodiment identifies an action of requesting redelivery of TA-Q-BIN destined for the user as a predetermined action regarding self-management, and the user requests redelivery of TA-Q-BIN. In this case, since the credit rating of a lower value is calculated than when the user has not requested the redelivery of TA-Q-BIN, the estimation accuracy of the credit rating of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action for setting automatic distribution of received emails as a predetermined action related to self-management, and the estimation unit 133 allows the user to automatically distribute emails. When is set, the credit rating of a higher value is calculated than when the user does not set the automatic mail sorting.

As a result, the estimation device 100 according to the embodiment identifies an action for setting automatic distribution of received emails as a predetermined action related to self-management, and is used when the user has set automatic distribution of emails. Since the credit rating of a higher value is calculated than when the user does not set the automatic distribution of emails, the estimation accuracy of the credit rating of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action of reserving the use of a predetermined facility as a predetermined action related to self-management, and the estimation unit 133 reserves the use of the facility. When the period until the facility is used exceeds a predetermined threshold value, a higher credit rating than when the period does not exceed the predetermined threshold value is calculated.

As a result, the estimation device 100 according to the embodiment specifies the action of reserving the use of the predetermined facility as the predetermined action related to self-management, and the period from the reservation of the use of the facility to the use of the facility is predetermined. When the threshold value is exceeded, the credit rating of a higher value is calculated than when the period does not exceed the predetermined threshold value, so that the estimation accuracy of the credit rating of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action for setting the delivery mode of the push notification to the user as a predetermined action related to self-management, and the estimation unit 133 specifies the push notification by the user. When the delivery mode of is set, the credit rating of a higher value is calculated than when the delivery target of the push notification is not set.

As a result, the estimation device 100 according to the embodiment specifies an action for setting the delivery mode of the push notification to the user as a predetermined action related to self-management, and the user sets the delivery mode of the push notification. Calculates the credit rating of a higher value than when the push notification delivery target is not set, so that the estimation accuracy of the credit rating of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action of installing a disaster prevention-related application on the user's terminal as a predetermined action related to self-management, and the estimation unit 133 indicates that the user performs disaster prevention. When the related application is installed, the credit rating of a higher value is calculated than when the user does not install the disaster prevention related application.

As a result, the estimation device 100 according to the embodiment specifies an action of installing a disaster prevention-related application on the user's terminal as a predetermined action related to self-management, and when the user installs the disaster prevention-related application. Calculates a higher credit rating than when the user does not have a disaster prevention-related application installed, so that the estimation accuracy of the user's credit rating can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action related to the management of the user's health as a predetermined action related to self-management.

As a result, the estimation device 100 according to the embodiment identifies the behavior related to the management of the health of the user as a predetermined behavior related to self-management, so that the estimation accuracy of the credit rating of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action of inputting a health-related search query as an action related to health management, and the estimation unit 133 causes the user to make a health-related search query. If you do, it will calculate a higher credit rating than if you did not enter a health-related search query.

As a result, the estimation device 100 according to the embodiment identifies an action for inputting a health-related search query as an action related to health management, and when the user inputs a health-related search query, the health-related search query is input. Since the credit rating of a higher value is calculated than when the search query of is not entered, the estimation accuracy of the credit rating of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action of purchasing a health-related transaction target as an action related to health management, and the estimation unit 133 indicates that the user sets a health-related transaction target. If you are buying, calculate a higher credit rating than if you were not buying a health-related transaction.

As a result, the estimation device 100 according to the embodiment identifies the behavior of purchasing the health-related transaction target as the behavior related to health management, and when the user purchases the health-related transaction target, the health-related transaction target is purchased. Since the credit rating of a higher value is calculated than when the transaction target of is not purchased, the estimation accuracy of the credit rating of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the estimation unit 133 determines whether or not the user's life pattern is regular based on the behavior specified by the specific unit 132, and determines whether or not the user's life pattern is regular. If is regular, it calculates a higher credit rating than if the lifestyle pattern is not regular.

As a result, the estimation device 100 according to the embodiment determines whether or not the user's life pattern is regular based on the specified behavior, and if the user's life pattern is regular, the estimation device 100 determines whether or not the user's life pattern is regular. Since the credit rating of a higher value is calculated than when the life pattern is not regular, the estimation accuracy of the credit rating of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies an action for registering a future schedule and an action corresponding to the schedule as predetermined actions, and the estimation unit 133 allows the user to schedule the schedule. In addition to registering, if the action corresponding to the schedule is performed, the credit rating of a higher value is calculated than when the action corresponding to the schedule is not performed.

As a result, the estimation device 100 according to the embodiment identifies an action for registering a future schedule and an action corresponding to the schedule as predetermined actions, and the user registers the schedule and acts corresponding to the schedule. When the above is performed, the credit rating of a higher value is calculated than when the action corresponding to the schedule is not performed, so that the estimation accuracy of the credit rating of the user can be improved.

Further, in the estimation device 100 according to the embodiment, the specific unit 132 specifies a predetermined type of action related to self-management as a predetermined action.

As a result, the estimation device 100 according to the embodiment identifies a predetermined type of action related to self-management as a predetermined action, so that the estimation accuracy of the creditworthiness of the user can be improved.

Although some of the embodiments of the present application have been described in detail with reference to the drawings, these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to practice the present invention in other improved forms.

10 User terminal 20 Management service providing server 30 Financial service providing server 100 Estimating device 110 Communication unit 120 Storage unit 121 Management behavior database 122 User database 130 Control unit 131 Acquisition unit 132 Specific unit 133 Estimating unit 134 Providing unit N network

Claims (20)

Among the actions taken by the user, the specific part that identifies the predetermined action related to self-management,
An estimation device having an estimation unit that estimates the creditworthiness of the user based on the behavior specified by the specific unit. The estimation device according to claim 1, wherein the estimation unit estimates the creditworthiness of the user based on whether or not the user manages himself / herself. The estimation unit uses a model that learns the relationship between the creditworthiness of the user and the predetermined behavior among the actions performed by the user, and uses the predetermined action performed by the target user to be the credit rating estimation target. The estimation device according to claim 1 or 2, wherein the creditworthiness of the target user is estimated from the above. The estimation device according to any one of claims 1 to 3, wherein the specific unit specifies an action related to scheduled management as a predetermined action related to self-management. As an action related to the management of the schedule, the specific unit specifies an action in which the user installs an application for managing the schedule on the terminal of the user.
The estimation unit according to claim 4, wherein when the user has the application installed, the estimation unit calculates a higher credit rating than when the user does not have the application installed. Estimator. The specific unit identifies an action in which the user registers a schedule in an application that manages the schedule as an action related to the management of the schedule.
Claim 4 or 5 is characterized in that, when the user has registered the schedule, the estimation unit calculates a higher credit rating than when the user has not registered the schedule. The estimation device described in. As an action related to the management of the schedule, the specific unit identifies the behavior of the user to purchase a transaction target for managing the schedule.
4. The estimation unit is characterized in that when the user purchases the transaction target, the estimation unit calculates a higher credit rating than when the user does not purchase the transaction target. The estimator according to any one of 6 to 6. The specific unit identifies an action of requesting redelivery of Takkyubin addressed to the user as a predetermined action related to the self-management.
The estimation unit is characterized in that when the user requests the redelivery of the TA-Q-BIN, the credit rating is calculated to be lower than that when the user does not request the redelivery of the TA-Q-BIN. The estimation device according to any one of claims 1 to 7. The specific unit identifies an action for setting automatic distribution of received emails as a predetermined action related to the self-management.
The estimation unit is characterized in that when the user has set the automatic distribution of the mail, the credit rating of a higher value is calculated than when the user has not set the automatic distribution of the mail. The estimation device according to any one of claims 1 to 8. The specific unit specifies an action of reserving the use of a predetermined facility as a predetermined action related to the self-management.
When the period from the reservation for the use of the facility to the use of the facility exceeds a predetermined threshold value, the estimation unit calculates a higher credit rating than when the period does not exceed the predetermined threshold value. The estimation device according to any one of claims 1 to 9, wherein the estimation device. The specific unit specifies an action for setting a delivery mode of a push notification to the user as a predetermined action related to the self-management.
The claim is characterized in that when the user has set the delivery mode of the push notification, the estimation unit calculates a higher credit rating than when the delivery target of the push notification is not set. Item 4. The estimation device according to any one of Items 1 to 10. The specific unit specifies an action of installing a disaster prevention-related application on the user's terminal as a predetermined action related to the self-management.
The estimation unit is characterized in that when the user has the disaster prevention-related application installed, a higher credit rating is calculated than when the user has not installed the disaster prevention-related application. The estimation device according to any one of claims 1 to 11. The estimation device according to any one of claims 1 to 12, wherein the specific unit specifies an action related to health management of the user as a predetermined action related to the self-management. The specific unit identifies an action for inputting a health-related search query as an action related to the management of health.
The claim is characterized in that when the user inputs the health-related search query, the estimation unit calculates a higher credit rating than when the user does not input the health-related search query. Item 13. The estimation device according to item 13. The specific department identifies the behavior of purchasing a health-related transaction target as the behavior related to the management of health.
The claim is characterized in that when the user purchases the health-related transaction target, the estimation unit calculates a higher credit rating than when the user does not purchase the health-related transaction target. Item 13. The estimation device according to item 13. The estimation unit determines whether or not the life pattern of the user is regular based on the behavior specified by the specific unit, and if the user's life pattern is regular, the said unit. The estimation device according to any one of claims 1 to 15, characterized in that a credit rating of a higher value is calculated than when the life pattern is not regular. The specific unit identifies, as the predetermined action, an action of registering a future schedule and an action corresponding to the schedule.
When the user registers the schedule and takes an action corresponding to the schedule, the estimation unit calculates a higher credit rating than when the user does not perform the action corresponding to the schedule. The estimation device according to any one of claims 1 to 16. The estimation device according to any one of claims 1 to 17, wherein the specific unit specifies a predetermined type of action related to self-management as the predetermined action. The estimation method performed by the estimation device
Among the actions taken by the user, a specific process that identifies a predetermined action related to self-management, and
An estimation method including an estimation step of estimating the creditworthiness of the user based on the behavior specified by the specific process. Among the actions taken by the user, a specific procedure to identify a predetermined action related to self-management, and
An estimation program characterized by causing a computer to execute an estimation procedure for estimating the creditworthiness of the user based on the behavior specified by the specific procedure.

Images