Information processing apparatus, learning apparatus, information processing method, and program

Abstract

To more appropriately determine the notification target. 【Solution means】An acquisition unit that acquires the target information of a plurality of targets having debts, inputs each of the target information into a model, acquires each score regarding the payment output by the model, and refers to each of the scores of the targets and the magnitude of the debts, and a processing unit that determines a notification target to whom a payment request is to be notified from among the plurality of targets, and the model is a model that is learned to output a score regarding the repayment according to or not according to the actual repayment by the target after the first notification of the repayment of the debt when the target information of the target having the debt is input. An information processing apparatus.

Description

Technical Field

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

Background Art

[0002] Conventionally, there is known a collection business management system for managing the collection urging business for delinquent taxpayers, which includes collection procedure determination means for determining and executing a collection urging procedure for a delinquent taxpayer based on attribute data and delinquent status data of the delinquent taxpayer held in advance (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventionally, among a plurality of delinquent taxpayers, consideration has not been given to which delinquent taxpayer should be urged preferentially. For this reason, it has sometimes been impossible to determine an appropriate notification target.

[0005] The present invention has been made in consideration of such circumstances, and one of its objects is to provide an information processing apparatus, a learning apparatus, an information processing method, and a program that can more appropriately determine a notification target.

Means for Solving the Problems

[0006] One aspect of the present invention is an information processing apparatus including: an acquisition unit that acquires subject information of a plurality of subjects having debts; an input unit that inputs each of the subject information into a model and acquires a score regarding each payment output by the model; and a processing unit that refers to each of the scores of the subjects and the magnitudes of the debts and determines a notification target to whom a payment request is to be notified from among the plurality of subjects. When subject information of a subject having a debt is input, the model is a model learned to output a score regarding the repayment according to whether or not the subject actually repaid after a first notification of repayment of the debt.

Effect of the Invention

[0007] According to one aspect of the present invention, it is possible to provide an information processing apparatus, a learning apparatus, an information processing method, and a program capable of more appropriately determining a notification target.

Brief Description of the Drawings

[0008]

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

Figure 14

Embodiments for Carrying Out the Invention

[0009] Hereinafter, with reference to the drawings, embodiments of the information processing apparatus, learning apparatus, information processing method, and program of the present invention will be described. Various apparatuses such as "servers" that appear below and provide services to users or perform internal analysis may be realized by a decentralized group of apparatuses, and the operators of each apparatus may be different. Also, the holder of the hardware of the apparatus (provider of the cloud server) and the operator who actually operates the apparatus may be different. The application program and the settlement server cooperate to provide an electronic payment service. In the following description, the application program is referred to as a payment application. The electronic payment service is a service that supports the settlement related to the purchase of goods and services in a store. A store is, for example, a physical store (actual store) existing in the real space, but may also include a virtual store for e-commerce. The virtual store may include those provided by a party different from the operator of the electronic payment service. In that case, when making a purchase settlement in the virtual store, it may be controlled to transition to the interface screen of the electronic payment service. In the electronic payment service, a store is, for example, treated as belonging to a franchise (brand), and processing such as settlement when a purchase action is performed in the store is mainly carried out between the user and the franchise. Instead of this, processing such as settlement may be carried out between the user and the store.

[0010] [Electronic Payment Service] FIG. 1 is a diagram showing an example of the configuration of an electronic payment system that realizes an electronic payment service. The electronic payment service is realized centering around a payment server 100. The electronic payment system that realizes the electronic payment service includes, for example, one or more user terminal devices 10, one or more first store terminal devices 50, one or more second store terminal devices 70, a payment server 100, a card server 200, an information processing device 300, and a learning device 400. These devices communicate with each other via, for example, a network NW. The network NW includes, for example, the Internet, a LAN (Local Area Network), a wireless base station, a provider device, and the like. Some or all of the functional configurations included in the electronic payment system may be distributed among a plurality of devices in any form or integrated into any device.

[0011] [User terminal device] The user terminal device 10 is, for example, a portable terminal device such as a smartphone or a tablet terminal. The user terminal device 10 is a computer device having at least an optical reading function, a communication function, a display function, an input reception function, and a program execution function. In the following description, the configurations for realizing these functions are referred to as a camera, a communication device, a touch panel, a CPU (Central Processing Unit), etc., respectively. In the user terminal device 10, the payment application 20 is executed by a processor such as a CPU, and it operates to provide an electronic payment service to the user in cooperation with the payment server 100. The payment application 20 is installed in the user terminal device 10 from, for example, an application store, and controls a camera, a communication device, a touch panel, etc. A mini-application 30 that operates within the payment application 20 is installed in the user terminal device 10. The mini-application 30 provides services related to credit cards to the user in cooperation with the card server 200, for example.

[0012] [First store terminal device] The first store terminal device 50 is installed in a store, for example. The first store terminal device 50 is a computer device having at least a product price acquisition function, an optical reading function, a program execution function, and a communication function. The first store terminal device 50 includes a so-called POS (Point of Sale) device, and the product price acquisition function and the optical reading function may be realized by the POS device. The store code image 60 is placed in the store and is a code image such as a QR code (registered trademark) printed on a paper or plastic medium. Note that the store code image 60 may be displayed by a display placed in the store (which may be a display of a terminal device such as a smartphone).

[0013] [Second Store Terminal Device] The second store terminal device 70 is used by the operator of the franchise store. The second store terminal device 70 is a smartphone, a tablet terminal, a personal computer, or the like. In the second store terminal device 70, the interface 72 for the franchise store operates. The interface 72 for the franchise store may be an application for the franchise store or a browser. The interface 72 for the franchise store accepts settings of coupons, etc. by the operator of the franchise store and transmits them to the settlement server 100. The second store terminal device 70, which is a smartphone, has a function of displaying a code image corresponding to the store code image or reading the code image displayed by the user terminal device 10 by executing an application for the franchise store.

[0014] [Settlement Server] The settlement server 100 realizes electronic settlement based on the settlement information received from the user terminal device 10 or the first store terminal device 50. The first store terminal device 50 may include a POS device and a franchise store server. In that case, the settlement information is transmitted from the POS device to the settlement server 100 via the franchise store server. In the following description, this is not particularly distinguished, and it is assumed that the settlement information is transmitted from the first store terminal device 50.

[0015] FIG. 2 and FIG. 3 are sequence diagrams illustrating a general flow of electronic settlement. There may be two patterns, pattern 1 and pattern 2, in electronic settlement.

[0016] In the case of pattern 1 shown in FIG. 2 (hereinafter referred to as user scan), the user terminal device 10 in the state where the payment application 20 is activated decodes the store code image 60 by means of an optical reading function (S1). The store code image 60 contains information on the store URL (Uniform Resource Locator). This store URL is obtained by adding information capable of identifying the store to the domain of the electronic payment service, and is associated with the franchise store ID, store ID, etc. in the payment server 100 (described later). The payment application 20 transmits first payment information including the store URL and the account ID to the payment server 100 (S2). The payment server 100 searches for store information (described later) from the franchise store ID and store ID corresponding to the store URL, acquires information on the franchise store name and store name (S3), and transmits it to the payment application 20 (S4). The user inputs the payment amount into the user terminal device 10 on the screen where the franchise store name and store name are displayed (S5). Then, the user terminal device 10 generates second payment information including at least the payment amount and transmits it to the payment server 100 (S6). The payment server 100 performs an electronic payment based on the received second payment information (S7). Then, the payment server 100 transmits a payment completion notification (information for displaying a payment completion screen) to the payment application 20 (S8), and the payment application 20 displays a payment completion screen (S9). Note that when the store code image 60 is displayed by a display placed in the store, the store code image 60 may contain not only the store URL but also payment amount information. In this case, the procedure for the user to input the payment amount is omitted, and the payment amount information is included in the first payment information and transmitted to the payment server 100. Information on the franchise store name and store name may be included and displayed on the payment completion screen.

[0017] In the case of Pattern 2 shown in FIG. 3 (hereinafter referred to as store scan), when the payment application 20 is launched, when a payment operation is performed in the payment application 20, when the automatic update timing (for example, every minute) is reached, and at other timings, the payment application 20 sends a request to issue a one-time code to the payment server 100 (S11). The payment server 100 generates a one-time code (S12) and sends it to the payment application 20 (S13). The payment application 20 displays a code image such as a QR code or a barcode generated based on the one-time code (S14). The user holds (presents) the display surface of the user terminal device 10 in front of the first store terminal device 50, and the first store terminal device 50 decodes the code image by means of an optical reading function and acquires a one-time code or the like (S15). Then, the first store terminal device 50 generates payment information including a one-time code, a payment amount, a franchise store ID, a store ID, etc., and sends it to the payment server 100 (S16). The information on the payment amount has been acquired in advance by barcode reading, manual input, or the like. The payment server 100 identifies the user corresponding to the one-time code based on the received information and performs an electronic payment (S17). Then, the payment server 100 sends a payment completion notification to the payment application 20 (S18), and the payment application 20 displays a payment completion screen (S19).

[0018] Note that the electronic payment may be performed in only one of the above patterns. Also, the "account ID" described in FIG. 2 may be other information (for example, a telephone number) that can be used as identification information of the user. Further, in the store scan, the issuance of the one-time code may be omitted, and the payment application 20 may display a code image generated based on the user's account ID. In that case, instead of identifying the user corresponding to the one-time code, the payment server 100 identifies the user corresponding to the account ID.

[0019] [Functional Configuration of Payment Server] FIG. 4 is a configuration diagram of the settlement server 100. The settlement server 100 includes, for example, a communication unit 110, a content providing unit 120, a settlement processing unit 130, an information management unit 140, and a storage unit 170. Components other than the communication unit 110 and the storage unit 170 are realized, for example, by a hardware processor such as a CPU executing a program (software). Some or all of these components may be realized by hardware (including a circuit unit; circuitry) such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), GPU (Graphics Processing Unit), SOC (System On Chip), or may be realized by cooperation between software and hardware. The program may be stored in advance in a storage device (a storage device having a non-transitory storage medium) such as an HDD (Hard Disk Drive) or a flash memory, or may be stored in a removable storage medium (a non-transitory storage medium) such as a DVD or a CD-ROM, and may be installed in the storage device when the storage medium is mounted on a drive device.

[0020] The storage unit 170 is an HDD, a flash memory, a RAM (Random Access Memory), or the like. The storage unit 170 may be a NAS (Network Attached Storage) device accessible by the settlement server 100 via a network. Information such as user information 172, content information 174, and franchise / store information 176 is stored in the storage unit 170. A part of this information may be stored in the storage unit of the user terminal device 10. Details of each piece of information will be described later.

[0021] The communication unit 110 is a communication interface for connecting to the network NW. The communication unit 110 is, for example, a network interface card.

[0022] The content providing unit 120 has, for example, the function of a web server and provides information (content) for displaying various screens of the electronic payment service to the user terminal device 10. The content providing unit 120 appropriately reads necessary content from the content information 174 and provides it to the user terminal device 10. The user terminal device 10 receives various inputs by the user in a state where the content is reproduced by the payment application 20, and transmits the above-described payment information and the like to the payment server 100. The above content may be generated by the payment application 20. In this case, the content providing unit 120 provides information necessary for generating the content to the payment application 20.

[0023] The payment processing unit 130 performs payment processing based on the payment information transmitted by the user terminal device 10 or the first store terminal device 50. The payment processing unit 130 performs payment processing while referring to the user information 172.

[0024] [User Information] FIG. 5 is a diagram showing an example of the content of the user information 172. The user information 172 is an example of the user's registration information. The user information 172 includes, for example, a user URL, an account ID, a phone number, a password, as well as an email address, a user ID, name, address, date of birth, registration date, remaining charge amount, credit payment setting, credit payment limit, credit payment usage amount, available credit payment amount, payment method setting, bank account, credit card number, charge history information, payment history information, and other information that are associated. The user URL is used for money transfer processing between users. When newly registering for the electronic payment service, registration of a phone number and a password is required. The account ID is issued to the user by the payment server 100, and the user ID is an ID that the user can optionally set (not necessarily set). Similarly, the email address, and the name, address, and date of birth are also information that the user can optionally set (not necessarily set). The registration date is the date when the user registered for the electronic payment service (the date when the account was created). Hereinafter, an instance of the user (electronic payment account) in which these pieces of information are associated is referred to as an account.

[0025] The remaining recharge amount is information indicating the remaining amount of electronic money set by the user by remitting money to the account in advance. As means of remittance, there are remittance from an ATM (Automatic Teller Machine) of a designated operator (bank), remittance from a registered bank account, etc. The credit payment setting is information indicating whether the setting for enabling electronic payment by credit payment using the payment application 20 has been completed or not, and is set to either "completed" or "not completed". The credit payment limit is the limit amount of credit payment available per month, the credit payment used amount is the amount of credit payment already used in the current month, and the available credit payment amount is the amount of credit payment available in the current month obtained by subtracting the credit payment used amount from the credit payment limit. Although only one credit payment limit is shown in the figure, in reality, there are further upper limits per day, etc., and the lower of them may be set as the credit payment limit. Further details of the credit payment will be described later. The payment method setting is setting information indicating whether the user performs an electronic payment using the remaining recharge amount or a payment by credit payment at that time. Each of the bank account and the credit card number is information (account number, card number) of a bank account or a credit card number to which the electronic payment service can make a deposit. The recharge history information is the history of the user increasing the remaining recharge amount by remitting money to the electronic payment service in advance. The payment history information is information showing the breakdown of the payments made by the user (date and time, store ID of the store where the purchase action was performed, payment amount, payment method, etc.) for each payment.

[0026] [Merchant / Store Information] FIG. 6 is a diagram showing an example of the content of the merchant / store information 176. The merchant / store information 176 includes, for example, a first table 176A in which a merchant ID and a store ID are associated with a store URL, a second table 176B in which a merchant name and a sales amount (described above) are associated with the merchant ID, and a third table 176C in which a store name is associated with the store ID. In addition to these information, the merchant / store information 176 may include information such as the category of the merchant or store, the location of the store, and the payment pattern.

[0027] The information management unit 140 acquires information provided by other server devices and the card server 200. Based on the information acquired from the user terminal device 10 and the second store terminal device 70, the information management unit 140 manages the user information 172 and the franchise / store information 176. The information management unit 140 performs operations such as adding, editing, and deleting new records for the user information 172 and the franchise / store information 176.

[0028] [Electronic payment] When the settlement processing unit 130 acquires settlement information from the user terminal device 10 or the first store terminal device 50, it refers to the user information 172 to obtain the "settlement method setting" of the user. For users whose "settlement method setting" is set to "charge balance", the settlement processing unit 130 performs electronic payment as follows. The settlement processing unit 130 performs electronic payment, for example, by reducing the charge balance managed in association with the user ID and increasing the item value of the sales amount of the franchise. The item value of the sales amount of the franchise is not used as electronic money itself, and the amount corresponding to the item value of the sales amount is transferred to the bank account in a cycle according to the agreement between the franchise and the electronic payment service.

[0029] When the "settlement information" is set to "credit payment (credit payment using code information)" for the user, the settlement processing unit 130 performs electronic settlement as follows. Credit payment is a payment method through cooperation with a credit card company, which is a separate entity from the operator of the electronic payment service. The operator of the electronic payment service acts as the creditor and allows electronic payment that does not depend on the remaining recharge amount within the credit payment limit. In addition, in order to receive the credit payment service, it may be required to obtain a credit card provided by the operator of the electronic payment service. The amount used for credit payment is settled in one lump sum on the payment date of the following month, for example, by direct debit from a bank account. In this case, the settlement processing unit 130 performs provisional settlement by adding the settlement amount to the credit payment usage amount and subtracting the same amount from the available credit payment amount. At the end of the month, it performs the process of direct debiting the settlement for the current month to the payment date of the following month as described above, or requests the operator of the credit card company to perform the process. If the settlement amount exceeds the available credit payment amount at the time of provisional settlement, an error notification is returned to the settlement application 20.

[0030] [Card Server] The card server 200 provides services related to credit cards to the user terminal device 10 in cooperation with the settlement application 20 or the mini application 30. Hereinafter, it is assumed that the mini application 30 provides services related to credit cards. The card server 200, for example, displays various information such as the usage history of the credit card and information related to the usage fees of the credit card on the display unit of the user terminal device 10 according to the operations of the user on the mini application 30.

[0031] [Information Processing Device] FIG. 7 is a diagram showing an example of the functional configuration of the information processing apparatus 300. The information processing apparatus 300 includes, for example, an acquisition unit 310, a processing unit 320, and a storage unit 370. The components of the acquisition unit 310 and the processing unit 320 are realized, for example, by a hardware processor such as a CPU executing a program (software). Some or all of these components may be realized by hardware (including a circuit unit; circuitry) such as an LSI, an ASIC, an FPGA, a GPU, or an SOC, or may be realized by cooperation between software and hardware. The program may be stored in advance in a storage device (a storage device having a non-transitory storage medium) such as an HDD or a flash memory, or may be stored in a removable storage medium (a non-transitory storage medium) such as a DVD or a CD-ROM, and may be installed in the storage device when the storage medium is mounted on a drive device.

[0032] The storage unit 370 is an HDD, a flash memory, a RAM, or the like. The storage unit 370 may be a NAS device accessible by the information processing apparatus 300 via a network. The storage unit 370 stores input information 372, a first model 374, a second model 376, output result information 378, target person information 380, and the like. Information stored in the storage unit 370, such as one or both of the first model 374 and the second model 376, may be stored in a device different from the information processing apparatus 300. Hereinafter, when the first model 374 and the second model 376 are not distinguished, they may be referred to as a "model".

[0033] The acquisition unit 310 acquires target person information of a plurality of target persons having debts. The processing unit 320 inputs each of the target person information into the model, acquires each score regarding the payment output by the model, refers to each score of the target person and the amount of the debt, and determines a notification target person to whom a payment request is to be notified from among the plurality of target persons. Details of the processing of the acquisition unit 310 and the processing unit 320 will be described later.

[0034] [Learning device] The learning device 400 causes a model to learn using learning information. The learning device 400 generates, for example, a first model 374 and a second model 376, and provides the generated first model 374 and second model 376 to the information processing device 300. Details of the learning will be described later.

[0035] [Overview] The processing unit 320 of the information processing device 300 inputs each of the subject information of a plurality of subjects having debts into the model, and acquires a score regarding each payment output by the model. The processing unit 320 refers to the score of each subject and the amount of the debt, and determines a notification target to whom a payment request is to be notified from among the plurality of subjects.

[0036] Debts are debts incurred by using post-payment settlement for credit card use, financial services such as financing and cashing, etc. The use of a credit card may be the use of a credit card at a store, the use of a credit card on the WEB, or the use of credit payment for an electronic payment service. In the following description, it will be described as a debt due to post-payment settlement for credit card use.

[0037] The model is a model that is learned to output a score regarding whether or not the subject actually responded to the repayment after the first notification of the debt repayment when the subject information of the subject having the debt is input. One or both of the first model 374 and the second model 376 are examples of the "model".

[0038] The processing unit 320 determines a notification target from among the subjects based on the score (first score or second score) output by the model and the amount of the debt of the subject (the remaining creditor's rights of the administrator against the subject). Thereby, by using the model, it is possible to more appropriately determine the notification target. The processing unit 320 may use one model, or may use two models as follows.

[0039] The processing unit 320 inputs each of the subject information into the first model 374 and obtains the first score regarding each repayment output by the first model 374. The processing unit 320 inputs each of the subject information into the second model 376 and obtains the second score regarding each repayment output by the second model 376. The processing unit 320 determines the notification target using the first score and the second score.

[0040] The first model 374 is a model learned to output a score regarding whether the subject actually repaid or did not repay in response to the repayment after the first notification of debt repayment and before the second notification when the subject information of the subject is input.

[0041] The second model 376 is a model learned to output a score regarding whether the specific subject actually repaid or did not repay in response to the repayment after the second notification of debt repayment after the first notification when the specific subject information of the specific subject who did not actually repay after the first notification among the subjects whose subject information was used for learning the first model 374 is input. This will be specifically described below.

[0042] [Regarding notifications related to repayment] FIG. 8 is a diagram for explaining notifications related to repayment. The administrator sends one or more notifications as shown in FIG. 8 to the subjects who do not repay the debt to encourage the repayment payment. The administrator sends the first notification to the first notification target among the subjects. The first notification target is extracted using a model as described later. The first notification target is, for example, a subject for whom payment can be expected.

[0043] After the first notification, the second notification is sent to the second notification target who did not make a payment within the predetermined period. If the payment is not made even by this second notification, the administrator takes a predetermined action. The predetermined action is a proactive action for the second notification target to make a payment.

[0044] The above-mentioned first notice may be, for example, a notice of a pleading decision, and the second notice may be the delivery of a pleading from the court. The first notice may be a notice by phone, email, etc., and the second notice may be the same notice as the first notice, a different notice, or a more proactive notice (a notice that urges more actively) than the first notice. Also, instead of the first notice, a first action may be executed, and instead of the second notice, a second action may be executed. The action may be, for example, stopping a predetermined service or registering the situation of the target person in a database.

[0045] Here, it may be difficult to send the first notice to all of the target persons from the perspective of cost. Therefore, it is desirable to determine the first notice target persons so that the claims can be recovered efficiently. For example, it is desirable that the first notice target persons are those with a high possibility of repayment or those from whom a large amount of recoverable claims can be obtained. In order to appropriately extract the first notice target persons, the following processing is performed.

[0046] [Flowchart] FIG. 9 is a flowchart showing an example of the flow of processing executed by the information processing apparatus 300. First, the information processing apparatus 300 acquires the first score of each target person (S100). Next, the information processing apparatus 300 acquires the second score of each target person (S102). Next, the information processing apparatus 300 acquires the integrated score of each target person based on the first score and the second score of each target person (S104). Instead of the above processing, the processing from S100 to S104 may be performed for each target person.

[0047] Next, the information processing apparatus 300 generates output result information (details will be described later) using the integrated score (S106). Next, the information processing apparatus 300 determines the first notice target persons based on the output result information and the set criteria (S108). Thereby, the processing of one routine of this flowchart ends.

[0048] [Acquisition of the First Score, Second Score, and Integrated Score] FIG. 10 is a diagram for explaining the derivation of each score. The processing unit 320 of the information processing apparatus 300 inputs the input information 372 into the first model 374 and acquires the first score output by the first model 374. The processing unit 320 inputs the input information 372 into the second model 376 and acquires the second score output by the second model 376.

[0049] The processing unit 320 derives an integrated score based on the first score and the second score. The integrated score is a score obtained by statistically processing the first score and the second score. For example, it is a score obtained by adding the first score and the second score. In the statistical processing, the weight of the first score may be increased, or the weight of the second score may be increased.

[0050] The first score and the second score may be scores indicating the probability of making a payment. The integrated score may be obtained as follows. TS is the comprehensive score (the final payment probability), A is the first score, and B is the second score. TS = A + B(100 - A)

[0051] In this way, by using the first score and the second score, it is possible to more appropriately extract the notification target. For example, it is possible to expect to extract the person who makes a repayment by the first notification and the person who does not make a repayment by the first notification but makes a repayment by the second notification. Thereby, by using the first score and the second score, the overall repayment probability is improved.

[0052] [Input Information] FIG. 11 is a diagram for explaining the input information. The input information (target person information) includes one or more of attribute information, settlement information, creditor's right information, and related service information (related settlement information). The input information may be attribute information, settlement information, and creditor's right information, or may be information including related service information in addition to these information. The input information input into the first model 374 and the second model 376 may be the same information or may be partially different information.

[0053] (Attribute information) The attribute information includes, for example, one or more pieces of information among the age of the target person, gender, address, presence or absence of a telephone number, length of residence, length of contract, annual income, family classification, etc. The address is information (non-communication flag) indicating whether the address of the target person can be confirmed. The presence or absence of a telephone number is information indicating the presence or absence of a telephone at the home or workplace of the target person. The length of contract is the number of years of using the post-payment settlement service. The family classification is information indicating the family composition. The family classification is, for example, a family composition such as single or with dependents.

[0054] The settlement information includes, for example, one or more pieces of information among the settlement frequency of the post-payment settlement, settlement unit price, information of the affiliated store where the settlement was made, number of times of outstanding receivables due to the post-payment settlement, etc. The information of the affiliated store is the type of the affiliated store, the location of the affiliated store, etc.

[0055] The claim information includes, for example, one or more pieces of information among the claim balance, outstanding period, ribo information, cashing information, contact information, etc. The ribo information is the usage status of ribo payment such as the amount of ribo payment, the period of ribo payment, the monthly repayment amount, usage frequency, number of times of use, etc. The cashing information is the usage status of cashing such as the usage amount of cashing, the repayment period of cashing, the monthly repayment amount, usage frequency, number of times of use, etc. The contact information is information indicating whether contact has been made within a predetermined period.

[0056] The related service information is, for example, the usage status of the electronic payment service and the usage status of other services. The usage status of the electronic payment service is, for example, the usage status of electronic payment of the electronic payment service. The usage status of electronic payment is, for example, the usage status of electronic payment made using the payment app 20. The usage status is, for example, information on the usage date and time, information on the usage time zone, information on the affiliated store used, remittance information which is the usage status of the remittance service, operation information, usage amount of the electronic payment service, number of times of use, number of times of use of a predetermined type of affiliated store in the electronic payment service, usage frequency, etc.

[0057] The usage date and time is information such as whether it is a weekend usage or a weekday usage. The usage time zone is information indicating whether the time of use is late at night, early in the morning, or during the day. The information of the affiliated store is the type of the affiliated store, the location of the affiliated store, etc.

[0058] The usage status of the money transfer service is the usage status of the money transfer service provided by the payment app 20. The money transfer service is a service that allows a user who uses the payment app 20 to transfer money from the target person. The usage status of the money transfer service is information such as the amount, number of times, and time zone of the transfer.

[0059] The operation information is the information of the operation history of the target person operating the payment app 20. The operation information is, for example, the number of times and frequency of displaying the home screen of the payment app 20 on the display unit.

[0060] The related service information may be information such as the remaining charge amount included in the user information 172 in addition to (instead of) the above information, credit payment setting information, credit payment limit, credit payment usage amount, available credit payment amount, payment method setting information, charge history information, payment history information, etc. The related service information may further include information of the user managed by the service provided by the electronic payment service or the service provided within the electronic payment service.

[0061] By using the related service information, it is possible to extract a target person who is more likely to make a repayment. The actions and usage status of the target person in other services are correlated with the probability of making a repayment. Therefore, by using the related service information, it is possible to more appropriately determine the notification target person.

[0062] [Output result information] The processing unit 320 generates output result information 378 based on the integrated score and the remaining claim amount of the target person. FIG. 12 is a diagram showing an example of the output result information 378. The vertical axis in FIG. 12 is the integrated score, and the horizontal axis in FIG. 12 is the remaining claim amount. In the example of FIG. 12, the vertical axis and the horizontal axis are divided and represented within a predetermined range, but they may be represented continuously instead of by a range.

[0063] Although omitted in FIG. 12, the number of people belonging to the range is associated with and represented in the range. For example, for each combination of the comprehensive score and the remaining claim amount, the number of people belonging to that combination is associated with and represented.

[0064] [Determination of the First Notification Target Person] The processing unit 320 determines the first notification target person based on the output result information and the set criteria. In the example of FIG. 12, the target person included in the area AR is the first notification target person. For example, the processing unit 320 may determine the target person with an integrated score equal to or higher than the threshold as the first notification target person. For example, the processing unit 320 may determine the target person with an integrated score equal to or higher than the threshold and a remaining claim amount equal to or higher than a predetermined amount as the first notification target person. The processing unit 320 may determine the first notification target person such that the integrated score is equal to or higher than the threshold and the total remaining claim amount of the target persons with an integrated score equal to or higher than the threshold reaches a desired amount or more. In this case, the threshold is adjusted to satisfy the above. The settled first notification target persons are managed as target person information 380.

[0065] The processing unit 320 may, for example, determine the target persons of the preset number of persons to be the first notification target persons. The processing unit 320 may, for example, preferentially determine the target persons with a high integrated score as the first notification target persons. The processing unit 320 may, for example, determine the preset number of persons as the first notification target persons in descending order of the remaining claim amount among the target persons whose integrated score is equal to or higher than the threshold value. The processing unit 320 may, for example, determine the preset number of persons as the first notification target persons in descending order of the total score among the target persons whose remaining claim amount is equal to or higher than the threshold value. The processing unit 320 may, for example, on the premise of extracting the target persons of the preset number of persons whose integrated score is equal to or higher than the threshold value, extract the target persons so that the total remaining claim amount of the extracted target persons of the preset number is equal to or higher than the threshold value or is maximized.

[0066] The processing unit 320 may derive, for each target person, the score of the target person and the score corresponding to the size of the debt of the target person, and determine the notification target persons based on the derived score and the score corresponding to the size of the debt. For example, the processing unit 320 may derive a determination score based on the integrated score and the remaining claim amount, and determine the target persons based on the determination score. For example, a claim balance score is obtained for each remaining claim amount. The claim balance score may be a higher score as the remaining claim amount is larger. The claim balance score may be the highest score when the remaining claim amount is medium, and may be a score that decreases as the remaining claim amount decreases or increases.

[0067] The claim balance score may be a score obtained based on the history of actual payments after the first notification in the past. In this case, a claim balance score is set for each range of the remaining claim amount. The processing unit 320 may obtain the determination score by making the weight of the remaining claim amount smaller than the integrated score when deriving the determination score.

[0068] [Re - input to the model] After sending the first notice, the processing unit 320 may calculate the score (the first score, the second score, or the integrated score) again for the person who has not repaid within the set period. The processing unit 320 may calculate a determination score based on the calculated score or based on the calculated score and the remaining debt amount. For example, the processing unit 320 may decide to execute different actions for the person whose determination score meets the criteria and the person whose determination score does not meet the criteria. For example, it may be determined that for the person who meets the criteria, the first action is taken, and for the person who does not meet the criteria, the second action is taken. The second action is a communication (such as a phone call, an email, or a legal measure) that requests repayment more aggressively than the first action. The first action may be to take no action. Conversely, it may be determined that for the person who meets the criteria, the second action is taken, and for the person who does not meet the criteria, the first action is taken.

[0069] [Model Generation] The learning device 400 acquires the person information of a plurality of persons with debts, the presence or absence of repayment by the person, and information regarding the timing of repayment. The learning device 400 learns the person information of the person and the person information associated with repayment information indicating whether the person actually repaid or did not repay after the first notice of debt repayment, and generates a model learned to output a score corresponding to the repayment information of the person when the person information of the person is input. For example, when the person information of the person who has repaid is input, the model is generated to output a high score.

[0070] (Generation of the First Model) The learning device 400 learns the learning information in which the person information of the person and the repayment information indicating whether the person actually repaid or did not repay after the first notice of debt repayment and before the second notice after the first notice are associated, and generates the first model 374 learned to output a score corresponding to the repayment information of the person when the person information of the person is input.

[0071] FIG. 13 is a diagram for explaining the generation of the first model 374. The learning information is information in which the subject information and the correct answer information are associated. The subject information is input information associated with the past first notification target. The correct answer information is information indicating whether the first notification target made a payment or did not make a payment after the first notification. Making a payment after the first notification means making a payment within a predetermined period such as 30 days, 60 days, or 180 days. When the subject information is input, the learning device 400 learns the first model 374 so as to output a first score corresponding to the correct answer information associated with the subject information. For example, when the input information of a subject who has made a payment is input, the learning device 400 learns the first model 374 so as to output a high score, and when the input information of a subject who has not made a payment is input, the learning device 400 learns the first model 374 so as to output a low score.

[0072] As described above, the learning device 400 learns the first model 374 so as to generate the first model 374 that outputs a first score with high accuracy.

[0073] (Generation of the second model) The learning device 400 learns the subject information of the subjects who did not repay in response to the first notification among the subjects, and the subject information in which the repayment information indicating whether the subject actually repaid or did not repay in response to the second notification of debt repayment is associated, and when the subject information of the subject is input, generates a second model 376 that is learned to output a score corresponding to the repayment information of the subject.

[0074] FIG. 14 is a diagram for explaining the generation of the second model 376. The learning information is information in which the target person information and the correct answer information are associated. The target person information is input information associated with a past second notification target person. The correct answer information is information indicating whether the second notification target person made a payment after the second notification. Making a payment after the second notification means making a payment within a predetermined period such as 30 days, 60 days, or 180 days. When the target person information is input, the learning device 400 learns the second model 376 so as to output a second score corresponding to the correct answer information associated with the target person information. For example, when the input information of a person who made a payment is input, the learning device 400 learns the second model 376 so as to output a high score, and when the input information of a person who did not make a payment is input, the learning device 400 learns the second model 376 so as to output a low score.

[0075] As described above, the learning device 400 learns the second model 376 so as to generate the second model 376 that outputs a highly accurate second score.

[0076] Instead of outputting the first score, the first model 374 may be a model that outputs the number of days until a payment is made after the first notification. In this case, the correct data corresponding to the input information is the number of days until the target person who actually received the first notification makes a payment, and for the target person who did not make a payment, the number of days is unknown or infinite. The first model 374 learns to output the number of days until a payment is made according to the input information when the input information is input, and outputs the number of days until a payment is made according to the input information when the input information is input.

[0077] Instead of outputting the second score, the second model 376 may be a model that outputs the number of days until payment is made after the second notification. In this case, for the correct data corresponding to the input information, the number of days until the person who actually received the second notification makes a payment becomes the correct data, and for those who did not make a payment, the number of days becomes unknown or infinite. The second model 376 learns to output the number of days until a payment corresponding to the input information is made when the input information is input, and outputs the number of days until a payment corresponding to the input information is made when the input information is input.

[0078] For example, the administrator may refer to the number of days output by the above first model 374 or second model 376 and determine the day to take action after sending the first notification or the second notification. For example, take action (contact such as a phone call or email) after the number of days output by the first model 374 or second model 376 has elapsed. For example, since there is a high possibility of payment being made before the number of days output by the first model 374 or second model 376 has elapsed, the action is not executed until then, and by executing the action thereafter, the work can be carried out more efficiently.

[0079] According to the embodiment described above, the information processing apparatus 300 inputs each of the target person information of a plurality of target persons having debts into the model, obtains each score regarding payment output by the model, refers to each score of the target person and the amount of the debt, and determines the notification target person to whom the payment request is to be notified from among the plurality of target persons, so that the notification target person can be determined more appropriately.

[0080] As described above, the embodiments for implementing the present invention have been described using the embodiments, but the present invention is not limited to such embodiments at all, and various modifications and substitutions can be made without departing from the gist of the present invention.

Description of Reference Numerals

[0081] 10 User terminal device 20 Settlement application 100 Settlement server 120 Content Provision Unit 130 Payment Processing Unit 140 Information Management Unit 300 Information Processing Device 310 Acquisition Unit 320 Processing Unit 372 Input Information 374 First Model 376 Second Model 400 Learning Device

Claims

1. An acquisition unit that acquires target person information of a plurality of targets who have debts; Input each of the subject information into a model, and obtain a score for each deposit output by the model; Referencing the score and the size of the debt for each of the subjects, a processing unit for determining a notification recipient to notify of a deposit request from among the plurality of recipients; The model is trained to, when subject information of a subject who had a debt is input, output a score regarding the repayment, whether or not the subject actually repaid the debt after a first notice of repayment of the debt and before a second notice, The second notice is a notice regarding repayment of the debt to be notified to the target person if the target person does not respond to the repayment after the first notice, Information processing device.

2. An acquisition unit that acquires target person information of a plurality of targets who have debts; Input each of the subject information into a model, and obtain a score for each deposit output by the model; Referencing the score and the size of the debt for each of the subjects, a processing unit for determining a notification recipient to notify of a deposit request from among the plurality of recipients; The model is trained to receive subject information of a subject who had a debt, and to output a score regarding the repayment, whether the subject actually repaid the debt or not, after a first notice of repayment of the debt, The target information includes payment information related to the use of a physical credit card and related payment information in an electronic payment service different from the payment information related to the use of a physical credit card; Information processing device.

3. An acquisition unit that acquires target person information of a plurality of targets who have debts; Inputting each of the subject information into a first model, and obtaining a first score for each repayment output by the first model; Inputting each of the subject information into a second model, and obtaining a second score for each repayment output by the second model; Referencing the first score, the second score, and the size of the debt for each of the subjects; a processing unit for determining a notification recipient to notify of a deposit request from among the plurality of recipients; The second model is a model trained to output a score regarding whether the specific target actually responded to the repayment or not responded to the repayment after the second notification of the repayment of the debt after the first notification when specific target information of a specific target who did not actually repay after the first notification is input among the targets of the target information used for training the first model. Information processing device.

4. The first model is a model trained to output a score regarding the repayment, which is whether or not the subject actually complied with the repayment, after the first notice of repayment of the debt and before the second notice, when the subject's subject information is input. The information processing device according to claim 3 .

5. The input information which is the subject information is Including attribute information indicating the attributes of the subject, payment information regarding the subject's deferred payment, and debt information regarding the debt, The information processing device according to claim 4.

6. The input information, which is the target information and the specific target information, The information includes attribute information indicating the attributes of the subject, payment information regarding the deferred payment of the subject, and debt information regarding the debt, which are the same information; The information processing device according to claim 5 .

7. The deferred payment is payment information regarding the use of a physical credit card, The input information further includes related payment information for an electronic payment service other than the deferred payment service. The information processing device according to claim 6.

8. The related payment information includes one or more of information on the day of the week when the electronic payment service was used, information on the time of day, information indicating the usage status of a remittance service in the electronic payment service, information indicating the type of affiliated store that used the electronic payment service, and information indicating the operation history of a payment app used in the electronic payment service. The information processing device according to claim 7.

9. The processing unit derives the score of the target person and a score corresponding to the size of the debt of the target person for each of the target people, and determines a notification target person based on the derived score and the score corresponding to the size of the debt. The information processing device according to claim 1 .

10. comprising the first model and the second model; The information processing device according to claim 3 .

11. Acquire information on a plurality of subjects who have debts, and information on whether or not the subjects have made repayments and the timing of the repayments; learning learning information in which the subject's information is associated with repayment information indicating whether the subject actually responded to or did not respond to the repayment after a first notice of debt repayment and before a second notice following the first notice, and generating a first model trained to output a score according to the subject's repayment information when the subject's information is input; learning information in which subject information of the subjects who did not repay in response to the first notice is associated with repayment information indicating whether the subject actually repaid or did not repay after the second notice of debt repayment, and generating a second model trained to output a score according to the repayment information of the subject when the subject information of the subject is input; Learning device.

12. The computer Acquire target information of multiple targets who have debts, Input each of the subject information into a model, and obtain a score for each deposit output by the model; Referencing the score and the size of the debt for each of the subjects, determining a notification recipient to notify of a deposit request from among the plurality of recipients; The model is trained to, when subject information of a subject who had a debt is input, output a score regarding the repayment, whether or not the subject actually repaid the debt after a first notice of repayment of the debt and before a second notice, The second notice is a notice regarding repayment of the debt to be notified to the target person if the target person does not respond to the repayment after the first notice, Information processing methods.

13. On the computer, A process of acquiring target information of a plurality of targets having debts; inputting each of the subject information into a model and obtaining a score for each deposit output by the model; referencing the score and the size of the debt for each of the subjects; determining a notification recipient to notify of a deposit request from among the plurality of recipients; The model is trained to, when subject information of a subject who had a debt is input, output a score regarding the repayment, whether or not the subject actually repaid the debt after a first notice of repayment of the debt and before a second notice, The second notice is a notice regarding repayment of the debt to be notified to the target person if the target person does not respond to the repayment after the first notice, program.

14. The computer Acquire target information of multiple targets who have debts, Input each of the subject information into a model, and obtain a score for each deposit output by the model; Referencing the score and the size of the debt for each of the subjects, determining a notification recipient to notify of a deposit request from among the plurality of recipients; The model is trained to receive subject information of a subject who had a debt, and to output a score regarding the repayment, whether the subject actually repaid the debt or not, after a first notice of repayment of the debt, The target information includes payment information related to the use of a physical credit card and related payment information in an electronic payment service different from the payment information related to the use of a physical credit card; Information processing methods.

15. On the computer, A process of acquiring target information of a plurality of targets having debts; inputting each of the subject information into a model and obtaining a score for each deposit output by the model; referencing the score and the size of the debt for each of the subjects; determining a notification recipient to notify of a deposit request from among the plurality of recipients; The model is trained to receive subject information of a subject who had a debt, and to output a score regarding the repayment, whether the subject actually repaid the debt or not, after a first notice of repayment of the debt, The target information includes payment information related to the use of a physical credit card and related payment information in an electronic payment service different from the payment information related to the use of a physical credit card; program.

16. The computer Acquire target information of multiple targets who have debts, Inputting each of the subject information into a first model, and obtaining a first score for each repayment output by the first model; Inputting each of the subject information into a second model, and obtaining a second score for each repayment output by the second model; Referencing the first score, the second score, and the size of the debt for each of the subjects; determining a notification recipient to notify of a deposit request from among the plurality of recipients; The second model is a model trained to output a score regarding whether the specific target actually responded to the repayment or not responded to the repayment after the second notification of the repayment of the debt after the first notification when specific target information of a specific target who did not actually repay after the first notification is input among the targets of the target information used for training the first model. Information processing methods.

17. On the computer, A process of acquiring target information of a plurality of targets having debts; inputting each of the subject information into a first model and obtaining a first score for each repayment output by the first model; inputting each of the subject information into a second model and obtaining a second score for each repayment output by the second model; Referencing the first score, the second score, and the size of the debt for each of the subjects; determining a notification recipient to notify of a deposit request from among the plurality of recipients; The second model is a model trained to output a score regarding whether the specific target actually responded to the repayment or not responded to the repayment after the second notification of the repayment of the debt after the first notification when specific target information of a specific target who did not actually repay after the first notification is input among the targets of the target information used for training the first model. program.

Images