Information processing device and information processing method

Abstract

An information processing device according to one example comprises: an acquisition unit that acquires a first history pertaining to a history of inter-individual remittance in a payment service for performing payment; and an output unit that outputs information pertaining to a user who has relatively high influence pertaining to the payment in a community of the inter-individual remittance. The information processing device includes an evaluation unit that evaluates the influence of each user in the community by using the history and a machine-learning model.

Description

Information Processing Apparatus and Information Processing Method

[0001] The present invention relates to a technique for evaluating the influence regarding settlement.

[0002] In settlement services, techniques related to money transfer between individuals are known. For example, Patent Document 1 discloses an invention that grants privileges available in settlement services based on money transfer information and user information from a remitter user to a recipient user.

[0003] Japanese Patent No. 7460374

[0004] The invention described in Patent Document 1 did not identify users with influence within the community based on the history of money transfer between individuals in electronic payment services.

[0005] In contrast, the present invention provides an improved technique for identifying users with influence within a community in electronic payment services.

[0006] An information processing apparatus according to one aspect of the present disclosure includes an acquisition unit that acquires a first history regarding the history of money transfer between individuals in a settlement service that performs settlement, and an output unit that outputs information regarding a user having relatively high influence regarding the settlement within the community in the money transfer between individuals.

[0007] An information processing method according to another aspect of the present disclosure includes a step in which a computer acquires a first history regarding the history of money transfer between individuals in a settlement service that performs settlement, and a step in which the computer outputs information regarding a user having relatively high influence regarding the settlement within the community in the money transfer between individuals.

[0008] According to the present invention, it is possible to provide an improved technique for identifying users with influence within a community in electronic payment services.

[0009] A diagram illustrating the system configuration of an information processing system 1 according to one embodiment. A diagram illustrating the functional configuration of the information processing system 1. A diagram illustrating the hardware configuration of the information processing device 10. A sequence chart illustrating the method of sending money between users and the method of obtaining the first history in person-to-person money transfers. A diagram illustrating the money transfer database 1000. A sequence chart illustrating the method of identifying communities and influencers. A diagram illustrating the money transfer network 2000. A flowchart illustrating the method of identifying highly influential users using GNN. A diagram illustrating the payment database 3000. A flowchart illustrating the method of identifying influencers based on PageRank. A diagram illustrating the influencer database 4000.

[0010] 1. Diagram 1 illustrates the system configuration of an information processing system 1 according to one embodiment. In this example, the information processing system 1 (or simply referred to as the system) is a system for estimating the influence of a user on payments within a specific community in an electronic payment service. In this example, the electronic payment service is a service that allows users to make payments using electronic payment methods (e.g., QR code®, NFC touch, or carrier billing) from their own devices, and can be used, for example, on a smartphone with a dedicated application (or simply referred to as the "payment app") installed. In addition to various payments, the electronic payment service includes services related to money transfers between users, so-called person-to-person transfers. In this example, person-to-person transfers are a function for transferring electronic money, etc., between multiple users belonging to the electronic payment service, and are used, for example, for splitting bills for meals, settling travel expenses for multiple people, collecting money, sending remittances, or giving gifts. The community is a group of users identified based on person-to-person transfers, and includes, for example, friends, acquaintances, colleagues, or family. Influence is an indicator that represents the magnitude of the influence an individual user has on the community.

[0011] In person-to-person money transfers, when evaluating a user's influence on a community's payments, a simpler evaluation model could be considered: identifying key players (hereinafter referred to as "influencers") based on factors such as the number of edges (e.g., number of connections with other users) and the number of transfers made by the target user. In this example, influencers are likely to be individuals with discretion or ability regarding payments such as monetary transactions (e.g., popular among friends, group leaders, or company representatives). In other words, users who are active in person-to-person money transfers in electronic payment services are more likely to influence the total payment amount within their community than users who are not. Therefore, it is expected that promoting to identified influencers will be more cost-effective than conducting various marketing activities (e.g., sales promotions) targeting individual users within a community. Furthermore, the influence on payments can be estimated with higher accuracy by using machine learning models in addition to the above method. This invention provides the following system for identifying influential users within a community in an electronic payment service.

[0012] The information processing system 1 includes an information processing device 10, user terminals 20 (for example, user terminals 21, 22, or 23), and a management server 30. In this example, each component of the system is connected via a network 9 as shown in Figure 1. In this example, the network 9 is a computer network such as the Internet or a mobile network.

[0013] The information processing device 10 is an information processing device or server device in the information processing system 1. In this example, the information processing device 10 obtains the history of person-to-person transfers for each user in the payment service (an example of the first history) from the management server 30. The information processing device 10 identifies users (an example of influencers) who have a relatively high influence on payments within the community in person-to-person transfers. In this example, the information processing device 10 evaluates the influence of each user using the first history and a machine learning model. The machine learning model will be described later.

[0014] User terminal 20 is a terminal used by an end user (an example of a user) in an electronic payment service. User terminal 20 includes, for example, a smartphone, tablet, or personal computer. In this example, user terminal 20 has a dedicated application (or simply referred to as the application) related to the electronic payment service installed, and each user makes payments and person-to-person transfers through this application. User terminal 20 outputs various data related to the records of payments and person-to-person transfers made through the application to the management server 30. This data includes, for example, the first history of person-to-person transfers. When distinguishing between multiple user terminals 20, they are referred to as user terminal 21, user terminal 22, ..., and so on. In Figure 1, for example, user terminal 21 connects to user terminal 22 or user terminal 23 via network 9 and makes a transfer. The transfer screen displayed on user terminal 21 is an example of a UI (User Interface) for a user to make a transfer to another user.

[0015] The management server 30 is a server device that manages information about user behavior in the electronic payment service. In this example, the management server 30 obtains information from the user terminal 20, such as the history of person-to-person transfers, the history of payments, and information about the user. This information is stored as data in the management server 30's database and shared with the information processing device 10 via the network 9. The various types of data managed by the management server 30 will be described later.

[0016] Figure 2 is a diagram illustrating the functional configuration of the information processing system 1. In this embodiment, the information processing device 10 has functional blocks (or components) consisting of an acquisition unit 11, a identification unit 12, an evaluation unit 13, an output unit 14, a benefit granting unit 15, a storage unit 191, and a control unit 192. In this example, the storage unit 191 stores various data, programs, and software, including a database. In this example, the control unit 192 performs various controls.

[0017] The acquisition unit 11 acquires a first history of person-to-person money transfers in the payment service. In this example, the first history includes information such as the sending user, receiving user, transfer amount, and transfer date and time. The acquisition unit 11 acquires the first history, payment history, and user information from the management server 30.

[0018] The identification unit 12 identifies the community in person-to-person money transfers. The identification unit 12 identifies the community using the first history. In this example, the community is identified as a user group in which multiple users send money to each other. As a method for extracting the community, the identification unit 12 uses, for example, the Overlapping Graph Clustering (hereinafter referred to as "OGC") method. OGC is a clustering method used when a user as a node belongs to multiple clusters (i.e., communities). For example, if user A is involved in money transfers in two different communities, a friends group and a colleagues group, a graph structure can be considered in which both communities overlap with user A. In real-world relationships, it is common for users to belong to multiple communities in this way. In this example, the identification unit 12 calculates the participation rate, which represents the degree to which the user is involved in each community, and determines that the user belongs to a community in which the participation rate is greater than 0.

[0019] The evaluation unit 13 evaluates the influence of each user in the community using history and a machine learning model. In this example, the machine learning model is a model that has been trained to accept input with the first history as an explanatory variable and output an indicator showing the influence of the user on payments in the community (hereinafter referred to as "influence") as the target variable, and includes, for example, a GNN (Graph Neural Network). In this example, the evaluation unit 13 evaluates the influence of users from the growth prediction of payment amounts in the community using history and the GNN.

[0020] Furthermore, with respect to the evaluation unit 13, a machine learning model evaluates influence based on PageRank. In this example, PageRank is an algorithm for determining the importance of a target webpage when the relationship between citations and cited content on a webpage is replaced with nodes and links, and includes, for example, a method for estimating importance based on the number of citations. The evaluation unit 13 defines users as nodes and remittances as directed edges in a remittance network built based on the first history, and identifies high-value users within the community using the PageRank method.

[0021] The output unit 14 outputs information about users who have a relatively high influence on settlements within a community in person-to-person transfers. The output unit 14 obtains information about influencers for each community from the evaluation unit 13 and outputs it, for example, to the reward granting unit 15.

[0022] The reward granting unit 15 grants rewards to users whose influence meets predetermined conditions. These conditions include, for example, conditions related to a threshold set in advance for the degree of influence, and more specifically, conditions such as the degree of influence being higher than the threshold. The rewards are, for example, rewards related to payments and include coupons, points, discount vouchers, or various campaigns. The reward granting unit 15 grants rewards to influencers within the community. This is expected to increase the total payment amount for the community as a whole and is more cost-effective than conducting promotions for individual users.

[0023] Figure 3 illustrates the hardware configuration of the information processing device 10. Physically, the information processing device 10 is configured as a computer including a processor 101, memory 102, storage 103, communication device 104, input device (optional), display device (optional), and a bus connecting these. Each of these devices operates on power supplied from a battery (not shown). In the following description, the term "device" can be read as a circuit, device, unit, etc. The hardware configuration of the information processing device 10 may include one or more of the devices shown in Figure 3, or it may be configured without some of the devices. Alternatively, multiple devices with different enclosures may be connected via communication to constitute the information processing device 10.

[0024] Each function in the information processing device 10 is realized by loading predetermined software (programs) onto hardware such as the processor 101 and memory 102, which allows the processor 101 to perform calculations, control communication by the communication device 104, and control at least one of the reading and writing of data in the memory 102 and storage 103.

[0025] The processor 101 controls the entire computer, for example, by running the operating system. The processor 101 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. Also, for example, a baseband signal processing unit or a call processing unit may be implemented by the processor 101.

[0026] The processor 101 reads programs (program code), software modules, data, etc., from at least one of the storage 103 and the communication device 104 into the memory 102 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described later. Functional blocks of the information processing device 10 may be stored in the memory 102 and implemented by control programs that run on the processor 101. Various processes may be executed by one processor 101, or they may be executed simultaneously or sequentially by two or more processors 101. The processor 101 may be implemented by one or more chips. The program may also be transmitted to the information processing device 10 via a telecommunications line.

[0027] Memory 102 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. Memory 102 may also be called a register, cache, main memory, etc. Memory 102 can store executable programs (program code), software modules, etc., for carrying out the method according to this embodiment.

[0028] The storage 103 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. The storage 103 may also be called an auxiliary storage device.

[0029] The communication device 104 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc.

[0030] Each device, such as the processor 101 and memory 102, is connected by a bus for communicating information. The bus may be configured using a single bus, or different buses may be used for each device.

[0031] The information processing device 10 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by this hardware. For example, the processor 101 may be implemented using at least one of these hardware components.

[0032] In this example, the program stored in the storage 103 includes a program (hereinafter referred to as the "server program") that causes the computer to function as a server in the information processing system 1. When the processor 101 is executing the server program, the processor 101, memory 102, storage 103, and communication device 104 are examples of functional blocks for operating the information processing device 10. The processor 101 is an example of a specific unit 12, an evaluation unit 13, an output unit 14, a privilege granting unit 15, and a control unit 192. At least one of the memory 102 and the storage 103 is an example of a storage unit 191. The communication device 104 is an example of an acquisition unit 11 and an output unit 14.

[0033] Although a detailed explanation will be omitted, the user terminal 20 is a computer having a processor, memory, storage, communication device, display device, input device, and output device, specifically, for example, a smartphone, tablet terminal, or personal computer. In this example, the program stored in the storage of the user terminal 20 includes a program for causing the computer to function as a client in the information processing system 1 (hereinafter referred to as the "client program").

[0034] The management server 30 is a computer having a processor, memory, storage, and communication devices. In this example, the programs stored in the management server 30's storage include a program (hereinafter referred to as the "management server program") that causes the computer to function as a management server in the information processing system 1. The configuration of the information processing system 1 has now been described. Next, the operation of the information processing system 1 will be described.

[0035] 2. Operation 2-1. Method of sending money between users in person-to-person transfers and method of obtaining the first transaction history Figure 4 is a sequence chart illustrating the method of sending money between users in person-to-person transfers and the method of obtaining the first transaction history. Here, we will explain an example of the operation of processing related to person-to-person transfers in the information processing system 1. First, we will illustrate the case in which a sending user operating user terminal 21 sends electronic money or the like to a receiving user operating user terminal 22.

[0036] In step S101, the user terminal 21 receives data input from the user regarding the remittance. In this example, the user inputs the remittance method (e.g., by specifying via a partnered contact), the recipient (e.g., the owner of the user terminal 22), the amount to be remitted, and a message into the user terminal 21, following the various UIs presented by the dedicated application for the electronic payment service, the so-called "payment app".

[0037] In step S102, user terminal 21 sends electronic money to user terminal 22. The transfer is performed according to the user's input, and authentication and confirmation are also performed simultaneously. User terminal 21 updates the electronic money balance according to the transfer amount (i.e., reduces it). User terminal 21 records a timestamp at the time the transfer is confirmed, linked to the data entered by the user. This process is performed for data for each transaction, such as a transfer.

[0038] In step S103, user terminal 22 receives electronic money from user terminal 21 via network 9. At this time, user terminal 22 may notify the owner user that the money has been received. User terminal 22 updates (i.e., increases) the balance of the electronic money according to the amount received. User terminal 22 records a timestamp at the time the receipt is completed. At this time, user terminal 22 records the transaction data and the timestamp of receipt linked together.

[0039] In step S104, user terminal 21 obtains receipt confirmation from user terminal 22. Receipt confirmation includes information such as the recipient, the amount received, or the date and time of receipt. After obtaining receipt confirmation, user terminal 21 confirms the process related to updating the electronic money balance.

[0040] In step S105, the user terminal 21 updates the remittance history from steps S101 to S104. The history update includes confirming the transaction, updating the status, and reflecting various data. The following processes are initiated, for example, when the remittance history is updated.

[0041] In step S106, the user terminal 21 sends various data related to the remittance to the management server 30. This process is performed automatically when the remittance is completed, or it is performed periodically. In this example, the person-to-person remittance in steps S101 to S105 was described as being carried out by a direct (i.e., P2P) exchange from the sending terminal to the receiving terminal, but the transaction may also be carried out via the management server 30. In this case, the management server 30 may assign timestamps related to the remittance and receipt, and record various data in a database.

[0042] In step S107, the management server 30 records data related to person-to-person money transfers in its database. The database managed by the management server 30 will now be described.

[0043] FIG. 5 is a diagram illustrating a remittance database 1000. In this example, the remittance database 1000 includes a plurality of records regarding the history of person-to-person remittances. Each record corresponds to information for each remittance. Each record includes a remittance ID, remittance information, receiving information, remittance amount, and status. The remittance ID is unique identification information for each remittance. The remittance information is information regarding the remitter, and includes, for example, a timestamp indicating the remittance date and time and a remittance terminal indicating the remitter's terminal. The receiving information is information regarding the recipient, and includes, for example, a timestamp indicating the receiving date and time and a receiving terminal indicating the recipient's terminal. The remittance amount is the amount of electronic money sent by the remitter to the recipient. The status is a status indicating the progress of the remittance, and includes, for example, a status such as success or in progress. The management server 30 acquires the history regarding person-to-person remittances from the user terminal 20 and manages the data based on unique identifiers. Note that the management server 30 may cooperate with an existing database regarding an electronic payment service and update, for example, the balance of the electronic money held by the user according to the remittance history. The database for managing the balance may be aggregated and managed by the management server 30, or may be held dispersedly by the user terminal 20 or the network. In addition to the database regarding the balance, the management server 30 may hold a database regarding settlement or a database regarding the user individual. Also, these databases may be managed separately or may be managed integratively.

[0044] As described above, the information processing system 1 can perform remittances between users in person-to-person remittances and acquire the first history. Also, the information processing system 1 can acquire various data from the user terminal 20 and accumulate the data in the database.

[0045] 2-2. Method for Identifying Community and Influencer FIG. 6 is a sequence chart illustrating a method for identifying a community and an influencer. Here, an operation example of a method for identifying a community in person-to-person remittances and a user having a high influence regarding settlement within the community will be described. The following processing is started triggered by an instruction from a user of the system or automatic processing by a preset program.

[0046] In step S201, the information processing apparatus 10 makes various data requests to the management server 30 regarding person-to-person remittances. The requests include an output instruction regarding specific data or an instruction regarding database linkage. In this example, the information processing apparatus 10 requests the management server 30 to output the remittance history for person-to-person remittances for a specific period, for example, the most recent one year (for example, from September 1, 2023 to August 31, 2024) or up to three years at most.

[0047] In step S202, the management server 30 reads out the remittance history from the database. In this example, the management server 30 acquires various data from the database according to the request of the information processing apparatus 10.

[0048] In step S203, the management server 30 outputs the data read from the database to the information processing apparatus 10. In this example, the information processing apparatus 10 may acquire the data in any format, for example, a data format such as CSV.

[0049] In step S204, the information processing apparatus 10 identifies the community. The information processing apparatus 10 uses the OGC method based on the history data regarding person-to-person remittances. Here, the method for identifying the community will be described.

[0050] Figure 7 is a diagram illustrating a remittance network 2000. Figure 7 is an example of a diagram showing a network structure related to person-to-person remittances. In this example, the remittance network 2000 represents the connections between users based on the remittance history using nodes and edges, and has a cluster structure that includes community classification. Community C is the range of communities classified based on the OGC method. Node N is an identification object in the graph structure corresponding to a single user. Multiple nodes N are connected to each other using edges. Edges are represented as connecting lines that link nodes N together according to the remittance history. In this example, the information processing device 10 determines, for example, that a user of node N11 whose involvement rate with community C1 is greater than 0 belongs to community C1. Note that the outlines of community C1 and the nodes belonging to its group are represented by solid lines, and the outlines of community C2 and the nodes belonging to its group are represented by dotted lines. For node N121 whose involvement rate with both community C1 and community C2 is greater than 0, the information processing device 10 determines that node N121 belongs to both communities C. In this example, nodes that belong to both community C1 and community C2 are depicted using grayscale hatching. Note that the remittance network 2000 in Figure 7 represents a basic network structure and can be modified in any way. For example, metadata such as effective edges indicating the remittance direction, the total number of remittances and the total amount of remittances may be added, or other restrictions on communities may be set.

[0051] Returning to Figure 6, in step S205, the information processing device 10 evaluates the user using a machine learning model. In this example, the information processing device 10 implements a machine learning model that has been trained on training data to evaluate the influence of users belonging to the community on payments. Therefore, the following processes include processes based on the learning base of the machine learning model. Here, with respect to step S205, two different calculation methods using GNN and PageRank as machine learning models for calculating the degree of influence will be explained in detail. Which of the two methods described below to implement is decided, for example, by the operator of the information processing system 1.

[0052] Figure 8 is a flowchart illustrating a method for identifying influential users using GNN. The information processing device 10 performs the following processes to calculate the influence of users. In step S11, the information processing device 10 obtains the remittance history for a specific period. In this example, the information processing device 10 refers to the remittance database 1000 and obtains the remittance history between users for a specific period, for example, the most recent year (for example, from September 1, 2023 to August 31, 2024).

[0053] In step S12, the information processing device 10 identifies the community using OGC. In this example, the processing from steps S11 to S12 corresponds to the processing from steps S203 to S204. The information processing device 10 identifies the community in the remittance network 2000 and proceeds to the following steps.

[0054] In step S13, the information processing device 10 extracts users with high scores on the first indicator within the community. In this example, the first indicator is an indicator related to the importance of the graph structure of the remittance network 2000, and includes indicators defined as proximity centrality, degree centrality, betweenness centrality, or flow centrality, for example. The information processing device 10 identifies nodes (i.e., users) that play a central role in the community based on the remittance network 2000, such as nodes with many connections to other users or nodes that are close in distance from each other, effective edges indicating the direction or strength of remittances between users, and metadata indicating the amount of remittances aggregated for each remittance or each user. As an example, the information processing device 10 extracts top-ranking nodes in a cluster (e.g., above a certain threshold) as candidates for users with relatively high influence (hereinafter referred to as "influencer candidates"). Note that the extraction of influencer candidates according to the first indicator can be carried out using any method.

[0055] In step S14, the information processing device 10 calculates a growth forecast using GNN for the users extracted in step S13. In this example, the information processing device 10 works in cooperation with the management server 30 to obtain the payment history in the electronic payment service. The payment history will now be explained.

[0056] Figure 9 illustrates a payment database 3000. In this example, the payment database 3000 includes multiple records relating to the payment history in the electronic payment service. Each record corresponds to information for each payment on the terminal where the application is installed. Each record includes a transaction ID, transaction information, payment details, payment amount, and status. The transaction ID is unique identification information for each transaction in which payment is made, and includes, for example, an identifier assigned to the transaction data. The transaction information is information about the transaction, and includes, for example, a timestamp, payment terminal, and payment destination. The timestamp represents the date and time the payment was made, the payment terminal represents information about the user terminal 20 that made the payment using the payment function in the application, and the payment destination represents information about the location, such as a partner store, or store terminal, where the payment was made. The payment details are information about the content of the payment, and include, for example, order details, purchased goods, or service details. The payment amount is the amount of electronic money paid in the transaction. The status is a status indicating the transaction status. The management server 30 obtains the payment history from the user terminal 20 (or store terminal, etc.) and manages the data based on unique identifiers.

[0057] The information processing device 10 retrieves payment history from the management server 30 as needed. In this case, the information processing device 10 retrieves payment history for a specific period in the community including the identified top users, for example, the most recent year (September 1, 2023 to August 31, 2024, as described above). Here, the growth prediction using GNN is estimated, for example, based on the past payment history retrieved by the information processing device 10. In this example, the GNN is a machine learning model (hereinafter simply referred to as the "first machine learning model") that accepts time-series features (hereinafter simply referred to as "features") up to a reference point (for example, August 31, 2024) as input for each extracted influencer candidate user as explanatory variables, and outputs the total payment amount at a point later than the reference point for all users belonging to the community (for example, one month later, September 30, 2024) as the target variable. In this example, the features for each user are identified, for example, based on past payment history, and are used to estimate the boosting effect (an example of influence) on the total amount used by the payment app across the entire community.

[0058] In step S15, the information processing device 10 identifies the user whose prediction results improve the most in the first machine learning model as an influential user. In this example, the information processing device 10 outputs the prediction result to the first machine learning model as the target variable when the user's features (e.g., number of transactions or transaction amount) are increased by a certain amount for a point in time to be predicted (e.g., September 30, 2024). Alternatively, the information processing device 10 obtains the difference in the total transaction amount for the entire community before and after increasing the features of the target user as the target variable. In these cases, the information processing device 10 identifies the user whose value of the target variable improves the most as an influential user in the community, i.e., an influencer. The information processing device 10 repeatedly performs the above process for each community to identify influencers involved in the community's transaction growth.

[0059] In the above embodiment, we used as an example an explanation of outputting a target variable related to the settlement amount as a growth prediction using GNN, but this can be anything. For example, it could output growth predictions such as the number of people in the community (increase or decrease), or the total number of settlements in the entire community.

[0060] Based on the above, the information processing system 1 can identify influencers based on growth predictions using GNN. Furthermore, the information processing system 1 can extract key figures within a community based on the transaction history in person-to-person transfers. This allows the information processing system 1 to perform user evaluations in person-to-person transfers within electronic payment services. Next, a method for identifying influencers based on PageRank will be described.

[0061] Figure 10 is a flowchart illustrating a method for identifying influencers based on PageRank. In step S21, the information processing device 10 identifies a community using a predetermined method. This process corresponds to step S204 described above.

[0062] In step S22, the information processing device 10 extracts users with high scores on the second indicator within the community based on PageRank. Here, unlike the first indicator, the second indicator is calculated using a machine learning model that implements an algorithm related to PageRank. In this example, the information processing device 10 inputs a graph such as the remittance network 2000 as an explanatory variable into a machine learning model (hereinafter referred to as the "second machine learning model") that has been trained using existing information such as graph structures relating to citation relationships of web pages and the PageRank of each web page as training data. The second machine learning model outputs the second indicator for each user as the target variable, based on the perspective that the PageRank (i.e., the level of influence) is determined, for example, by whether or not the user is effectively connected to important nodes. The information processing device 10 extracts users with high scores on the second indicator as influencer candidates. The information processing device 10 may also decide that the users extracted at this point are influencers.

[0063] In step S23, the information processing device 10 identifies influential users in combination with the growth forecast regarding community payments as described in the flowchart of Figure 8. This allows the information processing device 10 to obtain forecasts of future fluctuations in payment amounts that potential influencers will have on the community, i.e., expected values ​​regarding sales.

[0064] Based on the above, the information processing system 1 can identify influencers based on PageRank. Furthermore, the information processing system 1 can evaluate the influence that influencers have on payments within the entire community.

[0065] Return to Figure 6. In step S206, the information processing device 10 identifies influencers based on the method described above. In this example, the information processing device 10 outputs information about influencers identified for each community to a database, linked with the estimated results regarding influence. Now, let's describe the database related to influencers.

[0066] Figure 11 illustrates an influencer database 4000. In this example, the influencer database 4000 includes multiple records for influencers in each community. Each record corresponds to the community-specific information identified in step S204. Each record includes a community ID, user information, growth forecast effect, rank, and remarks. The community ID is unique identification information for each community, including, for example, an identifier such as community C1 in the remittance network 2000. The user information is information about one or more users extracted as influencers, including, for example, rank, user, and user terminal. The rank represents the user's influence ranking within the target community, the user represents the user's individual identification information, and the user terminal represents information about the terminal owned by the user. The growth forecast effect is the expected increase in the total settlement amount of the community calculated by the influencer (an example of influence), including, for example, a numerical value of the amount that is expected to increase. The rank is an estimated degree of value (an example of influence) based on PageRank, and is ranked on an 11-point scale from 0 to 10. The notes section contains various information about the influencer. The ranking may also be determined based on a combination of factors, including growth prediction effect and rank.

[0067] Returning to Figure 6, in step S207, the information processing device 10 grants benefits to influencers identified based on the influencer database 4000. In this example, the information processing device 10 grants coupons or points via the user terminal 20 owned by the influencer. This is expected to promote the economic effects that influencers have on the community. In addition, the information processing device 10 may carry out various marketing activities for influencers. For example, the information processing device 10 may contact influencers via direct messages and carry out various public relations activities such as advertising services or promoting new products. Based on the influencer database 4000, the information processing device 10 can exclude users from the marketing measures if providing incentives such as benefits is not expected to have an effect on the entire community. This is expected to improve the ROI of marketing measures implemented only for influencers.

[0068] As a result, the information processing device 10 can identify influential users within the community of the electronic payment service. The information processing device 10 can provide benefits and conduct various marketing activities for influencers who demonstrate a high level of influence regarding payments. This is expected to yield more cost-effective results than conducting promotions for individual users.

[0069] 3. Modifications The present invention is not limited to the embodiments described above, and various modifications are possible. Several modifications are described below. Two or more of the matters described below may be combined and applied.

[0070] (1) Information Processing System 1 The hardware configuration and network configuration of the information processing system 1 are not limited to those exemplified in the embodiments. The information processing system 1 may have any hardware configuration and network configuration as long as it can realize the required functions. For example, multiple physical devices may cooperate to function as the information processing system 1. For example, at least a part of the functions of the management server 30 may be implemented in the information processing device 10. For example, the information processing device 10 may have functions related to the management server 30, such as managing a database for remittance, settlement, or user information. At least a part of the functions of the user terminal 20 may be implemented in the management server 30. For example, the management server 30 may have functions related to the user terminal 20, such as performing approval or recording of transactions such as remittance and settlement.

[0071] (2) Information Processing Device 10 Some of the functions of the information processing device 10 may be implemented on other servers. These servers may be, for example, physical servers or virtual servers (including so-called cloud servers). Furthermore, the correspondence between functional elements and hardware is not limited to those illustrated in the embodiments. For example, at least some of the functions described in the embodiments as being implemented on the information processing device 10 may be implemented on other devices or systems, or conversely, at least some of the functions described as being implemented on other devices or systems may be implemented on the information processing device 10. In this example, at least some of the information processing device 10 may be implemented on a user terminal 20 or a management server 30. For example, the user terminal 20 may acquire information on a specified influencer via an API and output it to the information processing device 10. This allows the information processing device 10 to grant benefits according to the user's situation. The management server 30 may also have a function to perform aggregation processing on various data performed by the information processing device 10.

[0072] (3) User terminal 20 The user terminal 20 is not limited to those illustrated in the embodiment. The user terminal 20 may perform the above-described processing using any display screen, input device, external device, or various UI. The user terminal 20 may implement any functions necessary for outputting various data or history to the management server 30. In this example, the user terminal 20 may perform approval of the remittance via the management server 30.

[0073] (4) Management Server 30 The management server 30 is not limited to those illustrated in the embodiment. The management server 30 may perform the above-described processing by any input device, external device, or various UI. The management server 30 may implement any functions necessary for recording and managing information related to the electronic payment service. In this example, the management server 30 may implement various analysis functions that can be used to identify influencers. The management server 30 may output analysis results based on various data to the information processing device 10.

[0074] (5) Method of sending money between users in person-to-person transfers and method of obtaining the first history The sequence chart shown in Figure 4 is merely an example of operation, and the operation of the information processing system 1 is not limited thereto. Some of the illustrated operations may be changed or omitted, the order may be changed, or new operations may be added. The processing related to steps S101 to S105 may be processes that are executed via the management server 30. In this case, the management server 30 may have central data processing functions such as approval of transfers and storage of transfer history. In this embodiment, the operation examples described above have been explained in relation to person-to-person transfers, but they may be replaced with processing related to electronic payments using a user terminal 20 in a store, etc. For example, in the information processing system 1, electronic payments using various payment methods (e.g., QR code (registered trademark)) may be made from the user terminal 21 to the store terminal. In addition, a function may be introduced in the information processing system 1 in which records related to payments are appropriately aggregated in the management server 30.

[0075] (6) Method for identifying communities and influencers The sequence chart shown in Figure 6 is merely an example of operation, and the operation of the information processing system 1 is not limited thereto. Some of the illustrated operations may be changed or omitted, the order may be changed, or new operations may be added. In step S204, the information processing device 10 may perform an identification method that takes into account the granularity of the community. In this example, the granularity of the community is determined based on the setting of priority according to the size of the community. For example, the information processing device 10 identifies communities by prioritizing clusters that are somewhat larger in size and have room for community expansion, such as friends or colleagues, over small communities identified as families. In addition, the information processing device 10 may determine the priority of communities according to a diversity score linked to the attribute information of the node (i.e., user).

[0076] (7) Method for Identifying Highly Influential Users by GNN The flowchart shown in Figure 8 is merely an example of operation, and the operation of the information processing system 1 is not limited thereto. Some of the illustrated operations may be changed or omitted, the order may be changed, or new operations may be added. In step S13, the information processing device 10 may extract users in any way. The information processing device 10 may identify top users by calculating a first indicator based on the graph structure in the remittance network 2000 as well as user attribute information. In step S14, the information processing device 10 may use any data for the variables given to the GNN. The GNN may output growth predictions based on past settlement data as well as settlement data that was traded only on the Web or only on specific e-commerce sites. In step S15, the information processing device 10 may evaluate influence and identify influencers in any way. The information processing device 10 may identify influencers by making a comprehensive determination based on indicators such as future settlement amounts, number of settlements, or community size.

[0077] (8) Method for identifying influencers based on PageRank The flowchart shown in Figure 10 is merely an example of operation, and the operation of the information processing system 1 is not limited thereto. Some of the illustrated operations may be changed or omitted, the order may be changed, or new operations may be added. In step S22, the information processing device 10 may calculate the second indicator in any way. The information processing device 10 may identify influencers based on the PageRank algorithm, specifically how many edges indicating the direction of remittance are concentrated (i.e., how much electronic money is concentrated in one user). This may be, for example, a user evaluation that targets only remittances above a threshold amount, excluding small remittances.

[0078] (9) Database (Data) The database (or the data itself) of the information processing system 1 shown in Figures 5, 7, 9, and 11 is not limited to those illustrated in the embodiment. Any data may be registered in the database in this example. The remittance database 1000 may record any data. For example, messages, tags, keywords, labels, or various metadata may be attached to the remittance information. The remittance network 2000 may have any graph structure. For example, a three-dimensional structure may be used. The settlement database 3000 may record any data. For example, it may include information about settlements on the Web. The influencer database 4000 may record any data. For example, data regarding whether or not benefits have been granted may be recorded for each user. The data recorded in these databases may be of any type, for example, text, images, graphs, or lists.

[0079] (10) Other programs executed by the processor 101 may be provided by downloading them via a network such as the Internet, or they may be provided recorded on a computer-readable non-temporary recording medium such as a DVD-ROM. Each processor may be, for example, a CPU, an MPU (Micro Processing Unit), or a GPU (Graphics Processing Unit).

[0080] The block diagrams used in the description of the above embodiments show functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may also be realized by combining software with the one or more of the above devices.

[0081] Functions include, but are not limited to, judgment, decision, determination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmission unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited.

[0082] For example, the information processing device 10 in one embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure.

[0083] Each aspect or embodiment described in this disclosure may be applied to at least one of the following: LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (new Radio), W-CDMA®, GSM®, CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi®), IEEE 802.16 (WiMAX®), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth®, and other appropriate systems, as well as next-generation systems extended based thereon. Furthermore, multiple systems may be applied in combination (for example, a combination of at least one of LTE and LTE-A with 5G).

[0084] The processing procedures, sequences, flowcharts, etc., of each aspect or embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements in an exemplary order and are not limited to the specific order presented.

[0085] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be sent to other devices.

[0086] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0087] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Therefore, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0088] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc., whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name. Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technologies (such as infrared or microwave), at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0089] The information, signals, etc., described herein may be represented using any of the following different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc., which may be referred to throughout the above description, may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof. Terms used herein and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meaning.

[0090] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information.

[0091] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0092] Any reference to elements using the designations “First,” “Second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to the First and Second elements do not imply that only two elements may be employed, or that the First element must precede the Second element in any way.

[0093] In the above-described configuration of each device, the term "part" may be replaced with "means," "circuit," "device," etc.

[0094] Where the terms “include,” “including,” and variations thereof are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0095] In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0096] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different."

[0097] 1... Information processing system, 10... Information processing device, 20... User terminal, 21... User terminal, 22... User terminal, 23... User terminal, 30... Management server, 9... Network, 11... Acquisition unit, 12... Identification unit, 13... Evaluation unit, 14... Output unit, 15... Reward granting unit, 191... Storage unit, 192... Control unit, 101... Processor, 102... Memory, 103... Storage, 104... Communication device, 1000... Remittance database, 2000... Remittance network, 3000... Settlement database, 4000... Influencer database, C... Community, N... Node

Claims

1. An information processing device having an acquisition unit that acquires a first history of person-to-person transfers in a payment service that performs payments, and an output unit that outputs information about users who have a relatively high influence on the payments within the community in the person-to-person transfers.

2. The information processing apparatus according to claim 1, further comprising an evaluation unit that evaluates the influence of each user in the community using the history and a machine learning model.

3. The information processing apparatus according to claim 2, wherein the machine learning model includes a GNN (Graph Neural Network).

4. The information processing apparatus according to claim 3, wherein the evaluation unit evaluates the influence of the user from a prediction of the growth of settlement amounts in the community using the history and the GNN.

5. The information processing apparatus according to claim 2, wherein the machine learning model evaluates the influence based on PageRank.

6. The information processing apparatus according to claim 1, further comprising a benefit granting unit that grants benefits to users whose influence meets predetermined conditions.

7. An information processing method comprising the steps of: obtaining a first history of person-to-person transfers in a payment service where a computer performs payments; and outputting information about users who have a relatively high influence on payments within the community in the person-to-person transfers.

Images