Information processing device, information processing method, and program

JP2026137265APending Publication Date: 2026-08-27SUMITOMO MITSUI CARD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2025023237
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2025-02-17
Publication Date
2026-08-27

AI Technical Summary

Benefits of technology

【0013】 本発明によれば、情報処理装置は、ユーザ及び加盟店のデジタルツインを利用してより適切なマーケティング施策を決定することができるため、ユーザ及び加盟店の特性に応じたパーソナライズレコメンドを実行できるようになる。また、情報処理装置は、データの詳細度がより高まったユーザデータを利用してサービスや商品のレコメンドをする際に、そのカード会員に対してレコメンドした詳細な理由を提供できるようになる。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026137265000001_ABST
    Figure 2026137265000001_ABST
Patent Text Reader

Abstract

Aligning the value that member stores provide to users with the needs of those users. [Solution] The information processing device stores a merchant profile that summarizes information about the merchant, a general customer profile that shows information about the user, and a merchant customer profile that shows information about the merchant and customer groups for each customer type of the merchant. The information processing device sends candidate scenarios generated based on the merchant customer profile and target customer list to the merchant, and when it receives a request from the merchant for the candidate scenarios, it generates candidate recommendations for customers from the merchant. The information processing device verifies whether the candidate recommendations are appropriate in light of the information in the merchant profile and the representative user's customer profile, generates the verified candidate recommendations as recommendations for users, and sends promotional notifications based on the user-provided recommendations approved by the merchant to the user terminals of users associated with the customer types included in the user-provided recommendations.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program. More specifically, the present invention relates to an information processing apparatus, an information processing method, and a program that construct digital twins of users and franchise stores and execute processes for matching the value (value proposition) provided by the franchise stores to users with the needs of the users.

Background Art

[0002] According to the Information and Communications in 2024 Edition, the household penetration rate of information and communication equipment in 2023 is 97.4% for "mobile terminals as a whole", and 90.6% for "smartphones", which is the majority of them. Therefore, companies can easily contact individuals via any digital means and have come to be able to acquire a vast amount of behavioral data, demographic data, purchase data, etc. regarding individuals.

[0003] The ratio of cashless payments has been increasing year by year. Along with this, the amount of cashless payment data held by credit card companies has become enormous. Therefore, the importance of integrating and analyzing various accumulated data has been increasing.

[0004] For example, credit card companies have used this data to provide multiple preferential information to card members and promote card usage in order to support the marketing of franchise stores, and have provided a system for this (Patent Document 1).

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

Summary of the Invention

[0006] In the technology described in Patent Document 1, while it was partially possible to provide preferential information (first preferential information) based on predetermined attribute information of cardholders, where the recipients were identified, the technology also provided mass-market preferential information (second preferential information) presented to all cardholders to cover the portion that could not be covered by the first type of preferential information. In the conventional technology, conventional segment analysis and attribute-based marketing measures did not adequately understand the cardholders who were the customers. As a result, merchants were forced to use customer information with low data detail, and were unable to execute marketing measures through appropriate channels and at appropriate times. Furthermore, even if customer behavior prediction data was available using various data, it could not be precisely linked to individual marketing measures.

[0007] Furthermore, even when it came to evaluating implemented marketing strategies, the effort, cost, and time involved in the evaluation process made it difficult to determine the optimal strategies. As a result, some marketing strategies compromised the customer experience, causing franchisees to struggle to acquire customers.

[0008] On the other hand, cardholders were unable to receive the information and services they wanted at the time they desired, forcing them to research and obtain information themselves, which was extremely time-consuming.

[0009] While some credit card companies offer data services to support merchant marketing using cashless payment data (Patent Document 2), many credit card companies perform subjective tasks in selecting promotional targets in their marketing support services. As a result, the number of merchants to whom data services can be provided is limited, it is difficult to consistently achieve results for merchants, and a lot of wasted effort is generated due to the subjective nature of the work. In other words, since much of the conventional analysis service is done manually, a lot of the work is done by people thinking and doing the work, and as the amount of data to be analyzed increases, productivity decreases and the scalability of the data service does not improve.

[0010] Therefore, there was a need for information processing devices, methods, and programs that could improve the accuracy of marketing when merchants conducted marketing activities targeting cardholders by combining accumulated cashless payment data, cardholder data, and merchant data. Furthermore, there was a need to move from traditional mass-market (broad segment) approaches to personalized user proposals by understanding the diverse service values ​​of merchants, building digital twin models of users and merchants using factual data and generative AI, and making value propositions that understand why users buy.

[0011] The present invention was made to solve these problems and aims to provide an information processing device, an information processing method, and a program that construct digital twins of users and affiliated stores in a medical record format, perform a process to determine marketing measures to be provided to users, and / or perform a process to match the value that affiliated stores provide to users with the needs of users. [Means for solving the problem]

[0012] To solve the above problems, the information processing device according to the present invention comprises a control unit and a storage unit, The aforementioned storage unit is A member store record storage unit that stores member store records containing information about member stores, A general-purpose customer record storage unit that stores a general-purpose customer record showing information about a user for one person and / or any group of people, A franchisee customer record storage unit that stores information about franchisee stores and customer group records for each type of customer of the franchisee, wherein the customer group records include information on general-purpose customer records for each type of customer who enjoys the service value of the franchisee, Equipped with, The control unit, The process involves generating candidate scenarios for the merchant based on the merchant customer records and target customer list, and transmitting the candidate scenarios to the merchant computer of the merchant in the interaction, wherein the target customer list includes customer record information for a representative user for each of the customer types. In response to receiving a request from the merchant computer regarding the candidate scenarios for merchant provision, the system generates recommendation candidates from the merchant to the customer based on the request, the candidate scenarios for merchant provision associated with the request, and the customer record information of the representative user. Based on the merchant's profile, the request, the candidate scenario for the merchant provided to the merchant associated with the request, the representative user's customer profile, and the candidate recommendation, the system verifies whether the candidate recommendation is appropriate in light of the information in the merchant's profile and the representative user's customer profile, and generates the verified candidate recommendation as a recommendation for the user. Transmitting the user-provided recommendations to the merchant's computer, Sending promotional notifications based on user-provided recommendations approved by the merchant to the user terminals of users associated with customer types included in the user-provided recommendations, It is configured to execute. [Effects of the Invention]

[0013] According to the present invention, the information processing device can determine more appropriate marketing measures by utilizing digital twins of users and merchants, thereby enabling personalized recommendations tailored to the characteristics of users and merchants. Furthermore, when the information processing device recommends services or products using user data with increased detail, it can provide the cardholder with detailed reasons for the recommendation.

[0014] By using the digital twins of users and franchise stores, the information processing device makes it easier for franchise stores to match the value provided to users with user needs. The information processing device can elaborate and enhance the reports on marketing measures for franchise stores.

Brief Description of Drawings

[0015] A detailed understanding of the embodiments disclosed in this specification can be obtained from the following description exemplified in relation to the accompanying drawings. [Figure 1] It is a configuration diagram of the entire system including the information processing device 10. [Figure 2] It is a system configuration diagram of the information processing device 10. [Figure 3] It is a flowchart for explaining the general customer medical record generation process. [Figure 4] It is a flowchart for explaining the franchise medical record and franchise tag information generation process. [Figure 5] It is a flowchart for explaining the user interaction execution process and the interaction content analysis process. [Figure 6] It is a flowchart for explaining the franchise interaction execution process and the target customer list generation process. [Figure 7] It is a flowchart for explaining the franchise interaction execution process and the customer promotion execution process. [Figure 8] It is a diagram showing an example of the general customer medical record 800. [Figure 9] It is a diagram showing an example of the franchise medical record 900. [Figure 10] It is a diagram showing an example of the franchise customer medical record 1000. [Figure 11] It is a diagram showing an example of the report 1100 for franchise stores.

Modes for Carrying Out the Invention

[0017] The information processing device 10 generates a general-purpose customer record for one customer (N1) based on user data and financial transaction data, and generates a predetermined number of general-purpose customer records (e.g., N100, N1000, etc.) for any group based on the information in the general-purpose customer record of N1.

[0018] The information processing device 10 generates a merchant's customer record and merchant tag information for the merchant based on the merchant data read from the merchant data storage unit 107 and information obtained from external sources such as the internet.

[0019] The information processing device 10 can interact with the user through an AI chatbot program, conduct various promotions for the user, and update the user's general customer record and affiliate store record based on the results of the user interaction.

[0020] The information processing device 10 interacts with the merchant through an AI chatbot program to generate customer group profiles (merchant customer profiles) for each customer type for the merchant. The information processing device 10 obtains customer characteristic tags of users based on financial transaction data of users who actually use the merchant, identifies user clusters for each customer type based on the obtained customer characteristic tags and the merchant customer profiles, and refines the merchant customer profiles by adding information of the identified user clusters to the merchant customer profiles. The information processing device 10 generates customer profiles for representative users for each customer type of the refined merchant customer profiles, and generates a target customer list that includes the information of the representative users' customer profiles.

[0021] The information processing device 10 interacts with the merchant through an AI chatbot program to generate candidate scenarios for the merchant based on the merchant's customer records and target customer list, and provides them to the merchant's computer 12. When the information processing device 10 receives a request for a candidate scenario from the merchant's computer 12, it generates candidate recommendations for the merchant to provide to its customers. The information processing device 10 can verify whether the generated candidate recommendations are appropriate in light of the merchant's records and the representative user's customer records. The information processing device 10 sends a promotional notification based on the candidate recommendations approved by the merchant to a user terminal 11 that has customer characteristic tags associated with the customer types included in the candidate recommendations. Based on the results of the promotional notification, the information processing device 10 updates the user information, customer characteristic tags, and psychographic data in the user data storage unit 106, as well as the general-purpose customer records (N1) in the general-purpose customer record storage unit 109, for users who have actually used the products or services.

[0022] The user terminal 11 may be any type of device capable of operating in a wireless environment (e.g., a smartphone, a tablet, etc.) and is not limited to any specific device. The user terminal 11 can send and receive various data by communicating with the information processing device 10 via an AI agent (AI chatbot program) provided by the information processing device 10.

[0023] The merchant computer 12 may be any type of device capable of operating in a wired or wireless environment (e.g., a PC, tablet terminal, etc.) and is not limited to any specific device. The merchant computer 12 can send and receive various data by communicating with the information processing device 10 via an AI agent (AI chatbot program) provided by the information processing device 10.

[0024] (System Configuration) Figure 2 is a system configuration diagram of an information processing device 10 according to an embodiment of the present invention. As shown in Figure 2, the information processing device 10 includes a control unit 101, a main memory unit 102, an auxiliary memory unit 103, an IF unit 104, and an output unit 105, which are interconnected by a bus 120 or the like, similar to a general computer. The information processing device 10 includes a user data storage unit 106, a merchant data storage unit 107, a financial transaction data storage unit 108, a general-purpose customer medical record storage unit 109, a merchant medical record storage unit 110, a scenario candidate list storage unit 111, a merchant customer medical record storage unit 112, and a merchant report storage unit 113, in the form of a file / database (DB).

[0025] The control unit 101, also known as the central processing unit (CPU), controls each component of the information processing device 10 and performs data calculations. It also reads various programs stored in the auxiliary storage unit 103 into the main memory unit 102 and executes them. The control unit 101 may also be a graphics processing unit (GPU) or a neural processing unit (NPU), and can perform high-performance inference tasks and other processing required by AI (artificial intelligence). The main memory unit 102, also known as main memory, stores various received data, computer-executable instructions, and data after calculation processing by those instructions. The auxiliary storage unit 103 is a storage device such as a hard disk drive (HDD) or solid-state drive (SSD), and is used for long-term storage of data and programs.

[0026] The embodiment shown in Figure 2 describes an embodiment in which the control unit 101, main memory unit 102, and auxiliary storage unit 103 are located inside the same computer. However, in other embodiments, the information processing device 10 can be configured to achieve parallel distributed processing by multiple computers by using multiple control units 101, main memory unit 102, and auxiliary storage unit 103. In another embodiment, it is also possible to set up multiple servers for the information processing device 10, and have multiple servers share a single auxiliary storage unit 103.

[0027] The IF unit 104 acts as an interface (IF) for sending and receiving data with other systems and devices, and also provides an interface for receiving various commands and input data (various masters, tables, etc.) from the system operator. The output unit 105 provides a display screen for displaying the processed data and printing means for printing the data.

[0028] The user data storage unit 106 stores user data related to the user. In this specification, the user is intended to be a credit card holder who may be a customer of the merchant, but is not limited to credit card holders. User data may include, but is not limited to, the user's card information, the user's demographic data, and the user's psychographic data. In the embodiments described herein, "card" is used as an example of a credit card, but "card" may include any payment card other than a credit card, such as a prepaid card, debit card, or electronic money, or any point card.

[0029] In one embodiment of the present invention, the user data storage unit 106 may include, but is not limited to, user ID, user information, card information, customer characteristic tags, demographic data, and psychographic data. For example, the user data stored in the user data storage unit 106 may have information indicating the point in time the data is from, and after a data update, it may have both the user data before the update and the user data after the update. The user data storage unit 106 may include information from a questionnaire conducted at any time. In the present invention, since the questionnaire can be created based on the contents of a general-purpose customer record or the user's past transaction history, the information processing device 10 can generate questionnaires with different content for each user. The questionnaire can be conducted while the information processing device 10 is interacting with the user, or at a predetermined time, and is not particularly limited.

[0030] The data items included in the user data storage unit 106 are described below. The user ID is the identifier of the user. The user identifier may be a cardholder ID, card number, account number, etc. User information indicates information that the user provides to become a cardholder, such as the user's name, date of birth, and contact information. Card information indicates one or more card information associated with the user, for example, information such as the card number, expiration date, and security code of a credit card. Card information may also include bank account information, point card information, etc. Customer characteristic tags may be indicated by keywords that represent the user's persona, for example, the user's values, needs, and lifestyle. Demographic data indicates information that shows the demographic characteristics of the user, for example, information such as age, gender, occupation, residential area, family structure, and annual income. Psychographic data indicates information that shows the psychological characteristics of the user, for example, information such as personality, hobbies, preferences, values, and lifestyle.

[0031] Returning to Figure 2, the merchant data storage unit 107 stores merchant data related to the merchant. The merchant data may include, but is not limited to, the merchant ID, merchant information, merchant tag information, and merchant-related externally acquired information, and may also include other data items.

[0032] The merchant ID is an identifier for a merchant. A merchant refers to a store, facility, or e-commerce business that can provide specific services such as card payments by entering into a merchant agreement with a credit card company or the like. Merchant information indicates information about the merchant, such as the merchant's name, contact information, industry, and geographical area of ​​location. Merchant information may also include group information such as chain stores or collective information such as commercial and service facilities. Merchant tag information indicates the characteristics of the goods and services available at the merchant and is tag information generated by the information processing device 10 based on merchant data and information about the merchant obtained from the internet. Externally acquired merchant-related information is merchant-related information obtained about the merchant from an external source such as the internet. Merchant information obtained from the internet may be acquired in advance at any time, or it may be acquired when generating merchant tag information, and is not limited to this.

[0033] Returning to Figure 2, the financial transaction data storage unit 108 stores financial transaction data such as transaction history data for card payments associated with the user, usage data for cash advances, financial asset data such as deposits, and / or arbitrary point data. The financial transaction data includes user identification information (e.g., card number, account number, etc.).

[0034] The general-purpose customer record storage unit 109 stores a business-ready general-purpose customer record, i.e., document data summarizing information about the customer, generated by an arbitrary generative AI using the user data and financial transaction data of each user (N1). Figure 8 shows an example of a general-purpose customer record 800. The general-purpose customer record 800 can also be called a customer's digital twin record. The general-purpose customer record 800 can include, but is not limited to, information such as basic attributes, customer characteristic tags (user personas), consumption and value change trends, and interest mind maps. The general-purpose customer record is updated based on the content of conversations between the user and the AI ​​agent, daily settlement data, and the results of user surveys conducted at arbitrary times.

[0035] The general-purpose customer record storage unit 109 stores a general-purpose customer record for one customer (N1), and can also store general-purpose customer records for arbitrary groups generated based on the record information of a predetermined number of users (e.g., N10, N100, N1000, etc.). These arbitrary groups can be defined based on business purposes; for example, they may be groups of customers with identical user persona personalities indicated by customer characteristic tags in user data, or groups of customers with identical industry information in their card payment transaction history data for financial transactions. For example, the former group might be "urban working women," and the latter "convenience store users." These arbitrary groups may also be called representative users.

[0036] The merchant record storage unit 110 stores business-ready merchant record information, i.e., document data summarizing information about merchants, generated by an arbitrary generating AI using merchant data and information about the merchants obtained from the internet. The merchant record information may be associated with the information of one or more merchants. Multiple merchants may be grouped together in the same chain based on group information, or they may be grouped together by merchants located in a specific shopping center based on aggregate information. The merchant information obtained from the internet may be obtained in advance at any time, or it may be obtained when generating the merchant tag information, and is not limited to these.

[0037] Figure 9 shows an example of a Merchant Profile 900. The Merchant Profile 900 can also be called a merchant's digital twin profile. The Merchant Profile 900 is not limited to, but can include information such as basic attributes, service overview, a list of value provided to customers, what problems the merchant can solve and to whom, and what added value the merchant can provide. The Merchant Profile information is updated based on the content of conversations between the merchant and the AI ​​agent, the results of promotions conducted for users, etc. The Merchant Profile information may be associated with multiple user persona segments. For example, the Merchant Profile information may include the segment name, main demographic data (age), main characteristics of the segment, what customers look for in the target service, target user volume size (large / medium / small), estimated usage price, products / services, problem solutions, value creation, problems customers want to solve, customer concerns, and customer benefits.

[0038] The scenario candidate list storage unit 111 stores user-provided scenario candidates and merchant-provided scenario candidates generated by the generating AI. User-provided scenario candidates may be suggestions regarding the user's interests and desired products / services. Merchant-provided scenario candidates can be generated from detailed merchant-specific customer profiles and target customer lists.

[0039] The affiliated store customer record storage unit 112 stores affiliated store customer records, that is, affiliated store customer records that include information about the affiliated store as well as customer group records for each type of customer of the affiliated store. The customer group records include general customer records (detailed user information) for each type of customer who enjoys the service value of the affiliated store. A customer group includes at least one user. Figure 10 shows an example of an affiliated store customer record 1000. The affiliated store customer record 1000 may include information about the basic attributes of the affiliated store, customer types (user personas), etc.

[0040] The merchant report storage unit 113 stores analytical reports for merchants, which are generated based on merchant customer records and a predetermined number of general-purpose customer records associated with the customer types in the merchant customer records. The analytical reports may include, for example, information such as value propositions for each customer segment, including products and services, solutions to problems, and points of value creation, as well as customer profiles such as problems customers want to solve, customer concerns, and customer benefits.

[0041] (Processing flow: General-purpose customer medical record generation process) Figure 3 is a flowchart illustrating the general-purpose customer record generation process according to the present invention. This process flow illustrates an example of the process for generating a general-purpose customer record for one customer (N1), and an example of the process for generating a general-purpose customer record for an arbitrary group of customers.

[0042] In S301, the information processing device 10 receives a general-purpose customer medical record generation instruction. The general-purpose customer medical record generation instruction may be entered by the operator (administrator) of the information processing device 10, but may also be entered automatically by the information processing device 10 at a predetermined timing, and is not particularly limited.

[0043] In S302, the information processing device 10 selects a specific user and reads the user data of the selected user from the user data storage unit 106 and the financial transaction data of the selected user from the financial transaction data storage unit 108. Since the user data includes the user ID, the information processing device 10 can read the financial transaction data associated with that user ID.

[0044] In S303, the information processing device 10 merges the user data and financial transaction data read in S302 to generate primary aggregated data. The primary aggregated data is data that integrates the user data and financial transaction data of the selected user.

[0045] In S304, the information processing device 10 inputs the user's primary aggregated data into an arbitrary generation AI to generate a general-purpose customer medical record (N1) in a predetermined format as illustrated in Figure 8. The information processing device 10 stores the generated general-purpose customer medical record for the user in the general-purpose customer medical record storage unit 109.

[0046] The information processing device 10 performs the same processing as in S302 to S304 for other users, generates a general-purpose customer medical record for each user, and stores the generated general-purpose customer medical records in the general-purpose customer medical record storage unit 109.

[0047] In S305, the information processing device 10 reads N1 general-purpose customer records from multiple users and performs clustering to generate general-purpose customer records for arbitrary groups based on the information from N1 general-purpose customer records from multiple users. As is known to those skilled in the art, clustering is the process of classifying a dataset into several groups (also called "clusters") based on specific rules. The information processing device 10 may perform clustering on data that matches arbitrary conditions (e.g., residential area, gender, age group, etc.), or it may perform clustering to group general-purpose customer records of customers whose user persona personalities match, as indicated by customer characteristic tags in the user data. The classification conditions for the groups generated by clustering are not particularly limited. The information processing device 10 may limit the number of general-purpose customer record data included in a group to any number (e.g., N10, N100, N1000, ..., etc.).

[0048] In S306, the information processing device 10 receives a general-purpose customer record of any number of data points from any group of general-purpose customers generated by the generating AI, and stores the output result of the generating AI in the general-purpose customer record storage unit 109 as a general-purpose customer record of any group (also called a general-purpose customer record for a specific purpose). The general-purpose customer record of any group may be used as information that represents a typical customer profile.

[0049] (Processing flow: Generating merchant medical records and merchant tag information) Figure 4 is a flowchart illustrating the process for generating member store records and member store tag information according to the present invention. The following example describes how to generate member store records and member store tag information for a specific member store, but the information processing device 10 performs the same process for other member stores.

[0050] In S401, the information processing device 10 selects a specific merchant and reads the merchant data of the selected merchant from the merchant data storage unit 107. The information processing device 10 searches for information associated with the selected merchant from an external source such as the internet and stores the acquired information in the merchant data storage unit 107 as "merchant-related externally acquired information". The merchant-related externally acquired information for each merchant may be configured to be searched for from an external source such as the internet, downloaded, and stored at predetermined intervals.

[0051] In S402, the information processing device 10 generates merchant tag information based on the read merchant data and the merchant-related externally acquired information, and stores the merchant tag information of the selected merchant in the merchant data storage unit 107. The merchant tag information indicates and is not limited to the characteristics of the goods and services available at the merchant, but may be something like "#Credit card payment accepted", "#Health food store", or "#Fashion for people in their 20s".

[0052] In S403, the information processing device 10 inputs the read merchant data and the merchant-related externally acquired information into the generating AI, and stores the data output from the generating AI as a merchant profile 900, as exemplified in Figure 9, in the merchant profile storage unit 110. The merchant profile 900 may include information such as the merchant's basic attributes, service overview, value provided to customers, what problems and needs it can solve for whom, and what added value it can provide to whom.

[0053] (Processing flow: User interaction execution process and interaction content analysis process) Figure 5 is a flowchart illustrating the user dialogue execution process and dialogue content analysis process according to the present invention. This process flow illustrates an example in which a credit card member accesses the information processing device 10 via the user terminal 11 using their user ID, and receives product and service suggestions that meet their needs while interacting with an AI chatbot program. The AI ​​chatbot program is described as a program residing inside the information processing device 10, but it may be configured to reside on other devices or servers.

[0054] In S501, the information processing device 10 responds to a request from the user terminal 11 by activating an AI agent and initiating a dialogue with the user. The AI ​​agent is an AI chatbot program executed by the information processing device 10. The content of the chat (dialogue) may be determined by using various data stored in the information processing device 10 and through data exchange with the generating AI. The dialogue between the information processing device 10 and the user terminal 11 via the AI ​​agent can be conducted via voice or text.

[0055] In S502, the information processing device 10 queries the general-purpose customer medical record storage unit 109 based on the user ID of the user with whom it is having an interaction, and reads the general-purpose customer medical record (N1) of that user from the general-purpose customer medical record storage unit 109. The information processing device 10 queries the merchant data storage unit 107 and reads the merchant tag information from the merchant data storage unit 107.

[0056] In S503, the information processing device 10 passes the read general-purpose customer medical record and affiliate store tag information to the generation AI, receives user-provided scenario candidates generated by the generation AI, and stores them in the scenario candidate list storage unit 111. User-provided scenario candidates may be suggestions regarding the user's interests and desired products / services outlined in the dialogue. In other embodiments of the present invention, the information processing device 10 may be configured so that user-provided scenario candidates are generated in the S505 process, which is executed after receiving a request from the user.

[0057] In S504, the information processing device 10 determines whether it has received dialogue content from the user that includes a request. If the information processing device 10 has not received dialogue content from the user that includes a request and a predetermined number of dialogues have not taken place, it can ask a question to prompt the user to speak based on the content of a scenario candidate (for example, "Are you interested in ~?"), or it can ask a question based on the settlement details of the general customer record for the past month (for example, "You recently purchased XX, are you interested in YY?"). If it determines that a request has been received, the process proceeds to S505; on the other hand, if it determines that a request has not been received, the process proceeds to S508.

[0058] In S505, the information processing device 10 inputs the received requests and scenario candidates into the generating AI. The generating AI queries the merchant medical record storage unit 110 to read the merchant medical record information associated with the requests and scenario candidates, and generates recommendation candidates for merchants and users that match the requests and scenario candidates. The information processing device 10 receives the recommendation candidates for merchants and users that match the requests and scenario candidates.

[0059] In S506, the information processing device 10 inputs the received request and the candidate scenarios, along with the candidate recommendations for affiliated stores and users, and the user's general customer record, into the generating AI, and has the AI ​​verify whether the affiliated stores and candidate recommendations provided to the user are appropriate in light of the information in the general customer record. The information processing device 10 receives the affiliated stores and candidate recommendations verified by the generating AI. The verified candidate recommendations may simply be called "recommendations." Through this verification, the affiliated stores and candidate recommendations provided to the user are modified in light of the information in the general customer record, and ethically inappropriate expressions may also be corrected.

[0060] In S507, the information processing device 10 sends verified merchants and recommendations to the user terminal 11. The user then continues interacting with the AI ​​agent, and the process returns to S504.

[0061] If S508 determines that no request has been received from the user, for example, if a statement or signal indicating the end of the chat is received, the information processing device 10 calculates the CV (conversion) value for each of the requests, scenario candidates, affiliated stores and recommendations used in the dialogue between the user and the AI ​​agent, as well as the set of wording of the user's responses to the affiliated stores and recommendations. The calculation of the CV value may be performed by analyzing the wording of the user's responses, for example, the CV value may be determined based on the number of positive words, the number of negative words, etc. Weights may also be assigned to the positive and negative words, and the CV value may be determined based on those weights.

[0062] In S509, the information processing device 10 updates the general customer profile and merchant profile used in the dialogue based on the set of requests, scenario candidates, merchants and recommendations with relatively high CV values, as well as the user's response wording to the merchants and recommendations. The general customer profile can be updated with information such as which of the user's requests and scenario candidates were preferred and which were not, and which selling points of the merchant's recommendations the user was interested in. The merchant profile can be updated with information such as which customer characteristic tags (persona personalities) of users were interested in or not interested in the merchant's products and services.

[0063] Through such user interactions, the user's personality is understood, the general customer record and the merchant record are updated, and more personalized promotions can be implemented. During the interaction with the user, the information processing device 10 can also generate a questionnaire about a specific merchant's products or services based on the general customer record, past payment history, and spoken content, and have the user answer it. If there is any information such as coupons related to the products or services the user has selected during the interaction, the information processing device 10 can also suggest additional information to the user, such as coupons, and if the user requests it, it can also store the coupon information in the user data storage unit 106, linked to the user.

[0064] Next, with reference to Figures 6 and 7, the dialogue execution process between the information processing device 10 and the merchant computer 12 and the process of proposing promotions to customers will be described. The processing flow in Figures 6 and 7 illustrates an example in which a merchant accesses the information processing device 10 via the merchant computer 12 using their merchant ID and, while interacting with the AI ​​chatbot program, decides on promotions for potential customers. The AI ​​chatbot program is described as a program residing within the information processing device 10, but it may be configured to reside on other devices or servers.

[0065] (Processing flow: Merchant dialogue execution process and target customer list generation process) Figure 6 is a flowchart illustrating the merchant dialogue execution process and target customer list generation process according to the present invention.

[0066] In S601, the information processing device 10 responds to a request from the merchant computer 12 by activating the AI ​​agent and initiating a dialogue with the merchant computer 12. As described above, the AI ​​agent is an AI chatbot program executed by the information processing device 10. The content of the chat (dialogue) may be determined by using various data stored in the information processing device 10 and through the exchange of data with the generating AI. The dialogue between the information processing device 10 and the merchant computer 12 via the AI ​​agent can be conducted via voice or text.

[0067] In S602, the information processing device 10 queries the merchant record storage unit 110 based on the merchant ID of the merchant it is interacting with, and reads the merchant record from the merchant record storage unit 110. The information processing device 10 queries the financial transaction data storage unit 108 based on the merchant ID, and reads the financial transaction data related to the cashless payment made at the merchant.

[0068] The information processing device 10 inputs the read merchant customer records and financial transaction data into the generating AI, receives the merchant customer records generated by the generating AI, and stores them in the merchant customer record storage unit 112. The merchant customer record is a record information that redefines the merchant customer record from the perspective of customer type. The merchant customer record may include, but is not limited to, basic attributes of the merchant, one or more customer types (for example, urban workwomen, family-oriented housewives, etc.), main demographic data of the customer type, customer characteristics, types of distinctive services that are frequently used, what the customer type seeks in the products and services they are interested in, and values ​​that they consider important.

[0069] In S603, the information processing device 10 queries the user data storage unit 106 based on the user identification information contained in the financial transaction data read in S602 to read the customer characteristic tag. This provides information on the customer characteristic tags of users using the merchant with whom the interaction is taking place. Based on the merchant customer record and the customer characteristic tag, the information processing device 10 identifies user clusters for each customer type of the merchant. The user clusters can indicate how many users belong to each customer type. The information processing device 10 adds the user clusters for each customer type of the merchant to the merchant customer record.

[0070] In S604, the information processing device 10 queries the general-purpose customer record storage unit 109 based on the user identification information contained in the financial transaction data read in S602, and reads the general-purpose customer record of the customer using the affiliated store with which it is interacting. The information processing device 10 inputs the read general-purpose customer record and the affiliated store customer record to which the user cluster has been added into the generating AI, receives the detailed affiliated store customer record from the generating AI, and stores it in the affiliated store customer record storage unit 112. The detailed affiliated store customer record includes information on the general-purpose customer record of users belonging to the customer type, that is, it includes information on what customer groups are using each customer type.

[0071] In another embodiment of the present invention, the information processing device 10 queries the user data storage unit 106 based on the user identification information contained in the financial transaction data read in S602 to read questionnaire information, inputs the questionnaire information together with the general customer record and the merchant customer record into the generating AI, and receives a detailed merchant customer record from the generating AI. In this case, the detailed merchant customer record further includes questionnaire information of users belonging to the customer type.

[0072] In S605, the information processing device 10 queries the general-purpose customer record storage unit 109 based on each customer type in the detailed member store customer record, and reads the general-purpose customer record (N1) of a user having a customer characteristic tag associated with the customer type from the general-purpose customer record storage unit 109. A customer type and a customer characteristic tag are associated if they match, or if they are similar within a predetermined acceptable range.

[0073] The information processing device 10 derives feature quantities for each piece of information contained in the read general-purpose customer medical record. These feature quantities may be obtained using well-known methods in the field of machine learning. Based on the feature quantities derived for each piece of information in each read general-purpose customer medical record, the information processing device 10 can determine which feature quantities to adopt as representative users for each customer type. For example, if a feature quantity for a certain piece of information is derived from a relatively large number of general-purpose customer medical records, that feature quantity may be adopted as the representative user feature quantity for that customer type. The information processing device 10 can then use each of the determined feature quantities to generate customer medical records for representative users. Finally, the information processing device 10 generates a target customer list containing information from the representative users' customer medical records for each customer type.

[0074] Alternatively, the information processing device 10 queries the general-purpose customer record storage unit 109 based on each customer type in the detailed affiliated store customer record, and reads general-purpose customer records (e.g., N100, N1000, etc.) of any group associated with the customer type from the general-purpose customer record storage unit 109. A customer type and an arbitrary group are associated if they match, or if they are similar within a predetermined acceptable range. The information processing device 10 can use the read general-purpose customer records of any group to generate a representative user's customer record. The information processing device 10 generates a target customer list containing information on the representative user's customer record for each customer type. After the generation of the target customer list, the process described in Figure 7 is executed.

[0075] (Processing flow: Merchant dialogue execution process and customer promotion execution process) Figure 7 is a flowchart illustrating the merchant dialogue execution process and customer promotion execution process according to the present invention.

[0076] In S701, the information processing device 10 inputs the detailed merchant customer record and the target customer list generated in S605 into the generation AI, receives the candidate scenarios for merchant provision generated by the generation AI from the generation AI, and stores them in the scenario candidate list storage unit 111. That is, the candidate scenarios are associated with the merchant customer record and the representative user's customer record. The information processing device 10 provides the received candidate scenarios for merchant provision to the merchant computer 12 of the merchant with whom it is interacting. The merchant computer 12 can send dialogue content, including the candidate scenarios it is interested in and requests regarding those candidate scenarios, as well as other content, to the information processing device 10. The candidate scenarios for merchant provision include information such as how the merchant's products and services can solve the representative user's needs and problems, and the added value that can be provided to the representative user, for each customer type.

[0077] In S702, the information processing device 10 determines whether it has received dialogue content containing a request from the merchant computer 12. The request may include information such as which scenario candidate was selected by the merchant from among the scenario candidates provided to the merchant computer 12, or questions regarding the selected scenario candidate. Examples of information not included in the request may include information that the merchant has accepted a verified recommendation candidate provided by the information processing device 10, a request to create an analysis report for the merchant, or information that the merchant is not interested in any of the scenario candidates. If it is determined that a request has been received, the process proceeds to S703; on the other hand, if it is determined that a request has not been received, the process proceeds to S706.

[0078] In S703, the information processing device 10 inputs the received request, the scenario candidate associated with the request, and the representative user's customer record information into the generating AI. The generating AI generates recommendation candidates that the affiliated store will provide to the customer, i.e., candidates for appeal concepts, creatives, and channels. As is well known to those skilled in the art, creatives in marketing refer to materials and expressions created for marketing purposes, and in one embodiment of the present invention, creatives can include, for example, email subject lines, main copy, lead paragraphs, appeal headlines and body text, images, etc. The information processing device 10 receives the candidates for appeal concepts, creatives, and channels (recommendation candidates) from the generating AI.

[0079] In S704, the information processing device 10 inputs the merchant's customer record, requests, scenario candidates associated with those requests, the representative user's customer record, and recommendation candidates into the generating AI, and verifies whether the recommendation candidates to be provided to the user are appropriate in light of the information in the merchant's customer record and the representative user's customer record. The information processing device 10 receives the recommendation candidates verified by the generating AI. The verified recommendation candidates may simply be called "recommendations." Through this verification, the recommendations provided to the user (verified recommendation candidates) may be modified in light of the information in the merchant's customer record and the representative user's customer record.

[0080] In S705, the information processing device 10 provides recommendations to the merchant computer 12 via the AI ​​chatbot. Subsequently, the merchant computer 12 and the AI ​​chatbot engage in a dialogue, and the information processing device 10 obtains the merchant's evaluation of the recommendations through this dialogue. After that, the process returns to S702.

[0081] If S706 determines that no request has been received from the merchant, the information processing device 10 queries the user data storage unit 106 based on the customer type included in the recommendation to obtain the contact information (e.g., email address) of a user who has a customer feature tag associated with the customer type, and uses the obtained contact information to send a promotional notification based on the recommendation to the user terminal 11 of that user. If it is determined that no request has been received from the merchant, for example, information has been received indicating that the recommendation provided by the information processing device 10 has been approved. The user to whom the promotional notification is sent may be a user who has a high correlation with the feature quantities of the information included in the customer type.

[0082] In S707, the information processing device 10 updates the merchant's customer record and the merchant's customer record based on the recommendations sent to the user terminal 11. The information processing device 10 also updates the user information, customer characteristic tags, and psychographic data in the user data storage unit 106, as well as the general-purpose customer record (N1) in the general-purpose customer record storage unit 109, based on the results of the promotion notification (for example, payment data generated at the merchant after the notification). Verification of the results of the promotion notification may be performed by comparing the promotion content with the actual payment data within a predetermined period, and this matching process may also utilize a generation AI.

[0083] In S708, if the information processing device 10 receives a request in S702 to create an analysis report for the affiliated store, it passes the detailed affiliated store customer record and a predetermined number of general-purpose customer records associated with the customer type in the detailed affiliated store customer record to the generation AI, generates an analysis report for the affiliated store, and stores it in the affiliated store report storage unit 113. The information processing device 10 can send the generated analysis report for the affiliated store to the affiliated store computer 12. Figure 11 shows an example of a report 1100 for an affiliated store. Report 1100 shows an example of a customer analysis report for an affiliated store, and the analysis results are shown for each user type. Note that the type of report is not limited to an analysis report, and other types of reports may be generated, and the report does not necessarily have to be intended for distribution to the affiliated store.

[0084] Although the principles of the present invention have been described above with reference to exemplary embodiments, those skilled in the art will understand that various embodiments with modifications in configuration and details can be realized without departing from the spirit of the invention. That is, the present invention can take the form of, for example, a system, apparatus, method, program, or storage medium. [Explanation of Symbols]

[0085] 10 Information Processing Devices 11 User terminals 12. Merchant Computer 13, 14 Network 101 Control Unit 102 Main memory 103 Auxiliary storage 104 IF section 105 Output section 106 User data storage unit 107 Merchant Data Storage Unit 108 Financial Transaction Data Storage Unit 109 General-purpose customer medical record storage unit 110 Member Store Medical Record Storage Department 111 Scenario Candidate List Memory Unit 112 Member Store Customer Record Storage Department 113 Member Store Report Storage Section

Claims

1. An information processing device comprising a control unit and a storage unit, The aforementioned storage unit is A member store record storage unit that stores member store records containing information about member stores, A general-purpose customer record storage unit that stores a general-purpose customer record showing information about a user for one person and / or any group, A store for storing store customer records, which include information about the store and customer group records for each customer type of the store, wherein the customer group records include information on general-purpose customer records for each customer type that enjoys the service value of the store, and the store for storing store customer records, Equipped with, The control unit, The process involves generating candidate scenarios for the merchant based on the merchant customer records and target customer list, and transmitting the candidate scenarios to the merchant computer of the merchant in the interaction, wherein the target customer list includes customer record information for a representative user for each of the customer types. In response to receiving a request from the merchant computer regarding the candidate scenarios for merchant provision, the system generates recommendation candidates from the merchant to the customer based on the request, the candidate scenarios for merchant provision associated with the request, and the customer record information of the representative user. Based on the merchant's profile, the request, the candidate scenario for the merchant provided to the merchant associated with the request, the representative user's customer profile, and the candidate recommendation, the system verifies whether the candidate recommendation is appropriate in light of the information in the merchant's profile and the representative user's customer profile, and generates the verified candidate recommendation as a recommendation for the user. Transmitting the user-provided recommendations to the merchant's computer, Sending promotional notifications based on user-provided recommendations approved by the merchant to the user terminals of users associated with customer types included in the user-provided recommendations, An information processing device configured to perform the following actions.

2. The storage unit further comprises a user data storage unit for storing user data related to the user, Based on the user-provided recommendations, update the merchant's customer record and the merchant's customer record associated with the conversation. Based on the results of the promotional notification, update the user data and the general customer record of the user associated with the promotional notification. An information processing apparatus according to claim 1, configured to further perform the following:

3. The information processing device according to claim 1, wherein the aforementioned member store customer record is generated based on further information from user questionnaires.

4. The information processing device according to claim 1, further configured to read from the general-purpose customer record storage unit the general-purpose customer records of users having customer feature tags associated with each customer type of the affiliated store's customer record, derive the feature quantities of each piece of information contained in the read general-purpose customer record, and generate a customer record of the representative user using the derived feature quantities.

5. The process involves generating a merchant customer record based on the merchant record associated with the merchant during the conversation and the financial transaction data associated with the merchant, Based on the user identification information contained in the aforementioned financial transaction data, the customer characteristic tags of the user associated with the merchant during the conversation are obtained. Based on the aforementioned merchant customer record and customer characteristic tags, the system identifies user clusters for each customer type of the merchant during the conversation and adds the user clusters for each customer type of the merchant during the conversation to the merchant customer record. Based on the user identification information contained in the financial transaction data, the general-purpose customer record of the user associated with the merchant in the interaction is read from the general-purpose customer record storage unit, and based on the read general-purpose customer record and the merchant customer record to which the user cluster has been added, the merchant customer record is refined and stored in the merchant customer record storage unit. The information processing apparatus of claim 4, further configured to perform the following:

6. A method performed by an information processing device comprising a control unit and a storage unit, The aforementioned storage unit is A member store record storage unit that stores member store records containing information about member stores, A general-purpose customer record storage unit that stores a general-purpose customer record showing information about a user for one person and / or any group, A store for storing store customer records, which include information about the store and customer group records for each customer type of the store, wherein the customer group records include information on general-purpose customer records for each customer type that enjoys the service value of the store, and the store for storing store customer records, Equipped with, The control unit generates candidate scenarios for the merchant based on the merchant customer records and the target customer list, and transmits the candidate scenarios to the merchant computer of the merchant in the interaction, wherein the target customer list includes customer record information for representative users for each of the customer types. In response to receiving a request from the merchant computer for the merchant-provided scenario candidate, the control unit generates recommendation candidates from the merchant to the customer based on the request, the merchant-provided scenario candidate associated with the request, and the customer record information of the representative user. The control unit verifies whether the recommendation candidates are appropriate in light of the information in the merchant's record and the representative user's customer record, based on the merchant's record of the merchant in the dialogue, the request, the candidate scenarios for the merchant associated with the request, the representative user's customer record, and the recommendation candidates, and generates the verified recommendation candidates as recommendations for the user. The control unit transmits the user-provided recommendations to the merchant computer, The control unit transmits a promotional notification based on the user-provided recommendation approved by the merchant to the user terminal of a user associated with the customer type included in the user-provided recommendation. A method for providing this.

7. A program that, when executed, causes a computer to perform the method described in claim 6.

8. An information processing device comprising a control unit and a storage unit, The aforementioned storage unit is A merchant data storage unit that stores merchant data related to the merchant, including merchant tag information, A member store record storage unit that stores member store records containing information about member stores, A general-purpose customer record storage unit that stores a general-purpose customer record showing information about a user for one person and / or any group, Equipped with, The control unit, The general-purpose customer record associated with the user in the conversation is read from the general-purpose customer record storage unit, and the merchant tag information is read from the merchant data storage unit. Based on the read general-purpose customer medical record and the affiliated store tag information, a candidate scenario for user provision is generated, In response to receiving a user request from a user terminal, the system reads the merchant profile associated with the user request and the scenario candidate from the merchant profile storage unit, and generates recommendation candidates for merchants and users that match the user request and the scenario candidate. Based on the generated recommendation candidates for the affiliated store and the user, and the general customer profile associated with the user during the conversation, the system verifies whether the recommendation candidates for the affiliated store and the user provided to the user during the conversation are appropriate in comparison to the general customer profile, and receives the verified affiliated store and recommendations. Transmit verified merchants and recommendations to the user terminal, If no further user requests are received, the first value for each of the verified merchants and recommendations is calculated by analyzing the response from the user terminal. Based at least on the user requests, scenario candidates, verified merchants, and recommendations for which the first value is relatively high, the general customer profile associated with the user in the conversation and the merchant profile associated with the user requests and scenario candidates are updated. An information processing device configured to perform the following actions.

9. The process involves merging user data and financial transaction data of selected users to generate primary aggregated data, Based on the aforementioned primary aggregated data, a general-purpose customer medical record is generated, and the generated general-purpose customer medical record is stored in the general-purpose customer medical record storage unit. The general-purpose customer records of multiple users are read from the general-purpose customer record storage unit, clustering is performed on the read general-purpose customer records of multiple users to generate a general-purpose customer record of an arbitrary group, and the general-purpose customer record of the arbitrary group is stored in the general-purpose customer record storage unit. The information processing apparatus of claim 8, configured to further perform the following:

10. The process involves reading the merchant data of the selected merchant and obtaining externally acquired merchant-related information retrieved from an external source for the selected merchant, Based on the read merchant data and the acquired externally obtained merchant-related information, merchant tag information is generated, and the generated merchant tag information is stored in the merchant data storage unit. Based on the read member store data and the acquired member store-related external information, a member store record is generated, and the generated member store record is stored in the member store record storage unit. The information processing apparatus of claim 8, configured to further perform the following:

11. A method performed by an information processing device comprising a control unit and a storage unit, The aforementioned storage unit is A merchant data storage unit that stores merchant data related to the merchant, including merchant tag information, A member store record storage unit that stores member store records containing information about member stores, A general-purpose customer record storage unit that stores a general-purpose customer record showing information about a user for one person and / or any group, Equipped with, The control unit reads the general-purpose customer record associated with the user in the conversation from the general-purpose customer record storage unit, and reads the merchant tag information from the merchant data storage unit. The control unit generates candidate scenarios for user provision based on the general-purpose customer medical record and the affiliated store tag information read out, The control unit, in response to receiving a user request from the user terminal, reads the merchant profile associated with the user request and the scenario candidate from the merchant profile storage unit, and generates recommendation candidates for merchants and users that match the user request and the scenario candidate. The control unit verifies whether the candidate recommendations for the affiliated store and the user provided to the user during the conversation are appropriate in comparison to the general customer record, based on the generated candidate recommendations for the affiliated store and the user and the general customer record associated with the user during the conversation, and receives the verified affiliated store and recommendations. The control unit transmits verified merchants and recommendations to the user terminal. If the control unit has not received any further user requests, it calculates a first value for each of the verified merchants and recommendations by analyzing the response from the user terminal. The control unit updates the general-purpose customer record associated with the user in the conversation and the merchant record associated with the user request and the scenario candidate, based at least on the user request, the scenario candidate, the verified merchant, and the recommendation, in which the first value is relatively high. A method for providing this.

12. A program that, when executed, causes a computer to perform the method according to claim 11.

Citation Information

Patent Citations

  • Production of magnetic head

    JP1987097109A

  • System for promoting use of credit card

    JP2018032216A

  • Support system, method, and program

    JP7566104B1