system

Abstract

Provide a system. A means for prompting a user to input a purchase history and desired functions; a server means for receiving the purchase history and desired function data; An AI model means to analyze the received data and recommend the most suitable credit card; means for generating and presenting recommendation results to a user; A means for proposing new functions based on the generated analysis results; A system including:

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Currently, many people have many options when it comes to choosing a credit card, and they spend time and effort trying to find the card that best suits them. This problem prevents users from choosing the card that best suits their spending habits and from making the most of the resulting benefits and services. It also makes it difficult for credit card providers to effectively add features and services that are attractive to users. The present invention aims to solve these problems. [Means for solving the problem]

[0005] This invention proposes a system including means for prompting a user to input their purchase history and desired features, server means for receiving the data on the purchase history and desired features, AI model means for analyzing the received data and recommending the most suitable credit card, means for generating and presenting the recommendation results to the user, and means for proposing the addition of new functions based on the generated analysis results. This system enables users to quickly and accurately find the most suitable credit card for them, and also enables card providers to add attractive features that meet the user's needs.

[0006] "User" refers to a person who uses the credit card suggestion system to input their purchase history and desired features to find the most suitable credit card.

[0007] "Purchase history" refers to data related to a user's past consumption activities, including information such as expenditure amounts by category and purchase frequency.

[0008] "Desired features" are the conditions for benefits and services that users want from a credit card, and examples include point redemption rates, travel benefits, whether or not there is an annual fee, etc.

[0009] "Server" refers to a computer system that is responsible for receiving information sent by a user, analyzing the data, generating results, and providing the results to the user.

[0010] An "AI model" refers to artificial intelligence that analyzes data received from users regarding their purchase history and desired features, and recommends the most suitable credit card.

[0011] "Recommendation Results" refers to information generated as a result of analysis by the AI ​​model, including a list of the most suitable credit cards for the user and their detailed information.

[0012] "Proposal for adding new features" refers to the act of proposing new benefits or services to credit card providers based on the results of the generative AI's analysis of massive amounts of user data.

[0013] "Credit card provider" refers to a company or financial institution that issues credit cards and provides card services to users. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] System Overview

[0036] This invention is a system in which an AI analyzes information when a user inputs their purchase history and desired features to suggest the most suitable credit card. Furthermore, the AI ​​generation is used to suggest new features and services to card providers. This system saves users time and effort in selecting a credit card, and also helps card providers analyze data to offer more attractive services.

[0037] System configuration

[0038] The system consists of the following components:

[0039] 1. Terminal: The device used by the user, providing an interface for entering purchase history and desired functions and checking the results.

[0040] 2. Server: Receives data sent by the user from the device, analyzes the data using the AI ​​model, and generates and sends the analysis results to the device.

[0041] 3. AI model: Analyzes the received data and performs analytical processing to recommend the best credit card for the user.

[0042] Program processing

[0043] 1. Enter your purchase history and desired features

[0044] A user logs in using a terminal and enters their purchase history and desired features. For example, consider a case where a user enters "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Enriched travel benefits," and "No annual fee" as desired features. This information is sent to the server by the terminal.

[0045] 2. Data Receipt and Analysis

[0046] The server preprocesses the received data and inputs it into the AI ​​model, which then lists the most suitable credit cards based on the customer's purchase history and desired features. The AI ​​model then references past data from similar users to recommend the most suitable card.

[0047] 3. Generating and displaying results

[0048] Based on the analysis results of the AI ​​model, the server generates a list of recommended credit cards for the user and their detailed information (such as point redemption rates and benefits).The results are sent to the terminal so that the user can check them.The user can then select the most suitable card from the presented list.

[0049] 4. Proposal for new feature addition

[0050] The generative AI analyzes massive amounts of user data and makes proposals to credit card providers for the addition of new features and services. For example, if it determines based on the analysis data that adding a "points reward function specialized for online shopping" is likely to increase the number of subscribers, it will report that proposal to the provider.

[0051] Specific examples

[0052] When User A enters his monthly purchase history of "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Rich travel perks," and "No annual fee" as desired features, the input data is sent to the server. The server analyzes the data using an AI model and lists the most suitable credit cards: "Card X (1.5% point return rate)" and "Card Y (travel perks, no annual fee)." The results are sent to the terminal, where User A can check them and select, for example, "Card X." Furthermore, based on the analysis results, the server's generation AI can propose to providers the addition of "point return features specialized for online shopping."

[0053] In this way, the present invention provides a means for users to quickly and easily find the best credit card for them, and is a system that can also propose new functions to credit card providers based on useful data.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The user starts up the device and logs in to the application. The user enters their email address and password and presses the login button.

[0057] Step 2:

[0058] The device sends the user's authentication information, which includes an email address and password, to the server.

[0059] Step 3:

[0060] The server compares the received authentication information with the registration information in the database and authenticates the user. If the authentication is successful, the server sends a login success message to the terminal.

[0061] Step 4:

[0062] The terminal displays a login success message and presents the user with a form to enter their purchase history and desired features.

[0063] Step 5:

[0064] The user enters their purchase history in a specified form, for example, by entering amounts for each category such as food, entertainment, and travel.

[0065] Step 6:

[0066] Users select the features they want, such as points redemption rate, travel benefits, whether or not there is an annual fee, etc., by selecting checkboxes or drop-down menus.

[0067] Step 7:

[0068] The terminal transmits the purchase history and desired function data input by the user to the server.

[0069] Step 8:

[0070] The server pre-processes the data it receives, including formatting and unifying the data.

[0071] Step 9:

[0072] The server inputs the preprocessed data into the AI ​​model, which analyzes the received data and lists the best credit cards for the user.

[0073] Step 10:

[0074] The server generates a list of recommended credit cards and their details based on the analysis results of the AI ​​model.

[0075] Step 11:

[0076] The analysis results generated by the server are sent to the terminal.

[0077] Step 12:

[0078] The terminal displays the analysis results received from the server to the user, including a list of credit cards and their details.

[0079] Step 13:

[0080] The user selects the card that best suits them from the list of credit cards presented.

[0081] Step 14:

[0082] The server uses generated AI to analyze the vast amount of user data collected and make suggestions to credit card providers about adding new features and services.

[0083] Step 15:

[0084] The server generates a proposal to add new features and sends it to the credit card provider.

[0085] Step 16:

[0086] Credit card providers will review your proposal and implement new features and services to improve your competitive position.

[0087] The above is the processing steps and specific operation contents of the present invention.

[0088] Example 1

[0089] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0090] When users choose the best credit card for them, there is a lack of a way to receive prompt and accurate suggestions based on their purchase history and desired features, which makes the selection process time-consuming and labor-intensive.Another issue is that card providers are not properly being suggested new features and services based on users' needs.

[0091] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0092] In this invention, the server includes means for prompting a user to input their purchase history and desired functions, means for receiving the data on the purchase history and desired functions, means for preprocessing the received data and converting it into an analyzable format, artificial intelligence means for analyzing the received and preprocessed data and recommending an optimal credit card, means for generating and presenting the recommendation results to the user, and means for proposing the addition of new functions based on the generated analysis results. This allows the user to quickly and accurately receive a recommendation for the optimal credit card and to make proposals for new functions and services to the card provider.

[0093] "User" refers to a person who uses the system to input their purchase history and desired features and receive suggestions for the most suitable credit card.

[0094] "Purchase history" refers to data regarding the price and category of products purchased by a user in the past.

[0095] "Desired features" refer to the benefits and service requirements that users want from a credit card.

[0096] "Server" refers to a computer system that receives, processes, and analyzes data sent by users.

[0097] "Means of preprocessing data and converting it into an analyzable format" refers to the process of formatting the received data into a form that is easy for the AI ​​model to analyze.

[0098] "Artificial intelligence means" refers to machine learning models and algorithms that analyze the received and pre-processed data and recommend the most suitable credit card.

[0099] "Means for generating and presenting recommended results to the user" refers to the process of displaying a list and details of the most suitable credit cards to the user based on the analysis results.

[0100] "Means for proposing new features" refers to the process of proposing new features and services to card providers based on the generated analysis results.

[0101] The present invention is a system in which an AI analyzes a user's purchase history and desired features and then proposes the most suitable credit card. Furthermore, the system uses the generation AI to propose new features and services to card providers. Specific details for implementing the present invention are described below.

[0102] System Configuration

[0103] The system consists of the following components:

[0104] 1. Terminal: A device used by a user that provides an interface for entering purchase history and desired functions and checking the results. Examples of terminals include smartphones and PCs.

[0105] 2. Server: Receives data sent by the user from the device and analyzes the data using an AI model. It also generates the analysis results and sends them to the device. A high-performance computing server is used as the server.

[0106] 3. AI model: Analyzes the received data and performs analysis to recommend the best credit card for the user. The AI ​​model uses machine learning frameworks such as TENSORFLOW (registered trademark) and PyTorch.

[0107] Hardware and software used

[0108] Hardware

[0109] Devices: smartphones, computers

[0110] Server: High-performance computing server

[0111] software

[0112] AI models: TensorFlow, PyTorch

[0113] Database management system: MySQL (registered trademark), PostgreSQL

[0114] Interface software: React, Vue.js

[0115] Specific examples of program processing

[0116] The user logs in to the system on the terminal. After logging in, the user follows the system's instructions and enters their monthly purchase history and desired credit card features.

[0117] For example, user A enters the following data:

[0118] Purchase History:

[0119] Food expenses: 30,000 yen

[0120] Entertainment expenses: 10,000 yen

[0121] Travel: 50,000 yen

[0122] Desired features:

[0123] High point return rate

[0124] Extensive travel benefits

[0125] No annual fee

[0126] This input data is sent from the device to a server, where it is received and pre-processed. The pre-processed data is then input into an AI model, which references similar past data to create a list of the most suitable credit cards for the user.

[0127] For example, the AI ​​model will list "Card X (point return rate 1.5%)" and "Card Y (travel benefits, no annual fee)" as the analysis results. These results are sent to the terminal via the server, where User A can check them. User A can then select the most suitable credit card from the presented list.

[0128] Furthermore, based on the analysis results, the generative AI will propose new features to card providers, such as a point reward function specialized for online shopping, allowing card providers to develop and provide new features and services based on user needs.

[0129] An example of a prompt for this system is:

[0130] Prompt statement:

[0131] Purchase History:

[0132] Food expenses: 30,000 yen

[0133] Entertainment expenses: 10,000 yen

[0134] Travel: 50,000 yen

[0135] Desired features:

[0136] High point return rate

[0137] Extensive travel benefits

[0138] No annual fee

[0139] In this way, the present invention provides users with a means for quickly and easily finding the best credit card, and also allows card providers to make suggestions for adding new functions based on useful data.

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1:

[0142] A user logs in to the system using a terminal. On the login screen, the user enters their user ID and password. The entered authentication information is sent from the terminal to the server. The server authenticates the user based on the received information, and if authentication is successful, the main screen is displayed.

[0143] Step 2:

[0144] The user enters their purchase history and desired features on the main screen. For example, they enter the following data:

[0145] Purchase history: Food: 30,000 yen, Entertainment: 10,000 yen, Travel: 50,000 yen

[0146] Desired features: High point redemption rate, extensive travel benefits, no annual fee

[0147] The input data is transmitted from the terminal to the server.

[0148] Step 3:

[0149] The server receives the data sent from the device. After receiving the data, it performs pre-processing on the data. This processing includes data cleaning (e.g., filling in missing values) and data normalization (e.g., scaling numerical data). The pre-processed data is converted into an analyzable format and input into the AI ​​model. For example, a user's monthly expenditure data is converted into an appropriate numerical format.

[0150] Step 4:

[0151] The server inputs the preprocessed data into the AI ​​model. The AI ​​model analyzes the input data and lists the most suitable credit cards based on the user's purchase history and desired features. The AI ​​model references past similar user data to select the most suitable card. For example, it may obtain results such as "Card X (1.5% points return rate)" and "Card Y (travel benefits, no annual fee)."

[0152] Step 5:

[0153] The server receives the recommendations generated by the AI ​​model. Based on the recommendations, it generates data to display to the user. This generation process includes adding details about the recommended credit card (e.g., reward points and benefits) and converting the data into an easy-to-read format. The generated information is then sent to the device.

[0154] Step 6:

[0155] The terminal displays the recommended results received from the server to the user, who can then review the list of credit cards presented and select the card in the most suitable category.

[0156] Step 7:

[0157] The generative AI generates proposals for adding new features and services to card providers based on the analyzed data. The proposals are sent from the server to the providers. For example, it may propose new features such as a "points redemption function specialized for online shopping" based on user trends.

[0158] (Application example 1)

[0159] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0160] Conventional credit card recommendation systems are unable to adequately address a user's individual purchasing history or desired features, making it difficult to provide the appropriate card to the user. Furthermore, when users engage in a variety of purchasing activities, it is difficult to find the optimal card to use, especially on online shopping sites. Furthermore, it is also difficult to propose appropriate new features and services to card providers. To solve these problems, a system is needed that can respond to the diverse needs of users and efficiently recommend the most suitable credit card for online shopping sites.

[0161] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0162] In this invention, the server includes a means for prompting the user to input their purchase history and desired features, a server means for receiving the data on the purchase history and desired features, and an AI model means for analyzing the received data and recommending the most suitable credit card. This makes it possible to efficiently recommend the most suitable credit card for use on the online shopping site based on the information entered by the user.

[0163] A "user" is an individual or corporation who uses the system to input purchase history and desired features and receive credit card recommendations.

[0164] "Purchase history" is information about transactions and purchases that a user has made in the past, and is data entered by category, such as food expenses, entertainment expenses, and travel expenses.

[0165] "Desired features" refers to the benefits and features that users want from a credit card, and include specific conditions such as point redemption rates, travel benefits, and no annual fees.

[0166] A "server" is a computer system that receives data sent by users and provides it to an AI model for analysis.

[0167] An "AI model" is an artificial intelligence model that analyzes user input data and recommends the most suitable credit card.

[0168] "Recommended results" are a list of optimal credit cards presented to the user based on the results of the AI ​​model's analysis.

[0169] "Proposing new features" refers to using generative AI to analyze accumulated user data and recommend new features and services to credit card providers.

[0170] An "online shopping site" is a website that offers products and services over the Internet and allows users to make purchases.

[0171] "Suitability for use on a shopping site" is a characteristic that indicates whether the credit card is most suitable for use by a user on a shopping site.

[0172] This invention is a system that analyzes data entered by users based on their purchase history and desired features, and recommends the most suitable credit card. The system consists of a terminal used by the user, a server that receives and analyzes the data, and an AI model that presents the analysis results. The system also uses generative AI to propose new features and services to credit card providers.

[0173] System Overview

[0174] First, the user uses the terminal to input their purchase history and desired features. For example, they might input purchase history such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," as well as desired features such as "High point return rate," "Comprehensive travel benefits," and "No annual fee." This information is sent from the terminal to the server.

[0175] The server preprocesses the received data and inputs it into the AI ​​model. The AI ​​model then lists the most suitable credit cards based on the user's purchase history and desired features. For example, based on the user's input data, the model can recommend "Card X (1.5% reward point rate)" and "Card Y (travel benefits, no annual fee)."

[0176] Hardware and software used

[0177] Hardware: Smartphone (user device), server

[0178] software:

[0179] Flask: A Python web framework

[0180] TensorFlow: A framework for AI models

[0181] scikit-learn: A library for data preprocessing

[0182] Data processing and calculation

[0183] The server properly formats the data sent by the user, including their purchase history and desired features, and scales it so that the AI ​​model can analyze it. The received data is converted into numerical data through a standardization process. The AI ​​model then analyzes the data and outputs the optimal credit card recommendation.

[0184] The analysis results are sent to the user's device based on the recommendation list generated by the AI ​​model, allowing the user to review the results and select the most suitable credit card.

[0185] In addition, generative AI will analyze massive amounts of user data and suggest new features and services to credit card providers, such as adding a "points reward function specialized for online shopping."

[0186] Specific examples

[0187] When User A enters his monthly purchase history, such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Rich travel perks," and "No annual fee" as desired features, the input data is sent to the server. The server uses an AI model to analyze the data and create a list of options, such as "Card X (1.5% point return rate)" and "Card Y (travel perks available, no annual fee)."

[0188] Prompt Sentence Examples

[0189] If User B enters his monthly purchase history (food: 25,000 yen, entertainment: 20,000 yen, travel: 10,000 yen) and selects "high point return rate" and "full travel benefits" as desired features, the data is sent to the server. The server uses an AI model to analyze the data and create a list of cards, such as "Card A (point return rate 2.0%)" and "Card B (full travel benefits, no annual fee)."

[0190] Example prompt sentence:

[0191] User purchase history:

[0192] Food expenses: 25,000 yen

[0193] Entertainment expenses: 20,000 yen

[0194] Travel: 10,000 yen

[0195] Desired credit card features:

[0196] High point redemption rate

[0197] Extensive travel benefits

[0198] Please suggest the best credit card for me.

[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0200] Step 1:

[0201] The user enters their purchase history and desired features.

[0202] Using their smartphone or other device, users input their purchase history, such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," as well as desired credit card features, such as "High point return rate," "Plenty of travel benefits," and "No annual fee." The input data is sent from the user device to the server.

[0203] Step 2:

[0204] The server preprocesses the data received.

[0205] The server receives the purchase history and desired feature data sent by the user and performs a standardization process using the scikit-learn library to standardize and scale this data, for example, converting numerical data into an appropriate range, which makes it easier for the AI ​​model to analyze the data.

[0206] Step 3:

[0207] The server inputs the preprocessed data into the AI ​​model for analysis.

[0208] The server inputs the preprocessed data into the AI ​​model, which analyzes the data and generates a list of optimal credit cards based on the user's purchasing history and desired features. This analysis refers to past data of similar users to identify the most suitable credit cards.

[0209] Step 4:

[0210] The server generates recommendation results and sends them to the user terminal.

[0211] The server creates a list of recommended credit cards for the user based on the analysis results generated by the AI ​​model. This list includes detailed information such as the credit card name, point redemption rate, and benefits. This list is then sent to the user's device in JSON format or similar.

[0212] Step 5:

[0213] The user reviews the recommendations and selects a credit card.

[0214] The user can review the recommended credit card list displayed on the terminal and select the most suitable credit card. The user can compare the details of each card and choose the card that best suits their needs.

[0215] Step 6:

[0216] The server uses generated AI to propose new features to credit card providers.

[0217] The server analyzes a huge amount of user data and proposes new features and services to credit card providers. In this processing step, new features such as a "points redemption function specialized for online shopping" are proposed to the provider. These proposals are generated from the results of AI analysis based on user data.

[0218] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0219] System Overview

[0220] This invention is a system in which an AI analyzes information when a user inputs their purchase history and desired features to recommend the most suitable credit card. Furthermore, the AI ​​generation system is used to propose new features and services to card providers. This system is combined with an emotion engine that recognizes the user's emotions, enabling more personalized card recommendations. The emotion engine analyzes the user's emotions when inputting information and influences the recommendation results.

[0221] System configuration

[0222] The system consists of the following components:

[0223] 1. Terminal: A device used by users that provides an interface for inputting purchase history and desired features and checking the results. It also has an emotion engine that analyzes user emotions in real time.

[0224] 2. Server: Receives data sent by the user from the device, analyzes the data using the AI ​​model, and generates and sends the analysis results to the device.

[0225] 3. AI model: Analyzes the received data and performs analytical processing to recommend the best credit card for the user.

[0226] 4. Emotion Engine: Analyzes the user's emotions and sends the analysis results to the server, which then adjusts the recommendation results based on this emotional data.

[0227] Program processing

[0228] 1. Enter your purchase history and desired features

[0229] A user logs in using a terminal and enters their purchase history and desired features. For example, consider a case where a user enters "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Enriched travel benefits," and "No annual fee" as desired features. This information is sent to the server by the terminal.

[0230] 2. Acquiring Emotion Data

[0231] The emotion engine installed in the device analyzes the facial expressions and voices of users when they input information, and obtains emotional data in real time. For example, when a user expresses emotions such as "satisfaction," "dissatisfaction," or "excitement," the emotion engine converts these into numerical values.

[0232] 3. Data Receipt and Analysis

[0233] The server preprocesses the received purchase history, desired features, and emotional data and inputs it into the AI ​​model. The AI ​​model analyzes this data and lists the most suitable credit cards. At this time, it also includes emotional data in its analysis, making recommendations that reflect the user's emotional state.

[0234] 4. Generating and displaying results

[0235] Based on the analysis results of the AI ​​model, the server generates a list of recommended credit cards for the user and their detailed information (such as point redemption rates and benefits).The results are sent to the terminal so that the user can check them.The user can then select the most suitable card from the presented list.

[0236] 5. Proposal for new feature addition

[0237] The generative AI analyzes massive amounts of user data and emotional data and makes proposals to credit card providers for the addition of new features and services. For example, if it determines based on the analysis data that adding a "points reward feature specialized for online shopping" is likely to increase the number of subscribers, it will report that proposal to the provider.

[0238] Specific examples

[0239] User A enters his monthly purchase history (food: ¥30,000), entertainment: ¥10,000, and travel: ¥50,000) and selects his desired features (high point redemption rate, extensive travel perks, and no annual fee). The input data is sent to the server. The server analyzes the data using an AI model and lists the most suitable credit cards: Card X (1.5% point redemption rate) and Card Y (travel perks, no annual fee). The results are sent to the device, where User A can review them and select, for example, Card X. Based on the analysis results, the server's generation AI can also suggest to the provider that a new "point redemption feature specialized for online shopping" be added. During this process, the emotion engine analyzes User A's emotions at the time of input, and this emotional data also influences the recommendation results.

[0240] In this way, the present invention provides a means for users to quickly and easily find the best credit card for them, and by taking into account the user's emotions, it is possible to make more personalized recommendations.It is also a system that can propose new features to credit card providers based on useful data.

[0241] The processing flow will be explained below.

[0242] Step 1:

[0243] The user starts up the device and logs in to the application. The user enters their email address and password and presses the login button.

[0244] Step 2:

[0245] The device sends the user's authentication information, which includes an email address and password, to the server.

[0246] Step 3:

[0247] The server compares the received authentication information with the registration information in the database and authenticates the user. If the authentication is successful, the server sends a login success message to the terminal.

[0248] Step 4:

[0249] The device displays a login success message and a form for the user to enter their purchase history and desired features. At this point, the device's built-in emotion engine begins to operate and begins to collect emotion data from the user's facial expressions and voice.

[0250] Step 5:

[0251] The user enters their purchase history into a specified form. For example, they enter amounts for each category, such as food, entertainment, and travel. The emotion engine analyzes the user's emotions from their facial expressions and voice when entering data, and sends the results to the server in real time.

[0252] Step 6:

[0253] The user selects the desired features, such as points redemption rate, travel benefits, whether or not there is an annual fee, etc., using checkboxes or drop-down menus. The emotion engine continues to obtain emotion data and sends it to the server.

[0254] Step 7:

[0255] The terminal transmits the purchase history and desired function data input by the user, as well as emotion data from the emotion engine, to the server.

[0256] Step 8:

[0257] The server preprocesses the received purchase history, desired features, and sentiment data, including data cleanup and formatting.

[0258] Step 9:

[0259] The server inputs the preprocessed data into an AI model, which analyzes purchase history, desired features, and emotional data to create a list of the most suitable credit cards.

[0260] Step 10:

[0261] The server generates a list of recommended credit cards and their details based on the analysis results of the AI ​​model, and this list also reflects the user's satisfaction and interest level as indicated by the emotional data.

[0262] Step 11:

[0263] The server generates analysis results and sends them to the device, including the reason for the recommendation based on the emotional data.

[0264] Step 12:

[0265] The device receives the analysis results from the server and displays them to the user, including a list of credit cards and their details, as well as the reasons for the recommendations based on the user's emotional data.

[0266] Step 13:

[0267] Users can select the card that best suits them from a list of credit cards presented to them, while checking the reasons why each card is recommended.

[0268] Step 14:

[0269] The server uses generative AI to analyze the vast amount of collected user data and sentiment data and make suggestions to credit card providers about adding new features and services.

[0270] Step 15:

[0271] The server generates a proposal for adding new features and sends it to the credit card provider, which also reflects the user's needs and satisfaction based on the emotional data.

[0272] Step 16:

[0273] Credit card providers will review your proposal and implement new features and services to improve your competitive position.

[0274] Example 2

[0275] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0276] Conventional credit card recommendation systems only considered a user's purchase history and desired features when making recommendations, which resulted in problems in which the system was unable to fully reflect the user's emotions and individual needs. Furthermore, proposals for new features to card providers did not take into account the user's emotional data, making it difficult to reflect actual user needs. This made it difficult for users to find the optimal credit card that satisfied them, and for card providers to add effective services.

[0277] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0278] In this invention, the server includes a terminal means for acquiring user emotion data, an AI model means for preprocessing the received purchase history, desired features, and emotion data to recommend the most suitable credit card, and a generation AI means for proposing the addition of new functions based on the generated analysis results. This enables analysis including emotion data, making it possible to recommend more personalized credit cards and propose the addition of new functions that reflect the user's needs.

[0279] "Purchase history" refers to data relating to past purchases of products and services made by a user.

[0280] "Desired features" refers to the requirements for benefits and services that come with the credit card that the user desires.

[0281] A "server" is a central computer that receives, analyzes, and processes data sent by users.

[0282] "Emotion data" is data that quantifies the user's emotional state and is based on an analysis of facial expressions and voice at the time of input.

[0283] A "terminal" is a device operated by a user, and is a device for inputting data and acquiring emotion data.

[0284] An "AI model" is an analytical system built with algorithms based on artificial intelligence, which is used to recommend the most suitable credit card based on user data.

[0285] "Generative AI" is an artificial intelligence system that analyzes user data and emotional data to propose new features and services.

[0286] "Recommended results" are a list and detailed information of the most suitable credit cards for the user, generated as a result of the AI ​​model's analysis.

[0287] This invention relates to a system in which, when a user inputs their purchase history and desired features, AI analyzes the information and suggests the most suitable credit card. This system achieves more personalized card recommendations by combining it with an emotion engine that recognizes the user's emotions. Specific configurations and processing procedures based on the roles of the server, terminal, and user are explained.

[0288] System configuration

[0289] 1. Terminal

[0290] It is a device used by users that provides an interface for inputting purchase history and desired functions and checking the results. It also has an emotion engine (e.g., Microsoft® Azure® Cognitive Services or Emotion API) that analyzes the emotions of users as they input their data in real time.

[0291] 2. Server

[0292] It receives data sent by the user from the device, analyzes the data using an AI model (e.g., TensorFlow, PyTorch), and generates and sends the analysis results to the device.

[0293] 3. AI Model

[0294] The received data is analyzed and processed to recommend the best credit card for the user. A deep learning framework (e.g. TensorFlow) can be used for construction.

[0295] 4. Emotion Engine

[0296] The user's emotions are analyzed and the analysis results are sent to the server, which then adjusts the recommendation results based on this emotional data. The emotion engine can use facial recognition technology and voice analysis technology.

[0297] Specific operation of the system

[0298] The user logs in to the device and enters their purchase history and desired features. For example, they enter purchase history such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," and select the desired features as "High point return rate," "Enriched travel benefits," and "No annual fee." This data is sent to the server by the device.

[0299] Next, the device's built-in emotion engine analyzes the user's facial expressions and voice in real time to obtain emotion data. This emotion data is then quantified, for example, as "Satisfied: 80%," "Dissatisfied: 10%," or "Excited: 10%." This emotion data is also sent to the server.

[0300] The server preprocesses the received purchase history, desired features, and sentiment data and inputs it into the AI ​​model. The AI ​​model analyzes this data and lists the most suitable credit cards. For example, it might recommend "Card X (1.5% reward point rate)" or "Card Y (travel benefits, no annual fee)."

[0301] The analysis results are sent from the server to the device and presented to the user. The user can then select the most suitable card from the recommended list. For example, if the user selects "Card X," the selection is also sent to the server and reflected in the final list.

[0302] The generative AI also analyzes the accumulated user data and emotional data to propose new features and services to credit card providers. For example, a "points redemption feature specialized for online shopping" may be proposed based on the analysis data.

[0303] Prompt Sentence Examples

[0304] Purchase history and desired features entered by the user:

[0305] Food: 30,000 yen, Entertainment: 10,000 yen, Travel: 50,000 yen

[0306] Desired features: high point redemption rate, extensive travel benefits, no annual fee

[0307] Emotional Data:

[0308] Satisfaction: 80%, Dissatisfaction: 10%, Excitement: 10%

[0309] Use this information to recommend the best credit cards for you, and also suggest new features that should be added.

[0310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0311] Step 1:

[0312] The user enters their purchase history and desired features on the device.

[0313] Specifically, the user enters "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen" as purchase history on the device's GUI interface, and selects "High point return rate," "Enriched travel benefits," and "No annual fee" as desired features. This information is used for subsequent processing, and is saved as digital data within the device.

[0314] Input: Purchase history, desired features

[0315] Output: Digital data in the terminal

[0316] Step 2:

[0317] The device acquires emotion data.

[0318] Specifically, the device's built-in emotion engine analyzes the user's facial expressions and voice in real time and quantifies the emotional data. For example, the user's facial expressions and tone of voice when inputting information can be analyzed as "Satisfaction: 80%," "Dissatisfaction: 10%," and "Excitement: 10%."

[0319] Input: User's facial expression, voice

[0320] Output: Emotion data (quantified data)

[0321] Step 3:

[0322] The server receives the input data and the emotion data.

[0323] The device sends purchase history, desired features, and emotional data to the server, which receives this data and stores it in an initial database.

[0324] Input: purchase history, desired features, emotional data

[0325] Output: Data stored in the initial database on the server

[0326] Step 4:

[0327] The server preprocesses the data.

[0328] Specifically, the data format is standardized on the server, unnecessary data is filtered out, and preprocessing such as normalizing data with different units is performed. After preprocessing is complete, the data is converted into a format suitable for input into the AI ​​model.

[0329] Input: Data stored in the initial database

[0330] Output: Data in a format that can be input into an AI model

[0331] Step 5:

[0332] The AI ​​model analyzes the most suitable credit card.

[0333] The server inputs the preprocessed data into an AI model for analysis. The AI ​​model then lists the most suitable credit cards based on the customer's purchase history, desired features, and emotional data. As a result, it recommends cards such as "Card X (1.5% reward point rate)" and "Card Y (travel benefits, no annual fee)."

[0334] Input: Data in a format that can be fed into an AI model

[0335] Output: A list of recommended credit cards

[0336] Step 6:

[0337] The server generates the analysis results and sends them to the terminal.

[0338] Based on the analysis results of the AI ​​model, the server generates a list of recommended credit cards for the user along with detailed information (e.g., point redemption rate, benefits), and sends this result to the terminal.

[0339] Input: A list of recommended credit cards

[0340] Output: Analysis results sent to the device

[0341] Step 7:

[0342] The user reviews the recommendations and selects a card.

[0343] The user checks the analysis results received on the terminal and selects the most suitable card from the listed credit cards. For example, they can select "Card X." The selected card information is sent to the server and reflected in the final list.

[0344] Input: Analysis results sent to the device

[0345] Output: Selected credit card information

[0346] Step 8:

[0347] Generative AI will suggest new features to add.

[0348] The generative AI analyzes the accumulated user data and emotional data and proposes new features and services to card providers. For example, it may propose a "points redemption feature specialized for online shopping."

[0349] Input: User data, emotion data

[0350] Output: New feature suggestions to card providers

[0351] (Application example 2)

[0352] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0353] Conventional credit card recommendation systems suggest the most suitable card based on a user's purchase history and desired features, but they are unable to provide personalized recommendations that take into account the user's emotions. It is also difficult to use the data obtained to suggest new features or specific campaigns. As a result, users are unable to receive more satisfying recommendations, and providers are unable to obtain sufficient useful information.

[0354] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0355] In this invention, the server includes means for prompting the user to input their purchase history and desired features, server means for receiving the data on the purchase history and desired features, AI model means for analyzing the received data and recommending the most suitable credit card, means for generating and presenting the recommendation results to the user, means for proposing the addition of new features based on the generated analysis results, means for performing sentiment analysis, means for recommending a more personalized credit card based on the analysis results, and means for generating proposals for new features and discount campaigns. This enables personalized recommendations that take the user's emotions into consideration, and also enables providers to propose new features and campaigns.

[0356] "Purchase history" refers to data on past purchases of products or services made by a user.

[0357] "Desired features" refers to specific features such as new benefits or conditions that the user desires, such as a point return rate or no annual fee.

[0358] A "server" is a computer system for receiving and processing data from users.

[0359] An "AI model" is a system that uses artificial intelligence to analyze data and includes an algorithm to recommend the best credit card for the user.

[0360] "Emotion analysis" is the process of analyzing a user's emotional state from facial expressions, voice, etc., and acquiring this as data.

[0361] "Recommended results" refers to the list of optimal credit cards presented to the user as a result of the AI ​​model's analysis.

[0362] "New feature addition proposal" is the process of making proposals to credit card providers for adding new features and services based on user data.

[0363] "Personalized recommendations" refers to individually suggesting the best credit card for each user based on their characteristics and emotional state.

[0364] "Proposing new features and discount campaigns" is the process of analyzing user data and sentiment data and proposing new services and discount campaigns to providers based on the results of that analysis.

[0365] MODE FOR CARRYING OUT THE INVENTION

[0366] System Overview

[0367] This invention is a system in which an AI analyzes information when a user inputs their purchase history and desired features to recommend the most suitable credit card. This system is combined with an emotion engine that recognizes the user's emotions to achieve more personalized card recommendations. It also uses generative AI to propose new features and services to card providers.

[0368] Hardware and software used

[0369] The system uses the following hardware and software:

[0370] Device: A device used by a user, such as a smartphone, smart glasses, or head-mounted display.

[0371] Emotion engine: Software that analyzes emotions from a user's facial expressions and voice. Built using TensorFlow and PyTorch.

[0372] Server: A computer system that receives data and analyzes it with an AI model. It uses frameworks such as Django or Flask.

[0373] AI model: An algorithm that performs data analysis. Specifically, this includes generative AI models trained in TensorFlow or PyTorch.

[0374] Data processing and calculation

[0375] 1. Sending input data from the terminal:

[0376] Users use a smartphone app to enter their purchase history and desired features.

[0377] For example: "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," and "Travel: 50,000 yen." Select "High point return rate," "Full travel benefits," and "No annual fee" as desired features.

[0378] The emotion engine analyzes facial expressions and voice in real time as the user types in, and generates emotion data.

[0379] These data are transmitted from the terminal to the server.

[0380] 2. Data Receipt and Analysis:

[0381] The server preprocesses the received purchase history, desired features, and emotional data and inputs it into the AI ​​model.

[0382] The AI ​​model performs analysis and lists the most suitable credit cards. Emotional data is also included in the analysis, and recommendations are generated taking into account the user's emotional state.

[0383] 3. Generating and displaying recommendations:

[0384] Based on the analysis results of the AI ​​model, the server generates a list of the most suitable credit cards and their details.

[0385] The results are sent to the terminal and can be viewed by the user.

[0386] Example: "Card X (1.5% point return rate)" "Card Y (travel benefits, no annual fee)"

[0387] 4. New feature suggestions:

[0388] Generative AI analyzes vast amounts of user and emotional data and makes suggestions to credit card providers about adding new features and services.

[0389] Example prompt sentence:

[0390] "The user's purchase history is as follows: Food: 30,000 yen, Entertainment: 10,000 yen, Travel: 50,000 yen. Desired features: High point reward rate, ample travel benefits, no annual fee. Emotional state: Satisfied. Please suggest the best credit card based on this information."

[0391] In this way, the present invention provides a means for users to quickly and easily find the best credit card for them, and by taking into account the user's emotions, it realizes more personalized recommendations.It also provides a system that can propose new features and services to credit card providers based on useful data.

[0392] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0393] Step 1:

[0394] The user uses the terminal to input their purchase history and desired features.

[0395] The input items include, for example, "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," "Travel: 50,000 yen," and desired features such as "High point return rate," "Full travel benefits," and "No annual fee." This data is collected by the device.

[0396] Step 2:

[0397] The emotion engine analyzes the user's facial expressions and voice in real time and generates emotion data.

[0398] The input is the user's facial expression and voice data, and the output is a quantified emotional state such as "satisfied," "dissatisfied," or "excited."

[0399] Step 3:

[0400] The device transmits purchase history, desired features, and emotional data to the server.

[0401] The input includes purchase history, desired features, and emotional data collected on the terminal, which are sent as data to the server.

[0402] Step 4:

[0403] The server preprocesses the data received.

[0404] The input includes purchase history, desired features, and sentiment data, and the output is preprocessed data that has been subjected to noise removal and data normalization.

[0405] Step 5:

[0406] The server inputs the preprocessed data into an AI model to analyze the most suitable credit card.

[0407] The preprocessed data is provided as input to the AI ​​model, and a list of optimal credit cards is generated as output, such as "Card X (1.5% reward point rate)" and "Card Y (travel perks, no annual fee)."

[0408] Step 6:

[0409] The server generates recommendations based on the analysis results and sends them to the device.

[0410] The input includes the analysis results of the AI ​​model, and the output generates recommendations to be presented to the user.

[0411] Step 7:

[0412] The user reviews the recommendations on the device and selects the most suitable credit card.

[0413] The input includes the recommendation results sent by the server and the output is the user's selection.

[0414] Step 8:

[0415] The server uses generative AI to suggest new features to add.

[0416] The inputs include a huge amount of user data and emotional data, and the output is suggestions for adding new features and services. A specific example of such a suggestion is a "points redemption function specialized for online shopping."

[0417] This process allows users to quickly select the best credit card, receive personalized recommendations that take their emotions into account, and even suggest new features to credit card providers.

[0418] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0419] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0420] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0421] [Second embodiment]

[0422] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0423] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0424] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0425] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0426] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0427] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0428] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0429] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0430] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0431] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0432] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0433] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0434] System Overview

[0435] This invention is a system in which an AI analyzes information when a user inputs their purchase history and desired features to suggest the most suitable credit card. Furthermore, the AI ​​generation is used to suggest new features and services to card providers. This system saves users time and effort in selecting a credit card, and also helps card providers analyze data to offer more attractive services.

[0436] System configuration

[0437] The system consists of the following components:

[0438] 1. Terminal: The device used by the user, providing an interface for entering purchase history and desired functions and checking the results.

[0439] 2. Server: Receives data sent by the user from the device, analyzes the data using the AI ​​model, and generates and sends the analysis results to the device.

[0440] 3. AI model: Analyzes the received data and performs analytical processing to recommend the best credit card for the user.

[0441] Program processing

[0442] 1. Enter your purchase history and desired features

[0443] A user logs in using a terminal and enters their purchase history and desired features. For example, consider a case where a user enters "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Enriched travel benefits," and "No annual fee" as desired features. This information is sent to the server by the terminal.

[0444] 2. Data Receipt and Analysis

[0445] The server preprocesses the received data and inputs it into the AI ​​model, which then lists the most suitable credit cards based on the customer's purchase history and desired features. The AI ​​model then references past data from similar users to recommend the most suitable card.

[0446] 3. Generating and displaying results

[0447] Based on the analysis results of the AI ​​model, the server generates a list of recommended credit cards for the user and their detailed information (such as point redemption rates and benefits).The results are sent to the terminal so that the user can check them.The user can then select the most suitable card from the presented list.

[0448] 4. Proposal for new feature addition

[0449] The generative AI analyzes massive amounts of user data and makes proposals to credit card providers for the addition of new features and services. For example, if it determines based on the analysis data that adding a "points reward function specialized for online shopping" is likely to increase the number of subscribers, it will report that proposal to the provider.

[0450] Specific examples

[0451] When User A enters his monthly purchase history of "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Rich travel perks," and "No annual fee" as desired features, the input data is sent to the server. The server analyzes the data using an AI model and lists the most suitable credit cards: "Card X (1.5% point return rate)" and "Card Y (travel perks, no annual fee)." The results are sent to the terminal, where User A can check them and select, for example, "Card X." Furthermore, based on the analysis results, the server's generation AI can propose to providers the addition of "point return features specialized for online shopping."

[0452] In this way, the present invention provides a means for users to quickly and easily find the best credit card for them, and is a system that can also propose new functions to credit card providers based on useful data.

[0453] The processing flow will be explained below.

[0454] Step 1:

[0455] The user starts up the device and logs in to the application. The user enters their email address and password and presses the login button.

[0456] Step 2:

[0457] The device sends the user's authentication information, which includes an email address and password, to the server.

[0458] Step 3:

[0459] The server compares the received authentication information with the registration information in the database and authenticates the user. If the authentication is successful, the server sends a login success message to the terminal.

[0460] Step 4:

[0461] The terminal displays a login success message and presents the user with a form to enter their purchase history and desired features.

[0462] Step 5:

[0463] The user enters their purchase history in a specified form, for example, by entering amounts for each category such as food, entertainment, and travel.

[0464] Step 6:

[0465] Users select the features they want, such as points redemption rate, travel benefits, whether or not there is an annual fee, etc., by selecting checkboxes or drop-down menus.

[0466] Step 7:

[0467] The terminal transmits the purchase history and desired function data input by the user to the server.

[0468] Step 8:

[0469] The server pre-processes the data it receives, including formatting and unifying the data.

[0470] Step 9:

[0471] The server inputs the preprocessed data into the AI ​​model, which analyzes the received data and lists the best credit cards for the user.

[0472] Step 10:

[0473] The server generates a list of recommended credit cards and their details based on the analysis results of the AI ​​model.

[0474] Step 11:

[0475] The analysis results generated by the server are sent to the terminal.

[0476] Step 12:

[0477] The terminal displays the analysis results received from the server to the user, including a list of credit cards and their details.

[0478] Step 13:

[0479] The user selects the card that best suits them from the list of credit cards presented.

[0480] Step 14:

[0481] The server uses generated AI to analyze the vast amount of user data collected and make suggestions to credit card providers about adding new features and services.

[0482] Step 15:

[0483] The server generates a proposal to add new features and sends it to the credit card provider.

[0484] Step 16:

[0485] Credit card providers will review your proposal and implement new features and services to improve your competitive position.

[0486] The above is the processing steps and specific operation contents of the present invention.

[0487] Example 1

[0488] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0489] When users choose the best credit card for them, there is a lack of a way to receive prompt and accurate suggestions based on their purchase history and desired features, which makes the selection process time-consuming and labor-intensive.Another issue is that card providers are not properly being suggested new features and services based on users' needs.

[0490] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0491] In this invention, the server includes means for prompting a user to input their purchase history and desired functions, means for receiving the data on the purchase history and desired functions, means for preprocessing the received data and converting it into an analyzable format, artificial intelligence means for analyzing the received and preprocessed data and recommending an optimal credit card, means for generating and presenting the recommendation results to the user, and means for proposing the addition of new functions based on the generated analysis results. This allows the user to quickly and accurately receive a recommendation for the optimal credit card and to make proposals for new functions and services to the card provider.

[0492] "User" refers to a person who uses the system to input their purchase history and desired features and receive suggestions for the most suitable credit card.

[0493] "Purchase history" refers to data regarding the price and category of products purchased by a user in the past.

[0494] "Desired features" refer to the benefits and service requirements that users want from a credit card.

[0495] "Server" refers to a computer system that receives, processes, and analyzes data sent by users.

[0496] "Means of preprocessing data and converting it into an analyzable format" refers to the process of formatting the received data into a form that is easy for the AI ​​model to analyze.

[0497] "Artificial intelligence means" refers to machine learning models and algorithms that analyze the received and pre-processed data and recommend the most suitable credit card.

[0498] "Means for generating and presenting recommended results to the user" refers to the process of displaying a list and details of the most suitable credit cards to the user based on the analysis results.

[0499] "Means for proposing new features" refers to the process of proposing new features and services to card providers based on the generated analysis results.

[0500] The present invention is a system in which an AI analyzes a user's purchase history and desired features and then proposes the most suitable credit card. Furthermore, the system uses the generation AI to propose new features and services to card providers. Specific details for implementing the present invention are described below.

[0501] System Configuration

[0502] The system consists of the following components:

[0503] 1. Terminal: A device used by a user that provides an interface for entering purchase history and desired functions and checking the results. Examples of terminals include smartphones and PCs.

[0504] 2. Server: Receives data sent by the user from the device and analyzes the data using an AI model. It also generates the analysis results and sends them to the device. A high-performance computing server is used as the server.

[0505] 3. AI model: Analyzes the received data and performs analysis to recommend the best credit card for the user. The AI ​​model uses machine learning frameworks such as TensorFlow and PyTorch.

[0506] Hardware and software used

[0507] Hardware

[0508] Devices: smartphones, computers

[0509] Server: High-performance computing server

[0510] software

[0511] AI models: TensorFlow, PyTorch

[0512] Database management systems: MySQL, PostgreSQL

[0513] Interface software: React, Vue.js

[0514] Specific examples of program processing

[0515] The user logs in to the system on the terminal. After logging in, the user follows the system's instructions and enters their monthly purchase history and desired credit card features.

[0516] For example, user A enters the following data:

[0517] Purchase History:

[0518] Food expenses: 30,000 yen

[0519] Entertainment expenses: 10,000 yen

[0520] Travel: 50,000 yen

[0521] Desired features:

[0522] High point return rate

[0523] Extensive travel benefits

[0524] No annual fee

[0525] This input data is sent from the device to a server, where it is received and pre-processed. The pre-processed data is then input into an AI model, which references similar past data to create a list of the most suitable credit cards for the user.

[0526] For example, the AI ​​model will list "Card X (point return rate 1.5%)" and "Card Y (travel benefits, no annual fee)" as the analysis results. These results are sent to the terminal via the server, where User A can check them. User A can then select the most suitable credit card from the presented list.

[0527] Furthermore, based on the analysis results, the generative AI will propose new features to card providers, such as a point reward function specialized for online shopping, allowing card providers to develop and provide new features and services based on user needs.

[0528] An example of a prompt for this system is:

[0529] Prompt statement:

[0530] Purchase History:

[0531] Food expenses: 30,000 yen

[0532] Entertainment expenses: 10,000 yen

[0533] Travel: 50,000 yen

[0534] Desired features:

[0535] High point return rate

[0536] Extensive travel benefits

[0537] No annual fee

[0538] In this way, the present invention provides users with a means for quickly and easily finding the best credit card, and also allows card providers to make suggestions for adding new functions based on useful data.

[0539] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0540] Step 1:

[0541] A user logs in to the system using a terminal. On the login screen, the user enters their user ID and password. The entered authentication information is sent from the terminal to the server. The server authenticates the user based on the received information, and if authentication is successful, the main screen is displayed.

[0542] Step 2:

[0543] The user enters their purchase history and desired features on the main screen. For example, they enter the following data:

[0544] Purchase history: Food: 30,000 yen, Entertainment: 10,000 yen, Travel: 50,000 yen

[0545] Desired features: High point redemption rate, extensive travel benefits, no annual fee

[0546] The input data is transmitted from the terminal to the server.

[0547] Step 3:

[0548] The server receives the data sent from the device. After receiving the data, it performs pre-processing on the data. This processing includes data cleaning (e.g., filling in missing values) and data normalization (e.g., scaling numerical data). The pre-processed data is converted into an analyzable format and input into the AI ​​model. For example, a user's monthly expenditure data is converted into an appropriate numerical format.

[0549] Step 4:

[0550] The server inputs the preprocessed data into the AI ​​model. The AI ​​model analyzes the input data and lists the most suitable credit cards based on the user's purchase history and desired features. The AI ​​model references past similar user data to select the most suitable card. For example, it may obtain results such as "Card X (1.5% points return rate)" and "Card Y (travel benefits, no annual fee)."

[0551] Step 5:

[0552] The server receives the recommendations generated by the AI ​​model. Based on the recommendations, it generates data to display to the user. This generation process includes adding details about the recommended credit card (e.g., reward points and benefits) and converting the data into an easy-to-read format. The generated information is then sent to the device.

[0553] Step 6:

[0554] The terminal displays the recommended results received from the server to the user, who can then review the list of credit cards presented and select the card in the most suitable category.

[0555] Step 7:

[0556] The generative AI generates proposals for adding new features and services to card providers based on the analyzed data. The proposals are sent from the server to the providers. For example, it may propose new features such as a "points redemption function specialized for online shopping" based on user trends.

[0557] (Application example 1)

[0558] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0559] Conventional credit card recommendation systems are unable to adequately address a user's individual purchasing history or desired features, making it difficult to provide the appropriate card to the user. Furthermore, when users engage in a variety of purchasing activities, it is difficult to find the optimal card to use, especially on online shopping sites. Furthermore, it is also difficult to propose appropriate new features and services to card providers. To solve these problems, a system is needed that can respond to the diverse needs of users and efficiently recommend the most suitable credit card for online shopping sites.

[0560] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0561] In this invention, the server includes a means for prompting the user to input their purchase history and desired features, a server means for receiving the data on the purchase history and desired features, and an AI model means for analyzing the received data and recommending the most suitable credit card. This makes it possible to efficiently recommend the most suitable credit card for use on the online shopping site based on the information entered by the user.

[0562] A "user" is an individual or corporation who uses the system to input purchase history and desired features and receive credit card recommendations.

[0563] "Purchase history" is information about transactions and purchases that a user has made in the past, and is data entered by category, such as food expenses, entertainment expenses, and travel expenses.

[0564] "Desired features" refers to the benefits and features that users want from a credit card, and include specific conditions such as point redemption rates, travel benefits, and no annual fees.

[0565] A "server" is a computer system that receives data sent by users and provides it to an AI model for analysis.

[0566] An "AI model" is an artificial intelligence model that analyzes user input data and recommends the most suitable credit card.

[0567] "Recommended results" are a list of optimal credit cards presented to the user based on the results of the AI ​​model's analysis.

[0568] "Proposing new features" refers to using generative AI to analyze accumulated user data and recommend new features and services to credit card providers.

[0569] An "online shopping site" is a website that offers products and services over the Internet and allows users to make purchases.

[0570] "Suitability for use on a shopping site" is a characteristic that indicates whether the credit card is most suitable for use by a user on a shopping site.

[0571] This invention is a system that analyzes data entered by users based on their purchase history and desired features, and recommends the most suitable credit card. The system consists of a terminal used by the user, a server that receives and analyzes the data, and an AI model that presents the analysis results. The system also uses generative AI to propose new features and services to credit card providers.

[0572] System Overview

[0573] First, the user uses the terminal to input their purchase history and desired features. For example, they might input purchase history such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," as well as desired features such as "High point return rate," "Comprehensive travel benefits," and "No annual fee." This information is sent from the terminal to the server.

[0574] The server preprocesses the received data and inputs it into the AI ​​model. The AI ​​model then lists the most suitable credit cards based on the user's purchase history and desired features. For example, based on the user's input data, the model can recommend "Card X (1.5% reward point rate)" and "Card Y (travel benefits, no annual fee)."

[0575] Hardware and software used

[0576] Hardware: Smartphone (user device), server

[0577] software:

[0578] Flask: A Python web framework

[0579] TensorFlow: A framework for AI models

[0580] scikit-learn: A library for data preprocessing

[0581] Data processing and calculation

[0582] The server properly formats the data sent by the user, including their purchase history and desired features, and scales it so that the AI ​​model can analyze it. The received data is converted into numerical data through a standardization process. The AI ​​model then analyzes the data and outputs the optimal credit card recommendation.

[0583] The analysis results are sent to the user's device based on the recommendation list generated by the AI ​​model, allowing the user to review the results and select the most suitable credit card.

[0584] In addition, generative AI will analyze massive amounts of user data and suggest new features and services to credit card providers, such as adding a "points reward function specialized for online shopping."

[0585] Specific examples

[0586] When User A enters his monthly purchase history, such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Rich travel perks," and "No annual fee" as desired features, the input data is sent to the server. The server uses an AI model to analyze the data and create a list of options, such as "Card X (1.5% point return rate)" and "Card Y (travel perks available, no annual fee)."

[0587] Prompt Sentence Examples

[0588] If User B enters his monthly purchase history (food: 25,000 yen, entertainment: 20,000 yen, travel: 10,000 yen) and selects "high point return rate" and "full travel benefits" as desired features, the data is sent to the server. The server uses an AI model to analyze the data and create a list of cards, such as "Card A (point return rate 2.0%)" and "Card B (full travel benefits, no annual fee)."

[0589] Example prompt sentence:

[0590] User purchase history:

[0591] Food expenses: 25,000 yen

[0592] Entertainment expenses: 20,000 yen

[0593] Travel: 10,000 yen

[0594] Desired credit card features:

[0595] High point redemption rate

[0596] Extensive travel benefits

[0597] Please suggest the best credit card for me.

[0598] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0599] Step 1:

[0600] The user enters their purchase history and desired features.

[0601] Using their smartphone or other device, users input their purchase history, such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," as well as desired credit card features, such as "High point return rate," "Plenty of travel benefits," and "No annual fee." The input data is sent from the user device to the server.

[0602] Step 2:

[0603] The server preprocesses the data received.

[0604] The server receives the purchase history and desired feature data sent by the user and performs a standardization process using the scikit-learn library to standardize and scale this data, for example, converting numerical data into an appropriate range, which makes it easier for the AI ​​model to analyze the data.

[0605] Step 3:

[0606] The server inputs the preprocessed data into the AI ​​model for analysis.

[0607] The server inputs the preprocessed data into the AI ​​model, which analyzes the data and generates a list of optimal credit cards based on the user's purchasing history and desired features. This analysis refers to past data of similar users to identify the most suitable credit cards.

[0608] Step 4:

[0609] The server generates recommendation results and sends them to the user terminal.

[0610] The server creates a list of recommended credit cards for the user based on the analysis results generated by the AI ​​model. This list includes detailed information such as the credit card name, point redemption rate, and benefits. This list is then sent to the user's device in JSON format or similar.

[0611] Step 5:

[0612] The user reviews the recommendations and selects a credit card.

[0613] The user can review the recommended credit card list displayed on the terminal and select the most suitable credit card. The user can compare the details of each card and choose the card that best suits their needs.

[0614] Step 6:

[0615] The server uses generated AI to propose new features to credit card providers.

[0616] The server analyzes a huge amount of user data and proposes new features and services to credit card providers. In this processing step, new features such as a "points redemption function specialized for online shopping" are proposed to the provider. These proposals are generated from the results of AI analysis based on user data.

[0617] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0618] System Overview

[0619] This invention is a system in which an AI analyzes information when a user inputs their purchase history and desired features to recommend the most suitable credit card. Furthermore, the AI ​​generation system is used to propose new features and services to card providers. This system is combined with an emotion engine that recognizes the user's emotions, enabling more personalized card recommendations. The emotion engine analyzes the user's emotions when inputting information and influences the recommendation results.

[0620] System configuration

[0621] The system consists of the following components:

[0622] 1. Terminal: A device used by users that provides an interface for inputting purchase history and desired features and checking the results. It also has an emotion engine that analyzes user emotions in real time.

[0623] 2. Server: Receives data sent by the user from the device, analyzes the data using the AI ​​model, and generates and sends the analysis results to the device.

[0624] 3. AI model: Analyzes the received data and performs analytical processing to recommend the best credit card for the user.

[0625] 4. Emotion Engine: Analyzes the user's emotions and sends the analysis results to the server, which then adjusts the recommendation results based on this emotional data.

[0626] Program processing

[0627] 1. Enter your purchase history and desired features

[0628] A user logs in using a terminal and enters their purchase history and desired features. For example, consider a case where a user enters "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Enriched travel benefits," and "No annual fee" as desired features. This information is sent to the server by the terminal.

[0629] 2. Acquiring Emotion Data

[0630] The emotion engine installed in the device analyzes the facial expressions and voices of users when they input information, and obtains emotional data in real time. For example, when a user expresses emotions such as "satisfaction," "dissatisfaction," or "excitement," the emotion engine converts these into numerical values.

[0631] 3. Data Receipt and Analysis

[0632] The server preprocesses the received purchase history, desired features, and emotional data and inputs it into the AI ​​model. The AI ​​model analyzes this data and lists the most suitable credit cards. At this time, it also includes emotional data in its analysis, making recommendations that reflect the user's emotional state.

[0633] 4. Generating and displaying results

[0634] Based on the analysis results of the AI ​​model, the server generates a list of recommended credit cards for the user and their detailed information (such as point redemption rates and benefits).The results are sent to the terminal so that the user can check them.The user can then select the most suitable card from the presented list.

[0635] 5. Proposal for new feature addition

[0636] The generative AI analyzes massive amounts of user data and emotional data and makes proposals to credit card providers for the addition of new features and services. For example, if it determines based on the analysis data that adding a "points reward feature specialized for online shopping" is likely to increase the number of subscribers, it will report that proposal to the provider.

[0637] Specific examples

[0638] User A enters his monthly purchase history (food: ¥30,000), entertainment: ¥10,000, and travel: ¥50,000) and selects his desired features (high point redemption rate, extensive travel perks, and no annual fee). The input data is sent to the server. The server analyzes the data using an AI model and lists the most suitable credit cards: Card X (1.5% point redemption rate) and Card Y (travel perks, no annual fee). The results are sent to the device, where User A can review them and select, for example, Card X. Based on the analysis results, the server's generation AI can also suggest to the provider that a new "point redemption feature specialized for online shopping" be added. During this process, the emotion engine analyzes User A's emotions at the time of input, and this emotional data also influences the recommendation results.

[0639] In this way, the present invention provides a means for users to quickly and easily find the best credit card for them, and by taking into account the user's emotions, it is possible to make more personalized recommendations.It is also a system that can propose new features to credit card providers based on useful data.

[0640] The processing flow will be explained below.

[0641] Step 1:

[0642] The user starts up the device and logs in to the application. The user enters their email address and password and presses the login button.

[0643] Step 2:

[0644] The device sends the user's authentication information, which includes an email address and password, to the server.

[0645] Step 3:

[0646] The server compares the received authentication information with the registration information in the database and authenticates the user. If the authentication is successful, the server sends a login success message to the terminal.

[0647] Step 4:

[0648] The device displays a login success message and a form for the user to enter their purchase history and desired features. At this point, the device's built-in emotion engine begins to operate and begins to collect emotion data from the user's facial expressions and voice.

[0649] Step 5:

[0650] The user enters their purchase history into a specified form. For example, they enter amounts for each category, such as food, entertainment, and travel. The emotion engine analyzes the user's emotions from their facial expressions and voice when entering data, and sends the results to the server in real time.

[0651] Step 6:

[0652] The user selects the desired features, such as points redemption rate, travel benefits, whether or not there is an annual fee, etc., using checkboxes or drop-down menus. The emotion engine continues to obtain emotion data and sends it to the server.

[0653] Step 7:

[0654] The terminal transmits the purchase history and desired function data input by the user, as well as emotion data from the emotion engine, to the server.

[0655] Step 8:

[0656] The server preprocesses the received purchase history, desired features, and sentiment data, including data cleanup and formatting.

[0657] Step 9:

[0658] The server inputs the preprocessed data into an AI model, which analyzes purchase history, desired features, and emotional data to create a list of the most suitable credit cards.

[0659] Step 10:

[0660] The server generates a list of recommended credit cards and their details based on the analysis results of the AI ​​model, and this list also reflects the user's satisfaction and interest level as indicated by the emotional data.

[0661] Step 11:

[0662] The server generates analysis results and sends them to the device, including the reason for the recommendation based on the emotional data.

[0663] Step 12:

[0664] The device receives the analysis results from the server and displays them to the user, including a list of credit cards and their details, as well as the reasons for the recommendations based on the user's emotional data.

[0665] Step 13:

[0666] Users can select the card that best suits them from a list of credit cards presented to them, while checking the reasons why each card is recommended.

[0667] Step 14:

[0668] The server uses generative AI to analyze the vast amount of collected user data and sentiment data and make suggestions to credit card providers about adding new features and services.

[0669] Step 15:

[0670] The server generates a proposal for adding new features and sends it to the credit card provider, which also reflects the user's needs and satisfaction based on the emotional data.

[0671] Step 16:

[0672] Credit card providers will review your proposal and implement new features and services to improve your competitive position.

[0673] Example 2

[0674] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0675] Conventional credit card recommendation systems only considered a user's purchase history and desired features when making recommendations, which resulted in problems in which the system was unable to fully reflect the user's emotions and individual needs. Furthermore, proposals for new features to card providers did not take into account the user's emotional data, making it difficult to reflect actual user needs. This made it difficult for users to find the optimal credit card that satisfied them, and for card providers to add effective services.

[0676] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0677] In this invention, the server includes a terminal means for acquiring user emotion data, an AI model means for preprocessing the received purchase history, desired features, and emotion data to recommend the most suitable credit card, and a generation AI means for proposing the addition of new functions based on the generated analysis results. This enables analysis including emotion data, making it possible to recommend more personalized credit cards and propose the addition of new functions that reflect the user's needs.

[0678] "Purchase history" refers to data relating to past purchases of products and services made by a user.

[0679] "Desired features" refers to the requirements for benefits and services that come with the credit card that the user desires.

[0680] A "server" is a central computer that receives, analyzes, and processes data sent by users.

[0681] "Emotion data" is data that quantifies the user's emotional state and is based on an analysis of facial expressions and voice at the time of input.

[0682] A "terminal" is a device operated by a user, and is a device for inputting data and acquiring emotion data.

[0683] An "AI model" is an analytical system built with algorithms based on artificial intelligence, which is used to recommend the most suitable credit card based on user data.

[0684] "Generative AI" is an artificial intelligence system that analyzes user data and emotional data to propose new features and services.

[0685] "Recommended results" are a list and detailed information of the most suitable credit cards for the user, generated as a result of the AI ​​model's analysis.

[0686] This invention relates to a system in which, when a user inputs their purchase history and desired features, AI analyzes the information and suggests the most suitable credit card. This system achieves more personalized card recommendations by combining it with an emotion engine that recognizes the user's emotions. Specific configurations and processing procedures based on the roles of the server, terminal, and user are explained.

[0687] System configuration

[0688] 1. Terminal

[0689] It is a device used by users that provides an interface for inputting purchase history and desired functions and checking the results. It also has an emotion engine (e.g., Microsoft Azure Cognitive Services or Emotion API) that analyzes the emotions of users as they input data in real time.

[0690] 2. Server

[0691] It receives data sent by the user from the device, analyzes the data using an AI model (e.g., TensorFlow, PyTorch), and generates and sends the analysis results to the device.

[0692] 3. AI Model

[0693] The received data is analyzed and processed to recommend the best credit card for the user. A deep learning framework (e.g. TensorFlow) can be used for construction.

[0694] 4. Emotion Engine

[0695] The user's emotions are analyzed and the analysis results are sent to the server, which then adjusts the recommendation results based on this emotional data. The emotion engine can use facial recognition technology and voice analysis technology.

[0696] Specific operation of the system

[0697] The user logs in to the device and enters their purchase history and desired features. For example, they enter purchase history such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," and select the desired features as "High point return rate," "Enriched travel benefits," and "No annual fee." This data is sent to the server by the device.

[0698] Next, the device's built-in emotion engine analyzes the user's facial expressions and voice in real time to obtain emotion data. This emotion data is then quantified, for example, as "Satisfied: 80%," "Dissatisfied: 10%," or "Excited: 10%." This emotion data is also sent to the server.

[0699] The server preprocesses the received purchase history, desired features, and sentiment data and inputs it into the AI ​​model. The AI ​​model analyzes this data and lists the most suitable credit cards. For example, it might recommend "Card X (1.5% reward point rate)" or "Card Y (travel benefits, no annual fee)."

[0700] The analysis results are sent from the server to the device and presented to the user. The user can then select the most suitable card from the recommended list. For example, if the user selects "Card X," the selection is also sent to the server and reflected in the final list.

[0701] The generative AI also analyzes the accumulated user data and emotional data to propose new features and services to credit card providers. For example, a "points redemption feature specialized for online shopping" may be proposed based on the analysis data.

[0702] Prompt Sentence Examples

[0703] Purchase history and desired features entered by the user:

[0704] Food: 30,000 yen, Entertainment: 10,000 yen, Travel: 50,000 yen

[0705] Desired features: high point redemption rate, extensive travel benefits, no annual fee

[0706] Emotional Data:

[0707] Satisfaction: 80%, Dissatisfaction: 10%, Excitement: 10%

[0708] Use this information to recommend the best credit cards for you, and also suggest new features that should be added.

[0709] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0710] Step 1:

[0711] The user enters their purchase history and desired features on the device.

[0712] Specifically, the user enters "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen" as purchase history on the device's GUI interface, and selects "High point return rate," "Enriched travel benefits," and "No annual fee" as desired features. This information is used for subsequent processing, and is saved as digital data within the device.

[0713] Input: Purchase history, desired features

[0714] Output: Digital data in the terminal

[0715] Step 2:

[0716] The device acquires emotion data.

[0717] Specifically, the device's built-in emotion engine analyzes the user's facial expressions and voice in real time and quantifies the emotional data. For example, the user's facial expressions and tone of voice when inputting information can be analyzed as "Satisfaction: 80%," "Dissatisfaction: 10%," and "Excitement: 10%."

[0718] Input: User's facial expression, voice

[0719] Output: Emotion data (quantified data)

[0720] Step 3:

[0721] The server receives the input data and the emotion data.

[0722] The device sends purchase history, desired features, and emotional data to the server, which receives this data and stores it in an initial database.

[0723] Input: purchase history, desired features, emotional data

[0724] Output: Data stored in the initial database on the server

[0725] Step 4:

[0726] The server preprocesses the data.

[0727] Specifically, the data format is standardized on the server, unnecessary data is filtered out, and preprocessing such as normalizing data with different units is performed. After preprocessing is complete, the data is converted into a format suitable for input into the AI ​​model.

[0728] Input: Data stored in the initial database

[0729] Output: Data in a format that can be input into an AI model

[0730] Step 5:

[0731] The AI ​​model analyzes the most suitable credit card.

[0732] The server inputs the preprocessed data into an AI model for analysis. The AI ​​model then lists the most suitable credit cards based on the customer's purchase history, desired features, and emotional data. As a result, it recommends cards such as "Card X (1.5% reward point rate)" and "Card Y (travel benefits, no annual fee)."

[0733] Input: Data in a format that can be fed into an AI model

[0734] Output: A list of recommended credit cards

[0735] Step 6:

[0736] The server generates the analysis results and sends them to the terminal.

[0737] Based on the analysis results of the AI ​​model, the server generates a list of recommended credit cards for the user along with detailed information (e.g., point redemption rate, benefits), and sends this result to the terminal.

[0738] Input: A list of recommended credit cards

[0739] Output: Analysis results sent to the device

[0740] Step 7:

[0741] The user reviews the recommendations and selects a card.

[0742] The user checks the analysis results received on the terminal and selects the most suitable card from the listed credit cards. For example, they can select "Card X." The selected card information is sent to the server and reflected in the final list.

[0743] Input: Analysis results sent to the device

[0744] Output: Selected credit card information

[0745] Step 8:

[0746] Generative AI will suggest new features to add.

[0747] The generative AI analyzes the accumulated user data and emotional data and proposes new features and services to card providers. For example, it may propose a "points redemption feature specialized for online shopping."

[0748] Input: User data, emotion data

[0749] Output: New feature suggestions to card providers

[0750] (Application example 2)

[0751] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0752] Conventional credit card recommendation systems suggest the most suitable card based on a user's purchase history and desired features, but they are unable to provide personalized recommendations that take into account the user's emotions. It is also difficult to use the data obtained to suggest new features or specific campaigns. As a result, users are unable to receive more satisfying recommendations, and providers are unable to obtain sufficient useful information.

[0753] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0754] In this invention, the server includes means for prompting the user to input their purchase history and desired features, server means for receiving the data on the purchase history and desired features, AI model means for analyzing the received data and recommending the most suitable credit card, means for generating and presenting the recommendation results to the user, means for proposing the addition of new features based on the generated analysis results, means for performing sentiment analysis, means for recommending a more personalized credit card based on the analysis results, and means for generating proposals for new features and discount campaigns. This enables personalized recommendations that take the user's emotions into consideration, and also enables providers to propose new features and campaigns.

[0755] "Purchase history" refers to data on past purchases of products or services made by a user.

[0756] "Desired features" refers to specific features such as new benefits or conditions that the user desires, such as a point return rate or no annual fee.

[0757] A "server" is a computer system for receiving and processing data from users.

[0758] An "AI model" is a system that uses artificial intelligence to analyze data and includes an algorithm to recommend the best credit card for the user.

[0759] "Emotion analysis" is the process of analyzing a user's emotional state from facial expressions, voice, etc., and acquiring this as data.

[0760] "Recommended results" refers to the list of optimal credit cards presented to the user as a result of the AI ​​model's analysis.

[0761] "New feature addition proposal" is the process of making proposals to credit card providers for adding new features and services based on user data.

[0762] "Personalized recommendations" refers to individually suggesting the best credit card for each user based on their characteristics and emotional state.

[0763] "Proposing new features and discount campaigns" is the process of analyzing user data and sentiment data and proposing new services and discount campaigns to providers based on the results of that analysis.

[0764] MODE FOR CARRYING OUT THE INVENTION

[0765] System Overview

[0766] This invention is a system in which an AI analyzes information when a user inputs their purchase history and desired features to recommend the most suitable credit card. This system is combined with an emotion engine that recognizes the user's emotions to achieve more personalized card recommendations. It also uses generative AI to propose new features and services to card providers.

[0767] Hardware and software used

[0768] The system uses the following hardware and software:

[0769] Device: A device used by a user, such as a smartphone, smart glasses, or head-mounted display.

[0770] Emotion engine: Software that analyzes emotions from a user's facial expressions and voice. Built using TensorFlow and PyTorch.

[0771] Server: A computer system that receives data and analyzes it with an AI model. It uses frameworks such as Django or Flask.

[0772] AI model: An algorithm that performs data analysis. Specifically, this includes generative AI models trained in TensorFlow or PyTorch.

[0773] Data processing and calculation

[0774] 1. Sending input data from the terminal:

[0775] Users use a smartphone app to enter their purchase history and desired features.

[0776] For example: "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," and "Travel: 50,000 yen." Select "High point return rate," "Full travel benefits," and "No annual fee" as desired features.

[0777] The emotion engine analyzes facial expressions and voice in real time as the user types in, and generates emotion data.

[0778] These data are transmitted from the terminal to the server.

[0779] 2. Data Receipt and Analysis:

[0780] The server preprocesses the received purchase history, desired features, and emotional data and inputs it into the AI ​​model.

[0781] The AI ​​model performs analysis and lists the most suitable credit cards. Emotional data is also included in the analysis, and recommendations are generated taking into account the user's emotional state.

[0782] 3. Generating and displaying recommendations:

[0783] Based on the analysis results of the AI ​​model, the server generates a list of the most suitable credit cards and their details.

[0784] The results are sent to the terminal and can be viewed by the user.

[0785] Example: "Card X (1.5% point return rate)" "Card Y (travel benefits, no annual fee)"

[0786] 4. New feature suggestions:

[0787] Generative AI analyzes vast amounts of user and emotional data and makes suggestions to credit card providers about adding new features and services.

[0788] Example prompt sentence:

[0789] "The user's purchase history is as follows: Food: 30,000 yen, Entertainment: 10,000 yen, Travel: 50,000 yen. Desired features: High point reward rate, ample travel benefits, no annual fee. Emotional state: Satisfied. Please suggest the best credit card based on this information."

[0790] In this way, the present invention provides a means for users to quickly and easily find the best credit card for them, and by taking into account the user's emotions, it realizes more personalized recommendations.It also provides a system that can propose new features and services to credit card providers based on useful data.

[0791] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0792] Step 1:

[0793] The user uses the terminal to input their purchase history and desired features.

[0794] The input items include, for example, "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," "Travel: 50,000 yen," and desired features such as "High point return rate," "Full travel benefits," and "No annual fee." This data is collected by the device.

[0795] Step 2:

[0796] The emotion engine analyzes the user's facial expressions and voice in real time and generates emotion data.

[0797] The input is the user's facial expression and voice data, and the output is a quantified emotional state such as "satisfied," "dissatisfied," or "excited."

[0798] Step 3:

[0799] The device transmits purchase history, desired features, and emotional data to the server.

[0800] The input includes purchase history, desired features, and emotional data collected on the terminal, which are sent as data to the server.

[0801] Step 4:

[0802] The server preprocesses the data received.

[0803] The input includes purchase history, desired features, and sentiment data, and the output is preprocessed data that has been subjected to noise removal and data normalization.

[0804] Step 5:

[0805] The server inputs the preprocessed data into an AI model to analyze the most suitable credit card.

[0806] The preprocessed data is provided as input to the AI ​​model, and a list of optimal credit cards is generated as output, such as "Card X (1.5% reward point rate)" and "Card Y (travel perks, no annual fee)."

[0807] Step 6:

[0808] The server generates recommendations based on the analysis results and sends them to the device.

[0809] The input includes the analysis results of the AI ​​model, and the output generates recommendations to be presented to the user.

[0810] Step 7:

[0811] The user reviews the recommendations on the device and selects the most suitable credit card.

[0812] The input includes the recommendation results sent by the server and the output is the user's selection.

[0813] Step 8:

[0814] The server uses generative AI to suggest new features to add.

[0815] The inputs include a huge amount of user data and emotional data, and the output is suggestions for adding new features and services. A specific example of such a suggestion is a "points redemption function specialized for online shopping."

[0816] This process allows users to quickly select the best credit card, receive personalized recommendations that take their emotions into account, and even suggest new features to credit card providers.

[0817] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0818] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0819] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0820] [Third embodiment]

[0821] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0822] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0823] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0824] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0825] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0826] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0827] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0828] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0829] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0830] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0831] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0832] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0833] System Overview

[0834] This invention is a system in which an AI analyzes information when a user inputs their purchase history and desired features to suggest the most suitable credit card. Furthermore, the AI ​​generation is used to suggest new features and services to card providers. This system saves users time and effort in selecting a credit card, and also helps card providers analyze data to offer more attractive services.

[0835] System configuration

[0836] The system consists of the following components:

[0837] 1. Terminal: The device used by the user, providing an interface for entering purchase history and desired functions and checking the results.

[0838] 2. Server: Receives data sent by the user from the device, analyzes the data using the AI ​​model, and generates and sends the analysis results to the device.

[0839] 3. AI model: Analyzes the received data and performs analytical processing to recommend the best credit card for the user.

[0840] Program processing

[0841] 1. Enter your purchase history and desired features

[0842] A user logs in using a terminal and enters their purchase history and desired features. For example, consider a case where a user enters "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Enriched travel benefits," and "No annual fee" as desired features. This information is sent to the server by the terminal.

[0843] 2. Data Receipt and Analysis

[0844] The server preprocesses the received data and inputs it into the AI ​​model, which then lists the most suitable credit cards based on the customer's purchase history and desired features. The AI ​​model then references past data from similar users to recommend the most suitable card.

[0845] 3. Generating and displaying results

[0846] Based on the analysis results of the AI ​​model, the server generates a list of recommended credit cards for the user and their detailed information (such as point redemption rates and benefits).The results are sent to the terminal so that the user can check them.The user can then select the most suitable card from the presented list.

[0847] 4. Proposal for new feature addition

[0848] The generative AI analyzes massive amounts of user data and makes proposals to credit card providers for the addition of new features and services. For example, if it determines based on the analysis data that adding a "points reward function specialized for online shopping" is likely to increase the number of subscribers, it will report that proposal to the provider.

[0849] Specific examples

[0850] When User A enters his monthly purchase history of "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Rich travel perks," and "No annual fee" as desired features, the input data is sent to the server. The server analyzes the data using an AI model and lists the most suitable credit cards: "Card X (1.5% point return rate)" and "Card Y (travel perks, no annual fee)." The results are sent to the terminal, where User A can check them and select, for example, "Card X." Furthermore, based on the analysis results, the server's generation AI can propose to providers the addition of "point return features specialized for online shopping."

[0851] In this way, the present invention provides a means for users to quickly and easily find the best credit card for them, and is a system that can also propose new functions to credit card providers based on useful data.

[0852] The processing flow will be explained below.

[0853] Step 1:

[0854] The user starts up the device and logs in to the application. The user enters their email address and password and presses the login button.

[0855] Step 2:

[0856] The device sends the user's authentication information, which includes an email address and password, to the server.

[0857] Step 3:

[0858] The server compares the received authentication information with the registration information in the database and authenticates the user. If the authentication is successful, the server sends a login success message to the terminal.

[0859] Step 4:

[0860] The terminal displays a login success message and presents the user with a form to enter their purchase history and desired features.

[0861] Step 5:

[0862] The user enters their purchase history in a specified form, for example, by entering amounts for each category such as food, entertainment, and travel.

[0863] Step 6:

[0864] Users select the features they want, such as points redemption rate, travel benefits, whether or not there is an annual fee, etc., by selecting checkboxes or drop-down menus.

[0865] Step 7:

[0866] The terminal transmits the purchase history and desired function data input by the user to the server.

[0867] Step 8:

[0868] The server pre-processes the data it receives, including formatting and unifying the data.

[0869] Step 9:

[0870] The server inputs the preprocessed data into the AI ​​model, which analyzes the received data and lists the best credit cards for the user.

[0871] Step 10:

[0872] The server generates a list of recommended credit cards and their details based on the analysis results of the AI ​​model.

[0873] Step 11:

[0874] The analysis results generated by the server are sent to the terminal.

[0875] Step 12:

[0876] The terminal displays the analysis results received from the server to the user, including a list of credit cards and their details.

[0877] Step 13:

[0878] The user selects the card that best suits them from the list of credit cards presented.

[0879] Step 14:

[0880] The server uses generated AI to analyze the vast amount of user data collected and make suggestions to credit card providers about adding new features and services.

[0881] Step 15:

[0882] The server generates a proposal to add new features and sends it to the credit card provider.

[0883] Step 16:

[0884] Credit card providers will review your proposal and implement new features and services to improve your competitive position.

[0885] The above is the processing steps and specific operation contents of the present invention.

[0886] Example 1

[0887] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0888] When users choose the best credit card for them, there is a lack of a way to receive prompt and accurate suggestions based on their purchase history and desired features, which makes the selection process time-consuming and labor-intensive.Another issue is that card providers are not properly being suggested new features and services based on users' needs.

[0889] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0890] In this invention, the server includes means for prompting a user to input their purchase history and desired functions, means for receiving the data on the purchase history and desired functions, means for preprocessing the received data and converting it into an analyzable format, artificial intelligence means for analyzing the received and preprocessed data and recommending an optimal credit card, means for generating and presenting the recommendation results to the user, and means for proposing the addition of new functions based on the generated analysis results. This allows the user to quickly and accurately receive a recommendation for the optimal credit card and to make proposals for new functions and services to the card provider.

[0891] "User" refers to a person who uses the system to input their purchase history and desired features and receive suggestions for the most suitable credit card.

[0892] "Purchase history" refers to data regarding the price and category of products purchased by a user in the past.

[0893] "Desired features" refer to the benefits and service requirements that users want from a credit card.

[0894] "Server" refers to a computer system that receives, processes, and analyzes data sent by users.

[0895] "Means of preprocessing data and converting it into an analyzable format" refers to the process of formatting the received data into a form that is easy for the AI ​​model to analyze.

[0896] "Artificial intelligence means" refers to machine learning models and algorithms that analyze the received and pre-processed data and recommend the most suitable credit card.

[0897] "Means for generating and presenting recommended results to the user" refers to the process of displaying a list and details of the most suitable credit cards to the user based on the analysis results.

[0898] "Means for proposing new features" refers to the process of proposing new features and services to card providers based on the generated analysis results.

[0899] The present invention is a system in which an AI analyzes a user's purchase history and desired features and then proposes the most suitable credit card. Furthermore, the system uses the generation AI to propose new features and services to card providers. Specific details for implementing the present invention are described below.

[0900] System Configuration

[0901] The system consists of the following components:

[0902] 1. Terminal: A device used by a user that provides an interface for entering purchase history and desired functions and checking the results. Examples of terminals include smartphones and PCs.

[0903] 2. Server: Receives data sent by the user from the device and analyzes the data using an AI model. It also generates the analysis results and sends them to the device. A high-performance computing server is used as the server.

[0904] 3. AI model: Analyzes the received data and performs analysis to recommend the best credit card for the user. The AI ​​model uses machine learning frameworks such as TensorFlow and PyTorch.

[0905] Hardware and software used

[0906] Hardware

[0907] Devices: smartphones, computers

[0908] Server: High-performance computing server

[0909] software

[0910] AI models: TensorFlow, PyTorch

[0911] Database management systems: MySQL, PostgreSQL

[0912] Interface software: React, Vue.js

[0913] Specific examples of program processing

[0914] The user logs in to the system on the terminal. After logging in, the user follows the system's instructions and enters their monthly purchase history and desired credit card features.

[0915] For example, user A enters the following data:

[0916] Purchase History:

[0917] Food expenses: 30,000 yen

[0918] Entertainment expenses: 10,000 yen

[0919] Travel: 50,000 yen

[0920] Desired features:

[0921] High point return rate

[0922] Extensive travel benefits

[0923] No annual fee

[0924] This input data is sent from the device to a server, where it is received and pre-processed. The pre-processed data is then input into an AI model, which references similar past data to create a list of the most suitable credit cards for the user.

[0925] For example, the AI ​​model will list "Card X (point return rate 1.5%)" and "Card Y (travel benefits, no annual fee)" as the analysis results. These results are sent to the terminal via the server, where User A can check them. User A can then select the most suitable credit card from the presented list.

[0926] Furthermore, based on the analysis results, the generative AI will propose new features to card providers, such as a point reward function specialized for online shopping, allowing card providers to develop and provide new features and services based on user needs.

[0927] An example of a prompt for this system is:

[0928] Prompt statement:

[0929] Purchase History:

[0930] Food expenses: 30,000 yen

[0931] Entertainment expenses: 10,000 yen

[0932] Travel: 50,000 yen

[0933] Desired features:

[0934] High point return rate

[0935] Extensive travel benefits

[0936] No annual fee

[0937] In this way, the present invention provides users with a means for quickly and easily finding the best credit card, and also allows card providers to make suggestions for adding new functions based on useful data.

[0938] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0939] Step 1:

[0940] A user logs in to the system using a terminal. On the login screen, the user enters their user ID and password. The entered authentication information is sent from the terminal to the server. The server authenticates the user based on the received information, and if authentication is successful, the main screen is displayed.

[0941] Step 2:

[0942] The user enters their purchase history and desired features on the main screen. For example, they enter the following data:

[0943] Purchase history: Food: 30,000 yen, Entertainment: 10,000 yen, Travel: 50,000 yen

[0944] Desired features: High point redemption rate, extensive travel benefits, no annual fee

[0945] The input data is transmitted from the terminal to the server.

[0946] Step 3:

[0947] The server receives the data sent from the device. After receiving the data, it performs pre-processing on the data. This processing includes data cleaning (e.g., filling in missing values) and data normalization (e.g., scaling numerical data). The pre-processed data is converted into an analyzable format and input into the AI ​​model. For example, a user's monthly expenditure data is converted into an appropriate numerical format.

[0948] Step 4:

[0949] The server inputs the preprocessed data into the AI ​​model. The AI ​​model analyzes the input data and lists the most suitable credit cards based on the user's purchase history and desired features. The AI ​​model references past similar user data to select the most suitable card. For example, it may obtain results such as "Card X (1.5% points return rate)" and "Card Y (travel benefits, no annual fee)."

[0950] Step 5:

[0951] The server receives the recommendations generated by the AI ​​model. Based on the recommendations, it generates data to display to the user. This generation process includes adding details about the recommended credit card (e.g., reward points and benefits) and converting the data into an easy-to-read format. The generated information is then sent to the device.

[0952] Step 6:

[0953] The terminal displays the recommended results received from the server to the user, who can then review the list of credit cards presented and select the card in the most suitable category.

[0954] Step 7:

[0955] The generative AI generates proposals for adding new features and services to card providers based on the analyzed data. The proposals are sent from the server to the providers. For example, it may propose new features such as a "points redemption function specialized for online shopping" based on user trends.

[0956] (Application example 1)

[0957] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0958] Conventional credit card recommendation systems are unable to adequately address a user's individual purchasing history or desired features, making it difficult to provide the appropriate card to the user. Furthermore, when users engage in a variety of purchasing activities, it is difficult to find the optimal card to use, especially on online shopping sites. Furthermore, it is also difficult to propose appropriate new features and services to card providers. To solve these problems, a system is needed that can respond to the diverse needs of users and efficiently recommend the most suitable credit card for online shopping sites.

[0959] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0960] In this invention, the server includes a means for prompting the user to input their purchase history and desired features, a server means for receiving the data on the purchase history and desired features, and an AI model means for analyzing the received data and recommending the most suitable credit card. This makes it possible to efficiently recommend the most suitable credit card for use on the online shopping site based on the information entered by the user.

[0961] A "user" is an individual or corporation who uses the system to input purchase history and desired features and receive credit card recommendations.

[0962] "Purchase history" is information about transactions and purchases that a user has made in the past, and is data entered by category, such as food expenses, entertainment expenses, and travel expenses.

[0963] "Desired features" refers to the benefits and features that users want from a credit card, and include specific conditions such as point redemption rates, travel benefits, and no annual fees.

[0964] A "server" is a computer system that receives data sent by users and provides it to an AI model for analysis.

[0965] An "AI model" is an artificial intelligence model that analyzes user input data and recommends the most suitable credit card.

[0966] "Recommended results" are a list of optimal credit cards presented to the user based on the results of the AI ​​model's analysis.

[0967] "Proposing new features" refers to using generative AI to analyze accumulated user data and recommend new features and services to credit card providers.

[0968] An "online shopping site" is a website that offers products and services over the Internet and allows users to make purchases.

[0969] "Suitability for use on a shopping site" is a characteristic that indicates whether the credit card is most suitable for use by a user on a shopping site.

[0970] This invention is a system that analyzes data entered by users based on their purchase history and desired features, and recommends the most suitable credit card. The system consists of a terminal used by the user, a server that receives and analyzes the data, and an AI model that presents the analysis results. The system also uses generative AI to propose new features and services to credit card providers.

[0971] System Overview

[0972] First, the user uses the terminal to input their purchase history and desired features. For example, they might input purchase history such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," as well as desired features such as "High point return rate," "Comprehensive travel benefits," and "No annual fee." This information is sent from the terminal to the server.

[0973] The server preprocesses the received data and inputs it into the AI ​​model. The AI ​​model then lists the most suitable credit cards based on the user's purchase history and desired features. For example, based on the user's input data, the model can recommend "Card X (1.5% reward point rate)" and "Card Y (travel benefits, no annual fee)."

[0974] Hardware and software used

[0975] Hardware: Smartphone (user device), server

[0976] software:

[0977] Flask: A Python web framework

[0978] TensorFlow: A framework for AI models

[0979] scikit-learn: A library for data preprocessing

[0980] Data processing and calculation

[0981] The server properly formats the data sent by the user, including their purchase history and desired features, and scales it so that the AI ​​model can analyze it. The received data is converted into numerical data through a standardization process. The AI ​​model then analyzes the data and outputs the optimal credit card recommendation.

[0982] The analysis results are sent to the user's device based on the recommendation list generated by the AI ​​model, allowing the user to review the results and select the most suitable credit card.

[0983] In addition, generative AI will analyze massive amounts of user data and suggest new features and services to credit card providers, such as adding a "points reward function specialized for online shopping."

[0984] Specific examples

[0985] When User A enters his monthly purchase history, such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Rich travel perks," and "No annual fee" as desired features, the input data is sent to the server. The server uses an AI model to analyze the data and create a list of options, such as "Card X (1.5% point return rate)" and "Card Y (travel perks available, no annual fee)."

[0986] Prompt Sentence Examples

[0987] If User B enters his monthly purchase history (food: 25,000 yen, entertainment: 20,000 yen, travel: 10,000 yen) and selects "high point return rate" and "full travel benefits" as desired features, the data is sent to the server. The server uses an AI model to analyze the data and create a list of cards, such as "Card A (point return rate 2.0%)" and "Card B (full travel benefits, no annual fee)."

[0988] Example prompt sentence:

[0989] User purchase history:

[0990] Food expenses: 25,000 yen

[0991] Entertainment expenses: 20,000 yen

[0992] Travel: 10,000 yen

[0993] Desired credit card features:

[0994] High point redemption rate

[0995] Extensive travel benefits

[0996] Please suggest the best credit card for me.

[0997] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0998] Step 1:

[0999] The user enters their purchase history and desired features.

[1000] Using their smartphone or other device, users input their purchase history, such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," as well as desired credit card features, such as "High point return rate," "Plenty of travel benefits," and "No annual fee." The input data is sent from the user device to the server.

[1001] Step 2:

[1002] The server preprocesses the data received.

[1003] The server receives the purchase history and desired feature data sent by the user and performs a standardization process using the scikit-learn library to standardize and scale this data, for example, converting numerical data into an appropriate range, which makes it easier for the AI ​​model to analyze the data.

[1004] Step 3:

[1005] The server inputs the preprocessed data into the AI ​​model for analysis.

[1006] The server inputs the preprocessed data into the AI ​​model, which analyzes the data and generates a list of optimal credit cards based on the user's purchasing history and desired features. This analysis refers to past data of similar users to identify the most suitable credit cards.

[1007] Step 4:

[1008] The server generates recommendation results and sends them to the user terminal.

[1009] The server creates a list of recommended credit cards for the user based on the analysis results generated by the AI ​​model. This list includes detailed information such as the credit card name, point redemption rate, and benefits. This list is then sent to the user's device in JSON format or similar.

[1010] Step 5:

[1011] The user reviews the recommendations and selects a credit card.

[1012] The user can review the recommended credit card list displayed on the terminal and select the most suitable credit card. The user can compare the details of each card and choose the card that best suits their needs.

[1013] Step 6:

[1014] The server uses generated AI to propose new features to credit card providers.

[1015] The server analyzes a huge amount of user data and proposes new features and services to credit card providers. In this processing step, new features such as a "points redemption function specialized for online shopping" are proposed to the provider. These proposals are generated from the results of AI analysis based on user data.

[1016] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1017] System Overview

[1018] This invention is a system in which an AI analyzes information when a user inputs their purchase history and desired features to recommend the most suitable credit card. Furthermore, the AI ​​generation system is used to propose new features and services to card providers. This system is combined with an emotion engine that recognizes the user's emotions, enabling more personalized card recommendations. The emotion engine analyzes the user's emotions when inputting information and influences the recommendation results.

[1019] System configuration

[1020] The system consists of the following components:

[1021] 1. Terminal: A device used by users that provides an interface for inputting purchase history and desired features and checking the results. It also has an emotion engine that analyzes user emotions in real time.

[1022] 2. Server: Receives data sent by the user from the device, analyzes the data using the AI ​​model, and generates and sends the analysis results to the device.

[1023] 3. AI model: Analyzes the received data and performs analytical processing to recommend the best credit card for the user.

[1024] 4. Emotion Engine: Analyzes the user's emotions and sends the analysis results to the server, which then adjusts the recommendation results based on this emotional data.

[1025] Program processing

[1026] 1. Enter your purchase history and desired features

[1027] A user logs in using a terminal and enters their purchase history and desired features. For example, consider a case where a user enters "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Enriched travel benefits," and "No annual fee" as desired features. This information is sent to the server by the terminal.

[1028] 2. Acquiring Emotion Data

[1029] The emotion engine installed in the device analyzes the facial expressions and voices of users when they input information, and obtains emotional data in real time. For example, when a user expresses emotions such as "satisfaction," "dissatisfaction," or "excitement," the emotion engine converts these into numerical values.

[1030] 3. Data Receipt and Analysis

[1031] The server preprocesses the received purchase history, desired features, and emotional data and inputs it into the AI ​​model. The AI ​​model analyzes this data and lists the most suitable credit cards. At this time, it also includes emotional data in its analysis, making recommendations that reflect the user's emotional state.

[1032] 4. Generating and displaying results

[1033] Based on the analysis results of the AI ​​model, the server generates a list of recommended credit cards for the user and their detailed information (such as point redemption rates and benefits).The results are sent to the terminal so that the user can check them.The user can then select the most suitable card from the presented list.

[1034] 5. Proposal for new feature addition

[1035] The generative AI analyzes massive amounts of user data and emotional data and makes proposals to credit card providers for the addition of new features and services. For example, if it determines based on the analysis data that adding a "points reward feature specialized for online shopping" is likely to increase the number of subscribers, it will report that proposal to the provider.

[1036] Specific examples

[1037] User A enters his monthly purchase history (food: ¥30,000), entertainment: ¥10,000, and travel: ¥50,000) and selects his desired features (high point redemption rate, extensive travel perks, and no annual fee). The input data is sent to the server. The server analyzes the data using an AI model and lists the most suitable credit cards: Card X (1.5% point redemption rate) and Card Y (travel perks, no annual fee). The results are sent to the device, where User A can review them and select, for example, Card X. Based on the analysis results, the server's generation AI can also suggest to the provider that a new "point redemption feature specialized for online shopping" be added. During this process, the emotion engine analyzes User A's emotions at the time of input, and this emotional data also influences the recommendation results.

[1038] In this way, the present invention provides a means for users to quickly and easily find the best credit card for them, and by taking into account the user's emotions, it is possible to make more personalized recommendations.It is also a system that can propose new features to credit card providers based on useful data.

[1039] The processing flow will be explained below.

[1040] Step 1:

[1041] The user starts up the device and logs in to the application. The user enters their email address and password and presses the login button.

[1042] Step 2:

[1043] The device sends the user's authentication information, which includes an email address and password, to the server.

[1044] Step 3:

[1045] The server compares the received authentication information with the registration information in the database and authenticates the user. If the authentication is successful, the server sends a login success message to the terminal.

[1046] Step 4:

[1047] The device displays a login success message and a form for the user to enter their purchase history and desired features. At this point, the device's built-in emotion engine begins to operate and begins to collect emotion data from the user's facial expressions and voice.

[1048] Step 5:

[1049] The user enters their purchase history into a specified form. For example, they enter amounts for each category, such as food, entertainment, and travel. The emotion engine analyzes the user's emotions from their facial expressions and voice when entering data, and sends the results to the server in real time.

[1050] Step 6:

[1051] The user selects the desired features, such as points redemption rate, travel benefits, whether or not there is an annual fee, etc., using checkboxes or drop-down menus. The emotion engine continues to obtain emotion data and sends it to the server.

[1052] Step 7:

[1053] The terminal transmits the purchase history and desired function data input by the user, as well as emotion data from the emotion engine, to the server.

[1054] Step 8:

[1055] The server preprocesses the received purchase history, desired features, and sentiment data, including data cleanup and formatting.

[1056] Step 9:

[1057] The server inputs the preprocessed data into an AI model, which analyzes purchase history, desired features, and emotional data to create a list of the most suitable credit cards.

[1058] Step 10:

[1059] The server generates a list of recommended credit cards and their details based on the analysis results of the AI ​​model, and this list also reflects the user's satisfaction and interest level as indicated by the emotional data.

[1060] Step 11:

[1061] The server generates analysis results and sends them to the device, including the reason for the recommendation based on the emotional data.

[1062] Step 12:

[1063] The device receives the analysis results from the server and displays them to the user, including a list of credit cards and their details, as well as the reasons for the recommendations based on the user's emotional data.

[1064] Step 13:

[1065] Users can select the card that best suits them from a list of credit cards presented to them, while checking the reasons why each card is recommended.

[1066] Step 14:

[1067] The server uses generative AI to analyze the vast amount of collected user data and sentiment data and make suggestions to credit card providers about adding new features and services.

[1068] Step 15:

[1069] The server generates a proposal for adding new features and sends it to the credit card provider, which also reflects the user's needs and satisfaction based on the emotional data.

[1070] Step 16:

[1071] Credit card providers will review your proposal and implement new features and services to improve your competitive position.

[1072] Example 2

[1073] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1074] Conventional credit card recommendation systems only considered a user's purchase history and desired features when making recommendations, which resulted in problems in which the system was unable to fully reflect the user's emotions and individual needs. Furthermore, proposals for new features to card providers did not take into account the user's emotional data, making it difficult to reflect actual user needs. This made it difficult for users to find the optimal credit card that satisfied them, and for card providers to add effective services.

[1075] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1076] In this invention, the server includes a terminal means for acquiring user emotion data, an AI model means for preprocessing the received purchase history, desired features, and emotion data to recommend the most suitable credit card, and a generation AI means for proposing the addition of new functions based on the generated analysis results. This enables analysis including emotion data, making it possible to recommend more personalized credit cards and propose the addition of new functions that reflect the user's needs.

[1077] "Purchase history" refers to data relating to past purchases of products and services made by a user.

[1078] "Desired features" refers to the requirements for benefits and services that come with the credit card that the user desires.

[1079] A "server" is a central computer that receives, analyzes, and processes data sent by users.

[1080] "Emotion data" is data that quantifies the user's emotional state and is based on an analysis of facial expressions and voice at the time of input.

[1081] A "terminal" is a device operated by a user, and is a device for inputting data and acquiring emotion data.

[1082] An "AI model" is an analytical system built with algorithms based on artificial intelligence, which is used to recommend the most suitable credit card based on user data.

[1083] "Generative AI" is an artificial intelligence system that analyzes user data and emotional data to propose new features and services.

[1084] "Recommended results" are a list and detailed information of the most suitable credit cards for the user, generated as a result of the AI ​​model's analysis.

[1085] This invention relates to a system in which, when a user inputs their purchase history and desired features, AI analyzes the information and suggests the most suitable credit card. This system achieves more personalized card recommendations by combining it with an emotion engine that recognizes the user's emotions. Specific configurations and processing procedures based on the roles of the server, terminal, and user are explained.

[1086] System configuration

[1087] 1. Terminal

[1088] It is a device used by users that provides an interface for inputting purchase history and desired functions and checking the results. It also has an emotion engine (e.g., Microsoft Azure Cognitive Services or Emotion API) that analyzes the emotions of users as they input data in real time.

[1089] 2. Server

[1090] It receives data sent by the user from the device, analyzes the data using an AI model (e.g., TensorFlow, PyTorch), and generates and sends the analysis results to the device.

[1091] 3. AI Model

[1092] The received data is analyzed and processed to recommend the best credit card for the user. A deep learning framework (e.g. TensorFlow) can be used for construction.

[1093] 4. Emotion Engine

[1094] The user's emotions are analyzed and the analysis results are sent to the server, which then adjusts the recommendation results based on this emotional data. The emotion engine can use facial recognition technology and voice analysis technology.

[1095] Specific operation of the system

[1096] The user logs in to the device and enters their purchase history and desired features. For example, they enter purchase history such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," and select the desired features as "High point return rate," "Enriched travel benefits," and "No annual fee." This data is sent to the server by the device.

[1097] Next, the device's built-in emotion engine analyzes the user's facial expressions and voice in real time to obtain emotion data. This emotion data is then quantified, for example, as "Satisfied: 80%," "Dissatisfied: 10%," or "Excited: 10%." This emotion data is also sent to the server.

[1098] The server preprocesses the received purchase history, desired features, and sentiment data and inputs it into the AI ​​model. The AI ​​model analyzes this data and lists the most suitable credit cards. For example, it might recommend "Card X (1.5% reward point rate)" or "Card Y (travel benefits, no annual fee)."

[1099] The analysis results are sent from the server to the device and presented to the user. The user can then select the most suitable card from the recommended list. For example, if the user selects "Card X," the selection is also sent to the server and reflected in the final list.

[1100] The generative AI also analyzes the accumulated user data and emotional data to propose new features and services to credit card providers. For example, a "points redemption feature specialized for online shopping" may be proposed based on the analysis data.

[1101] Prompt Sentence Examples

[1102] Purchase history and desired features entered by the user:

[1103] Food: 30,000 yen, Entertainment: 10,000 yen, Travel: 50,000 yen

[1104] Desired features: high point redemption rate, extensive travel benefits, no annual fee

[1105] Emotional Data:

[1106] Satisfaction: 80%, Dissatisfaction: 10%, Excitement: 10%

[1107] Use this information to recommend the best credit cards for you, and also suggest new features that should be added.

[1108] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1109] Step 1:

[1110] The user enters their purchase history and desired features on the device.

[1111] Specifically, the user enters "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen" as purchase history on the device's GUI interface, and selects "High point return rate," "Enriched travel benefits," and "No annual fee" as desired features. This information is used for subsequent processing, and is saved as digital data within the device.

[1112] Input: Purchase history, desired features

[1113] Output: Digital data in the terminal

[1114] Step 2:

[1115] The device acquires emotion data.

[1116] Specifically, the device's built-in emotion engine analyzes the user's facial expressions and voice in real time and quantifies the emotional data. For example, the user's facial expressions and tone of voice when inputting information can be analyzed as "Satisfaction: 80%," "Dissatisfaction: 10%," and "Excitement: 10%."

[1117] Input: User's facial expression, voice

[1118] Output: Emotion data (quantified data)

[1119] Step 3:

[1120] The server receives the input data and the emotion data.

[1121] The device sends purchase history, desired features, and emotional data to the server, which receives this data and stores it in an initial database.

[1122] Input: purchase history, desired features, emotional data

[1123] Output: Data stored in the initial database on the server

[1124] Step 4:

[1125] The server preprocesses the data.

[1126] Specifically, the data format is standardized on the server, unnecessary data is filtered out, and preprocessing such as normalizing data with different units is performed. After preprocessing is complete, the data is converted into a format suitable for input into the AI ​​model.

[1127] Input: Data stored in the initial database

[1128] Output: Data in a format that can be input into an AI model

[1129] Step 5:

[1130] The AI ​​model analyzes the most suitable credit card.

[1131] The server inputs the preprocessed data into an AI model for analysis. The AI ​​model then lists the most suitable credit cards based on the customer's purchase history, desired features, and emotional data. As a result, it recommends cards such as "Card X (1.5% reward point rate)" and "Card Y (travel benefits, no annual fee)."

[1132] Input: Data in a format that can be fed into an AI model

[1133] Output: A list of recommended credit cards

[1134] Step 6:

[1135] The server generates the analysis results and sends them to the terminal.

[1136] Based on the analysis results of the AI ​​model, the server generates a list of recommended credit cards for the user along with detailed information (e.g., point redemption rate, benefits), and sends this result to the terminal.

[1137] Input: A list of recommended credit cards

[1138] Output: Analysis results sent to the device

[1139] Step 7:

[1140] The user reviews the recommendations and selects a card.

[1141] The user checks the analysis results received on the terminal and selects the most suitable card from the listed credit cards. For example, they can select "Card X." The selected card information is sent to the server and reflected in the final list.

[1142] Input: Analysis results sent to the device

[1143] Output: Selected credit card information

[1144] Step 8:

[1145] Generative AI will suggest new features to add.

[1146] The generative AI analyzes the accumulated user data and emotional data and proposes new features and services to card providers. For example, it may propose a "points redemption feature specialized for online shopping."

[1147] Input: User data, emotion data

[1148] Output: New feature suggestions to card providers

[1149] (Application example 2)

[1150] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1151] Conventional credit card recommendation systems suggest the most suitable card based on a user's purchase history and desired features, but they are unable to provide personalized recommendations that take into account the user's emotions. It is also difficult to use the data obtained to suggest new features or specific campaigns. As a result, users are unable to receive more satisfying recommendations, and providers are unable to obtain sufficient useful information.

[1152] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1153] In this invention, the server includes means for prompting the user to input their purchase history and desired features, server means for receiving the data on the purchase history and desired features, AI model means for analyzing the received data and recommending the most suitable credit card, means for generating and presenting the recommendation results to the user, means for proposing the addition of new features based on the generated analysis results, means for performing sentiment analysis, means for recommending a more personalized credit card based on the analysis results, and means for generating proposals for new features and discount campaigns. This enables personalized recommendations that take the user's emotions into consideration, and also enables providers to propose new features and campaigns.

[1154] "Purchase history" refers to data on past purchases of products or services made by a user.

[1155] "Desired features" refers to specific features such as new benefits or conditions that the user desires, such as a point return rate or no annual fee.

[1156] A "server" is a computer system for receiving and processing data from users.

[1157] An "AI model" is a system that uses artificial intelligence to analyze data and includes an algorithm to recommend the best credit card for the user.

[1158] "Emotion analysis" is the process of analyzing a user's emotional state from facial expressions, voice, etc., and acquiring this as data.

[1159] "Recommended results" refers to the list of optimal credit cards presented to the user as a result of the AI ​​model's analysis.

[1160] "New feature addition proposal" is the process of making proposals to credit card providers for adding new features and services based on user data.

[1161] "Personalized recommendations" refers to individually suggesting the best credit card for each user based on their characteristics and emotional state.

[1162] "Proposing new features and discount campaigns" is the process of analyzing user data and sentiment data and proposing new services and discount campaigns to providers based on the results of that analysis.

[1163] MODE FOR CARRYING OUT THE INVENTION

[1164] System Overview

[1165] This invention is a system in which an AI analyzes information when a user inputs their purchase history and desired features to recommend the most suitable credit card. This system is combined with an emotion engine that recognizes the user's emotions to achieve more personalized card recommendations. It also uses generative AI to propose new features and services to card providers.

[1166] Hardware and software used

[1167] The system uses the following hardware and software:

[1168] Device: A device used by a user, such as a smartphone, smart glasses, or head-mounted display.

[1169] Emotion engine: Software that analyzes emotions from a user's facial expressions and voice. Built using TensorFlow and PyTorch.

[1170] Server: A computer system that receives data and analyzes it with an AI model. It uses frameworks such as Django or Flask.

[1171] AI model: An algorithm that performs data analysis. Specifically, this includes generative AI models trained in TensorFlow or PyTorch.

[1172] Data processing and calculation

[1173] 1. Sending input data from the terminal:

[1174] Users use a smartphone app to enter their purchase history and desired features.

[1175] For example: "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," and "Travel: 50,000 yen." Select "High point return rate," "Full travel benefits," and "No annual fee" as desired features.

[1176] The emotion engine analyzes facial expressions and voice in real time as the user types in, and generates emotion data.

[1177] These data are transmitted from the terminal to the server.

[1178] 2. Data Receipt and Analysis:

[1179] The server preprocesses the received purchase history, desired features, and emotional data and inputs it into the AI ​​model.

[1180] The AI ​​model performs analysis and lists the most suitable credit cards. Emotional data is also included in the analysis, and recommendations are generated taking into account the user's emotional state.

[1181] 3. Generating and displaying recommendations:

[1182] Based on the analysis results of the AI ​​model, the server generates a list of the most suitable credit cards and their details.

[1183] The results are sent to the terminal and can be viewed by the user.

[1184] Example: "Card X (1.5% point return rate)" "Card Y (travel benefits, no annual fee)"

[1185] 4. New feature suggestions:

[1186] Generative AI analyzes vast amounts of user and emotional data and makes suggestions to credit card providers about adding new features and services.

[1187] Example prompt sentence:

[1188] "The user's purchase history is as follows: Food: 30,000 yen, Entertainment: 10,000 yen, Travel: 50,000 yen. Desired features: High point reward rate, ample travel benefits, no annual fee. Emotional state: Satisfied. Please suggest the best credit card based on this information."

[1189] In this way, the present invention provides a means for users to quickly and easily find the best credit card for them, and by taking into account the user's emotions, it realizes more personalized recommendations.It also provides a system that can propose new features and services to credit card providers based on useful data.

[1190] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1191] Step 1:

[1192] The user uses the terminal to input their purchase history and desired features.

[1193] The input items include, for example, "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," "Travel: 50,000 yen," and desired features such as "High point return rate," "Full travel benefits," and "No annual fee." This data is collected by the device.

[1194] Step 2:

[1195] The emotion engine analyzes the user's facial expressions and voice in real time and generates emotion data.

[1196] The input is the user's facial expression and voice data, and the output is a quantified emotional state such as "satisfied," "dissatisfied," or "excited."

[1197] Step 3:

[1198] The device transmits purchase history, desired features, and emotional data to the server.

[1199] The input includes purchase history, desired features, and emotional data collected on the terminal, which are sent as data to the server.

[1200] Step 4:

[1201] The server preprocesses the data received.

[1202] The input includes purchase history, desired features, and sentiment data, and the output is preprocessed data that has been subjected to noise removal and data normalization.

[1203] Step 5:

[1204] The server inputs the preprocessed data into an AI model to analyze the most suitable credit card.

[1205] The preprocessed data is provided as input to the AI ​​model, and a list of optimal credit cards is generated as output, such as "Card X (1.5% reward point rate)" and "Card Y (travel perks, no annual fee)."

[1206] Step 6:

[1207] The server generates recommendations based on the analysis results and sends them to the device.

[1208] The input includes the analysis results of the AI ​​model, and the output generates recommendations to be presented to the user.

[1209] Step 7:

[1210] The user reviews the recommendations on the device and selects the most suitable credit card.

[1211] The input includes the recommendation results sent by the server and the output is the user's selection.

[1212] Step 8:

[1213] The server uses generative AI to suggest new features to add.

[1214] The inputs include a huge amount of user data and emotional data, and the output is suggestions for adding new features and services. A specific example of such a suggestion is a "points redemption function specialized for online shopping."

[1215] This process allows users to quickly select the best credit card, receive personalized recommendations that take their emotions into account, and even suggest new features to credit card providers.

[1216] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1217] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1218] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1219] [Fourth embodiment]

[1220] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1221] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1222] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1223] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1224] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1225] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1226] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1227] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1228] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1229] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1230] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1231] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1232] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1233] System Overview

[1234] This invention is a system in which an AI analyzes information when a user inputs their purchase history and desired features to suggest the most suitable credit card. Furthermore, the AI ​​generation is used to suggest new features and services to card providers. This system saves users time and effort in selecting a credit card, and also helps card providers analyze data to offer more attractive services.

[1235] System configuration

[1236] The system consists of the following components:

[1237] 1. Terminal: The device used by the user, providing an interface for entering purchase history and desired functions and checking the results.

[1238] 2. Server: Receives data sent by the user from the device, analyzes the data using the AI ​​model, and generates and sends the analysis results to the device.

[1239] 3. AI model: Analyzes the received data and performs analytical processing to recommend the best credit card for the user.

[1240] Program processing

[1241] 1. Enter your purchase history and desired features

[1242] A user logs in using a terminal and enters their purchase history and desired features. For example, consider a case where a user enters "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Enriched travel benefits," and "No annual fee" as desired features. This information is sent to the server by the terminal.

[1243] 2. Data Receipt and Analysis

[1244] The server preprocesses the received data and inputs it into the AI ​​model, which then lists the most suitable credit cards based on the customer's purchase history and desired features. The AI ​​model then references past data from similar users to recommend the most suitable card.

[1245] 3. Generating and displaying results

[1246] Based on the analysis results of the AI ​​model, the server generates a list of recommended credit cards for the user and their detailed information (such as point redemption rates and benefits).The results are sent to the terminal so that the user can check them.The user can then select the most suitable card from the presented list.

[1247] 4. Proposal for new feature addition

[1248] The generative AI analyzes massive amounts of user data and makes proposals to credit card providers for the addition of new features and services. For example, if it determines based on the analysis data that adding a "points reward function specialized for online shopping" is likely to increase the number of subscribers, it will report that proposal to the provider.

[1249] Specific examples

[1250] When User A enters his monthly purchase history of "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Rich travel perks," and "No annual fee" as desired features, the input data is sent to the server. The server analyzes the data using an AI model and lists the most suitable credit cards: "Card X (1.5% point return rate)" and "Card Y (travel perks, no annual fee)." The results are sent to the terminal, where User A can check them and select, for example, "Card X." Furthermore, based on the analysis results, the server's generation AI can propose to providers the addition of "point return features specialized for online shopping."

[1251] In this way, the present invention provides a means for users to quickly and easily find the best credit card for them, and is a system that can also propose new functions to credit card providers based on useful data.

[1252] The processing flow will be explained below.

[1253] Step 1:

[1254] The user starts up the device and logs in to the application. The user enters their email address and password and presses the login button.

[1255] Step 2:

[1256] The device sends the user's authentication information, which includes an email address and password, to the server.

[1257] Step 3:

[1258] The server compares the received authentication information with the registration information in the database and authenticates the user. If the authentication is successful, the server sends a login success message to the terminal.

[1259] Step 4:

[1260] The terminal displays a login success message and presents the user with a form to enter their purchase history and desired features.

[1261] Step 5:

[1262] The user enters their purchase history in a specified form, for example, by entering amounts for each category such as food, entertainment, and travel.

[1263] Step 6:

[1264] Users select the features they want, such as points redemption rate, travel benefits, whether or not there is an annual fee, etc., by selecting checkboxes or drop-down menus.

[1265] Step 7:

[1266] The terminal transmits the purchase history and desired function data input by the user to the server.

[1267] Step 8:

[1268] The server pre-processes the data it receives, including formatting and unifying the data.

[1269] Step 9:

[1270] The server inputs the preprocessed data into the AI ​​model, which analyzes the received data and lists the best credit cards for the user.

[1271] Step 10:

[1272] The server generates a list of recommended credit cards and their details based on the analysis results of the AI ​​model.

[1273] Step 11:

[1274] The analysis results generated by the server are sent to the terminal.

[1275] Step 12:

[1276] The terminal displays the analysis results received from the server to the user, including a list of credit cards and their details.

[1277] Step 13:

[1278] The user selects the card that best suits them from the list of credit cards presented.

[1279] Step 14:

[1280] The server uses generated AI to analyze the vast amount of user data collected and make suggestions to credit card providers about adding new features and services.

[1281] Step 15:

[1282] The server generates a proposal to add new features and sends it to the credit card provider.

[1283] Step 16:

[1284] Credit card providers will review your proposal and implement new features and services to improve your competitive position.

[1285] The above is the processing steps and specific operation contents of the present invention.

[1286] Example 1

[1287] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1288] When users choose the best credit card for them, there is a lack of a way to receive prompt and accurate suggestions based on their purchase history and desired features, which makes the selection process time-consuming and labor-intensive.Another issue is that card providers are not properly being suggested new features and services based on users' needs.

[1289] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1290] In this invention, the server includes means for prompting a user to input their purchase history and desired functions, means for receiving the data on the purchase history and desired functions, means for preprocessing the received data and converting it into an analyzable format, artificial intelligence means for analyzing the received and preprocessed data and recommending an optimal credit card, means for generating and presenting the recommendation results to the user, and means for proposing the addition of new functions based on the generated analysis results. This allows the user to quickly and accurately receive a recommendation for the optimal credit card and to make proposals for new functions and services to the card provider.

[1291] "User" refers to a person who uses the system to input their purchase history and desired features and receive suggestions for the most suitable credit card.

[1292] "Purchase history" refers to data regarding the price and category of products purchased by a user in the past.

[1293] "Desired features" refer to the benefits and service requirements that users want from a credit card.

[1294] "Server" refers to a computer system that receives, processes, and analyzes data sent by users.

[1295] "Means of preprocessing data and converting it into an analyzable format" refers to the process of formatting the received data into a form that is easy for the AI ​​model to analyze.

[1296] "Artificial intelligence means" refers to machine learning models and algorithms that analyze the received and pre-processed data and recommend the most suitable credit card.

[1297] "Means for generating and presenting recommended results to the user" refers to the process of displaying a list and details of the most suitable credit cards to the user based on the analysis results.

[1298] "Means for proposing new features" refers to the process of proposing new features and services to card providers based on the generated analysis results.

[1299] The present invention is a system in which an AI analyzes a user's purchase history and desired features and then proposes the most suitable credit card. Furthermore, the system uses the generation AI to propose new features and services to card providers. Specific details for implementing the present invention are described below.

[1300] System Configuration

[1301] The system consists of the following components:

[1302] 1. Terminal: A device used by a user that provides an interface for entering purchase history and desired functions and checking the results. Examples of terminals include smartphones and PCs.

[1303] 2. Server: Receives data sent by the user from the device and analyzes the data using an AI model. It also generates the analysis results and sends them to the device. A high-performance computing server is used as the server.

[1304] 3. AI model: Analyzes the received data and performs analysis to recommend the best credit card for the user. The AI ​​model uses machine learning frameworks such as TensorFlow and PyTorch.

[1305] Hardware and software used

[1306] Hardware

[1307] Devices: smartphones, computers

[1308] Server: High-performance computing server

[1309] software

[1310] AI models: TensorFlow, PyTorch

[1311] Database management systems: MySQL, PostgreSQL

[1312] Interface software: React, Vue.js

[1313] Specific examples of program processing

[1314] The user logs in to the system on the terminal. After logging in, the user follows the system's instructions and enters their monthly purchase history and desired credit card features.

[1315] For example, user A enters the following data:

[1316] Purchase History:

[1317] Food expenses: 30,000 yen

[1318] Entertainment expenses: 10,000 yen

[1319] Travel: 50,000 yen

[1320] Desired features:

[1321] High point return rate

[1322] Extensive travel benefits

[1323] No annual fee

[1324] This input data is sent from the device to a server, where it is received and pre-processed. The pre-processed data is then input into an AI model, which references similar past data to create a list of the most suitable credit cards for the user.

[1325] For example, the AI ​​model will list "Card X (point return rate 1.5%)" and "Card Y (travel benefits, no annual fee)" as the analysis results. These results are sent to the terminal via the server, where User A can check them. User A can then select the most suitable credit card from the presented list.

[1326] Furthermore, based on the analysis results, the generative AI will propose new features to card providers, such as a point reward function specialized for online shopping, allowing card providers to develop and provide new features and services based on user needs.

[1327] An example of a prompt for this system is:

[1328] Prompt statement:

[1329] Purchase History:

[1330] Food expenses: 30,000 yen

[1331] Entertainment expenses: 10,000 yen

[1332] Travel: 50,000 yen

[1333] Desired features:

[1334] High point return rate

[1335] Extensive travel benefits

[1336] No annual fee

[1337] In this way, the present invention provides users with a means for quickly and easily finding the best credit card, and also allows card providers to make suggestions for adding new functions based on useful data.

[1338] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1339] Step 1:

[1340] A user logs in to the system using a terminal. On the login screen, the user enters their user ID and password. The entered authentication information is sent from the terminal to the server. The server authenticates the user based on the received information, and if authentication is successful, the main screen is displayed.

[1341] Step 2:

[1342] The user enters their purchase history and desired features on the main screen. For example, they enter the following data:

[1343] Purchase history: Food: 30,000 yen, Entertainment: 10,000 yen, Travel: 50,000 yen

[1344] Desired features: High point redemption rate, extensive travel benefits, no annual fee

[1345] The input data is transmitted from the terminal to the server.

[1346] Step 3:

[1347] The server receives the data sent from the device. After receiving the data, it performs pre-processing on the data. This processing includes data cleaning (e.g., filling in missing values) and data normalization (e.g., scaling numerical data). The pre-processed data is converted into an analyzable format and input into the AI ​​model. For example, a user's monthly expenditure data is converted into an appropriate numerical format.

[1348] Step 4:

[1349] The server inputs the preprocessed data into the AI ​​model. The AI ​​model analyzes the input data and lists the most suitable credit cards based on the user's purchase history and desired features. The AI ​​model references past similar user data to select the most suitable card. For example, it may obtain results such as "Card X (1.5% points return rate)" and "Card Y (travel benefits, no annual fee)."

[1350] Step 5:

[1351] The server receives the recommendations generated by the AI ​​model. Based on the recommendations, it generates data to display to the user. This generation process includes adding details about the recommended credit card (e.g., reward points and benefits) and converting the data into an easy-to-read format. The generated information is then sent to the device.

[1352] Step 6:

[1353] The terminal displays the recommended results received from the server to the user, who can then review the list of credit cards presented and select the card in the most suitable category.

[1354] Step 7:

[1355] The generative AI generates proposals for adding new features and services to card providers based on the analyzed data. The proposals are sent from the server to the providers. For example, it may propose new features such as a "points redemption function specialized for online shopping" based on user trends.

[1356] (Application example 1)

[1357] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1358] Conventional credit card recommendation systems are unable to adequately address a user's individual purchasing history or desired features, making it difficult to provide the appropriate card to the user. Furthermore, when users engage in a variety of purchasing activities, it is difficult to find the optimal card to use, especially on online shopping sites. Furthermore, it is also difficult to propose appropriate new features and services to card providers. To solve these problems, a system is needed that can respond to the diverse needs of users and efficiently recommend the most suitable credit card for online shopping sites.

[1359] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1360] In this invention, the server includes a means for prompting the user to input their purchase history and desired features, a server means for receiving the data on the purchase history and desired features, and an AI model means for analyzing the received data and recommending the most suitable credit card. This makes it possible to efficiently recommend the most suitable credit card for use on the online shopping site based on the information entered by the user.

[1361] A "user" is an individual or corporation who uses the system to input purchase history and desired features and receive credit card recommendations.

[1362] "Purchase history" is information about transactions and purchases that a user has made in the past, and is data entered by category, such as food expenses, entertainment expenses, and travel expenses.

[1363] "Desired features" refers to the benefits and features that users want from a credit card, and include specific conditions such as point redemption rates, travel benefits, and no annual fees.

[1364] A "server" is a computer system that receives data sent by users and provides it to an AI model for analysis.

[1365] An "AI model" is an artificial intelligence model that analyzes user input data and recommends the most suitable credit card.

[1366] "Recommended results" are a list of optimal credit cards presented to the user based on the results of the AI ​​model's analysis.

[1367] "Proposing new features" refers to using generative AI to analyze accumulated user data and recommend new features and services to credit card providers.

[1368] An "online shopping site" is a website that offers products and services over the Internet and allows users to make purchases.

[1369] "Suitability for use on a shopping site" is a characteristic that indicates whether the credit card is most suitable for use by a user on a shopping site.

[1370] This invention is a system that analyzes data entered by users based on their purchase history and desired features, and recommends the most suitable credit card. The system consists of a terminal used by the user, a server that receives and analyzes the data, and an AI model that presents the analysis results. The system also uses generative AI to propose new features and services to credit card providers.

[1371] System Overview

[1372] First, the user uses the terminal to input their purchase history and desired features. For example, they might input purchase history such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," as well as desired features such as "High point return rate," "Comprehensive travel benefits," and "No annual fee." This information is sent from the terminal to the server.

[1373] The server preprocesses the received data and inputs it into the AI ​​model. The AI ​​model then lists the most suitable credit cards based on the user's purchase history and desired features. For example, based on the user's input data, the model can recommend "Card X (1.5% reward point rate)" and "Card Y (travel benefits, no annual fee)."

[1374] Hardware and software used

[1375] Hardware: Smartphone (user device), server

[1376] software:

[1377] Flask: A Python web framework

[1378] TensorFlow: A framework for AI models

[1379] scikit-learn: A library for data preprocessing

[1380] Data processing and calculation

[1381] The server properly formats the data sent by the user, including their purchase history and desired features, and scales it so that the AI ​​model can analyze it. The received data is converted into numerical data through a standardization process. The AI ​​model then analyzes the data and outputs the optimal credit card recommendation.

[1382] The analysis results are sent to the user's device based on the recommendation list generated by the AI ​​model, allowing the user to review the results and select the most suitable credit card.

[1383] In addition, generative AI will analyze massive amounts of user data and suggest new features and services to credit card providers, such as adding a "points reward function specialized for online shopping."

[1384] Specific examples

[1385] When User A enters his monthly purchase history, such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Rich travel perks," and "No annual fee" as desired features, the input data is sent to the server. The server uses an AI model to analyze the data and create a list of options, such as "Card X (1.5% point return rate)" and "Card Y (travel perks available, no annual fee)."

[1386] Prompt Sentence Examples

[1387] If User B enters his monthly purchase history (food: 25,000 yen, entertainment: 20,000 yen, travel: 10,000 yen) and selects "high point return rate" and "full travel benefits" as desired features, the data is sent to the server. The server uses an AI model to analyze the data and create a list of cards, such as "Card A (point return rate 2.0%)" and "Card B (full travel benefits, no annual fee)."

[1388] Example prompt sentence:

[1389] User purchase history:

[1390] Food expenses: 25,000 yen

[1391] Entertainment expenses: 20,000 yen

[1392] Travel: 10,000 yen

[1393] Desired credit card features:

[1394] High point redemption rate

[1395] Extensive travel benefits

[1396] Please suggest the best credit card for me.

[1397] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1398] Step 1:

[1399] The user enters their purchase history and desired features.

[1400] Using their smartphone or other device, users input their purchase history, such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," as well as desired credit card features, such as "High point return rate," "Plenty of travel benefits," and "No annual fee." The input data is sent from the user device to the server.

[1401] Step 2:

[1402] The server preprocesses the data received.

[1403] The server receives the purchase history and desired feature data sent by the user and performs a standardization process using the scikit-learn library to standardize and scale this data, for example, converting numerical data into an appropriate range, which makes it easier for the AI ​​model to analyze the data.

[1404] Step 3:

[1405] The server inputs the preprocessed data into the AI ​​model for analysis.

[1406] The server inputs the preprocessed data into the AI ​​model, which analyzes the data and generates a list of optimal credit cards based on the user's purchasing history and desired features. This analysis refers to past data of similar users to identify the most suitable credit cards.

[1407] Step 4:

[1408] The server generates recommendation results and sends them to the user terminal.

[1409] The server creates a list of recommended credit cards for the user based on the analysis results generated by the AI ​​model. This list includes detailed information such as the credit card name, point redemption rate, and benefits. This list is then sent to the user's device in JSON format or similar.

[1410] Step 5:

[1411] The user reviews the recommendations and selects a credit card.

[1412] The user can review the recommended credit card list displayed on the terminal and select the most suitable credit card. The user can compare the details of each card and choose the card that best suits their needs.

[1413] Step 6:

[1414] The server uses generated AI to propose new features to credit card providers.

[1415] The server analyzes a huge amount of user data and proposes new features and services to credit card providers. In this processing step, new features such as a "points redemption function specialized for online shopping" are proposed to the provider. These proposals are generated from the results of AI analysis based on user data.

[1416] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1417] System Overview

[1418] This invention is a system in which an AI analyzes information when a user inputs their purchase history and desired features to recommend the most suitable credit card. Furthermore, the AI ​​generation system is used to propose new features and services to card providers. This system is combined with an emotion engine that recognizes the user's emotions, enabling more personalized card recommendations. The emotion engine analyzes the user's emotions when inputting information and influences the recommendation results.

[1419] System configuration

[1420] The system consists of the following components:

[1421] 1. Terminal: A device used by users that provides an interface for inputting purchase history and desired features and checking the results. It also has an emotion engine that analyzes user emotions in real time.

[1422] 2. Server: Receives data sent by the user from the device, analyzes the data using the AI ​​model, and generates and sends the analysis results to the device.

[1423] 3. AI model: Analyzes the received data and performs analytical processing to recommend the best credit card for the user.

[1424] 4. Emotion Engine: Analyzes the user's emotions and sends the analysis results to the server, which then adjusts the recommendation results based on this emotional data.

[1425] Program processing

[1426] 1. Enter your purchase history and desired features

[1427] A user logs in using a terminal and enters their purchase history and desired features. For example, consider a case where a user enters "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," and "Travel: 50,000 yen," and selects "High point return rate," "Enriched travel benefits," and "No annual fee" as desired features. This information is sent to the server by the terminal.

[1428] 2. Acquiring Emotion Data

[1429] The emotion engine installed in the device analyzes the facial expressions and voices of users when they input information, and obtains emotional data in real time. For example, when a user expresses emotions such as "satisfaction," "dissatisfaction," or "excitement," the emotion engine converts these into numerical values.

[1430] 3. Data Receipt and Analysis

[1431] The server preprocesses the received purchase history, desired features, and emotional data and inputs it into the AI ​​model. The AI ​​model analyzes this data and lists the most suitable credit cards. At this time, it also includes emotional data in its analysis, making recommendations that reflect the user's emotional state.

[1432] 4. Generating and displaying results

[1433] Based on the analysis results of the AI ​​model, the server generates a list of recommended credit cards for the user and their detailed information (such as point redemption rates and benefits).The results are sent to the terminal so that the user can check them.The user can then select the most suitable card from the presented list.

[1434] 5. Proposal for new feature addition

[1435] The generative AI analyzes massive amounts of user data and emotional data and makes proposals to credit card providers for the addition of new features and services. For example, if it determines based on the analysis data that adding a "points reward feature specialized for online shopping" is likely to increase the number of subscribers, it will report that proposal to the provider.

[1436] Specific examples

[1437] User A enters his monthly purchase history (food: ¥30,000), entertainment: ¥10,000, and travel: ¥50,000) and selects his desired features (high point redemption rate, extensive travel perks, and no annual fee). The input data is sent to the server. The server analyzes the data using an AI model and lists the most suitable credit cards: Card X (1.5% point redemption rate) and Card Y (travel perks, no annual fee). The results are sent to the device, where User A can review them and select, for example, Card X. Based on the analysis results, the server's generation AI can also suggest to the provider that a new "point redemption feature specialized for online shopping" be added. During this process, the emotion engine analyzes User A's emotions at the time of input, and this emotional data also influences the recommendation results.

[1438] In this way, the present invention provides a means for users to quickly and easily find the best credit card for them, and by taking into account the user's emotions, it is possible to make more personalized recommendations.It is also a system that can propose new features to credit card providers based on useful data.

[1439] The processing flow will be explained below.

[1440] Step 1:

[1441] The user starts up the device and logs in to the application. The user enters their email address and password and presses the login button.

[1442] Step 2:

[1443] The device sends the user's authentication information, which includes an email address and password, to the server.

[1444] Step 3:

[1445] The server compares the received authentication information with the registration information in the database and authenticates the user. If the authentication is successful, the server sends a login success message to the terminal.

[1446] Step 4:

[1447] The device displays a login success message and a form for the user to enter their purchase history and desired features. At this point, the device's built-in emotion engine begins to operate and begins to collect emotion data from the user's facial expressions and voice.

[1448] Step 5:

[1449] The user enters their purchase history into a specified form. For example, they enter amounts for each category, such as food, entertainment, and travel. The emotion engine analyzes the user's emotions from their facial expressions and voice when entering data, and sends the results to the server in real time.

[1450] Step 6:

[1451] The user selects the desired features, such as points redemption rate, travel benefits, whether or not there is an annual fee, etc., using checkboxes or drop-down menus. The emotion engine continues to obtain emotion data and sends it to the server.

[1452] Step 7:

[1453] The terminal transmits the purchase history and desired function data input by the user, as well as emotion data from the emotion engine, to the server.

[1454] Step 8:

[1455] The server preprocesses the received purchase history, desired features, and sentiment data, including data cleanup and formatting.

[1456] Step 9:

[1457] The server inputs the preprocessed data into an AI model, which analyzes purchase history, desired features, and emotional data to create a list of the most suitable credit cards.

[1458] Step 10:

[1459] The server generates a list of recommended credit cards and their details based on the analysis results of the AI ​​model, and this list also reflects the user's satisfaction and interest level as indicated by the emotional data.

[1460] Step 11:

[1461] The server generates analysis results and sends them to the device, including the reason for the recommendation based on the emotional data.

[1462] Step 12:

[1463] The device receives the analysis results from the server and displays them to the user, including a list of credit cards and their details, as well as the reasons for the recommendations based on the user's emotional data.

[1464] Step 13:

[1465] Users can select the card that best suits them from a list of credit cards presented to them, while checking the reasons why each card is recommended.

[1466] Step 14:

[1467] The server uses generative AI to analyze the vast amount of collected user data and sentiment data and make suggestions to credit card providers about adding new features and services.

[1468] Step 15:

[1469] The server generates a proposal for adding new features and sends it to the credit card provider, which also reflects the user's needs and satisfaction based on the emotional data.

[1470] Step 16:

[1471] Credit card providers will review your proposal and implement new features and services to improve your competitive position.

[1472] Example 2

[1473] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1474] Conventional credit card recommendation systems only considered a user's purchase history and desired features when making recommendations, which resulted in problems in which the system was unable to fully reflect the user's emotions and individual needs. Furthermore, proposals for new features to card providers did not take into account the user's emotional data, making it difficult to reflect actual user needs. This made it difficult for users to find the optimal credit card that satisfied them, and for card providers to add effective services.

[1475] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1476] In this invention, the server includes a terminal means for acquiring user emotion data, an AI model means for preprocessing the received purchase history, desired features, and emotion data to recommend the most suitable credit card, and a generation AI means for proposing the addition of new functions based on the generated analysis results. This enables analysis including emotion data, making it possible to recommend more personalized credit cards and propose the addition of new functions that reflect the user's needs.

[1477] "Purchase history" refers to data relating to past purchases of products and services made by a user.

[1478] "Desired features" refers to the requirements for benefits and services that come with the credit card that the user desires.

[1479] A "server" is a central computer that receives, analyzes, and processes data sent by users.

[1480] "Emotion data" is data that quantifies the user's emotional state and is based on an analysis of facial expressions and voice at the time of input.

[1481] A "terminal" is a device operated by a user, and is a device for inputting data and acquiring emotion data.

[1482] An "AI model" is an analytical system built with algorithms based on artificial intelligence, which is used to recommend the most suitable credit card based on user data.

[1483] "Generative AI" is an artificial intelligence system that analyzes user data and emotional data to propose new features and services.

[1484] "Recommended results" are a list and detailed information of the most suitable credit cards for the user, generated as a result of the AI ​​model's analysis.

[1485] This invention relates to a system in which, when a user inputs their purchase history and desired features, AI analyzes the information and suggests the most suitable credit card. This system achieves more personalized card recommendations by combining it with an emotion engine that recognizes the user's emotions. Specific configurations and processing procedures based on the roles of the server, terminal, and user are explained.

[1486] System configuration

[1487] 1. Terminal

[1488] It is a device used by users that provides an interface for inputting purchase history and desired functions and checking the results. It also has an emotion engine (e.g., Microsoft Azure Cognitive Services or Emotion API) that analyzes the emotions of users as they input data in real time.

[1489] 2. Server

[1490] It receives data sent by the user from the device, analyzes the data using an AI model (e.g., TensorFlow, PyTorch), and generates and sends the analysis results to the device.

[1491] 3. AI Model

[1492] The received data is analyzed and processed to recommend the best credit card for the user. A deep learning framework (e.g. TensorFlow) can be used for construction.

[1493] 4. Emotion Engine

[1494] The user's emotions are analyzed and the analysis results are sent to the server, which then adjusts the recommendation results based on this emotional data. The emotion engine can use facial recognition technology and voice analysis technology.

[1495] Specific operation of the system

[1496] The user logs in to the device and enters their purchase history and desired features. For example, they enter purchase history such as "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen," and select the desired features as "High point return rate," "Enriched travel benefits," and "No annual fee." This data is sent to the server by the device.

[1497] Next, the device's built-in emotion engine analyzes the user's facial expressions and voice in real time to obtain emotion data. This emotion data is then quantified, for example, as "Satisfied: 80%," "Dissatisfied: 10%," or "Excited: 10%." This emotion data is also sent to the server.

[1498] The server preprocesses the received purchase history, desired features, and sentiment data and inputs it into the AI ​​model. The AI ​​model analyzes this data and lists the most suitable credit cards. For example, it might recommend "Card X (1.5% reward point rate)" or "Card Y (travel benefits, no annual fee)."

[1499] The analysis results are sent from the server to the device and presented to the user. The user can then select the most suitable card from the recommended list. For example, if the user selects "Card X," the selection is also sent to the server and reflected in the final list.

[1500] The generative AI also analyzes the accumulated user data and emotional data to propose new features and services to credit card providers. For example, a "points redemption feature specialized for online shopping" may be proposed based on the analysis data.

[1501] Prompt Sentence Examples

[1502] Purchase history and desired features entered by the user:

[1503] Food: 30,000 yen, Entertainment: 10,000 yen, Travel: 50,000 yen

[1504] Desired features: high point redemption rate, extensive travel benefits, no annual fee

[1505] Emotional Data:

[1506] Satisfaction: 80%, Dissatisfaction: 10%, Excitement: 10%

[1507] Use this information to recommend the best credit cards for you, and also suggest new features that should be added.

[1508] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1509] Step 1:

[1510] The user enters their purchase history and desired features on the device.

[1511] Specifically, the user enters "Food: 30,000 yen," "Entertainment: 10,000 yen," and "Travel: 50,000 yen" as purchase history on the device's GUI interface, and selects "High point return rate," "Enriched travel benefits," and "No annual fee" as desired features. This information is used for subsequent processing, and is saved as digital data within the device.

[1512] Input: Purchase history, desired features

[1513] Output: Digital data in the terminal

[1514] Step 2:

[1515] The device acquires emotion data.

[1516] Specifically, the device's built-in emotion engine analyzes the user's facial expressions and voice in real time and quantifies the emotional data. For example, the user's facial expressions and tone of voice when inputting information can be analyzed as "Satisfaction: 80%," "Dissatisfaction: 10%," and "Excitement: 10%."

[1517] Input: User's facial expression, voice

[1518] Output: Emotion data (quantified data)

[1519] Step 3:

[1520] The server receives the input data and the emotion data.

[1521] The device sends purchase history, desired features, and emotional data to the server, which receives this data and stores it in an initial database.

[1522] Input: purchase history, desired features, emotional data

[1523] Output: Data stored in the initial database on the server

[1524] Step 4:

[1525] The server preprocesses the data.

[1526] Specifically, the data format is standardized on the server, unnecessary data is filtered out, and preprocessing such as normalizing data with different units is performed. After preprocessing is complete, the data is converted into a format suitable for input into the AI ​​model.

[1527] Input: Data stored in the initial database

[1528] Output: Data in a format that can be input into an AI model

[1529] Step 5:

[1530] The AI ​​model analyzes the most suitable credit card.

[1531] The server inputs the preprocessed data into an AI model for analysis. The AI ​​model then lists the most suitable credit cards based on the customer's purchase history, desired features, and emotional data. As a result, it recommends cards such as "Card X (1.5% reward point rate)" and "Card Y (travel benefits, no annual fee)."

[1532] Input: Data in a format that can be fed into an AI model

[1533] Output: A list of recommended credit cards

[1534] Step 6:

[1535] The server generates the analysis results and sends them to the terminal.

[1536] Based on the analysis results of the AI ​​model, the server generates a list of recommended credit cards for the user along with detailed information (e.g., point redemption rate, benefits), and sends this result to the terminal.

[1537] Input: A list of recommended credit cards

[1538] Output: Analysis results sent to the device

[1539] Step 7:

[1540] The user reviews the recommendations and selects a card.

[1541] The user checks the analysis results received on the terminal and selects the most suitable card from the listed credit cards. For example, they can select "Card X." The selected card information is sent to the server and reflected in the final list.

[1542] Input: Analysis results sent to the device

[1543] Output: Selected credit card information

[1544] Step 8:

[1545] Generative AI will suggest new features to add.

[1546] The generative AI analyzes the accumulated user data and emotional data and proposes new features and services to card providers. For example, it may propose a "points redemption feature specialized for online shopping."

[1547] Input: User data, emotion data

[1548] Output: New feature suggestions to card providers

[1549] (Application example 2)

[1550] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1551] Conventional credit card recommendation systems suggest the most suitable card based on a user's purchase history and desired features, but they are unable to provide personalized recommendations that take into account the user's emotions. It is also difficult to use the data obtained to suggest new features or specific campaigns. As a result, users are unable to receive more satisfying recommendations, and providers are unable to obtain sufficient useful information.

[1552] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1553] In this invention, the server includes means for prompting the user to input their purchase history and desired features, server means for receiving the data on the purchase history and desired features, AI model means for analyzing the received data and recommending the most suitable credit card, means for generating and presenting the recommendation results to the user, means for proposing the addition of new features based on the generated analysis results, means for performing sentiment analysis, means for recommending a more personalized credit card based on the analysis results, and means for generating proposals for new features and discount campaigns. This enables personalized recommendations that take the user's emotions into consideration, and also enables providers to propose new features and campaigns.

[1554] "Purchase history" refers to data on past purchases of products or services made by a user.

[1555] "Desired features" refers to specific features such as new benefits or conditions that the user desires, such as a point return rate or no annual fee.

[1556] A "server" is a computer system for receiving and processing data from users.

[1557] An "AI model" is a system that uses artificial intelligence to analyze data and includes an algorithm to recommend the best credit card for the user.

[1558] "Emotion analysis" is the process of analyzing a user's emotional state from facial expressions, voice, etc., and acquiring this as data.

[1559] "Recommended results" refers to the list of optimal credit cards presented to the user as a result of the AI ​​model's analysis.

[1560] "New feature addition proposal" is the process of making proposals to credit card providers for adding new features and services based on user data.

[1561] "Personalized recommendations" refers to individually suggesting the best credit card for each user based on their characteristics and emotional state.

[1562] "Proposing new features and discount campaigns" is the process of analyzing user data and sentiment data and proposing new services and discount campaigns to providers based on the results of that analysis.

[1563] MODE FOR CARRYING OUT THE INVENTION

[1564] System Overview

[1565] This invention is a system in which an AI analyzes information when a user inputs their purchase history and desired features to recommend the most suitable credit card. This system is combined with an emotion engine that recognizes the user's emotions to achieve more personalized card recommendations. It also uses generative AI to propose new features and services to card providers.

[1566] Hardware and software used

[1567] The system uses the following hardware and software:

[1568] Device: A device used by a user, such as a smartphone, smart glasses, or head-mounted display.

[1569] Emotion engine: Software that analyzes emotions from a user's facial expressions and voice. Built using TensorFlow and PyTorch.

[1570] Server: A computer system that receives data and analyzes it with an AI model. It uses frameworks such as Django or Flask.

[1571] AI model: An algorithm that performs data analysis. Specifically, this includes generative AI models trained in TensorFlow or PyTorch.

[1572] Data processing and calculation

[1573] 1. Sending input data from the terminal:

[1574] Users use a smartphone app to enter their purchase history and desired features.

[1575] For example: "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," and "Travel: 50,000 yen." Select "High point return rate," "Full travel benefits," and "No annual fee" as desired features.

[1576] The emotion engine analyzes facial expressions and voice in real time as the user types in, and generates emotion data.

[1577] These data are transmitted from the terminal to the server.

[1578] 2. Data Receipt and Analysis:

[1579] The server preprocesses the received purchase history, desired features, and emotional data and inputs it into the AI ​​model.

[1580] The AI ​​model performs analysis and lists the most suitable credit cards. Emotional data is also included in the analysis, and recommendations are generated taking into account the user's emotional state.

[1581] 3. Generating and displaying recommendations:

[1582] Based on the analysis results of the AI ​​model, the server generates a list of the most suitable credit cards and their details.

[1583] The results are sent to the terminal and can be viewed by the user.

[1584] Example: "Card X (1.5% point return rate)" "Card Y (travel benefits, no annual fee)"

[1585] 4. New feature suggestions:

[1586] Generative AI analyzes vast amounts of user and emotional data and makes suggestions to credit card providers about adding new features and services.

[1587] Example prompt sentence:

[1588] "The user's purchase history is as follows: Food: 30,000 yen, Entertainment: 10,000 yen, Travel: 50,000 yen. Desired features: High point reward rate, ample travel benefits, no annual fee. Emotional state: Satisfied. Please suggest the best credit card based on this information."

[1589] In this way, the present invention provides a means for users to quickly and easily find the best credit card for them, and by taking into account the user's emotions, it realizes more personalized recommendations.It also provides a system that can propose new features and services to credit card providers based on useful data.

[1590] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1591] Step 1:

[1592] The user uses the terminal to input their purchase history and desired features.

[1593] The input items include, for example, "Food expenses: 30,000 yen," "Entertainment expenses: 10,000 yen," "Travel: 50,000 yen," and desired features such as "High point return rate," "Full travel benefits," and "No annual fee." This data is collected by the device.

[1594] Step 2:

[1595] The emotion engine analyzes the user's facial expressions and voice in real time and generates emotion data.

[1596] The input is the user's facial expression and voice data, and the output is a quantified emotional state such as "satisfied," "dissatisfied," or "excited."

[1597] Step 3:

[1598] The device transmits purchase history, desired features, and emotional data to the server.

[1599] The input includes purchase history, desired features, and emotional data collected on the terminal, which are sent as data to the server.

[1600] Step 4:

[1601] The server preprocesses the data received.

[1602] The input includes purchase history, desired features, and sentiment data, and the output is preprocessed data that has been subjected to noise removal and data normalization.

[1603] Step 5:

[1604] The server inputs the preprocessed data into an AI model to analyze the most suitable credit card.

[1605] The preprocessed data is provided as input to the AI ​​model, and a list of optimal credit cards is generated as output, such as "Card X (1.5% reward point rate)" and "Card Y (travel perks, no annual fee)."

[1606] Step 6:

[1607] The server generates recommendations based on the analysis results and sends them to the device.

[1608] The input includes the analysis results of the AI ​​model, and the output generates recommendations to be presented to the user.

[1609] Step 7:

[1610] The user reviews the recommendations on the device and selects the most suitable credit card.

[1611] The input includes the recommendation results sent by the server and the output is the user's selection.

[1612] Step 8:

[1613] The server uses generative AI to suggest new features to add.

[1614] The inputs include a huge amount of user data and emotional data, and the output is suggestions for adding new features and services. A specific example of such a suggestion is a "points redemption function specialized for online shopping."

[1615] This process allows users to quickly select the best credit card, receive personalized recommendations that take their emotions into account, and even suggest new features to credit card providers.

[1616] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1617] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1618] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1619] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1620] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1621] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1622] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1623] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1624] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1625] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1626] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1627] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1628] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1629] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1630] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1631] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1632] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1633] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1634] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1635] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1636] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1637] The following is further disclosed regarding the above embodiment.

[1638] (Claim 1)

[1639] A means for prompting a user to input purchase history and desired functions;

[1640] a server means for receiving the purchase history and desired function data;

[1641] An AI model means to analyze the received data and recommend the most suitable credit card;

[1642] means for generating and presenting recommendation results to a user;

[1643] A means for proposing new functions based on the generated analysis results;

[1644] A system including:

[1645] (Claim 2)

[1646] 2. The system according to claim 1, wherein the server means receives and authenticates authentication information of a user.

[1647] (Claim 3)

[1648] The system according to claim 1, wherein the AI ​​model means analyzes purchase history and desired features to list the most suitable credit cards.

[1649] "Example 1"

[1650] (Claim 1)

[1651] A means for prompting a user to input purchase history and desired functions;

[1652] a server means for receiving the purchase history and desired function data;

[1653] means for preprocessing the received data and converting it into an analyzable format;

[1654] artificial intelligence means for analyzing the received and pre-processed data and recommending the most suitable credit card;

[1655] means for generating and presenting recommendation results to a user;

[1656] A means for proposing new functions based on the generated analysis results;

[1657] A system including:

[1658] (Claim 2)

[1659] 2. The system according to claim 1, wherein the server means receives and authenticates user authentication information.

[1660] (Claim 3)

[1661] 2. The system according to claim 1, wherein the artificial intelligence means analyzes purchase history and desired features to list the most suitable credit cards.

[1662] "Application Example 1"

[1663] (Claim 1)

[1664] A means for prompting a user to input purchase history and desired functions;

[1665] a server means for receiving the purchase history and desired function data;

[1666] An AI model means to analyze the received data and recommend the most suitable credit card;

[1667] means for generating and presenting recommendation results to a user;

[1668] A means for proposing new functions based on the generated analysis results;

[1669] A means for suggesting the most suitable credit card for a user to use on an online shopping site;

[1670] ...

[1671] A system including:

[1672] (Claim 2)

[1673] 2. The system according to claim 1, wherein the server means receives and authenticates authentication information of a user.

[1674] (Claim 3)

[1675] The system according to claim 1, wherein the AI ​​model means analyzes purchase history and desired features to list the most suitable credit cards, taking into account their suitability for use on online shopping sites.

[1676] "Example 2: Combining Emotion Engines"

[1677] (Claim 1)

[1678] A means for prompting a user to input purchase history and desired functions;

[1679] a server means for receiving the purchase history and desired function data;

[1680] a terminal means for acquiring emotion data of a user;

[1681] An AI model means for preprocessing the received purchase history, desired features, and sentiment data and recommending an optimal credit card;

[1682] means for generating and presenting recommendation results to a user;

[1683] A generation AI means that proposes the addition of new functions based on the generated analysis results;

[1684] A system including:

[1685] (Claim 2)

[1686] 2. The system according to claim 1, wherein the server means receives and authenticates authentication information of a user.

[1687] (Claim 3)

[1688] The system of claim 1, wherein the AI ​​model means analyzes purchase history, desired features, and emotional data to list the most suitable credit cards.

[1689] "Application example 2 when combining emotion engines"

[1690] (Claim 1)

[1691] A means for prompting a user to input purchase history and desired functions;

[1692] a server means for receiving the purchase history and desired function data;

[1693] An AI model means to analyze the received data and recommend the most suitable credit card;

[1694] means for generating and presenting recommendation results to a user;

[1695] A means for proposing new functions based on the generated analysis results;

[1696] a means for performing sentiment analysis;

[1697] A means of recommending more personalized credit cards based on the analysis results,

[1698] A means for generating proposals for new features and discount offers;

[1699] ...

[1700] A system including:

[1701] (Claim 2)

[1702] 2. The system according to claim 1, wherein the server means receives and authenticates authentication information of a user.

[1703] (Claim 3)

[1704] The system according to claim 1, wherein the AI ​​model means analyzes purchase history and desired features to list the most suitable credit cards. [Explanation of symbols]

[1705] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for prompting a user to input purchase history and desired functions; a server means for receiving the purchase history and desired function data; An AI model means to analyze the received data and recommend the most suitable credit card; means for generating and presenting recommendation results to a user; A means for proposing new functions based on the generated analysis results; A system including:

2. 2. The system according to claim 1, wherein said server means receives and authenticates user authentication information.

3. The system according to claim 1, wherein the AI ​​model means analyzes purchase history and desired features to list optimal credit cards.

Images