system

Abstract

We provide the system. [Solution] A system comprising: means for receiving two-dimensional code payment data; means for storing the received two-dimensional code payment data in a database; means for integrating user purchase data, health data, and financial data from multiple data sources; means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data; means for generating multiple scenarios of the user's future health status and financial status based on the analysis results; means for visualizing the generated scenarios in text, image, and video formats; means for transmitting the visualized scenarios to the user's terminal; and means for generating suggestions for behavioral change to the user.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Modern users in their 30s to 50s have a heightened awareness of the importance of self-management in both health and finance, but there is a problem in that they cannot specifically imagine what results their own lifestyle and financial behaviors will bring in the future. In addition, it is difficult to effectively manage information from different payment methods and data sources, making comprehensive self-management difficult. As a result, it becomes difficult for users to intuitively understand the need for behavior change, and the risks to health and finance are increasing.

Means for Solving the Problems

[0005] This invention is a system that integrates a user's QR code (registered trademark) payment data, purchase data, health data, and financial data, and uses AI to analyze the user's consumption trends, health status, and financial behavior. Based on the analysis results, this system generates multiple scenarios of the user's future health and financial status and visualizes them in text, image, and video formats. The visualized scenarios are then sent to the user's terminal, allowing the user to intuitively understand their future self. Furthermore, the system includes means for suggesting specific behavioral changes to the user based on the generated scenarios. This motivates the user to improve their current behavior and reduce health and financial risks.

[0006] "QR code payment data" refers to data generated when a user makes a payment using a QR code, including information about the purchased items, price, and date and time of payment.

[0007] A "database" is a system for systematically storing, managing, and retrieving information, and in this invention, it is used to securely store various types of received data.

[0008] "Data sources" refer to multiple sources of information that provide user data such as purchase data, health data, and financial data.

[0009] "Integration" refers to the process of centrally managing data from multiple data sources provided in different formats and converting it into an analyzable form.

[0010] "Consumption trends" refers to analyzing a user's past purchase history and spending patterns to predict their unique purchasing behavior.

[0011] "Health status" refers to the physical and mental health of the user, based on information about their current physical condition and lifestyle.

[0012] "Financial behavior" refers to all financial actions taken by users, including their income and expenses and investment activities.

[0013] "Analysis" is the process of evaluating user behavior patterns and states based on collected data, and predicting future trends and risks.

[0014] A "scenario" refers to multiple hypothetical future scenarios of a user's future health and financial situation, generated based on the analysis results.

[0015] "Visualization" refers to the process of converting a generated scenario into visual representations such as text, images, and videos.

[0016] "Device" refers to electronic devices such as smartphones, personal computers, and tablets that users use to display and operate information.

[0017] "Behavioral change suggestions" provide users with specific action plans to take to improve their health and financial situation, based on their current data and future scenarios. [Brief explanation of the drawing]

[0018] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7]It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the language used in the following description will be explained.

[0021] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0022] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] As shown in Figure 1, the 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.

[0029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0031] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0032] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0039] The Future Self Simulator, as described in this invention, is a system that integrates a user's QR code payment data, purchase data, health data, and financial data, and analyzes them using AI. The specific method for implementing this system is described below.

[0040] 1. Data Collection

[0041] server

[0042] When a user makes a QR code payment at a supermarket, the payment data is automatically sent to the server.

[0043] The server saves user payment data to the database in real time.

[0044] For example, when a user pays for food using a QR code, the product information, price, and purchase date and time are saved.

[0045] 2. Data Integration

[0046] server

[0047] The server integrates the collected QR code payment data, purchase data, health data, and financial data.

[0048] Standardize data from different formats and manage it as a single dataset.

[0049] For example, exercise data obtained from a user's fitness app could be integrated with spending data obtained from a banking app.

[0050] 3. Data Analysis

[0051] server

[0052] Based on integrated data, AI models are used to analyze consumer trends, health status, and financial behavior.

[0053] The analysis reveals the user's current lifestyle and financial behavior.

[0054] For example, we can evaluate the health risks and monthly spending patterns of users who frequently purchase certain foods.

[0055] 4. Generating future scenarios

[0056] server

[0057] The AI ​​model generates multiple scenarios for future health and financial conditions based on current data.

[0058] These scenarios are visualized in text, image, and video formats.

[0059] For example, it visualizes the user's health condition 10 years from now if they continue their current eating habits.

[0060] 5. Sending and displaying visual content

[0061] server

[0062] The generated visual content is sent to the user's device.

[0063] The content is displayed on the user's smartphone or computer.

[0064] terminal

[0065] The device displays the received visual content with an intuitive user interface.

[0066] Users can realistically see what their future self will look like and what their health condition will be.

[0067] For example, an image is displayed that realistically recreates what your body shape and financial situation might look like 10 years from now if you continue the program.

[0068] 6. Proposals for behavioral change

[0069] server

[0070] Based on the generated scenario, the server creates specific behavioral change suggestions for the user.

[0071] This proposal will be sent to the user's device in text format.

[0072] terminal

[0073] The device displays the proposed solutions to the user and presents actionable improvement measures in stages.

[0074] For example, suggestions such as "exercise three times a week" or "reduce eating out and cook at home" will be displayed.

[0075] 7. User behavior

[0076] User

[0077] The user reviews the future scenarios and suggestions presented on their device and understands the need for action.

[0078] I will take action to review my lifestyle and financial behavior in accordance with the proposed improvement measures.

[0079] For example, take concrete actions such as "add vegetables to your daily meals" or "create a monthly budget."

[0080] The above describes the configuration for implementing the Future Self Simulator. This system allows users to visualize their future health and financial situation in concrete terms, and provides them with the motivation to re-evaluate their current actions.

[0081] The following describes the processing flow.

[0082] Step 1:

[0083] Server: Receives user QR code payment data. Specifically, it retrieves payment information from the QR code payment system via API, links it to the user ID, and stores it.

[0084] Step 2:

[0085] Server: Stores received QR code payment data in a database. Records detailed information such as the name of the purchased item, price, and date and time of purchase.

[0086] Step 3:

[0087] Server: Integrates data from multiple data sources. Centralizes user purchase data, health data, and financial data, and standardizes data formats.

[0088] Step 4:

[0089] Server: Analyzes consumption trends, health status, and financial behavior based on integrated data. Uses AI models to evaluate users' current lifestyles and financial behavior.

[0090] Step 5:

[0091] Server: Based on the analysis results, it generates multiple scenarios for the user's future health and financial status. These include scenarios where the user continues their current behavior or improves it.

[0092] Step 6:

[0093] Server: Visualizes the generated scenarios. Utilizes generative AI technology to realistically represent scenarios in text, image, and video formats.

[0094] Step 7:

[0095] Server: Sends visualized scenarios to the user's device. Sends data to smartphones and PCs via API.

[0096] Step 8:

[0097] Terminal: Displays received visual content. An intuitive user interface allows users to check their future health and financial status.

[0098] Step 9:

[0099] Server: Based on future scenarios, generates specific behavioral change suggestions for users. These suggestions are generated in text format.

[0100] Step 10:

[0101] Terminal: Displays the proposed content to the user. Specific improvement measures are presented step-by-step, and the system is designed to be easy for the user to understand.

[0102] Step 11:

[0103] User: Review the presented future scenarios and proposed solutions, and implement necessary behavioral changes. Develop a concrete action plan and put it into action.

[0104] (Example 1)

[0105] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0106] Traditional data analysis systems have struggled to effectively integrate user purchasing data, exercise data, and financial data to predict users' future health and financial status. Furthermore, they lacked systems that could intuitively visualize analysis results and provide useful behavioral change suggestions to users. As a result, users lacked the motivation to take concrete actions to improve their health and financial status.

[0107] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0108] In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, exercise data, and financial data from multiple data sources, means for standardizing data in different formats and managing it as a single dataset, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, and means for generating suggestions for behavioral change to the user. This enables the user to concretely understand the impact of their current behavior on the future and motivates them to take concrete actions to improve their health status and financial status.

[0109] "QR code payment data" refers to data containing transaction information generated when a payment is made using a QR code.

[0110] A "database" is a system for systematically storing and managing collected data.

[0111] "Multiple data sources" refers to multiple sources of information that provide data of different types or formats.

[0112] "Purchase data" refers to data that includes information about products and services purchased by users.

[0113] "Exercise data" refers to data that includes information about a user's exercise habits and activity level.

[0114] "Financial data" refers to data that includes information about a user's income, expenses, and assets.

[0115] "Means of integration" refers to methods and techniques for combining data obtained from different data sources into a single dataset.

[0116] Standardization is the process of converting data provided in different formats or units into a common format or unit.

[0117] "Consumption trends" refer to patterns in what kinds of products and services users purchase and how frequently.

[0118] "Health status" refers to the overall state of the user's physical and mental health.

[0119] "Financial behavior" refers to a user's patterns of financial actions, such as income and expenses.

[0120] "Means of analysis" refers to techniques and methods for analyzing integrated data and identifying specific trends or patterns.

[0121] A "scenario" refers to a future situation or outcome predicted based on specific conditions or assumptions.

[0122] "Means of visualization" refers to methods and techniques for displaying the results of data analysis in an easily understandable visual format.

[0123] "Terminal" refers to digital devices used by users, such as computers, smartphones, and tablets.

[0124] "Suggestions for behavioral change" refer to specific advice and recommendations for improving the user's lifestyle and behavior.

[0125] The Future Self Simulator, as described in this invention, is a system that integrates and analyzes a user's QR code payment data, purchase data, exercise data, and financial data to predict and propose future health and financial conditions. The specific method for implementing this system is described below.

[0126] When a user makes a QR code payment at a supermarket or other store, the server receives the payment data. This payment data includes information about the purchased item (e.g., apples), its price, and the date and time of purchase. The received payment data is stored in the server's database in real time.

[0127] Next, the server collects user purchase data, exercise data (e.g., step count and exercise time from fitness apps), and financial data (e.g., monthly spending data from banking apps) from multiple data sources, and integrates and standardizes this data. Standardization allows data in different formats to be managed as a single dataset.

[0128] Based on integrated data, the server uses AI models to analyze users' consumption trends, health status, and financial behavior. This analysis provides a detailed understanding of users' current lifestyles and financial actions. For example, it can assess the health risks of users who frequently purchase certain foods, and evaluate their monthly spending patterns.

[0129] Based on the analysis results, the server generates multiple scenarios for the user's future health and financial status. These scenarios are visualized in text, image, and video formats. For example, it can visualize the user's health 10 years from now if they continue their current eating habits.

[0130] The generated visual content is sent from the server to the user's device (smartphone or PC). The device displays the received visual content using an intuitive user interface. This allows the user to realistically see what their future self and health status might look like.

[0131] Furthermore, based on the generated scenario, the server creates and sends to the user's terminal text-based suggestions for specific behavioral changes. These suggestions include specific advice to improve the user's lifestyle and financial behavior. Examples include "exercise three times a week" and "reduce eating out and cook at home more often."

[0132] Users can review future scenarios and suggestions presented on their devices and, based on these, revise their lifestyles and financial behaviors. For example, they can take specific actions such as "adding vegetables to their daily meals" or "creating a monthly budget."

[0133] The following are examples of prompts to input into the generating AI model.

[0134] "Explain how users can purchase food using QR code payments, and how that data can be analyzed to predict their future health."

[0135] "Describe in natural language a system that integrates current fitness and financial data to simulate future health and financial situations."

[0136] The above describes a specific embodiment of the Future Self Simulator of the present invention. This system allows users to visualize their future health and financial situation in detail and gain the motivation to reconsider their current actions.

[0137] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0138] Step 1:

[0139] Data collection

[0140] Input: User's QR code payment data.

[0141] Processing: When a user makes a QR code payment at a supermarket, the server automatically receives the payment data. The payment data includes information about the purchased items (product name, quantity, etc.), price, and date and time of purchase.

[0142] Output: Received payment data.

[0143] Specific operation: When a user purchases an apple using a QR code, the apple's information (e.g., apple, 1), price (100 yen), and purchase date and time (October 1, 2023, 15:00) are sent to the server.

[0144] Step 2:

[0145] Save to database

[0146] Input: Received payment data.

[0147] Processing: The server saves the received payment data to the database in real time.

[0148] Output: Payment data stored in the database.

[0149] Specific operation: The server saves the received Apple payment data to the "Purchase History" table in the database.

[0150] Step 3:

[0151] Collection of additional data

[0152] Input: User exercise data (e.g., obtained from a fitness app), financial data (e.g., obtained from a banking app).

[0153] Processing: The server collects user exercise data and financial data from multiple data sources. Exercise data includes the user's exercise volume (number of steps, exercise time, etc.), and financial data includes the user's spending information (spending items, amounts, date and time, etc.).

[0154] Output: Collected exercise data and financial data.

[0155] Specific operation: The server retrieves the number of steps the user walked in a day (5000 steps) from the fitness app and monthly food expenditure data (total 30,000 yen) from the banking app.

[0156] Step 4:

[0157] Data integration and standardization

[0158] Input: Collected QR code payment data, exercise data, and financial data.

[0159] Processing: The server standardizes data in different formats and manages it as a single dataset. Standardization converts each data format into a common format, making it possible to compare and analyze them with one another.

[0160] Output: Integrated and standardized dataset.

[0161] Specific operation: The server converts the purchase date and time of payment data into a unified format (e.g., YYYY-MM-DD HH:MM:SS), statistically aggregates the daily step count of exercise data, and synchronizes it with monthly expenditure data.

[0162] Step 5:

[0163] Data analysis

[0164] Input: Integrated and standardized dataset.

[0165] Processing: The server uses an AI model to analyze the user's consumption patterns, health status, and financial behavior. The analysis identifies specific patterns and risks (e.g., health risks, financial risks).

[0166] Output: Analysis results (e.g., analysis of consumption trends, assessment of health risks, patterns of financial behavior).

[0167] Specific operation: The AI ​​model detects when a user frequently purchases certain foods (e.g., high-calorie foods) and evaluates the result as a health risk.

[0168] Step 6:

[0169] Generating future scenarios

[0170] Input: Analysis results.

[0171] Processing: Based on the analysis results, the server generates multiple scenarios for the user's future health and financial status. These scenarios include predictions of the future if current lifestyle habits and financial behaviors continue.

[0172] Output: Future scenarios (e.g., visualization of future health and financial status).

[0173] Specific operation: The AI ​​model predicts and visualizes the health status (e.g., obesity risk) 10 years from now, assuming current consumption of high-calorie foods continues.

[0174] Step 7:

[0175] Visual content generation and transmission

[0176] Input: Future scenario.

[0177] Processing: The server visualizes future scenarios in text, image, and video formats, and sends the generated visual content to the user's device.

[0178] Output: The transmitted visual content.

[0179] Specific operation: Generates "Health status in 10 years" as text, "Prediction of future body shape" as an image, and "Future lifestyle simulation" as a video, and sends them to the user's smartphone.

[0180] Step 8:

[0181] Display of visual content

[0182] Input: Received visual content.

[0183] Processing: The device displays the received visual content in an intuitive user interface. Users can realistically see what their future self will look like and their health status.

[0184] Output: The displayed visual content.

[0185] Specific operation: The device displays received images and videos in full-screen mode and provides navigation buttons for the user to refer to past data.

[0186] Step 9:

[0187] Proposals for behavioral change

[0188] Input: The generated scenario.

[0189] Processing: Based on the generated scenario, the server generates specific behavioral change suggestions for the user in text format and sends them to the terminal.

[0190] Output: Proposals for behavioral change.

[0191] Specific actions: The system generates text messages suggesting things like "exercise three times a week" or "reduce eating out and cook at home," and sends them to the user's smartphone.

[0192] Step 10:

[0193] Display and implementation of behavioral change

[0194] Input: Received proposal content.

[0195] Processing: The terminal displays the suggested content to the user and presents actionable improvement measures in stages.

[0196] Output: The displayed suggestions.

[0197] Specific actions: The device displays suggestions for specific behavioral changes (e.g., "Add vegetables to your daily meals") and provides the necessary information to enable the user to take action.

[0198] Step 11:

[0199] User behavior

[0200] Input: The displayed future scenario and proposed content.

[0201] Process: The user reviews the future scenarios and suggestions presented on the device and understands their necessity. They then review their lifestyle and financial behavior according to the suggested improvements.

[0202] Output: Improved lifestyle and financial behavior.

[0203] Specific actions: Users perform specific actions, such as "add vegetables to their daily meals," and provide feedback on the results to the server.

[0204] The above describes the specific program processing of the Future Self Simulator. This system allows users to visualize their future health and financial situation in concrete terms, and provides them with the motivation to re-evaluate their current actions.

[0205] (Application Example 1)

[0206] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0207] Modern consumers possess diverse purchase history, health data, and financial data, and there is a growing need to integrate and analyze this data to predict future health and financial status. However, with increasing security risks, there is a lack of systems that can assess future security risks based on this data and propose appropriate security measures. Current systems struggle to efficiently integrate and analyze multiple data sources and present risk scenarios in an intuitively understandable format. Therefore, the challenge lies in achieving comprehensive security risk management and encouraging effective behavioral change in users.

[0208] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0209] In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, health data, and financial data from multiple data sources, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, means for generating suggestions for behavioral change to the user, means for analyzing the user's safety risks and generating future security risk scenarios, means for visualizing the generated security risk scenarios in text and image formats, means for transmitting the visualized security risk scenarios to the user's terminal, and means for generating and providing security countermeasures suggestions to the user. As a result, users can intuitively understand not only the impact of their actions on their health and finances, but also future security risks, and take appropriate measures.

[0210] "QR code payment data" refers to all data related to payments made using QR codes, and specifically includes transaction date and time, transaction amount, purchased items, etc.

[0211] A "database" is an information system for efficiently storing, managing, and retrieving large amounts of data, and relational database management systems (RDBMS) are often used for this purpose.

[0212] "Purchase data" refers to data containing information about products purchased by a user, including product name, purchase date and time, purchase location, and purchase price.

[0213] "Health data" refers to data related to the user's health, such as exercise data obtained from fitness apps and physical measurement data obtained from health apps.

[0214] "Financial data" refers to data related to a user's financial situation, including banking transactions, credit card usage history, and asset status.

[0215] "Consumer trends" refer to data that shows patterns in what kinds of products and services users prefer to purchase, and are based on purchase history and purchase frequency.

[0216] "Health status" refers to data indicating the user's physical and mental health, including measured health data and medical records.

[0217] "Financial behavior" refers to data that shows patterns in how users spend money, and is based on income and expenditure balances and category analysis of spending.

[0218] A "scenario" refers to a predicted future situation generated based on analyzed data, and includes the user's future health, financial situation, security risks, etc.

[0219] "Visualization" refers to the visual representation of data and scenarios, and is provided in formats such as graphs, charts, and videos.

[0220] "Security risks" refer to security-related risks that users may face, including phishing scams and the leakage of personal information.

[0221] A "security risk scenario" refers to a predicted situation regarding future security risks, generated based on analyzed data.

[0222] "Security measures" refer to the specific actions and policies that users take to address security risks.

[0223] The Future Security Advisor, as described in this invention, is a system that analyzes users' consumption trends, health status, and financial behavior based on QR code payment data, purchase data, health data, and financial data, and uses these analysis results to generate and present future health status, financial status, and security risk scenarios. This system enables users to intuitively understand the impact of their actions on the future and to take concrete actions to change their behavior and implement security measures.

[0224] 1. Data Collection

[0225] server

[0226] The system receives QR code payment data and stores it in a database. Specifically, when a user makes a QR code payment at a supermarket, the payment data (product information, price, purchase date and time, etc.) is automatically sent to the server.

[0227] We collect purchase data, health data, and financial data from multiple data sources. For example, we obtain exercise data from a fitness app and collect spending data from a banking app.

[0228] 2. Data Integration

[0229] server

[0230] The collected data is standardized and managed as a single integrated dataset. This allows for the integration of data in different formats and conversion into an analyzable format.

[0231] 3. Data Analysis

[0232] server

[0233] Based on integrated data, AI models (such as TENSORFLOW® and PyTorch) are used to analyze users' consumption trends, health status, and financial behavior. Based on the analysis results, users' current lifestyles and financial behaviors are revealed.

[0234] The analysis assesses user safety risks and generates future security risk scenarios.

[0235] 4. Generating and Visualizing Future Scenarios

[0236] server

[0237] Based on analysis results generated using AI models, future health, financial, and security risk scenarios are visualized in text, image, and video formats. Plotly is used for data visualization, and FFmpeg is used to generate the video.

[0238] 5. Sending and displaying content

[0239] server

[0240] Visualized scenarios are sent to the user's smartphone and displayed intuitively through the user interface. This utilizes a REST API and a front-end framework (React Native).

[0241] 6. Proposals for behavioral change

[0242] Server and hardware

[0243] Based on the generated scenario, the system sends users specific suggestions for behavioral change and security measures in text format, which are then displayed on their devices. Using a text generation model based on OpenAI® GPT-3®, users receive step-by-step improvement measures.

[0244] 7. User behavior

[0245] User

[0246] Review the presented future scenarios and proposals, and understand the need for action. Review your lifestyle and financial habits and implement security measures according to the specific improvement plans.

[0247] Specific example

[0248] For example, if a scenario is generated that highlights the risk of phishing scams, the user will understand what actions increase that risk and will be offered specific security measures such as "don't click on links in suspicious emails" and "change your password regularly."

[0249] Examples of prompts to input into a generative AI model

[0250] Use AI to generate future security risk scenarios based on users' QR code payment data, purchase data, health data, and financial data. Specifically, show how users' current actions could lead to future risks such as phishing scams, fraudulent emails, and personal data breaches, and then present specific risk management measures in text format.

[0251] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0252] Step 1:

[0253] The server receives payment data when a user makes a QR code payment at a supermarket. The input includes QR code payment data such as the transaction date and time, transaction amount, and purchased items, which is stored in a database. Specifically, when payment data is sent to the server, the server uses a database management system (MySQL®, PostgreSQL) to store it in real time.

[0254] Step 2:

[0255] The server stores data collected from multiple data sources, such as exercise data from fitness apps and spending data from banking apps, in a database. It takes exercise data (steps, exercise time) and financial data (transaction history, spending amount) as input and stores this data in a standardized format. Specifically, it actively collects data through a data collection API and performs standardization processing using a Python script.

[0256] Step 3:

[0257] The server integrates QR code payment data, purchase data, health data, and financial data stored in the database and manages them as a single dataset. Its input consists of individual data obtained from each data source, and it outputs this as an integrated dataset. Specifically, it uses a data conversion script (Python) to unify the data format and manage it centrally.

[0258] Step 4:

[0259] The server uses integrated data to analyze users' consumption trends, health status, and financial behavior using AI models (such as TensorFlow and PyTorch). It takes the integrated dataset as input and outputs evaluation results for consumption trends, health status, and financial behavior. Specifically, it supplies data to the AI ​​model and performs calculations to obtain the analysis results.

[0260] Step 5:

[0261] The server generates future health, financial, and security risk scenarios for users based on the analysis results. It uses the analysis results as input and outputs future scenarios. Specifically, it generates predictive scenarios using an AI model and visualizes them in text, image, and video formats. Plotly and FFmpeg are used for visualization.

[0262] Step 6:

[0263] The server sends the generated scenario to the user's smartphone and displays it intuitively on the device. The input is a visualized scenario, which is sent via a REST API and displayed using a user interface built with React Native. Specifically, the server displays the scenario data on the device and builds an interface that is easy for the user to understand.

[0264] Step 7:

[0265] The server and terminal will propose specific behavioral changes and security measures to the user based on the generated scenario. Using the generated scenario and its analysis results as input, it will output proposed behavioral changes and security measures. Specifically, it will use OpenAI GPT-3 to generate the proposed content and display it on the terminal in text format.

[0266] Step 8:

[0267] The user reviews the presented future scenario and suggestions, and understands the need for action. The system receives the scenario and suggestions displayed on the device as input and outputs specific actions to implement the improvement measures. These actions might include the user taking measures such as "not clicking on suspicious email links" or "changing passwords regularly."

[0268] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0269] The Future Self Simulator, the present invention, is a system that integrates a user's QR code payment data, purchase data, health data, and financial data, and analyzes them using AI. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides even more personalized services. The specific method for implementing this system is described below.

[0270] 1. Data Collection

[0271] server

[0272] When a user makes a QR code payment at a supermarket, the payment data is automatically sent to the server.

[0273] The server saves user payment data to the database in real time.

[0274] For example, when a user pays for food using a QR code, the product information, price, and purchase date and time are saved.

[0275] 2. Data Integration

[0276] server

[0277] The server integrates the collected QR code payment data, purchase data, health data, and financial data.

[0278] Standardize data from different formats and manage it as a single dataset.

[0279] For example, exercise data obtained from a user's fitness app could be integrated with spending data obtained from a banking app.

[0280] 3. Data Analysis

[0281] server

[0282] Based on the integrated data, use an AI model to analyze consumption trends, health status, and financial behavior.

[0283] The analysis reveals the user's current lifestyle and financial behavior.

[0284] For example, evaluate the health risks of users who frequently purchase specific foods and their monthly expenditure patterns.

[0285] 4. Generation of Future Scenarios

[0286] Server

[0287] The AI model generates multiple scenarios of future health and financial situations based on the current data. In this process, the emotion engine recognizes the user's emotions and adaptively generates scenarios.

[0288] This provides scenarios that take into account the user's psychological state.

[0289] For example, when the user is feeling stressed, generate scenarios that include suggestions for relaxation and stress relief.

[0290] 5. Transmission and Display of Visual Content

[0291] Server

[0292] Transmit the generated visual content to the user's terminal.

[0293] The content is displayed on the user's smartphone or computer.

[0294] Terminal

[0295] The terminal displays the received visual content through an intuitive user interface.

[0296] Users can realistically check the appearance and health status of their future selves.

[0297] For example, images that realistically reproduce the body shape and financial situation 10 years later if continued are displayed.

[0298] 6. Proposal for Behavior Variation

[0299] Server

[0300] Based on the generated scenario, the server generates specific proposals for behavior variation for the user. Based on the emotions of the user recognized by the emotion engine, the content of the proposal is also adaptively adjusted.

[0301] The content of the proposal is sent to the user's terminal in text form.

[0302] Terminal

[0303] The terminal displays the content of the proposal to the user and presents improvement measures that can be executed step by step.

[0304] An individualized approach is taken so that it is easy for the user to understand.

[0305] For example, when the user is in a depressed mood, proposals to start with small goals that can be easily executed are displayed.

[0306] 7. User Behavior

[0307] User

[0308] The user checks the future scenario and the content of the proposal presented on the terminal and understands the necessity of action.

[0309] Takes actions to review lifestyle and financial behaviors according to the presented improvement measures.

[0310] For example, executes specific actions such as "adding vegetables to daily meals" and "formulating a monthly budget".

[0311] The above describes the configuration for implementing the Future Self Simulator. Through this system, users can visualize their future health and financial situation in concrete terms, and gain motivation to re-evaluate their current actions. Furthermore, the introduction of an emotion engine enables more personalized suggestions that take the user's feelings into consideration.

[0312] The following describes the processing flow.

[0313] Step 1:

[0314] Server: Receives user QR code payment data. Specifically, it retrieves payment information from the QR code payment system via API, links it to the user ID, and stores it.

[0315] Step 2:

[0316] Server: Stores received QR code payment data in a database. Records detailed information such as the name of the purchased item, price, and date and time of purchase.

[0317] Step 3:

[0318] Server: Integrates data from multiple data sources. Centralizes user purchase data, health data, and financial data, and standardizes data formats.

[0319] Step 4:

[0320] Server: Analyzes consumption trends, health status, and financial behavior based on integrated data. Uses AI models to evaluate users' current lifestyles and financial behavior.

[0321] Step 5:

[0322] Server: Uses an emotion engine to recognize the user's emotions. It collects and analyzes emotion data from the user's voice, facial expressions, text input, etc.

[0323] Step 6:

[0324] Server: Based on the analysis results, it generates multiple scenarios for the user's future health and financial status. In this process, the emotion engine adaptively adjusts the scenarios according to the user's emotions as perceived.

[0325] Step 7:

[0326] Server: Visualizes the generated scenarios. Utilizes generative AI technology to realistically represent scenarios in text, image, and video formats.

[0327] Step 8:

[0328] Server: Sends visualized scenarios to the user's device. Sends data to smartphones and PCs via API.

[0329] Step 9:

[0330] Terminal: Displays received visual content. An intuitive user interface allows users to check their future health and financial status.

[0331] Step 10:

[0332] Server: Based on future scenarios, it generates specific behavioral change suggestions for the user. Based on the user's emotions recognized by the emotion engine, it adaptively adjusts the suggestions.

[0333] Step 11:

[0334] Terminal: Displays the proposed content to the user. Specific improvement measures are presented step-by-step, and the system is designed to be easy for the user to understand.

[0335] Step 12:

[0336] User: Review the presented future scenarios and proposed solutions, and implement necessary behavioral changes. Develop a concrete action plan and put it into action.

[0337] (Example 2)

[0338] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0339] In modern society, it is crucial for many users to properly manage their health and financial situation and plan for the future. However, it is difficult to comprehensively grasp information from multiple data sources and make predictions about the future. Furthermore, suggestions and scenarios that do not take into account individual emotional states have the problem of not being able to adequately respond to users' feelings and behavioral changes. To solve these problems, there is a need for a system that provides more advanced and personalized future predictions and action suggestions.

[0340] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, health data, and financial data from multiple data sources, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for recognizing the user's current emotional state using an emotion engine and reflecting this in the scenario generation, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, means for intuitively displaying the visualized scenarios through a user interface, means for generating suggestions for behavioral change to the user and adaptively adjusting the suggestion content based on emotions, and means for transmitting the suggestion content in text format to the user's terminal. As a result, the user can comprehensively understand their own consumption trends, health status, and financial status, and based on these, specifically predict future health and financial scenarios. Furthermore, by incorporating emotion recognition, users can receive actionable suggestions that take their feelings into consideration, thereby improving the rate of behavioral change implementation.

[0341] "QR code payment data" refers to information related to transactions using QR codes, including details such as product information, price, purchase date and time, and purchase location.

[0342] A "database" is a system or software for efficiently storing, managing, and retrieving structured information.

[0343] A "data source" is the system, application, or device from which data is generated or collected.

[0344] "Purchase data" refers to data that includes all information about transactions and purchases made by a user, such as product name, price, and purchase date and time.

[0345] "Health data" refers to data related to a user's health status and fitness activities, including information such as exercise volume, weight, and heart rate.

[0346] "Financial data" refers to data related to a user's economic activities and financial situation, including information such as income, expenses, savings, and investments.

[0347] "Integration" is the process of combining data of different formats and types obtained from multiple data sources into a single dataset.

[0348] "Consumption trends" refer to patterns or tendencies that show what kinds of products and services users purchase and how frequently.

[0349] "Health status" refers to the user's current physical and mental health condition.

[0350] "Financial behavior" refers to a user's patterns of financial actions, such as income, expenses, savings, and investments.

[0351] A "scenario" is a prediction or assumption of future events or circumstances, and may include multiple predictions about the user's health and financial status.

[0352] An "emotion engine" is an algorithm or mechanism for recognizing and analyzing a user's emotional state.

[0353] "Visualization" is the process of representing data and information as images or videos in a way that is easy for users to intuitively understand.

[0354] "User interface" is a general term for the interactive screens and methods of operation that users use to interact with a system.

[0355] "Behavioral change" refers to users taking specific actions to improve their lifestyle habits and behavioral patterns.

[0356] A "proposal" is a specific set of actions or advice designed to encourage users to change their behavior.

[0357] "Adaptive" refers to the ability to make flexible changes or adjustments according to the situation or conditions.

[0358] The Future Self Simulator, the present invention, is a system that integrates a user's QR code payment data, purchase data, health data, and financial data, and analyzes them using AI. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides even more personalized services. The specific method for implementing this system is described below.

[0359] Data collection

[0360] The server automatically receives payment data from the POS system when a user makes a QR code payment at a supermarket. The received data includes details such as product information, price, purchase date and time, and purchase location. The data is immediately stored in the database. For this reason, a common relational database (e.g., MySQL or PostgreSQL) is used as the database system.

[0361] For example, if a user purchases vegetables and beverages at a supermarket, the transaction information is sent to the server and stored in the database as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Beverages ¥150".

[0362] Data integration

[0363] The server periodically collects purchase data, health data (e.g., data from fitness trackers), and financial data (transaction history from banking apps) from multiple data sources, and performs a process of standardizing and integrating data in different formats. ETL (Extract, Transform, Load) tools (e.g., Apache® NiFi or Talend) are used for standardization.

[0364] For example, the server integrates exercise data such as "2023-10-01 07:00 AM Jogging 5km" and purchase data such as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Drinks ¥150" and manages them as a single dataset.

[0365] Data analysis

[0366] The server sends the integrated dataset to an AI analysis module, where it performs analysis using machine learning models (e.g., time series analysis or predictive models). For the analysis, programming languages ​​such as Python and R are used, and machine learning frameworks such as TensorFlow and PyTorch are utilized.

[0367] As a concrete example, the server might analyze the data and conclude that "the user purchases junk food at least three times a week, and their monthly food expenses are likely to exceed 30,000 yen."

[0368] Generating future scenarios

[0369] Based on the analysis results, the server sends prompts to the generating AI model to create scenarios for future health and financial situations. The generating AI model uses natural language generation models such as GPT-3 and BERT. Additionally, an emotion engine is used to recognize the user's current emotional state and incorporate it into the scenario generation.

[0370] An example of a prompt message that might be generated is: "Based on the user's health and purchase data from the past year, predict their health status 10 years from now and suggest lifestyle changes the user should adopt to avoid health risks."

[0371] Sending and displaying visual content

[0372] The server is designed to create visual content that visually represents the generated scenario (e.g., graphs showing future body shape and economic situation) and send it to the user's device. Data visualization libraries such as D3.js and Chart.js are used for visualization.

[0373] The device displays the received visual content through a user interface, rendering it in a way that the user can intuitively understand. For example, a "health prediction graph for 10 years from now" or an "estimated future savings image" might be displayed on the smartphone screen.

[0374] Proposals for behavioral change

[0375] The server generates specific behavioral change suggestions from the generated scenarios and visual content, and adaptively adjusts the suggestions based on the user's emotional state as recognized by the emotion engine. The generated suggestions are sent to the user's device in text format.

[0376] The device displays the received suggestions and presents personalized actions that are easy for the user to take. For example, it might display a specific suggestion such as "Add vegetables to one meal a day."

[0377] User behavior

[0378] Users review future scenarios and suggestions displayed on their devices and select actions to improve their lifestyle and financial behavior. They then execute these actions and add the results as feedback to their fitness tracker or financial app.

[0379] Through the above steps, the Future Self Simulator will be able to comprehensively understand the user's consumption trends, health status, and financial situation, specifically predict future health and financial scenarios, and provide actionable suggestions.

[0380] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0381] Step 1: Data Collection

[0382] The server automatically receives payment data from the POS system when a user makes a QR code payment at a supermarket. The input data includes details such as product information, price, purchase date and time, and purchase location. This data is immediately saved to the database using SQL queries. For example, if a user purchases vegetables and a beverage, it will be saved as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Beverage ¥150".

[0383] Step 2: Integration of the certificate

[0384] The server periodically collects purchase data, health data, and financial data from multiple data sources (e.g., fitness trackers and banking apps). The input data is raw data obtained from each data source. An ETL tool (e.g., Apache NiFi) is used to standardize the data in different formats and integrate it into a single dataset. The data is stored in a database in a unified format. For example, exercise data such as "2023-10-01 07:00 AM Jogging 5km" is integrated with purchase data such as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Drinks ¥150".

[0385] Step 3: Data Analysis

[0386] The server sends the integrated dataset to the analysis module. The input data consists of integrated lifestyle and consumption behavior data. For analysis, Python and R programs are used, and machine learning frameworks such as TensorFlow and PyTorch are employed to perform time series analysis and predictive models. The output data is a report on the user's consumption trends, health status, and financial behavior. For example, insights such as "the user buys junk food more than three times a week and is likely to spend more than 30,000 yen on food per month" can be obtained.

[0387] Step 4: Generating Future Scenarios

[0388] The server sends the analysis results as prompts to the generating AI model. The input data consists of a summary of the analysis results and the user's current emotional state. The generating AI model (e.g., GPT-3) is used to generate scenarios for future health and financial situations. The emotion engine considers the user's emotional state and reflects it in the scenarios. The output data consists of multiple future scenarios. For example, a scenario is generated that suggests relaxation methods for a stressed user.

[0389] Step 5: Send and display visual content

[0390] The server creates content that visually represents the generated scenarios. The input data is the generated scenarios. Using data visualization libraries such as D3.js or Chart.js, the scenarios are converted into graphs and images. The output data is sent to the user's device as visual content. The device displays the received visual content through its user interface. For example, a smartphone might display a "health prediction graph for 10 years from now" or an "estimated future savings image."

[0391] Step 6: Proposing behavioral change

[0392] The server generates behavioral change suggestions from the generated scenarios and visual content. The input data consists of scenarios and visual content. The emotion engine adjusts the suggestions based on the user's recognized emotions. The generated suggestions are sent to the user's device in text format. The device displays the received suggestions and presents easy-to-follow, step-by-step actions. For example, a specific suggestion such as "Add vegetables to one meal a day" might be displayed.

[0393] Step 7: User Behavior

[0394] The user reviews future scenarios and suggestions displayed on their device and selects actions to improve their lifestyle and financial behavior based on them. The input data consists of the displayed scenarios and suggestions. The user performs the suggested actions and records the results in a fitness tracker or financial app. For example, the user might take the action of "increasing their daily jogging distance by 1km" and record the result on their device.

[0395] (Application Example 2)

[0396] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0397] Conventional data analysis systems can analyze users' consumption trends, health status, and financial behavior, but they lack the ability to suggest behavioral changes that reflect individual emotions. Furthermore, when visually representing analysis results, they are often limited to 2D displays, making it difficult for users to intuitively understand them. To address these challenges, there is a need for behavioral change suggestions that take user emotions into account, as well as intuitive displays using 3D graphics.

[0398] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, health data, and financial data from multiple data sources, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, means for generating suggestions for behavioral change to the user, means for displaying part or all of the generated scenarios in 3D graphics, and means for generating suggestions for behavioral change based on the user's emotions using an emotion engine. This makes it possible to provide users with personalized, emotion-aware suggestions for specific behavioral change, and to allow them to intuitively understand the analysis results using 3D graphics.

[0399] "QR code payment data" refers to transaction information generated when a user makes a payment for goods or services using a QR code.

[0400] A "database" refers to a system for efficiently storing, managing, searching, and updating collected data.

[0401] "Data sources" refer to various original sources or suppliers that provide information such as a user's purchase history, health data, and financial transaction information.

[0402] "Purchase data" refers to transaction information when a user purchases goods or services.

[0403] "Health data" refers to information about a user's health, including data such as exercise habits, diet, weight, and blood pressure.

[0404] "Financial data" refers to data about a user's financial situation, such as income, expenses, savings, investments, and debt.

[0405] "Integrating" refers to the process of combining data from multiple different data sources into a single, consistent format.

[0406] "Consumption trends" refer to habits and patterns derived from users' purchasing behavior.

[0407] "Health status" refers to the overall situation and assessment of the user's current health.

[0408] "Financial activity" refers to financial transactions and actions related to a user's income, expenses, savings, etc.

[0409] A "scenario" refers to a prediction or plan for the future that takes specific conditions into account.

[0410] "Visualizing" refers to the act of representing information visually in the form of text, images, videos, and other media.

[0411] "Terminal" refers to electronic devices such as computers, smartphones, and tablets that users directly use.

[0412] "Suggestions for behavioral change" refer to specific guidance or advice aimed at improving or altering a user's current behavior.

[0413] "3D graphics" refers to computer graphics that display information to the user in a three-dimensional form.

[0414] An "emotion engine" refers to a computational model or system that determines a user's emotional state and generates responses and suggestions based on those emotions.

[0415] The embodiments for carrying out this invention will be described in detail below.

[0416] 1. Data Collection

[0417] When a user makes a QR code payment, the server automatically receives the data and stores it in a database. For example, when a user makes a QR code payment at a supermarket, the product information, price, and purchase date and time are saved in the database.

[0418] 2. Data Integration

[0419] The server integrates QR code payment data, purchase data, health data, and financial data collected from multiple data sources. It standardizes data in different formats and manages it as a single dataset. For example, it integrates exercise data obtained from a fitness app with spending data obtained from a banking app.

[0420] 3. Data Analysis

[0421] The server uses integrated data and AI models to analyze users' consumption trends, health status, and financial behavior, and generates multiple scenarios based on this analysis. Generative AI models are used for the analysis. For example, it evaluates the health risks of users who frequently purchase certain foods and their monthly spending patterns.

[0422] 4. Generating future scenarios

[0423] The AI ​​model generates multiple scenarios for future health and financial status based on current data. In this process, an emotion engine recognizes the user's emotions and provides scenarios that take their psychological state into consideration. For example, if the user is feeling stressed, it generates scenarios that include suggestions for relaxation and stress relief.

[0424] 5. Sending and displaying visual content

[0425] The server sends the generated visual content to the user's device. The device then intuitively displays the received visual content using 3D graphics. This allows the user to realistically see their future appearance, health, and financial situation. For example, an image is displayed that realistically recreates their physique and financial situation 10 years from now if they continue the program.

[0426] 6. Proposals for behavioral change

[0427] The server generates specific behavioral change suggestions for the user based on the generated scenario. The suggestions are adaptively adjusted based on the user's emotions as recognized by the emotion engine. The suggestions are sent to the user's device in text format and displayed in a way that is easy for the user to understand. For example, if the user is feeling down, suggestions to start with small, easily achievable goals will be displayed.

[0428] As a concrete example, a user can view a scenario based on spending 1500 yen, exercising for 30 minutes, and having a monthly income of 50000 yen. This scenario predicts their future health and financial situation, and uses an emotion engine to suggest behavioral changes to reduce stress. Furthermore, by inputting prompts like the following into the generative AI model, appropriate future scenarios are provided.

[0429] Example of a prompt:

[0430] "Input user purchase data, health data, and financial data to predict future health and financial status. Also, generate behavioral change suggestions when users are experiencing stress."

[0431] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0432] Step 1:

[0433] The server receives payment data when a user makes a QR code payment. The input includes transaction information generated by the QR code payment, such as product information, price, and purchase date and time. The server receives this data and stores it in a database. The output is the stored transaction information.

[0434] Step 2:

[0435] The server integrates data collected from multiple data sources. Inputs include QR code payment data, purchase data, health data, and financial data. It converts data in different formats into a unified format and integrates it into a single dataset. Specifically, it retrieves exercise data from a fitness app and spending data from a banking app. The output is a single, integrated dataset.

[0436] Step 3:

[0437] The server analyzes users' consumption trends, health status, and financial behavior based on an integrated dataset. The integrated dataset is included as input. The data is fed into an AI model for analysis, evaluating user behavior patterns and risks. Specifically, a generative AI model is used to assess the health risks and monthly spending patterns of users who frequently purchase certain foods. The output is the analysis results.

[0438] Step 4:

[0439] The server generates multiple scenarios for the user's future health and financial status based on the analysis results. The input includes the analysis results. Using an AI model and emotion engine, it generates future scenarios based on the user's current data and emotions. Specifically, if the user is experiencing stress, it generates scenarios that include suggestions for relaxation and stress relief. The output is the multiple scenarios generated.

[0440] Step 5:

[0441] The server sends the generated visual content to the user's device. The input includes multiple generated scenarios. These scenarios are visualized in text, image, and video formats and sent to the user's device. Specific actions include images that 3D-render the user's physique and financial situation 10 years later if they continue their current actions. The output is the visual content sent to the user's device.

[0442] Step 6:

[0443] The device intuitively displays received visual content using 3D graphics. The input includes visual content. The device displays this content, allowing the user to see their future self, health, and financial situation. Specifically, the user views the 3D graphics and intuitively understands future scenarios. The output is the displayed 3D graphics.

[0444] Step 7:

[0445] The server generates specific behavioral change suggestions for the user based on the generated scenario. Input includes the generated scenario and the user's emotional information. Using an emotional engine, it generates behavioral change suggestions adapted to the user's emotions and sends them to the user's device in text format. For example, if the user is feeling down, it will display suggestions to start with small, easily achievable goals. The output is the text of the behavioral change suggestions.

[0446] Step 8:

[0447] The user reviews the future scenarios and suggestions presented on the device and understands the need for action. Input includes displayed 3D graphics and suggested text for behavioral change. Based on this, the user takes action to review their lifestyle and financial behavior. Specific actions include "adding vegetables to daily meals" or "creating a monthly budget." The output is the result of the user's actions.

[0448] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0449] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0450] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0451] [Second Embodiment]

[0452] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0453] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0454] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0455] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0456] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0457] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0458] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0459] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0460] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0461] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0462] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0463] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0464] The Future Self Simulator, as described in this invention, is a system that integrates a user's QR code payment data, purchase data, health data, and financial data, and analyzes them using AI. The specific method for implementing this system is described below.

[0465] 1. Data Collection

[0466] server

[0467] When a user makes a QR code payment at a supermarket, the payment data is automatically sent to the server.

[0468] The server saves user payment data to the database in real time.

[0469] For example, when a user pays for food using a QR code, the product information, price, and purchase date and time are saved.

[0470] 2. Data Integration

[0471] server

[0472] The server integrates the collected QR code payment data, purchase data, health data, and financial data.

[0473] Standardize data from different formats and manage it as a single dataset.

[0474] For example, exercise data obtained from a user's fitness app could be integrated with spending data obtained from a banking app.

[0475] 3. Data Analysis

[0476] server

[0477] Based on integrated data, AI models are used to analyze consumer trends, health status, and financial behavior.

[0478] The analysis reveals the user's current lifestyle and financial behavior.

[0479] For example, we can evaluate the health risks and monthly spending patterns of users who frequently purchase certain foods.

[0480] 4. Generating future scenarios

[0481] server

[0482] The AI ​​model generates multiple scenarios for future health and financial conditions based on current data.

[0483] These scenarios are visualized in text, image, and video formats.

[0484] For example, it visualizes the user's health condition 10 years from now if they continue their current eating habits.

[0485] 5. Sending and displaying visual content

[0486] server

[0487] The generated visual content is sent to the user's device.

[0488] The content is displayed on the user's smartphone or computer.

[0489] terminal

[0490] The device displays the received visual content with an intuitive user interface.

[0491] Users can realistically see what their future self will look like and what their health condition will be.

[0492] For example, an image is displayed that realistically recreates what your body shape and financial situation might look like 10 years from now if you continue the program.

[0493] 6. Proposals for behavioral change

[0494] server

[0495] Based on the generated scenario, the server creates specific behavioral change suggestions for the user.

[0496] This proposal will be sent to the user's device in text format.

[0497] terminal

[0498] The device displays the proposed solutions to the user and presents actionable improvement measures in stages.

[0499] For example, suggestions such as "exercise three times a week" or "reduce eating out and cook at home" will be displayed.

[0500] 7. User behavior

[0501] User

[0502] The user reviews the future scenarios and suggestions presented on their device and understands the need for action.

[0503] I will take action to review my lifestyle and financial behavior in accordance with the proposed improvement measures.

[0504] For example, take concrete actions such as "add vegetables to your daily meals" or "create a monthly budget."

[0505] The above describes the configuration for implementing the Future Self Simulator. This system allows users to visualize their future health and financial situation in concrete terms, and provides them with the motivation to re-evaluate their current actions.

[0506] The following describes the processing flow.

[0507] Step 1:

[0508] Server: Receives user QR code payment data. Specifically, it retrieves payment information from the QR code payment system via API, links it to the user ID, and stores it.

[0509] Step 2:

[0510] Server: Stores received QR code payment data in a database. Records detailed information such as the name of the purchased item, price, and date and time of purchase.

[0511] Step 3:

[0512] Server: Integrates data from multiple data sources. Centralizes user purchase data, health data, and financial data, and standardizes data formats.

[0513] Step 4:

[0514] Server: Analyzes consumption trends, health status, and financial behavior based on integrated data. Uses AI models to evaluate users' current lifestyles and financial behavior.

[0515] Step 5:

[0516] Server: Based on the analysis results, it generates multiple scenarios for the user's future health and financial status. These include scenarios where the user continues their current behavior or improves it.

[0517] Step 6:

[0518] Server: Visualizes the generated scenarios. Utilizes generative AI technology to realistically represent scenarios in text, image, and video formats.

[0519] Step 7:

[0520] Server: Sends visualized scenarios to the user's device. Sends data to smartphones and PCs via API.

[0521] Step 8:

[0522] Terminal: Displays received visual content. An intuitive user interface allows users to check their future health and financial status.

[0523] Step 9:

[0524] Server: Based on future scenarios, generates specific behavioral change suggestions for users. These suggestions are generated in text format.

[0525] Step 10:

[0526] Terminal: Displays the proposed content to the user. Specific improvement measures are presented step-by-step, and the system is designed to be easy for the user to understand.

[0527] Step 11:

[0528] User: Review the presented future scenarios and proposed solutions, and implement necessary behavioral changes. Develop a concrete action plan and put it into action.

[0529] (Example 1)

[0530] Next, we will describe Example 1. 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".

[0531] Traditional data analysis systems have struggled to effectively integrate user purchasing data, exercise data, and financial data to predict users' future health and financial status. Furthermore, they lacked systems that could intuitively visualize analysis results and provide useful behavioral change suggestions to users. As a result, users lacked the motivation to take concrete actions to improve their health and financial status.

[0532] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0533] In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, exercise data, and financial data from multiple data sources, means for standardizing data in different formats and managing it as a single dataset, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, and means for generating suggestions for behavioral change to the user. This enables the user to concretely understand the impact of their current behavior on the future and motivates them to take concrete actions to improve their health status and financial status.

[0534] "QR code payment data" refers to data containing transaction information generated when a payment is made using a QR code.

[0535] A "database" is a system for systematically storing and managing collected data.

[0536] "Multiple data sources" refers to multiple sources of information that provide data of different types or formats.

[0537] "Purchase data" refers to data that includes information about products and services purchased by users.

[0538] "Exercise data" refers to data that includes information about a user's exercise habits and activity level.

[0539] "Financial data" refers to data that includes information about a user's income, expenses, and assets.

[0540] "Means of integration" refers to methods and techniques for combining data obtained from different data sources into a single dataset.

[0541] Standardization is the process of converting data provided in different formats or units into a common format or unit.

[0542] "Consumption trends" refer to patterns in what kinds of products and services users purchase and how frequently.

[0543] "Health status" refers to the overall state of the user's physical and mental health.

[0544] "Financial behavior" refers to a user's patterns of financial actions, such as income and expenses.

[0545] "Means of analysis" refers to techniques and methods for analyzing integrated data and identifying specific trends or patterns.

[0546] A "scenario" refers to a future situation or outcome predicted based on specific conditions or assumptions.

[0547] "Means of visualization" refers to methods and techniques for displaying the results of data analysis in an easily understandable visual format.

[0548] "Terminal" refers to digital devices used by users, such as computers, smartphones, and tablets.

[0549] "Suggestions for behavioral change" refer to specific advice and recommendations for improving the user's lifestyle and behavior.

[0550] The Future Self Simulator, as described in this invention, is a system that integrates and analyzes a user's QR code payment data, purchase data, exercise data, and financial data to predict and propose future health and financial conditions. The specific method for implementing this system is described below.

[0551] When a user makes a QR code payment at a supermarket or other store, the server receives the payment data. This payment data includes information about the purchased item (e.g., apples), its price, and the date and time of purchase. The received payment data is stored in the server's database in real time.

[0552] Next, the server collects user purchase data, exercise data (e.g., step count and exercise time from fitness apps), and financial data (e.g., monthly spending data from banking apps) from multiple data sources, and integrates and standardizes this data. Standardization allows data in different formats to be managed as a single dataset.

[0553] Based on integrated data, the server uses AI models to analyze users' consumption trends, health status, and financial behavior. This analysis provides a detailed understanding of users' current lifestyles and financial actions. For example, it can assess the health risks of users who frequently purchase certain foods, and evaluate their monthly spending patterns.

[0554] Based on the analysis results, the server generates multiple scenarios for the user's future health and financial status. These scenarios are visualized in text, image, and video formats. For example, it can visualize the user's health 10 years from now if they continue their current eating habits.

[0555] The generated visual content is sent from the server to the user's device (smartphone or PC). The device displays the received visual content using an intuitive user interface. This allows the user to realistically see what their future self and health status might look like.

[0556] Furthermore, based on the generated scenario, the server creates and sends to the user's terminal text-based suggestions for specific behavioral changes. These suggestions include specific advice to improve the user's lifestyle and financial behavior. Examples include "exercise three times a week" and "reduce eating out and cook at home more often."

[0557] Users can review future scenarios and suggestions presented on their devices and, based on these, revise their lifestyles and financial behaviors. For example, they can take specific actions such as "adding vegetables to their daily meals" or "creating a monthly budget."

[0558] The following are examples of prompts to input into the generating AI model.

[0559] "Explain how users can purchase food using QR code payments, and how that data can be analyzed to predict their future health."

[0560] "Describe in natural language a system that integrates current fitness and financial data to simulate future health and financial situations."

[0561] The above describes a specific embodiment of the Future Self Simulator of the present invention. This system allows users to visualize their future health and financial situation in detail and gain the motivation to reconsider their current actions.

[0562] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0563] Step 1:

[0564] Data collection

[0565] Input: User's QR code payment data.

[0566] Processing: When a user makes a QR code payment at a supermarket, the server automatically receives the payment data. The payment data includes information about the purchased items (product name, quantity, etc.), price, and date and time of purchase.

[0567] Output: Received payment data.

[0568] Specific operation: When a user purchases an apple using a QR code, the apple's information (e.g., apple, 1), price (100 yen), and purchase date and time (October 1, 2023, 15:00) are sent to the server.

[0569] Step 2:

[0570] Save to database

[0571] Input: Received payment data.

[0572] Processing: The server saves the received payment data to the database in real time.

[0573] Output: Payment data stored in the database.

[0574] Specific operation: The server saves the received Apple payment data to the "Purchase History" table in the database.

[0575] Step 3:

[0576] Collection of additional data

[0577] Input: User exercise data (e.g., obtained from a fitness app), financial data (e.g., obtained from a banking app).

[0578] Processing: The server collects user exercise data and financial data from multiple data sources. Exercise data includes the user's exercise volume (number of steps, exercise time, etc.), and financial data includes the user's spending information (spending items, amounts, date and time, etc.).

[0579] Output: Collected exercise data and financial data.

[0580] Specific operation: The server retrieves the number of steps the user walked in a day (5000 steps) from the fitness app and monthly food expenditure data (total 30,000 yen) from the banking app.

[0581] Step 4:

[0582] Data integration and standardization

[0583] Input: Collected QR code payment data, exercise data, and financial data.

[0584] Processing: The server standardizes data in different formats and manages it as a single dataset. Standardization converts each data format into a common format, making it possible to compare and analyze them with one another.

[0585] Output: Integrated and standardized dataset.

[0586] Specific operation: The server converts the purchase date and time of payment data into a unified format (e.g., YYYY-MM-DD HH:MM:SS), statistically aggregates the daily step count of exercise data, and synchronizes it with monthly expenditure data.

[0587] Step 5:

[0588] Data analysis

[0589] Input: Integrated and standardized dataset.

[0590] Processing: The server uses an AI model to analyze the user's consumption patterns, health status, and financial behavior. The analysis identifies specific patterns and risks (e.g., health risks, financial risks).

[0591] Output: Analysis results (e.g., analysis of consumption trends, assessment of health risks, patterns of financial behavior).

[0592] Specific operation: The AI ​​model detects when a user frequently purchases certain foods (e.g., high-calorie foods) and evaluates the result as a health risk.

[0593] Step 6:

[0594] Generating future scenarios

[0595] Input: Analysis results.

[0596] Processing: Based on the analysis results, the server generates multiple scenarios for the user's future health and financial status. These scenarios include predictions of the future if current lifestyle habits and financial behaviors continue.

[0597] Output: Future scenarios (e.g., visualization of future health and financial status).

[0598] Specific operation: The AI ​​model predicts and visualizes the health status (e.g., obesity risk) 10 years from now, assuming current consumption of high-calorie foods continues.

[0599] Step 7:

[0600] Visual content generation and transmission

[0601] Input: Future scenario.

[0602] Processing: The server visualizes future scenarios in text, image, and video formats, and sends the generated visual content to the user's device.

[0603] Output: The transmitted visual content.

[0604] Specific operation: Generates "Health status in 10 years" as text, "Prediction of future body shape" as an image, and "Future lifestyle simulation" as a video, and sends them to the user's smartphone.

[0605] Step 8:

[0606] Display of visual content

[0607] Input: Received visual content.

[0608] Processing: The device displays the received visual content in an intuitive user interface. Users can realistically see what their future self will look like and their health status.

[0609] Output: The displayed visual content.

[0610] Specific operation: The device displays received images and videos in full-screen mode and provides navigation buttons for the user to refer to past data.

[0611] Step 9:

[0612] Proposals for behavioral change

[0613] Input: The generated scenario.

[0614] Processing: Based on the generated scenario, the server generates specific behavioral change suggestions for the user in text format and sends them to the terminal.

[0615] Output: Proposals for behavioral change.

[0616] Specific actions: The system generates text messages suggesting things like "exercise three times a week" or "reduce eating out and cook at home," and sends them to the user's smartphone.

[0617] Step 10:

[0618] Display and implementation of behavioral change

[0619] Input: Received proposal content.

[0620] Processing: The terminal displays the suggested content to the user and presents actionable improvement measures in stages.

[0621] Output: The displayed suggestions.

[0622] Specific actions: The device displays suggestions for specific behavioral changes (e.g., "Add vegetables to your daily meals") and provides the necessary information to enable the user to take action.

[0623] Step 11:

[0624] User behavior

[0625] Input: The displayed future scenario and proposed content.

[0626] Process: The user reviews the future scenarios and suggestions presented on the device and understands their necessity. They then review their lifestyle and financial behavior according to the suggested improvements.

[0627] Output: Improved lifestyle and financial behavior.

[0628] Specific actions: Users perform specific actions, such as "add vegetables to their daily meals," and provide feedback on the results to the server.

[0629] The above describes the specific program processing of the Future Self Simulator. This system allows users to visualize their future health and financial situation in concrete terms, and provides them with the motivation to re-evaluate their current actions.

[0630] (Application Example 1)

[0631] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0632] Modern consumers possess diverse purchase history, health data, and financial data, and there is a growing need to integrate and analyze this data to predict future health and financial status. However, with increasing security risks, there is a lack of systems that can assess future security risks based on this data and propose appropriate security measures. Current systems struggle to efficiently integrate and analyze multiple data sources and present risk scenarios in an intuitively understandable format. Therefore, the challenge lies in achieving comprehensive security risk management and encouraging effective behavioral change in users.

[0633] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0634] In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, health data, and financial data from multiple data sources, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, means for generating suggestions for behavioral change to the user, means for analyzing the user's safety risks and generating future security risk scenarios, means for visualizing the generated security risk scenarios in text and image formats, means for transmitting the visualized security risk scenarios to the user's terminal, and means for generating and providing security countermeasures suggestions to the user. As a result, users can intuitively understand not only the impact of their actions on their health and finances, but also future security risks, and take appropriate measures.

[0635] "QR code payment data" refers to all data related to payments made using QR codes, and specifically includes transaction date and time, transaction amount, purchased items, etc.

[0636] A "database" is an information system for efficiently storing, managing, and retrieving large amounts of data, and relational database management systems (RDBMS) are often used for this purpose.

[0637] "Purchase data" refers to data containing information about products purchased by a user, including product name, purchase date and time, purchase location, and purchase price.

[0638] "Health data" refers to data related to the user's health, such as exercise data obtained from fitness apps and physical measurement data obtained from health apps.

[0639] "Financial data" refers to data related to a user's financial situation, including banking transactions, credit card usage history, and asset status.

[0640] "Consumer trends" refer to data that shows patterns in what kinds of products and services users prefer to purchase, and are based on purchase history and purchase frequency.

[0641] "Health status" refers to data indicating the user's physical and mental health, including measured health data and medical records.

[0642] "Financial behavior" refers to data that shows patterns in how users spend money, and is based on income and expenditure balances and category analysis of spending.

[0643] A "scenario" refers to a predicted future situation generated based on analyzed data, and includes the user's future health, financial situation, security risks, etc.

[0644] "Visualization" refers to the visual representation of data and scenarios, and is provided in formats such as graphs, charts, and videos.

[0645] "Security risks" refer to security-related risks that users may face, including phishing scams and the leakage of personal information.

[0646] A "security risk scenario" refers to a predicted situation regarding future security risks, generated based on analyzed data.

[0647] "Security measures" refer to the specific actions and policies that users take to address security risks.

[0648] The Future Security Advisor, as described in this invention, is a system that analyzes users' consumption trends, health status, and financial behavior based on QR code payment data, purchase data, health data, and financial data, and uses these analysis results to generate and present future health status, financial status, and security risk scenarios. This system enables users to intuitively understand the impact of their actions on the future and to take concrete actions to change their behavior and implement security measures.

[0649] 1. Data Collection

[0650] server

[0651] The system receives QR code payment data and stores it in a database. Specifically, when a user makes a QR code payment at a supermarket, the payment data (product information, price, purchase date and time, etc.) is automatically sent to the server.

[0652] We collect purchase data, health data, and financial data from multiple data sources. For example, we obtain exercise data from a fitness app and collect spending data from a banking app.

[0653] 2. Data Integration

[0654] server

[0655] The collected data is standardized and managed as a single integrated dataset. This allows for the integration of data in different formats and conversion into an analyzable format.

[0656] 3. Data Analysis

[0657] server

[0658] Based on integrated data, AI models (such as TensorFlow and PyTorch) are used to analyze users' consumption trends, health status, and financial behavior. Based on the analysis results, users' current lifestyles and financial behaviors are revealed.

[0659] The analysis assesses user safety risks and generates future security risk scenarios.

[0660] 4. Generating and Visualizing Future Scenarios

[0661] server

[0662] Based on analysis results generated using AI models, future health, financial, and security risk scenarios are visualized in text, image, and video formats. Plotly is used for data visualization, and FFmpeg is used to generate the video.

[0663] 5. Sending and displaying content

[0664] server

[0665] Visualized scenarios are sent to the user's smartphone and displayed intuitively through the user interface. This utilizes a REST API and a front-end framework (React Native).

[0666] 6. Proposals for behavioral change

[0667] Server and hardware

[0668] Based on the generated scenario, the system sends users specific suggestions for behavioral change and security measures in text format, which are then displayed on their devices. Using a text generation model based on OpenAI GPT-3, users receive step-by-step improvement plans.

[0669] 7. User behavior

[0670] User

[0671] Review the presented future scenarios and proposals, and understand the need for action. Review your lifestyle and financial habits and implement security measures according to the specific improvement plans.

[0672] Specific example

[0673] For example, if a scenario is generated that highlights the risk of phishing scams, the user will understand what actions increase that risk and will be offered specific security measures such as "don't click on links in suspicious emails" and "change your password regularly."

[0674] Examples of prompts to input into a generative AI model

[0675] Use AI to generate future security risk scenarios based on users' QR code payment data, purchase data, health data, and financial data. Specifically, show how users' current actions could lead to future risks such as phishing scams, fraudulent emails, and personal data breaches, and then present specific risk management measures in text format.

[0676] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0677] Step 1:

[0678] The server receives payment data when a user makes a QR code payment at a supermarket. The input includes QR code payment data such as the transaction date and time, transaction amount, and purchased items, which is then stored in a database. Specifically, when payment data is sent to the server, it is stored in real time using a database management system (MySQL, PostgreSQL).

[0679] Step 2:

[0680] The server stores data collected from multiple data sources, such as exercise data from fitness apps and spending data from banking apps, in a database. It takes exercise data (steps, exercise time) and financial data (transaction history, spending amount) as input and stores this data in a standardized format. Specifically, it actively collects data through a data collection API and performs standardization processing using a Python script.

[0681] Step 3:

[0682] The server integrates QR code payment data, purchase data, health data, and financial data stored in the database and manages them as a single dataset. Its input consists of individual data obtained from each data source, and it outputs this as an integrated dataset. Specifically, it uses a data conversion script (Python) to unify the data format and manage it centrally.

[0683] Step 4:

[0684] The server uses integrated data to analyze users' consumption trends, health status, and financial behavior using AI models (such as TensorFlow and PyTorch). It takes the integrated dataset as input and outputs evaluation results for consumption trends, health status, and financial behavior. Specifically, it supplies data to the AI ​​model and performs calculations to obtain the analysis results.

[0685] Step 5:

[0686] The server generates future health, financial, and security risk scenarios for users based on the analysis results. It uses the analysis results as input and outputs future scenarios. Specifically, it generates predictive scenarios using an AI model and visualizes them in text, image, and video formats. Plotly and FFmpeg are used for visualization.

[0687] Step 6:

[0688] The server sends the generated scenario to the user's smartphone and displays it intuitively on the device. The input is a visualized scenario, which is sent via a REST API and displayed using a user interface built with React Native. Specifically, the server displays the scenario data on the device and builds an interface that is easy for the user to understand.

[0689] Step 7:

[0690] The server and terminal will propose specific behavioral changes and security measures to the user based on the generated scenario. Using the generated scenario and its analysis results as input, it will output proposed behavioral changes and security measures. Specifically, it will use OpenAI GPT-3 to generate the proposed content and display it on the terminal in text format.

[0691] Step 8:

[0692] The user reviews the presented future scenario and suggestions, and understands the need for action. The system receives the scenario and suggestions displayed on the device as input and outputs specific actions to implement the improvement measures. These actions might include the user taking measures such as "not clicking on suspicious email links" or "changing passwords regularly."

[0693] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0694] The Future Self Simulator, the present invention, is a system that integrates a user's QR code payment data, purchase data, health data, and financial data, and analyzes them using AI. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides even more personalized services. The specific method for implementing this system is described below.

[0695] 1. Data Collection

[0696] server

[0697] When a user makes a QR code payment at a supermarket, the payment data is automatically sent to the server.

[0698] The server saves user payment data to the database in real time.

[0699] For example, when a user pays for food using a QR code, the product information, price, and purchase date and time are saved.

[0700] 2. Data Integration

[0701] server

[0702] The server integrates the collected QR code payment data, purchase data, health data, and financial data.

[0703] Standardize data from different formats and manage it as a single dataset.

[0704] For example, exercise data obtained from a user's fitness app could be integrated with spending data obtained from a banking app.

[0705] 3. Data Analysis

[0706] server

[0707] Based on integrated data, AI models are used to analyze consumer trends, health status, and financial behavior.

[0708] The analysis reveals the user's current lifestyle and financial behavior.

[0709] For example, we can evaluate the health risks and monthly spending patterns of users who frequently purchase certain foods.

[0710] 4. Generating future scenarios

[0711] server

[0712] The AI ​​model generates multiple scenarios for future health and financial status based on current data. During this process, an emotion engine recognizes the user's emotions and adaptively generates scenarios.

[0713] This allows for the provision of scenarios that take into account the user's psychological state.

[0714] For example, if a user is feeling stressed, the system will generate a scenario that includes suggestions for relaxation and stress relief.

[0715] 5. Sending and displaying visual content

[0716] server

[0717] The generated visual content is sent to the user's device.

[0718] The content is displayed on the user's smartphone or computer.

[0719] terminal

[0720] The device displays the received visual content with an intuitive user interface.

[0721] Users can realistically see what their future self will look like and what their health condition will be.

[0722] For example, an image is displayed that realistically recreates what your body shape and financial situation might look like 10 years from now if you continue the program.

[0723] 6. Proposals for behavioral change

[0724] server

[0725] The server generates specific behavioral change suggestions for the user based on the generated scenario. The suggestions are also adaptively adjusted based on the user's emotions recognized by the emotion engine.

[0726] The proposal will be sent to the user's device in text format.

[0727] terminal

[0728] The device displays the proposed solutions to the user and presents actionable improvement measures in stages.

[0729] A personalized approach is taken to ensure that users can easily understand the process.

[0730] For example, if a user is feeling down, suggestions will be displayed to start with small, easily achievable goals.

[0731] 7. User behavior

[0732] User

[0733] The user reviews the future scenarios and suggestions presented on their device and understands the need for action.

[0734] I will take action to review my lifestyle and financial behavior in accordance with the proposed improvement measures.

[0735] For example, take concrete actions such as "add vegetables to your daily meals" or "create a monthly budget."

[0736] The above describes the configuration for implementing the Future Self Simulator. Through this system, users can visualize their future health and financial situation in concrete terms, and gain motivation to re-evaluate their current actions. Furthermore, the introduction of an emotion engine enables more personalized suggestions that take the user's feelings into consideration.

[0737] The following describes the processing flow.

[0738] Step 1:

[0739] Server: Receives user QR code payment data. Specifically, it retrieves payment information from the QR code payment system via API, links it to the user ID, and stores it.

[0740] Step 2:

[0741] Server: Stores received QR code payment data in a database. Records detailed information such as the name of the purchased item, price, and date and time of purchase.

[0742] Step 3:

[0743] Server: Integrates data from multiple data sources. Centralizes user purchase data, health data, and financial data, and standardizes data formats.

[0744] Step 4:

[0745] Server: Analyzes consumption trends, health status, and financial behavior based on integrated data. Uses AI models to evaluate users' current lifestyles and financial behavior.

[0746] Step 5:

[0747] Server: Uses an emotion engine to recognize the user's emotions. It collects and analyzes emotion data from the user's voice, facial expressions, text input, etc.

[0748] Step 6:

[0749] Server: Based on the analysis results, it generates multiple scenarios for the user's future health and financial status. In this process, the emotion engine adaptively adjusts the scenarios according to the user's emotions as perceived.

[0750] Step 7:

[0751] Server: Visualizes the generated scenarios. Utilizes generative AI technology to realistically represent scenarios in text, image, and video formats.

[0752] Step 8:

[0753] Server: Sends visualized scenarios to the user's device. Sends data to smartphones and PCs via API.

[0754] Step 9:

[0755] Terminal: Displays received visual content. An intuitive user interface allows users to check their future health and financial status.

[0756] Step 10:

[0757] Server: Based on future scenarios, it generates specific behavioral change suggestions for the user. Based on the user's emotions recognized by the emotion engine, it adaptively adjusts the suggestions.

[0758] Step 11:

[0759] Terminal: Displays the proposed content to the user. Specific improvement measures are presented step-by-step, and the system is designed to be easy for the user to understand.

[0760] Step 12:

[0761] User: Review the presented future scenarios and proposed solutions, and implement necessary behavioral changes. Develop a concrete action plan and put it into action.

[0762] (Example 2)

[0763] Next, we will describe Example 2. 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".

[0764] In modern society, it is crucial for many users to properly manage their health and financial situation and plan for the future. However, it is difficult to comprehensively grasp information from multiple data sources and make predictions about the future. Furthermore, suggestions and scenarios that do not take into account individual emotional states have the problem of not being able to adequately respond to users' feelings and behavioral changes. To solve these problems, there is a need for a system that provides more advanced and personalized future predictions and action suggestions.

[0765] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, health data, and financial data from multiple data sources, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for recognizing the user's current emotional state using an emotion engine and reflecting this in the scenario generation, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, means for intuitively displaying the visualized scenarios through a user interface, means for generating suggestions for behavioral change to the user and adaptively adjusting the suggestion content based on emotions, and means for transmitting the suggestion content in text format to the user's terminal. As a result, the user can comprehensively understand their own consumption trends, health status, and financial status, and based on these, specifically predict future health and financial scenarios. Furthermore, by incorporating emotion recognition, users can receive actionable suggestions that take their feelings into consideration, thereby improving the rate of behavioral change implementation.

[0766] "QR code payment data" refers to information related to transactions using QR codes, including details such as product information, price, purchase date and time, and purchase location.

[0767] A "database" is a system or software for efficiently storing, managing, and retrieving structured information.

[0768] A "data source" is the system, application, or device from which data is generated or collected.

[0769] "Purchase data" refers to data that includes all information about transactions and purchases made by a user, such as product name, price, and purchase date and time.

[0770] "Health data" refers to data related to a user's health status and fitness activities, including information such as exercise volume, weight, and heart rate.

[0771] "Financial data" refers to data related to a user's economic activities and financial situation, including information such as income, expenses, savings, and investments.

[0772] "Integration" is the process of combining data of different formats and types obtained from multiple data sources into a single dataset.

[0773] "Consumption trends" refer to patterns or tendencies that show what kinds of products and services users purchase and how frequently.

[0774] "Health status" refers to the user's current physical and mental health condition.

[0775] "Financial behavior" refers to a user's patterns of financial actions, such as income, expenses, savings, and investments.

[0776] A "scenario" is a prediction or assumption of future events or circumstances, and may include multiple predictions about the user's health and financial status.

[0777] An "emotion engine" is an algorithm or mechanism for recognizing and analyzing a user's emotional state.

[0778] "Visualization" is the process of representing data and information as images or videos in a way that is easy for users to intuitively understand.

[0779] "User interface" is a general term for the interactive screens and methods of operation that users use to interact with a system.

[0780] "Behavioral change" refers to users taking specific actions to improve their lifestyle habits and behavioral patterns.

[0781] A "proposal" is a specific set of actions or advice designed to encourage users to change their behavior.

[0782] "Adaptive" refers to the ability to make flexible changes or adjustments according to the situation or conditions.

[0783] The Future Self Simulator, the present invention, is a system that integrates a user's QR code payment data, purchase data, health data, and financial data, and analyzes them using AI. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides even more personalized services. The specific method for implementing this system is described below.

[0784] Data collection

[0785] The server automatically receives payment data from the POS system when a user makes a QR code payment at a supermarket. The received data includes details such as product information, price, purchase date and time, and purchase location. The data is immediately stored in the database. For this reason, a common relational database (e.g., MySQL or PostgreSQL) is used as the database system.

[0786] For example, if a user purchases vegetables and beverages at a supermarket, the transaction information is sent to the server and stored in the database as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Beverages ¥150".

[0787] Data integration

[0788] The server periodically collects purchase data, health data (e.g., data from fitness trackers), and financial data (transaction history from banking apps) from multiple data sources, and performs a process of standardizing and integrating data in different formats. ETL (Extract, Transform, Load) tools (e.g., Apache NiFi or Talend) are used for standardization.

[0789] For example, the server integrates exercise data such as "2023-10-01 07:00 AM Jogging 5km" and purchase data such as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Drinks ¥150" and manages them as a single dataset.

[0790] Data analysis

[0791] The server sends the integrated dataset to an AI analysis module, where it performs analysis using machine learning models (e.g., time series analysis or predictive models). For the analysis, programming languages ​​such as Python and R are used, and machine learning frameworks such as TensorFlow and PyTorch are utilized.

[0792] As a concrete example, the server might analyze the data and conclude that "the user purchases junk food at least three times a week, and their monthly food expenses are likely to exceed 30,000 yen."

[0793] Generating future scenarios

[0794] Based on the analysis results, the server sends prompts to the generating AI model to create scenarios for future health and financial situations. The generating AI model uses natural language generation models such as GPT-3 and BERT. Additionally, an emotion engine is used to recognize the user's current emotional state and incorporate it into the scenario generation.

[0795] An example of a prompt message that might be generated is: "Based on the user's health and purchase data from the past year, predict their health status 10 years from now and suggest lifestyle changes the user should adopt to avoid health risks."

[0796] Sending and displaying visual content

[0797] The server is designed to create visual content that visually represents the generated scenario (e.g., graphs showing future body shape and economic situation) and send it to the user's device. Data visualization libraries such as D3.js and Chart.js are used for visualization.

[0798] The device displays the received visual content through a user interface, rendering it in a way that the user can intuitively understand. For example, a "health prediction graph for 10 years from now" or an "estimated future savings image" might be displayed on the smartphone screen.

[0799] Proposals for behavioral change

[0800] The server generates specific behavioral change suggestions from the generated scenarios and visual content, and adaptively adjusts the suggestions based on the user's emotional state as recognized by the emotion engine. The generated suggestions are sent to the user's device in text format.

[0801] The device displays the received suggestions and presents personalized actions that are easy for the user to take. For example, it might display a specific suggestion such as "Add vegetables to one meal a day."

[0802] User behavior

[0803] Users review future scenarios and suggestions displayed on their devices and select actions to improve their lifestyle and financial behavior. They then execute these actions and add the results as feedback to their fitness tracker or financial app.

[0804] Through the above steps, the Future Self Simulator will be able to comprehensively understand the user's consumption trends, health status, and financial situation, specifically predict future health and financial scenarios, and provide actionable suggestions.

[0805] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0806] Step 1: Data Collection

[0807] The server automatically receives payment data from the POS system when a user makes a QR code payment at a supermarket. The input data includes details such as product information, price, purchase date and time, and purchase location. This data is immediately saved to the database using SQL queries. For example, if a user purchases vegetables and a beverage, it will be saved as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Beverage ¥150".

[0808] Step 2: Integration of the certificate

[0809] The server periodically collects purchase data, health data, and financial data from multiple data sources (e.g., fitness trackers and banking apps). The input data is raw data obtained from each data source. An ETL tool (e.g., Apache NiFi) is used to standardize the data in different formats and integrate it into a single dataset. The data is stored in a database in a unified format. For example, exercise data such as "2023-10-01 07:00 AM Jogging 5km" is integrated with purchase data such as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Drinks ¥150".

[0810] Step 3: Data Analysis

[0811] The server sends the integrated dataset to the analysis module. The input data consists of integrated lifestyle and consumption behavior data. For analysis, Python and R programs are used, and machine learning frameworks such as TensorFlow and PyTorch are employed to perform time series analysis and predictive models. The output data is a report on the user's consumption trends, health status, and financial behavior. For example, insights such as "the user buys junk food more than three times a week and is likely to spend more than 30,000 yen on food per month" can be obtained.

[0812] Step 4: Generating Future Scenarios

[0813] The server sends the analysis results as prompts to the generating AI model. The input data consists of a summary of the analysis results and the user's current emotional state. The generating AI model (e.g., GPT-3) is used to generate scenarios for future health and financial situations. The emotion engine considers the user's emotional state and reflects it in the scenarios. The output data consists of multiple future scenarios. For example, a scenario is generated that suggests relaxation methods for a stressed user.

[0814] Step 5: Send and display visual content

[0815] The server creates content that visually represents the generated scenarios. The input data is the generated scenarios. Using data visualization libraries such as D3.js or Chart.js, the scenarios are converted into graphs and images. The output data is sent to the user's device as visual content. The device displays the received visual content through its user interface. For example, a smartphone might display a "health prediction graph for 10 years from now" or an "estimated future savings image."

[0816] Step 6: Proposing behavioral change

[0817] The server generates behavioral change suggestions from the generated scenarios and visual content. The input data consists of scenarios and visual content. The emotion engine adjusts the suggestions based on the user's recognized emotions. The generated suggestions are sent to the user's device in text format. The device displays the received suggestions and presents easy-to-follow, step-by-step actions. For example, a specific suggestion such as "Add vegetables to one meal a day" might be displayed.

[0818] Step 7: User Behavior

[0819] The user reviews future scenarios and suggestions displayed on their device and selects actions to improve their lifestyle and financial behavior based on them. The input data consists of the displayed scenarios and suggestions. The user performs the suggested actions and records the results in a fitness tracker or financial app. For example, the user might take the action of "increasing their daily jogging distance by 1km" and record the result on their device.

[0820] (Application Example 2)

[0821] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0822] Conventional data analysis systems can analyze users' consumption trends, health status, and financial behavior, but they lack the ability to suggest behavioral changes that reflect individual emotions. Furthermore, when visually representing analysis results, they are often limited to 2D displays, making it difficult for users to intuitively understand them. To address these challenges, there is a need for behavioral change suggestions that take user emotions into account, as well as intuitive displays using 3D graphics.

[0823] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, health data, and financial data from multiple data sources, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, means for generating suggestions for behavioral change to the user, means for displaying part or all of the generated scenarios in 3D graphics, and means for generating suggestions for behavioral change based on the user's emotions using an emotion engine. This makes it possible to provide users with personalized, emotion-aware suggestions for specific behavioral change, and to allow them to intuitively understand the analysis results using 3D graphics.

[0824] "QR code payment data" refers to transaction information generated when a user makes a payment for goods or services using a QR code.

[0825] A "database" refers to a system for efficiently storing, managing, searching, and updating collected data.

[0826] "Data sources" refer to various original sources or suppliers that provide information such as a user's purchase history, health data, and financial transaction information.

[0827] "Purchase data" refers to transaction information when a user purchases goods or services.

[0828] "Health data" refers to information about a user's health, including data such as exercise habits, diet, weight, and blood pressure.

[0829] "Financial data" refers to data about a user's financial situation, such as income, expenses, savings, investments, and debt.

[0830] "Integrating" refers to the process of combining data from multiple different data sources into a single, consistent format.

[0831] "Consumption trends" refer to habits and patterns derived from users' purchasing behavior.

[0832] "Health status" refers to the overall situation and assessment of the user's current health.

[0833] "Financial activity" refers to financial transactions and actions related to a user's income, expenses, savings, etc.

[0834] A "scenario" refers to a prediction or plan for the future that takes specific conditions into account.

[0835] "Visualizing" refers to the act of representing information visually in the form of text, images, videos, and other media.

[0836] "Terminal" refers to electronic devices such as computers, smartphones, and tablets that users directly use.

[0837] "Suggestions for behavioral change" refer to specific guidance or advice aimed at improving or altering a user's current behavior.

[0838] "3D graphics" refers to computer graphics that display information to the user in a three-dimensional form.

[0839] An "emotion engine" refers to a computational model or system that determines a user's emotional state and generates responses and suggestions based on those emotions.

[0840] The embodiments for carrying out this invention will be described in detail below.

[0841] 1. Data Collection

[0842] When a user makes a QR code payment, the server automatically receives the data and stores it in a database. For example, when a user makes a QR code payment at a supermarket, the product information, price, and purchase date and time are saved in the database.

[0843] 2. Data Integration

[0844] The server integrates QR code payment data, purchase data, health data, and financial data collected from multiple data sources. It standardizes data in different formats and manages it as a single dataset. For example, it integrates exercise data obtained from a fitness app with spending data obtained from a banking app.

[0845] 3. Data Analysis

[0846] The server uses integrated data and AI models to analyze users' consumption trends, health status, and financial behavior, and generates multiple scenarios based on this analysis. Generative AI models are used for the analysis. For example, it evaluates the health risks of users who frequently purchase certain foods and their monthly spending patterns.

[0847] 4. Generating future scenarios

[0848] The AI ​​model generates multiple scenarios for future health and financial status based on current data. In this process, an emotion engine recognizes the user's emotions and provides scenarios that take their psychological state into consideration. For example, if the user is feeling stressed, it generates scenarios that include suggestions for relaxation and stress relief.

[0849] 5. Sending and displaying visual content

[0850] The server sends the generated visual content to the user's device. The device then intuitively displays the received visual content using 3D graphics. This allows the user to realistically see their future appearance, health, and financial situation. For example, an image is displayed that realistically recreates their physique and financial situation 10 years from now if they continue the program.

[0851] 6. Proposals for behavioral change

[0852] The server generates specific behavioral change suggestions for the user based on the generated scenario. The suggestions are adaptively adjusted based on the user's emotions as recognized by the emotion engine. The suggestions are sent to the user's device in text format and displayed in a way that is easy for the user to understand. For example, if the user is feeling down, suggestions to start with small, easily achievable goals will be displayed.

[0853] As a concrete example, a user can view a scenario based on spending 1500 yen, exercising for 30 minutes, and having a monthly income of 50000 yen. This scenario predicts their future health and financial situation, and uses an emotion engine to suggest behavioral changes to reduce stress. Furthermore, by inputting prompts like the following into the generative AI model, appropriate future scenarios are provided.

[0854] Example of a prompt:

[0855] "Input user purchase data, health data, and financial data to predict future health and financial status. Also, generate behavioral change suggestions when users are experiencing stress."

[0856] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0857] Step 1:

[0858] The server receives payment data when a user makes a QR code payment. The input includes transaction information generated by the QR code payment, such as product information, price, and purchase date and time. The server receives this data and stores it in a database. The output is the stored transaction information.

[0859] Step 2:

[0860] The server integrates data collected from multiple data sources. Inputs include QR code payment data, purchase data, health data, and financial data. It converts data in different formats into a unified format and integrates it into a single dataset. Specifically, it retrieves exercise data from a fitness app and spending data from a banking app. The output is a single, integrated dataset.

[0861] Step 3:

[0862] The server analyzes users' consumption trends, health status, and financial behavior based on an integrated dataset. The integrated dataset is included as input. The data is fed into an AI model for analysis, evaluating user behavior patterns and risks. Specifically, a generative AI model is used to assess the health risks and monthly spending patterns of users who frequently purchase certain foods. The output is the analysis results.

[0863] Step 4:

[0864] The server generates multiple scenarios for the user's future health and financial status based on the analysis results. The input includes the analysis results. Using an AI model and emotion engine, it generates future scenarios based on the user's current data and emotions. Specifically, if the user is experiencing stress, it generates scenarios that include suggestions for relaxation and stress relief. The output is the multiple scenarios generated.

[0865] Step 5:

[0866] The server sends the generated visual content to the user's device. The input includes multiple generated scenarios. These scenarios are visualized in text, image, and video formats and sent to the user's device. Specific actions include images that 3D-render the user's physique and financial situation 10 years later if they continue their current actions. The output is the visual content sent to the user's device.

[0867] Step 6:

[0868] The device intuitively displays received visual content using 3D graphics. The input includes visual content. The device displays this content, allowing the user to see their future self, health, and financial situation. Specifically, the user views the 3D graphics and intuitively understands future scenarios. The output is the displayed 3D graphics.

[0869] Step 7:

[0870] The server generates specific behavioral change suggestions for the user based on the generated scenario. Input includes the generated scenario and the user's emotional information. Using an emotional engine, it generates behavioral change suggestions adapted to the user's emotions and sends them to the user's device in text format. For example, if the user is feeling down, it will display suggestions to start with small, easily achievable goals. The output is the text of the behavioral change suggestions.

[0871] Step 8:

[0872] The user reviews the future scenarios and suggestions presented on the device and understands the need for action. Input includes displayed 3D graphics and suggested text for behavioral change. Based on this, the user takes action to review their lifestyle and financial behavior. Specific actions include "adding vegetables to daily meals" or "creating a monthly budget." The output is the result of the user's actions.

[0873] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0874] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0875] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0876] [Third Embodiment]

[0877] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0878] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0879] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0880] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0881] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0882] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0883] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0884] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0885] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0886] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0887] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0888] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0889] The Future Self Simulator, as described in this invention, is a system that integrates a user's QR code payment data, purchase data, health data, and financial data, and analyzes them using AI. The specific method for implementing this system is described below.

[0890] 1. Data Collection

[0891] server

[0892] When a user makes a QR code payment at a supermarket, the payment data is automatically sent to the server.

[0893] The server saves user payment data to the database in real time.

[0894] For example, when a user pays for food using a QR code, the product information, price, and purchase date and time are saved.

[0895] 2. Data Integration

[0896] server

[0897] The server integrates the collected QR code payment data, purchase data, health data, and financial data.

[0898] Standardize data from different formats and manage it as a single dataset.

[0899] For example, exercise data obtained from a user's fitness app could be integrated with spending data obtained from a banking app.

[0900] 3. Data Analysis

[0901] server

[0902] Based on integrated data, AI models are used to analyze consumer trends, health status, and financial behavior.

[0903] The analysis reveals the user's current lifestyle and financial behavior.

[0904] For example, we can evaluate the health risks and monthly spending patterns of users who frequently purchase certain foods.

[0905] 4. Generating future scenarios

[0906] server

[0907] The AI ​​model generates multiple scenarios for future health and financial conditions based on current data.

[0908] These scenarios are visualized in text, image, and video formats.

[0909] For example, it visualizes the user's health condition 10 years from now if they continue their current eating habits.

[0910] 5. Sending and displaying visual content

[0911] server

[0912] The generated visual content is sent to the user's device.

[0913] The content is displayed on the user's smartphone or computer.

[0914] terminal

[0915] The device displays the received visual content with an intuitive user interface.

[0916] Users can realistically see what their future self will look like and what their health condition will be.

[0917] For example, an image is displayed that realistically recreates what your body shape and financial situation might look like 10 years from now if you continue the program.

[0918] 6. Proposals for behavioral change

[0919] server

[0920] Based on the generated scenario, the server creates specific behavioral change suggestions for the user.

[0921] This proposal will be sent to the user's device in text format.

[0922] terminal

[0923] The device displays the proposed solutions to the user and presents actionable improvement measures in stages.

[0924] For example, suggestions such as "exercise three times a week" or "reduce eating out and cook at home" will be displayed.

[0925] 7. User behavior

[0926] User

[0927] The user reviews the future scenarios and suggestions presented on their device and understands the need for action.

[0928] I will take action to review my lifestyle and financial behavior in accordance with the proposed improvement measures.

[0929] For example, take concrete actions such as "add vegetables to your daily meals" or "create a monthly budget."

[0930] The above describes the configuration for implementing the Future Self Simulator. This system allows users to visualize their future health and financial situation in concrete terms, and provides them with the motivation to re-evaluate their current actions.

[0931] The following describes the processing flow.

[0932] Step 1:

[0933] Server: Receives user QR code payment data. Specifically, it retrieves payment information from the QR code payment system via API, links it to the user ID, and stores it.

[0934] Step 2:

[0935] Server: Stores received QR code payment data in a database. Records detailed information such as the name of the purchased item, price, and date and time of purchase.

[0936] Step 3:

[0937] Server: Integrates data from multiple data sources. Centralizes user purchase data, health data, and financial data, and standardizes data formats.

[0938] Step 4:

[0939] Server: Analyzes consumption trends, health status, and financial behavior based on integrated data. Uses AI models to evaluate users' current lifestyles and financial behavior.

[0940] Step 5:

[0941] Server: Based on the analysis results, it generates multiple scenarios for the user's future health and financial status. These include scenarios where the user continues their current behavior or improves it.

[0942] Step 6:

[0943] Server: Visualizes the generated scenarios. Utilizes generative AI technology to realistically represent scenarios in text, image, and video formats.

[0944] Step 7:

[0945] Server: Sends visualized scenarios to the user's device. Sends data to smartphones and PCs via API.

[0946] Step 8:

[0947] Terminal: Displays received visual content. An intuitive user interface allows users to check their future health and financial status.

[0948] Step 9:

[0949] Server: Based on future scenarios, generates specific behavioral change suggestions for users. These suggestions are generated in text format.

[0950] Step 10:

[0951] Terminal: Displays the proposed content to the user. Specific improvement measures are presented step-by-step, and the system is designed to be easy for the user to understand.

[0952] Step 11:

[0953] User: Review the presented future scenarios and proposed solutions, and implement necessary behavioral changes. Develop a concrete action plan and put it into action.

[0954] (Example 1)

[0955] Next, we will describe Example 1. 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."

[0956] Traditional data analysis systems have struggled to effectively integrate user purchasing data, exercise data, and financial data to predict users' future health and financial status. Furthermore, they lacked systems that could intuitively visualize analysis results and provide useful behavioral change suggestions to users. As a result, users lacked the motivation to take concrete actions to improve their health and financial status.

[0957] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0958] In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, exercise data, and financial data from multiple data sources, means for standardizing data in different formats and managing it as a single dataset, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, and means for generating suggestions for behavioral change to the user. This enables the user to concretely understand the impact of their current behavior on the future and motivates them to take concrete actions to improve their health status and financial status.

[0959] "QR code payment data" refers to data containing transaction information generated when a payment is made using a QR code.

[0960] A "database" is a system for systematically storing and managing collected data.

[0961] "Multiple data sources" refers to multiple sources of information that provide data of different types or formats.

[0962] "Purchase data" refers to data that includes information about products and services purchased by users.

[0963] "Exercise data" refers to data that includes information about a user's exercise habits and activity level.

[0964] "Financial data" refers to data that includes information about a user's income, expenses, and assets.

[0965] "Means of integration" refers to methods and techniques for combining data obtained from different data sources into a single dataset.

[0966] Standardization is the process of converting data provided in different formats or units into a common format or unit.

[0967] "Consumption trends" refer to patterns in what kinds of products and services users purchase and how frequently.

[0968] "Health status" refers to the overall state of the user's physical and mental health.

[0969] "Financial behavior" refers to a user's patterns of financial actions, such as income and expenses.

[0970] "Means of analysis" refers to techniques and methods for analyzing integrated data and identifying specific trends or patterns.

[0971] A "scenario" refers to a future situation or outcome predicted based on specific conditions or assumptions.

[0972] "Means of visualization" refers to methods and techniques for displaying the results of data analysis in an easily understandable visual format.

[0973] "Terminal" refers to digital devices used by users, such as computers, smartphones, and tablets.

[0974] "Suggestions for behavioral change" refer to specific advice and recommendations for improving the user's lifestyle and behavior.

[0975] The Future Self Simulator, as described in this invention, is a system that integrates and analyzes a user's QR code payment data, purchase data, exercise data, and financial data to predict and propose future health and financial conditions. The specific method for implementing this system is described below.

[0976] When a user makes a QR code payment at a supermarket or other store, the server receives the payment data. This payment data includes information about the purchased item (e.g., apples), its price, and the date and time of purchase. The received payment data is stored in the server's database in real time.

[0977] Next, the server collects user purchase data, exercise data (e.g., step count and exercise time from fitness apps), and financial data (e.g., monthly spending data from banking apps) from multiple data sources, and integrates and standardizes this data. Standardization allows data in different formats to be managed as a single dataset.

[0978] Based on integrated data, the server uses AI models to analyze users' consumption trends, health status, and financial behavior. This analysis provides a detailed understanding of users' current lifestyles and financial actions. For example, it can assess the health risks of users who frequently purchase certain foods, and evaluate their monthly spending patterns.

[0979] Based on the analysis results, the server generates multiple scenarios for the user's future health and financial status. These scenarios are visualized in text, image, and video formats. For example, it can visualize the user's health 10 years from now if they continue their current eating habits.

[0980] The generated visual content is sent from the server to the user's device (smartphone or PC). The device displays the received visual content using an intuitive user interface. This allows the user to realistically see what their future self and health status might look like.

[0981] Furthermore, based on the generated scenario, the server creates and sends to the user's terminal text-based suggestions for specific behavioral changes. These suggestions include specific advice to improve the user's lifestyle and financial behavior. Examples include "exercise three times a week" and "reduce eating out and cook at home more often."

[0982] Users can review future scenarios and suggestions presented on their devices and, based on these, revise their lifestyles and financial behaviors. For example, they can take specific actions such as "adding vegetables to their daily meals" or "creating a monthly budget."

[0983] The following are examples of prompts to input into the generating AI model.

[0984] "Explain how users can purchase food using QR code payments, and how that data can be analyzed to predict their future health."

[0985] "Describe in natural language a system that integrates current fitness and financial data to simulate future health and financial situations."

[0986] The above describes a specific embodiment of the Future Self Simulator of the present invention. This system allows users to visualize their future health and financial situation in detail and gain the motivation to reconsider their current actions.

[0987] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0988] Step 1:

[0989] Data collection

[0990] Input: User's QR code payment data.

[0991] Processing: When a user makes a QR code payment at a supermarket, the server automatically receives the payment data. The payment data includes information about the purchased items (product name, quantity, etc.), price, and date and time of purchase.

[0992] Output: Received payment data.

[0993] Specific operation: When a user purchases an apple using a QR code, the apple's information (e.g., apple, 1), price (100 yen), and purchase date and time (October 1, 2023, 15:00) are sent to the server.

[0994] Step 2:

[0995] Save to database

[0996] Input: Received payment data.

[0997] Processing: The server saves the received payment data to the database in real time.

[0998] Output: Payment data stored in the database.

[0999] Specific operation: The server saves the received Apple payment data to the "Purchase History" table in the database.

[1000] Step 3:

[1001] Collection of additional data

[1002] Input: User exercise data (e.g., obtained from a fitness app), financial data (e.g., obtained from a banking app).

[1003] Processing: The server collects user exercise data and financial data from multiple data sources. Exercise data includes the user's exercise volume (number of steps, exercise time, etc.), and financial data includes the user's spending information (spending items, amounts, date and time, etc.).

[1004] Output: Collected exercise data and financial data.

[1005] Specific operation: The server retrieves the number of steps the user walked in a day (5000 steps) from the fitness app and monthly food expenditure data (total 30,000 yen) from the banking app.

[1006] Step 4:

[1007] Data integration and standardization

[1008] Input: Collected QR code payment data, exercise data, and financial data.

[1009] Processing: The server standardizes data in different formats and manages it as a single dataset. Standardization converts each data format into a common format, making it possible to compare and analyze them with one another.

[1010] Output: Integrated and standardized dataset.

[1011] Specific operation: The server converts the purchase date and time of payment data into a unified format (e.g., YYYY-MM-DD HH:MM:SS), statistically aggregates the daily step count of exercise data, and synchronizes it with monthly expenditure data.

[1012] Step 5:

[1013] Data analysis

[1014] Input: Integrated and standardized dataset.

[1015] Processing: The server uses an AI model to analyze the user's consumption patterns, health status, and financial behavior. The analysis identifies specific patterns and risks (e.g., health risks, financial risks).

[1016] Output: Analysis results (e.g., analysis of consumption trends, assessment of health risks, patterns of financial behavior).

[1017] Specific operation: The AI ​​model detects when a user frequently purchases certain foods (e.g., high-calorie foods) and evaluates the result as a health risk.

[1018] Step 6:

[1019] Generating future scenarios

[1020] Input: Analysis results.

[1021] Processing: Based on the analysis results, the server generates multiple scenarios for the user's future health and financial status. These scenarios include predictions of the future if current lifestyle habits and financial behaviors continue.

[1022] Output: Future scenarios (e.g., visualization of future health and financial status).

[1023] Specific operation: The AI ​​model predicts and visualizes the health status (e.g., obesity risk) 10 years from now, assuming current consumption of high-calorie foods continues.

[1024] Step 7:

[1025] Visual content generation and transmission

[1026] Input: Future scenario.

[1027] Processing: The server visualizes future scenarios in text, image, and video formats, and sends the generated visual content to the user's device.

[1028] Output: The transmitted visual content.

[1029] Specific operation: Generates "Health status in 10 years" as text, "Prediction of future body shape" as an image, and "Future lifestyle simulation" as a video, and sends them to the user's smartphone.

[1030] Step 8:

[1031] Display of visual content

[1032] Input: Received visual content.

[1033] Processing: The device displays the received visual content in an intuitive user interface. Users can realistically see what their future self will look like and their health status.

[1034] Output: The displayed visual content.

[1035] Specific operation: The device displays received images and videos in full-screen mode and provides navigation buttons for the user to refer to past data.

[1036] Step 9:

[1037] Proposals for behavioral change

[1038] Input: The generated scenario.

[1039] Processing: Based on the generated scenario, the server generates specific behavioral change suggestions for the user in text format and sends them to the terminal.

[1040] Output: Proposals for behavioral change.

[1041] Specific actions: The system generates text messages suggesting things like "exercise three times a week" or "reduce eating out and cook at home," and sends them to the user's smartphone.

[1042] Step 10:

[1043] Display and implementation of behavioral change

[1044] Input: Received proposal content.

[1045] Processing: The terminal displays the suggested content to the user and presents actionable improvement measures in stages.

[1046] Output: The displayed suggestions.

[1047] Specific actions: The device displays suggestions for specific behavioral changes (e.g., "Add vegetables to your daily meals") and provides the necessary information to enable the user to take action.

[1048] Step 11:

[1049] User behavior

[1050] Input: The displayed future scenario and proposed content.

[1051] Process: The user reviews the future scenarios and suggestions presented on the device and understands their necessity. They then review their lifestyle and financial behavior according to the suggested improvements.

[1052] Output: Improved lifestyle and financial behavior.

[1053] Specific actions: Users perform specific actions, such as "add vegetables to their daily meals," and provide feedback on the results to the server.

[1054] The above describes the specific program processing of the Future Self Simulator. This system allows users to visualize their future health and financial situation in concrete terms, and provides them with the motivation to re-evaluate their current actions.

[1055] (Application Example 1)

[1056] Next, we will explain Application Example 1. In the following explanation, 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."

[1057] Modern consumers possess diverse purchase history, health data, and financial data, and there is a growing need to integrate and analyze this data to predict future health and financial status. However, with increasing security risks, there is a lack of systems that can assess future security risks based on this data and propose appropriate security measures. Current systems struggle to efficiently integrate and analyze multiple data sources and present risk scenarios in an intuitively understandable format. Therefore, the challenge lies in achieving comprehensive security risk management and encouraging effective behavioral change in users.

[1058] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1059] In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, health data, and financial data from multiple data sources, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, means for generating suggestions for behavioral change to the user, means for analyzing the user's safety risks and generating future security risk scenarios, means for visualizing the generated security risk scenarios in text and image formats, means for transmitting the visualized security risk scenarios to the user's terminal, and means for generating and providing security countermeasures suggestions to the user. As a result, users can intuitively understand not only the impact of their actions on their health and finances, but also future security risks, and take appropriate measures.

[1060] "QR code payment data" refers to all data related to payments made using QR codes, and specifically includes transaction date and time, transaction amount, purchased items, etc.

[1061] A "database" is an information system for efficiently storing, managing, and retrieving large amounts of data, and relational database management systems (RDBMS) are often used for this purpose.

[1062] "Purchase data" refers to data containing information about products purchased by a user, including product name, purchase date and time, purchase location, and purchase price.

[1063] "Health data" refers to data related to the user's health, such as exercise data obtained from fitness apps and physical measurement data obtained from health apps.

[1064] "Financial data" refers to data related to a user's financial situation, including banking transactions, credit card usage history, and asset status.

[1065] "Consumer trends" refer to data that shows patterns in what kinds of products and services users prefer to purchase, and are based on purchase history and purchase frequency.

[1066] "Health status" refers to data indicating the user's physical and mental health, including measured health data and medical records.

[1067] "Financial behavior" refers to data that shows patterns in how users spend money, and is based on income and expenditure balances and category analysis of spending.

[1068] A "scenario" refers to a predicted future situation generated based on analyzed data, and includes the user's future health, financial situation, security risks, etc.

[1069] "Visualization" refers to the visual representation of data and scenarios, and is provided in formats such as graphs, charts, and videos.

[1070] "Security risks" refer to security-related risks that users may face, including phishing scams and the leakage of personal information.

[1071] A "security risk scenario" refers to a predicted situation regarding future security risks, generated based on analyzed data.

[1072] "Security measures" refer to the specific actions and policies that users take to address security risks.

[1073] The Future Security Advisor, as described in this invention, is a system that analyzes users' consumption trends, health status, and financial behavior based on QR code payment data, purchase data, health data, and financial data, and uses these analysis results to generate and present future health status, financial status, and security risk scenarios. This system enables users to intuitively understand the impact of their actions on the future and to take concrete actions to change their behavior and implement security measures.

[1074] 1. Data Collection

[1075] server

[1076] The system receives QR code payment data and stores it in a database. Specifically, when a user makes a QR code payment at a supermarket, the payment data (product information, price, purchase date and time, etc.) is automatically sent to the server.

[1077] We collect purchase data, health data, and financial data from multiple data sources. For example, we obtain exercise data from a fitness app and collect spending data from a banking app.

[1078] 2. Data Integration

[1079] server

[1080] The collected data is standardized and managed as a single integrated dataset. This allows for the integration of data in different formats and conversion into an analyzable format.

[1081] 3. Data Analysis

[1082] server

[1083] Based on integrated data, AI models (such as TensorFlow and PyTorch) are used to analyze users' consumption trends, health status, and financial behavior. Based on the analysis results, users' current lifestyles and financial behaviors are revealed.

[1084] The analysis assesses user safety risks and generates future security risk scenarios.

[1085] 4. Generating and Visualizing Future Scenarios

[1086] server

[1087] Based on analysis results generated using AI models, future health, financial, and security risk scenarios are visualized in text, image, and video formats. Plotly is used for data visualization, and FFmpeg is used to generate the video.

[1088] 5. Sending and displaying content

[1089] server

[1090] Visualized scenarios are sent to the user's smartphone and displayed intuitively through the user interface. This utilizes a REST API and a front-end framework (React Native).

[1091] 6. Proposals for behavioral change

[1092] Server and hardware

[1093] Based on the generated scenario, the system sends users specific suggestions for behavioral change and security measures in text format, which are then displayed on their devices. Using a text generation model based on OpenAI GPT-3, users receive step-by-step improvement plans.

[1094] 7. User behavior

[1095] User

[1096] Review the presented future scenarios and proposals, and understand the need for action. Review your lifestyle and financial habits and implement security measures according to the specific improvement plans.

[1097] Specific example

[1098] For example, if a scenario is generated that highlights the risk of phishing scams, the user will understand what actions increase that risk and will be offered specific security measures such as "don't click on links in suspicious emails" and "change your password regularly."

[1099] Examples of prompts to input into a generative AI model

[1100] Use AI to generate future security risk scenarios based on users' QR code payment data, purchase data, health data, and financial data. Specifically, show how users' current actions could lead to future risks such as phishing scams, fraudulent emails, and personal data breaches, and then present specific risk management measures in text format.

[1101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1102] Step 1:

[1103] The server receives payment data when a user makes a QR code payment at a supermarket. The input includes QR code payment data such as the transaction date and time, transaction amount, and purchased items, which is then stored in a database. Specifically, when payment data is sent to the server, it is stored in real time using a database management system (MySQL, PostgreSQL).

[1104] Step 2:

[1105] The server stores data collected from multiple data sources, such as exercise data from fitness apps and spending data from banking apps, in a database. It takes exercise data (steps, exercise time) and financial data (transaction history, spending amount) as input and stores this data in a standardized format. Specifically, it actively collects data through a data collection API and performs standardization processing using a Python script.

[1106] Step 3:

[1107] The server integrates QR code payment data, purchase data, health data, and financial data stored in the database and manages them as a single dataset. Its input consists of individual data obtained from each data source, and it outputs this as an integrated dataset. Specifically, it uses a data conversion script (Python) to unify the data format and manage it centrally.

[1108] Step 4:

[1109] The server uses integrated data to analyze users' consumption trends, health status, and financial behavior using AI models (such as TensorFlow and PyTorch). It takes the integrated dataset as input and outputs evaluation results for consumption trends, health status, and financial behavior. Specifically, it supplies data to the AI ​​model and performs calculations to obtain the analysis results.

[1110] Step 5:

[1111] The server generates future health, financial, and security risk scenarios for users based on the analysis results. It uses the analysis results as input and outputs future scenarios. Specifically, it generates predictive scenarios using an AI model and visualizes them in text, image, and video formats. Plotly and FFmpeg are used for visualization.

[1112] Step 6:

[1113] The server sends the generated scenario to the user's smartphone and displays it intuitively on the device. The input is a visualized scenario, which is sent via a REST API and displayed using a user interface built with React Native. Specifically, the server displays the scenario data on the device and builds an interface that is easy for the user to understand.

[1114] Step 7:

[1115] The server and terminal will propose specific behavioral changes and security measures to the user based on the generated scenario. Using the generated scenario and its analysis results as input, it will output proposed behavioral changes and security measures. Specifically, it will use OpenAI GPT-3 to generate the proposed content and display it on the terminal in text format.

[1116] Step 8:

[1117] The user reviews the presented future scenario and suggestions, and understands the need for action. The system receives the scenario and suggestions displayed on the device as input and outputs specific actions to implement the improvement measures. These actions might include the user taking measures such as "not clicking on suspicious email links" or "changing passwords regularly."

[1118] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1119] The Future Self Simulator, the present invention, is a system that integrates a user's QR code payment data, purchase data, health data, and financial data, and analyzes them using AI. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides even more personalized services. The specific method for implementing this system is described below.

[1120] 1. Data Collection

[1121] server

[1122] When a user makes a QR code payment at a supermarket, the payment data is automatically sent to the server.

[1123] The server saves user payment data to the database in real time.

[1124] For example, when a user pays for food using a QR code, the product information, price, and purchase date and time are saved.

[1125] 2. Data Integration

[1126] server

[1127] The server integrates the collected QR code payment data, purchase data, health data, and financial data.

[1128] Standardize data from different formats and manage it as a single dataset.

[1129] For example, exercise data obtained from a user's fitness app could be integrated with spending data obtained from a banking app.

[1130] 3. Data Analysis

[1131] server

[1132] Based on integrated data, AI models are used to analyze consumer trends, health status, and financial behavior.

[1133] The analysis reveals the user's current lifestyle and financial behavior.

[1134] For example, we can evaluate the health risks and monthly spending patterns of users who frequently purchase certain foods.

[1135] 4. Generating future scenarios

[1136] server

[1137] The AI ​​model generates multiple scenarios for future health and financial status based on current data. During this process, an emotion engine recognizes the user's emotions and adaptively generates scenarios.

[1138] This allows for the provision of scenarios that take into account the user's psychological state.

[1139] For example, if a user is feeling stressed, the system will generate a scenario that includes suggestions for relaxation and stress relief.

[1140] 5. Sending and displaying visual content

[1141] server

[1142] The generated visual content is sent to the user's device.

[1143] The content is displayed on the user's smartphone or computer.

[1144] terminal

[1145] The device displays the received visual content with an intuitive user interface.

[1146] Users can realistically see what their future self will look like and what their health condition will be.

[1147] For example, an image is displayed that realistically recreates what your body shape and financial situation might look like 10 years from now if you continue the program.

[1148] 6. Proposals for behavioral change

[1149] server

[1150] The server generates specific behavioral change suggestions for the user based on the generated scenario. The suggestions are also adaptively adjusted based on the user's emotions recognized by the emotion engine.

[1151] The proposal will be sent to the user's device in text format.

[1152] terminal

[1153] The device displays the proposed solutions to the user and presents actionable improvement measures in stages.

[1154] A personalized approach is taken to ensure that users can easily understand the process.

[1155] For example, if a user is feeling down, suggestions will be displayed to start with small, easily achievable goals.

[1156] 7. User behavior

[1157] User

[1158] The user reviews the future scenarios and suggestions presented on their device and understands the need for action.

[1159] I will take action to review my lifestyle and financial behavior in accordance with the proposed improvement measures.

[1160] For example, take concrete actions such as "add vegetables to your daily meals" or "create a monthly budget."

[1161] The above describes the configuration for implementing the Future Self Simulator. Through this system, users can visualize their future health and financial situation in concrete terms, and gain motivation to re-evaluate their current actions. Furthermore, the introduction of an emotion engine enables more personalized suggestions that take the user's feelings into consideration.

[1162] The following describes the processing flow.

[1163] Step 1:

[1164] Server: Receives user QR code payment data. Specifically, it retrieves payment information from the QR code payment system via API, links it to the user ID, and stores it.

[1165] Step 2:

[1166] Server: Stores received QR code payment data in a database. Records detailed information such as the name of the purchased item, price, and date and time of purchase.

[1167] Step 3:

[1168] Server: Integrates data from multiple data sources. Centralizes user purchase data, health data, and financial data, and standardizes data formats.

[1169] Step 4:

[1170] Server: Analyzes consumption trends, health status, and financial behavior based on integrated data. Uses AI models to evaluate users' current lifestyles and financial behavior.

[1171] Step 5:

[1172] Server: Uses an emotion engine to recognize the user's emotions. It collects and analyzes emotion data from the user's voice, facial expressions, text input, etc.

[1173] Step 6:

[1174] Server: Based on the analysis results, it generates multiple scenarios for the user's future health and financial status. In this process, the emotion engine adaptively adjusts the scenarios according to the user's emotions as perceived.

[1175] Step 7:

[1176] Server: Visualizes the generated scenarios. Utilizes generative AI technology to realistically represent scenarios in text, image, and video formats.

[1177] Step 8:

[1178] Server: Sends visualized scenarios to the user's device. Sends data to smartphones and PCs via API.

[1179] Step 9:

[1180] Terminal: Displays received visual content. An intuitive user interface allows users to check their future health and financial status.

[1181] Step 10:

[1182] Server: Based on future scenarios, it generates specific behavioral change suggestions for the user. Based on the user's emotions recognized by the emotion engine, it adaptively adjusts the suggestions.

[1183] Step 11:

[1184] Terminal: Displays the proposed content to the user. Specific improvement measures are presented step-by-step, and the system is designed to be easy for the user to understand.

[1185] Step 12:

[1186] User: Review the presented future scenarios and proposed solutions, and implement necessary behavioral changes. Develop a concrete action plan and put it into action.

[1187] (Example 2)

[1188] Next, we will describe Example 2. 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."

[1189] In modern society, it is crucial for many users to properly manage their health and financial situation and plan for the future. However, it is difficult to comprehensively grasp information from multiple data sources and make predictions about the future. Furthermore, suggestions and scenarios that do not take into account individual emotional states have the problem of not being able to adequately respond to users' feelings and behavioral changes. To solve these problems, there is a need for a system that provides more advanced and personalized future predictions and action suggestions.

[1190] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, health data, and financial data from multiple data sources, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for recognizing the user's current emotional state using an emotion engine and reflecting this in the scenario generation, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, means for intuitively displaying the visualized scenarios through a user interface, means for generating suggestions for behavioral change to the user and adaptively adjusting the suggestion content based on emotions, and means for transmitting the suggestion content in text format to the user's terminal. As a result, the user can comprehensively understand their own consumption trends, health status, and financial status, and based on these, specifically predict future health and financial scenarios. Furthermore, by incorporating emotion recognition, users can receive actionable suggestions that take their feelings into consideration, thereby improving the rate of behavioral change implementation.

[1191] "QR code payment data" refers to information related to transactions using QR codes, including details such as product information, price, purchase date and time, and purchase location.

[1192] A "database" is a system or software for efficiently storing, managing, and retrieving structured information.

[1193] A "data source" is the system, application, or device from which data is generated or collected.

[1194] "Purchase data" refers to data that includes all information about transactions and purchases made by a user, such as product name, price, and purchase date and time.

[1195] "Health data" refers to data related to a user's health status and fitness activities, including information such as exercise volume, weight, and heart rate.

[1196] "Financial data" refers to data related to a user's economic activities and financial situation, including information such as income, expenses, savings, and investments.

[1197] "Integration" is the process of combining data of different formats and types obtained from multiple data sources into a single dataset.

[1198] "Consumption trends" refer to patterns or tendencies that show what kinds of products and services users purchase and how frequently.

[1199] "Health status" refers to the user's current physical and mental health condition.

[1200] "Financial behavior" refers to a user's patterns of financial actions, such as income, expenses, savings, and investments.

[1201] A "scenario" is a prediction or assumption of future events or circumstances, and may include multiple predictions about the user's health and financial status.

[1202] An "emotion engine" is an algorithm or mechanism for recognizing and analyzing a user's emotional state.

[1203] "Visualization" is the process of representing data and information as images or videos in a way that is easy for users to intuitively understand.

[1204] "User interface" is a general term for the interactive screens and methods of operation that users use to interact with a system.

[1205] "Behavioral change" refers to users taking specific actions to improve their lifestyle habits and behavioral patterns.

[1206] A "proposal" is a specific set of actions or advice designed to encourage users to change their behavior.

[1207] "Adaptive" refers to the ability to make flexible changes or adjustments according to the situation or conditions.

[1208] The Future Self Simulator, the present invention, is a system that integrates a user's QR code payment data, purchase data, health data, and financial data, and analyzes them using AI. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides even more personalized services. The specific method for implementing this system is described below.

[1209] Data collection

[1210] The server automatically receives payment data from the POS system when a user makes a QR code payment at a supermarket. The received data includes details such as product information, price, purchase date and time, and purchase location. The data is immediately stored in the database. For this reason, a common relational database (e.g., MySQL or PostgreSQL) is used as the database system.

[1211] For example, if a user purchases vegetables and beverages at a supermarket, the transaction information is sent to the server and stored in the database as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Beverages ¥150".

[1212] Data integration

[1213] The server periodically collects purchase data, health data (e.g., data from fitness trackers), and financial data (transaction history from banking apps) from multiple data sources, and performs a process of standardizing and integrating data in different formats. ETL (Extract, Transform, Load) tools (e.g., Apache NiFi or Talend) are used for standardization.

[1214] For example, the server integrates exercise data such as "2023-10-01 07:00 AM Jogging 5km" and purchase data such as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Drinks ¥150" and manages them as a single dataset.

[1215] Data analysis

[1216] The server sends the integrated dataset to an AI analysis module, where it performs analysis using machine learning models (e.g., time series analysis or predictive models). For the analysis, programming languages ​​such as Python and R are used, and machine learning frameworks such as TensorFlow and PyTorch are utilized.

[1217] As a concrete example, the server might analyze the data and conclude that "the user purchases junk food at least three times a week, and their monthly food expenses are likely to exceed 30,000 yen."

[1218] Generating future scenarios

[1219] Based on the analysis results, the server sends prompts to the generating AI model to create scenarios for future health and financial situations. The generating AI model uses natural language generation models such as GPT-3 and BERT. Additionally, an emotion engine is used to recognize the user's current emotional state and incorporate it into the scenario generation.

[1220] An example of a prompt message that might be generated is: "Based on the user's health and purchase data from the past year, predict their health status 10 years from now and suggest lifestyle changes the user should adopt to avoid health risks."

[1221] Sending and displaying visual content

[1222] The server is designed to create visual content that visually represents the generated scenario (e.g., graphs showing future body shape and economic situation) and send it to the user's device. Data visualization libraries such as D3.js and Chart.js are used for visualization.

[1223] The device displays the received visual content through a user interface, rendering it in a way that the user can intuitively understand. For example, a "health prediction graph for 10 years from now" or an "estimated future savings image" might be displayed on the smartphone screen.

[1224] Proposals for behavioral change

[1225] The server generates specific behavioral change suggestions from the generated scenarios and visual content, and adaptively adjusts the suggestions based on the user's emotional state as recognized by the emotion engine. The generated suggestions are sent to the user's device in text format.

[1226] The device displays the received suggestions and presents personalized actions that are easy for the user to take. For example, it might display a specific suggestion such as "Add vegetables to one meal a day."

[1227] User behavior

[1228] Users review future scenarios and suggestions displayed on their devices and select actions to improve their lifestyle and financial behavior. They then execute these actions and add the results as feedback to their fitness tracker or financial app.

[1229] Through the above steps, the Future Self Simulator will be able to comprehensively understand the user's consumption trends, health status, and financial situation, specifically predict future health and financial scenarios, and provide actionable suggestions.

[1230] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1231] Step 1: Data Collection

[1232] The server automatically receives payment data from the POS system when a user makes a QR code payment at a supermarket. The input data includes details such as product information, price, purchase date and time, and purchase location. This data is immediately saved to the database using SQL queries. For example, if a user purchases vegetables and a beverage, it will be saved as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Beverage ¥150".

[1233] Step 2: Integration of the certificate

[1234] The server periodically collects purchase data, health data, and financial data from multiple data sources (e.g., fitness trackers and banking apps). The input data is raw data obtained from each data source. An ETL tool (e.g., Apache NiFi) is used to standardize the data in different formats and integrate it into a single dataset. The data is stored in a database in a unified format. For example, exercise data such as "2023-10-01 07:00 AM Jogging 5km" is integrated with purchase data such as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Drinks ¥150".

[1235] Step 3: Data Analysis

[1236] The server sends the integrated dataset to the analysis module. The input data consists of integrated lifestyle and consumption behavior data. For analysis, Python and R programs are used, and machine learning frameworks such as TensorFlow and PyTorch are employed to perform time series analysis and predictive models. The output data is a report on the user's consumption trends, health status, and financial behavior. For example, insights such as "the user buys junk food more than three times a week and is likely to spend more than 30,000 yen on food per month" can be obtained.

[1237] Step 4: Generating Future Scenarios

[1238] The server sends the analysis results as prompts to the generating AI model. The input data consists of a summary of the analysis results and the user's current emotional state. The generating AI model (e.g., GPT-3) is used to generate scenarios for future health and financial situations. The emotion engine considers the user's emotional state and reflects it in the scenarios. The output data consists of multiple future scenarios. For example, a scenario is generated that suggests relaxation methods for a stressed user.

[1239] Step 5: Send and display visual content

[1240] The server creates content that visually represents the generated scenarios. The input data is the generated scenarios. Using data visualization libraries such as D3.js or Chart.js, the scenarios are converted into graphs and images. The output data is sent to the user's device as visual content. The device displays the received visual content through its user interface. For example, a smartphone might display a "health prediction graph for 10 years from now" or an "estimated future savings image."

[1241] Step 6: Proposing behavioral change

[1242] The server generates behavioral change suggestions from the generated scenarios and visual content. The input data consists of scenarios and visual content. The emotion engine adjusts the suggestions based on the user's recognized emotions. The generated suggestions are sent to the user's device in text format. The device displays the received suggestions and presents easy-to-follow, step-by-step actions. For example, a specific suggestion such as "Add vegetables to one meal a day" might be displayed.

[1243] Step 7: User Behavior

[1244] The user reviews future scenarios and suggestions displayed on their device and selects actions to improve their lifestyle and financial behavior based on them. The input data consists of the displayed scenarios and suggestions. The user performs the suggested actions and records the results in a fitness tracker or financial app. For example, the user might take the action of "increasing their daily jogging distance by 1km" and record the result on their device.

[1245] (Application Example 2)

[1246] Next, we will explain application example 2. In the following explanation, 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."

[1247] Conventional data analysis systems can analyze users' consumption trends, health status, and financial behavior, but they lack the ability to suggest behavioral changes that reflect individual emotions. Furthermore, when visually representing analysis results, they are often limited to 2D displays, making it difficult for users to intuitively understand them. To address these challenges, there is a need for behavioral change suggestions that take user emotions into account, as well as intuitive displays using 3D graphics.

[1248] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, health data, and financial data from multiple data sources, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, means for generating suggestions for behavioral change to the user, means for displaying part or all of the generated scenarios in 3D graphics, and means for generating suggestions for behavioral change based on the user's emotions using an emotion engine. This makes it possible to provide users with personalized, emotion-aware suggestions for specific behavioral change, and to allow them to intuitively understand the analysis results using 3D graphics.

[1249] "QR code payment data" refers to transaction information generated when a user makes a payment for goods or services using a QR code.

[1250] A "database" refers to a system for efficiently storing, managing, searching, and updating collected data.

[1251] "Data sources" refer to various original sources or suppliers that provide information such as a user's purchase history, health data, and financial transaction information.

[1252] "Purchase data" refers to transaction information when a user purchases goods or services.

[1253] "Health data" refers to information about a user's health, including data such as exercise habits, diet, weight, and blood pressure.

[1254] "Financial data" refers to data about a user's financial situation, such as income, expenses, savings, investments, and debt.

[1255] "Integrating" refers to the process of combining data from multiple different data sources into a single, consistent format.

[1256] "Consumption trends" refer to habits and patterns derived from users' purchasing behavior.

[1257] "Health status" refers to the overall situation and assessment of the user's current health.

[1258] "Financial activity" refers to financial transactions and actions related to a user's income, expenses, savings, etc.

[1259] A "scenario" refers to a prediction or plan for the future that takes specific conditions into account.

[1260] "Visualizing" refers to the act of representing information visually in the form of text, images, videos, and other media.

[1261] "Terminal" refers to electronic devices such as computers, smartphones, and tablets that users directly use.

[1262] "Suggestions for behavioral change" refer to specific guidance or advice aimed at improving or altering a user's current behavior.

[1263] "3D graphics" refers to computer graphics that display information to the user in a three-dimensional form.

[1264] An "emotion engine" refers to a computational model or system that determines a user's emotional state and generates responses and suggestions based on those emotions.

[1265] The embodiments for carrying out this invention will be described in detail below.

[1266] 1. Data Collection

[1267] When a user makes a QR code payment, the server automatically receives the data and stores it in a database. For example, when a user makes a QR code payment at a supermarket, the product information, price, and purchase date and time are saved in the database.

[1268] 2. Data Integration

[1269] The server integrates QR code payment data, purchase data, health data, and financial data collected from multiple data sources. It standardizes data in different formats and manages it as a single dataset. For example, it integrates exercise data obtained from a fitness app with spending data obtained from a banking app.

[1270] 3. Data Analysis

[1271] The server uses integrated data and AI models to analyze users' consumption trends, health status, and financial behavior, and generates multiple scenarios based on this analysis. Generative AI models are used for the analysis. For example, it evaluates the health risks of users who frequently purchase certain foods and their monthly spending patterns.

[1272] 4. Generating future scenarios

[1273] The AI ​​model generates multiple scenarios for future health and financial status based on current data. In this process, an emotion engine recognizes the user's emotions and provides scenarios that take their psychological state into consideration. For example, if the user is feeling stressed, it generates scenarios that include suggestions for relaxation and stress relief.

[1274] 5. Sending and displaying visual content

[1275] The server sends the generated visual content to the user's device. The device then intuitively displays the received visual content using 3D graphics. This allows the user to realistically see their future appearance, health, and financial situation. For example, an image is displayed that realistically recreates their physique and financial situation 10 years from now if they continue the program.

[1276] 6. Proposals for behavioral change

[1277] The server generates specific behavioral change suggestions for the user based on the generated scenario. The suggestions are adaptively adjusted based on the user's emotions as recognized by the emotion engine. The suggestions are sent to the user's device in text format and displayed in a way that is easy for the user to understand. For example, if the user is feeling down, suggestions to start with small, easily achievable goals will be displayed.

[1278] As a concrete example, a user can view a scenario based on spending 1500 yen, exercising for 30 minutes, and having a monthly income of 50000 yen. This scenario predicts their future health and financial situation, and uses an emotion engine to suggest behavioral changes to reduce stress. Furthermore, by inputting prompts like the following into the generative AI model, appropriate future scenarios are provided.

[1279] Example of a prompt:

[1280] "Input user purchase data, health data, and financial data to predict future health and financial status. Also, generate behavioral change suggestions when users are experiencing stress."

[1281] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1282] Step 1:

[1283] The server receives payment data when a user makes a QR code payment. The input includes transaction information generated by the QR code payment, such as product information, price, and purchase date and time. The server receives this data and stores it in a database. The output is the stored transaction information.

[1284] Step 2:

[1285] The server integrates data collected from multiple data sources. Inputs include QR code payment data, purchase data, health data, and financial data. It converts data in different formats into a unified format and integrates it into a single dataset. Specifically, it retrieves exercise data from a fitness app and spending data from a banking app. The output is a single, integrated dataset.

[1286] Step 3:

[1287] The server analyzes users' consumption trends, health status, and financial behavior based on an integrated dataset. The integrated dataset is included as input. The data is fed into an AI model for analysis, evaluating user behavior patterns and risks. Specifically, a generative AI model is used to assess the health risks and monthly spending patterns of users who frequently purchase certain foods. The output is the analysis results.

[1288] Step 4:

[1289] The server generates multiple scenarios for the user's future health and financial status based on the analysis results. The input includes the analysis results. Using an AI model and emotion engine, it generates future scenarios based on the user's current data and emotions. Specifically, if the user is experiencing stress, it generates scenarios that include suggestions for relaxation and stress relief. The output is the multiple scenarios generated.

[1290] Step 5:

[1291] The server sends the generated visual content to the user's device. The input includes multiple generated scenarios. These scenarios are visualized in text, image, and video formats and sent to the user's device. Specific actions include images that 3D-render the user's physique and financial situation 10 years later if they continue their current actions. The output is the visual content sent to the user's device.

[1292] Step 6:

[1293] The device intuitively displays received visual content using 3D graphics. The input includes visual content. The device displays this content, allowing the user to see their future self, health, and financial situation. Specifically, the user views the 3D graphics and intuitively understands future scenarios. The output is the displayed 3D graphics.

[1294] Step 7:

[1295] The server generates specific behavioral change suggestions for the user based on the generated scenario. Input includes the generated scenario and the user's emotional information. Using an emotional engine, it generates behavioral change suggestions adapted to the user's emotions and sends them to the user's device in text format. For example, if the user is feeling down, it will display suggestions to start with small, easily achievable goals. The output is the text of the behavioral change suggestions.

[1296] Step 8:

[1297] The user reviews the future scenarios and suggestions presented on the device and understands the need for action. Input includes displayed 3D graphics and suggested text for behavioral change. Based on this, the user takes action to review their lifestyle and financial behavior. Specific actions include "adding vegetables to daily meals" or "creating a monthly budget." The output is the result of the user's actions.

[1298] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1299] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1300] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1301] [Fourth Embodiment]

[1302] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1303] As shown in Figure 7, the 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.

[1304] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1305] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1306] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1307] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1308] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1309] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1310] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1311] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1312] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1313] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1314] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1315] The Future Self Simulator, as described in this invention, is a system that integrates a user's QR code payment data, purchase data, health data, and financial data, and analyzes them using AI. The specific method for implementing this system is described below.

[1316] 1. Data Collection

[1317] server

[1318] When a user makes a QR code payment at a supermarket, the payment data is automatically sent to the server.

[1319] The server saves user payment data to the database in real time.

[1320] For example, when a user pays for food using a QR code, the product information, price, and purchase date and time are saved.

[1321] 2. Data Integration

[1322] server

[1323] The server integrates the collected QR code payment data, purchase data, health data, and financial data.

[1324] Standardize data from different formats and manage it as a single dataset.

[1325] For example, exercise data obtained from a user's fitness app could be integrated with spending data obtained from a banking app.

[1326] 3. Data Analysis

[1327] server

[1328] Based on integrated data, AI models are used to analyze consumer trends, health status, and financial behavior.

[1329] The analysis reveals the user's current lifestyle and financial behavior.

[1330] For example, we can evaluate the health risks and monthly spending patterns of users who frequently purchase certain foods.

[1331] 4. Generating future scenarios

[1332] server

[1333] The AI ​​model generates multiple scenarios for future health and financial conditions based on current data.

[1334] These scenarios are visualized in text, image, and video formats.

[1335] For example, it visualizes the user's health condition 10 years from now if they continue their current eating habits.

[1336] 5. Sending and displaying visual content

[1337] server

[1338] The generated visual content is sent to the user's device.

[1339] The content is displayed on the user's smartphone or computer.

[1340] terminal

[1341] The device displays the received visual content with an intuitive user interface.

[1342] Users can realistically see what their future self will look like and what their health condition will be.

[1343] For example, an image is displayed that realistically recreates what your body shape and financial situation might look like 10 years from now if you continue the program.

[1344] 6. Proposals for behavioral change

[1345] server

[1346] Based on the generated scenario, the server creates specific behavioral change suggestions for the user.

[1347] This proposal will be sent to the user's device in text format.

[1348] terminal

[1349] The device displays the proposed solutions to the user and presents actionable improvement measures in stages.

[1350] For example, suggestions such as "exercise three times a week" or "reduce eating out and cook at home" will be displayed.

[1351] 7. User behavior

[1352] User

[1353] The user reviews the future scenarios and suggestions presented on their device and understands the need for action.

[1354] I will take action to review my lifestyle and financial behavior in accordance with the proposed improvement measures.

[1355] For example, take concrete actions such as "add vegetables to your daily meals" or "create a monthly budget."

[1356] The above describes the configuration for implementing the Future Self Simulator. This system allows users to visualize their future health and financial situation in concrete terms, and provides them with the motivation to re-evaluate their current actions.

[1357] The following describes the processing flow.

[1358] Step 1:

[1359] Server: Receives user QR code payment data. Specifically, it retrieves payment information from the QR code payment system via API, links it to the user ID, and stores it.

[1360] Step 2:

[1361] Server: Stores received QR code payment data in a database. Records detailed information such as the name of the purchased item, price, and date and time of purchase.

[1362] Step 3:

[1363] Server: Integrates data from multiple data sources. Centralizes user purchase data, health data, and financial data, and standardizes data formats.

[1364] Step 4:

[1365] Server: Analyzes consumption trends, health status, and financial behavior based on integrated data. Uses AI models to evaluate users' current lifestyles and financial behavior.

[1366] Step 5:

[1367] Server: Based on the analysis results, it generates multiple scenarios for the user's future health and financial status. These include scenarios where the user continues their current behavior or improves it.

[1368] Step 6:

[1369] Server: Visualizes the generated scenarios. Utilizes generative AI technology to realistically represent scenarios in text, image, and video formats.

[1370] Step 7:

[1371] Server: Sends visualized scenarios to the user's device. Sends data to smartphones and PCs via API.

[1372] Step 8:

[1373] Terminal: Displays received visual content. An intuitive user interface allows users to check their future health and financial status.

[1374] Step 9:

[1375] Server: Based on future scenarios, generates specific behavioral change suggestions for users. These suggestions are generated in text format.

[1376] Step 10:

[1377] Terminal: Displays the proposed content to the user. Specific improvement measures are presented step-by-step, and the system is designed to be easy for the user to understand.

[1378] Step 11:

[1379] User: Review the presented future scenarios and proposed solutions, and implement necessary behavioral changes. Develop a concrete action plan and put it into action.

[1380] (Example 1)

[1381] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1382] Traditional data analysis systems have struggled to effectively integrate user purchasing data, exercise data, and financial data to predict users' future health and financial status. Furthermore, they lacked systems that could intuitively visualize analysis results and provide useful behavioral change suggestions to users. As a result, users lacked the motivation to take concrete actions to improve their health and financial status.

[1383] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1384] In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, exercise data, and financial data from multiple data sources, means for standardizing data in different formats and managing it as a single dataset, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, and means for generating suggestions for behavioral change to the user. This enables the user to concretely understand the impact of their current behavior on the future and motivates them to take concrete actions to improve their health status and financial status.

[1385] "QR code payment data" refers to data containing transaction information generated when a payment is made using a QR code.

[1386] A "database" is a system for systematically storing and managing collected data.

[1387] "Multiple data sources" refers to multiple sources of information that provide data of different types or formats.

[1388] "Purchase data" refers to data that includes information about products and services purchased by users.

[1389] "Exercise data" refers to data that includes information about a user's exercise habits and activity level.

[1390] "Financial data" refers to data that includes information about a user's income, expenses, and assets.

[1391] "Means of integration" refers to methods and techniques for combining data obtained from different data sources into a single dataset.

[1392] Standardization is the process of converting data provided in different formats or units into a common format or unit.

[1393] "Consumption trends" refer to patterns in what kinds of products and services users purchase and how frequently.

[1394] "Health status" refers to the overall state of the user's physical and mental health.

[1395] "Financial behavior" refers to a user's patterns of financial actions, such as income and expenses.

[1396] "Means of analysis" refers to techniques and methods for analyzing integrated data and identifying specific trends or patterns.

[1397] A "scenario" refers to a future situation or outcome predicted based on specific conditions or assumptions.

[1398] "Means of visualization" refers to methods and techniques for displaying the results of data analysis in an easily understandable visual format.

[1399] "Terminal" refers to digital devices used by users, such as computers, smartphones, and tablets.

[1400] "Suggestions for behavioral change" refer to specific advice and recommendations for improving the user's lifestyle and behavior.

[1401] The Future Self Simulator, as described in this invention, is a system that integrates and analyzes a user's QR code payment data, purchase data, exercise data, and financial data to predict and propose future health and financial conditions. The specific method for implementing this system is described below.

[1402] When a user makes a QR code payment at a supermarket or other store, the server receives the payment data. This payment data includes information about the purchased item (e.g., apples), its price, and the date and time of purchase. The received payment data is stored in the server's database in real time.

[1403] Next, the server collects user purchase data, exercise data (e.g., step count and exercise time from fitness apps), and financial data (e.g., monthly spending data from banking apps) from multiple data sources, and integrates and standardizes this data. Standardization allows data in different formats to be managed as a single dataset.

[1404] Based on integrated data, the server uses AI models to analyze users' consumption trends, health status, and financial behavior. This analysis provides a detailed understanding of users' current lifestyles and financial actions. For example, it can assess the health risks of users who frequently purchase certain foods, and evaluate their monthly spending patterns.

[1405] Based on the analysis results, the server generates multiple scenarios for the user's future health and financial status. These scenarios are visualized in text, image, and video formats. For example, it can visualize the user's health 10 years from now if they continue their current eating habits.

[1406] The generated visual content is sent from the server to the user's device (smartphone or PC). The device displays the received visual content using an intuitive user interface. This allows the user to realistically see what their future self and health status might look like.

[1407] Furthermore, based on the generated scenario, the server creates and sends to the user's terminal text-based suggestions for specific behavioral changes. These suggestions include specific advice to improve the user's lifestyle and financial behavior. Examples include "exercise three times a week" and "reduce eating out and cook at home more often."

[1408] Users can review future scenarios and suggestions presented on their devices and, based on these, revise their lifestyles and financial behaviors. For example, they can take specific actions such as "adding vegetables to their daily meals" or "creating a monthly budget."

[1409] The following are examples of prompts to input into the generating AI model.

[1410] "Explain how users can purchase food using QR code payments, and how that data can be analyzed to predict their future health."

[1411] "Describe in natural language a system that integrates current fitness and financial data to simulate future health and financial situations."

[1412] The above describes a specific embodiment of the Future Self Simulator of the present invention. This system allows users to visualize their future health and financial situation in detail and gain the motivation to reconsider their current actions.

[1413] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1414] Step 1:

[1415] Data collection

[1416] Input: User's QR code payment data.

[1417] Processing: When a user makes a QR code payment at a supermarket, the server automatically receives the payment data. The payment data includes information about the purchased items (product name, quantity, etc.), price, and date and time of purchase.

[1418] Output: Received payment data.

[1419] Specific operation: When a user purchases an apple using a QR code, the apple's information (e.g., apple, 1), price (100 yen), and purchase date and time (October 1, 2023, 15:00) are sent to the server.

[1420] Step 2:

[1421] Save to database

[1422] Input: Received payment data.

[1423] Processing: The server saves the received payment data to the database in real time.

[1424] Output: Payment data stored in the database.

[1425] Specific operation: The server saves the received Apple payment data to the "Purchase History" table in the database.

[1426] Step 3:

[1427] Collection of additional data

[1428] Input: User exercise data (e.g., obtained from a fitness app), financial data (e.g., obtained from a banking app).

[1429] Processing: The server collects user exercise data and financial data from multiple data sources. Exercise data includes the user's exercise volume (number of steps, exercise time, etc.), and financial data includes the user's spending information (spending items, amounts, date and time, etc.).

[1430] Output: Collected exercise data and financial data.

[1431] Specific operation: The server retrieves the number of steps the user walked in a day (5000 steps) from the fitness app and monthly food expenditure data (total 30,000 yen) from the banking app.

[1432] Step 4:

[1433] Data integration and standardization

[1434] Input: Collected QR code payment data, exercise data, and financial data.

[1435] Processing: The server standardizes data in different formats and manages it as a single dataset. Standardization converts each data format into a common format, making it possible to compare and analyze them with one another.

[1436] Output: Integrated and standardized dataset.

[1437] Specific operation: The server converts the purchase date and time of payment data into a unified format (e.g., YYYY-MM-DD HH:MM:SS), statistically aggregates the daily step count of exercise data, and synchronizes it with monthly expenditure data.

[1438] Step 5:

[1439] Data analysis

[1440] Input: Integrated and standardized dataset.

[1441] Processing: The server uses an AI model to analyze the user's consumption patterns, health status, and financial behavior. The analysis identifies specific patterns and risks (e.g., health risks, financial risks).

[1442] Output: Analysis results (e.g., analysis of consumption trends, assessment of health risks, patterns of financial behavior).

[1443] Specific operation: The AI ​​model detects when a user frequently purchases certain foods (e.g., high-calorie foods) and evaluates the result as a health risk.

[1444] Step 6:

[1445] Generating future scenarios

[1446] Input: Analysis results.

[1447] Processing: Based on the analysis results, the server generates multiple scenarios for the user's future health and financial status. These scenarios include predictions of the future if current lifestyle habits and financial behaviors continue.

[1448] Output: Future scenarios (e.g., visualization of future health and financial status).

[1449] Specific operation: The AI ​​model predicts and visualizes the health status (e.g., obesity risk) 10 years from now, assuming current consumption of high-calorie foods continues.

[1450] Step 7:

[1451] Visual content generation and transmission

[1452] Input: Future scenario.

[1453] Processing: The server visualizes future scenarios in text, image, and video formats, and sends the generated visual content to the user's device.

[1454] Output: The transmitted visual content.

[1455] Specific operation: Generates "Health status in 10 years" as text, "Prediction of future body shape" as an image, and "Future lifestyle simulation" as a video, and sends them to the user's smartphone.

[1456] Step 8:

[1457] Display of visual content

[1458] Input: Received visual content.

[1459] Processing: The device displays the received visual content in an intuitive user interface. Users can realistically see what their future self will look like and their health status.

[1460] Output: The displayed visual content.

[1461] Specific operation: The device displays received images and videos in full-screen mode and provides navigation buttons for the user to refer to past data.

[1462] Step 9:

[1463] Proposals for behavioral change

[1464] Input: The generated scenario.

[1465] Processing: Based on the generated scenario, the server generates specific behavioral change suggestions for the user in text format and sends them to the terminal.

[1466] Output: Proposals for behavioral change.

[1467] Specific actions: The system generates text messages suggesting things like "exercise three times a week" or "reduce eating out and cook at home," and sends them to the user's smartphone.

[1468] Step 10:

[1469] Display and implementation of behavioral change

[1470] Input: Received proposal content.

[1471] Processing: The terminal displays the suggested content to the user and presents actionable improvement measures in stages.

[1472] Output: The displayed suggestions.

[1473] Specific actions: The device displays suggestions for specific behavioral changes (e.g., "Add vegetables to your daily meals") and provides the necessary information to enable the user to take action.

[1474] Step 11:

[1475] User behavior

[1476] Input: The displayed future scenario and proposed content.

[1477] Process: The user reviews the future scenarios and suggestions presented on the device and understands their necessity. They then review their lifestyle and financial behavior according to the suggested improvements.

[1478] Output: Improved lifestyle and financial behavior.

[1479] Specific actions: Users perform specific actions, such as "add vegetables to their daily meals," and provide feedback on the results to the server.

[1480] The above describes the specific program processing of the Future Self Simulator. This system allows users to visualize their future health and financial situation in concrete terms, and provides them with the motivation to re-evaluate their current actions.

[1481] (Application Example 1)

[1482] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1483] Modern consumers possess diverse purchase history, health data, and financial data, and there is a growing need to integrate and analyze this data to predict future health and financial status. However, with increasing security risks, there is a lack of systems that can assess future security risks based on this data and propose appropriate security measures. Current systems struggle to efficiently integrate and analyze multiple data sources and present risk scenarios in an intuitively understandable format. Therefore, the challenge lies in achieving comprehensive security risk management and encouraging effective behavioral change in users.

[1484] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1485] In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, health data, and financial data from multiple data sources, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, means for generating suggestions for behavioral change to the user, means for analyzing the user's safety risks and generating future security risk scenarios, means for visualizing the generated security risk scenarios in text and image formats, means for transmitting the visualized security risk scenarios to the user's terminal, and means for generating and providing security countermeasures suggestions to the user. As a result, users can intuitively understand not only the impact of their actions on their health and finances, but also future security risks, and take appropriate measures.

[1486] "QR code payment data" refers to all data related to payments made using QR codes, and specifically includes transaction date and time, transaction amount, purchased items, etc.

[1487] A "database" is an information system for efficiently storing, managing, and retrieving large amounts of data, and relational database management systems (RDBMS) are often used for this purpose.

[1488] "Purchase data" refers to data containing information about products purchased by a user, including product name, purchase date and time, purchase location, and purchase price.

[1489] "Health data" refers to data related to the user's health, such as exercise data obtained from fitness apps and physical measurement data obtained from health apps.

[1490] "Financial data" refers to data related to a user's financial situation, including banking transactions, credit card usage history, and asset status.

[1491] "Consumer trends" refer to data that shows patterns in what kinds of products and services users prefer to purchase, and are based on purchase history and purchase frequency.

[1492] "Health status" refers to data indicating the user's physical and mental health, including measured health data and medical records.

[1493] "Financial behavior" refers to data that shows patterns in how users spend money, and is based on income and expenditure balances and category analysis of spending.

[1494] A "scenario" refers to a predicted future situation generated based on analyzed data, and includes the user's future health, financial situation, security risks, etc.

[1495] "Visualization" refers to the visual representation of data and scenarios, and is provided in formats such as graphs, charts, and videos.

[1496] "Security risks" refer to security-related risks that users may face, including phishing scams and the leakage of personal information.

[1497] A "security risk scenario" refers to a predicted situation regarding future security risks, generated based on analyzed data.

[1498] "Security measures" refer to the specific actions and policies that users take to address security risks.

[1499] The Future Security Advisor, as described in this invention, is a system that analyzes users' consumption trends, health status, and financial behavior based on QR code payment data, purchase data, health data, and financial data, and uses these analysis results to generate and present future health status, financial status, and security risk scenarios. This system enables users to intuitively understand the impact of their actions on the future and to take concrete actions to change their behavior and implement security measures.

[1500] 1. Data Collection

[1501] server

[1502] The system receives QR code payment data and stores it in a database. Specifically, when a user makes a QR code payment at a supermarket, the payment data (product information, price, purchase date and time, etc.) is automatically sent to the server.

[1503] We collect purchase data, health data, and financial data from multiple data sources. For example, we obtain exercise data from a fitness app and collect spending data from a banking app.

[1504] 2. Data Integration

[1505] server

[1506] The collected data is standardized and managed as a single integrated dataset. This allows for the integration of data in different formats and conversion into an analyzable format.

[1507] 3. Data Analysis

[1508] server

[1509] Based on integrated data, AI models (such as TensorFlow and PyTorch) are used to analyze users' consumption trends, health status, and financial behavior. Based on the analysis results, users' current lifestyles and financial behaviors are revealed.

[1510] The analysis assesses user safety risks and generates future security risk scenarios.

[1511] 4. Generating and Visualizing Future Scenarios

[1512] server

[1513] Based on analysis results generated using AI models, future health, financial, and security risk scenarios are visualized in text, image, and video formats. Plotly is used for data visualization, and FFmpeg is used to generate the video.

[1514] 5. Sending and displaying content

[1515] server

[1516] Visualized scenarios are sent to the user's smartphone and displayed intuitively through the user interface. This utilizes a REST API and a front-end framework (React Native).

[1517] 6. Proposals for behavioral change

[1518] Server and hardware

[1519] Based on the generated scenario, the system sends users specific suggestions for behavioral change and security measures in text format, which are then displayed on their devices. Using a text generation model based on OpenAI GPT-3, users receive step-by-step improvement plans.

[1520] 7. User behavior

[1521] User

[1522] Review the presented future scenarios and proposals, and understand the need for action. Review your lifestyle and financial habits and implement security measures according to the specific improvement plans.

[1523] Specific example

[1524] For example, if a scenario is generated that highlights the risk of phishing scams, the user will understand what actions increase that risk and will be offered specific security measures such as "don't click on links in suspicious emails" and "change your password regularly."

[1525] Examples of prompts to input into a generative AI model

[1526] Use AI to generate future security risk scenarios based on users' QR code payment data, purchase data, health data, and financial data. Specifically, show how users' current actions could lead to future risks such as phishing scams, fraudulent emails, and personal data breaches, and then present specific risk management measures in text format.

[1527] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1528] Step 1:

[1529] The server receives payment data when a user makes a QR code payment at a supermarket. The input includes QR code payment data such as the transaction date and time, transaction amount, and purchased items, which is then stored in a database. Specifically, when payment data is sent to the server, it is stored in real time using a database management system (MySQL, PostgreSQL).

[1530] Step 2:

[1531] The server stores data collected from multiple data sources, such as exercise data from fitness apps and spending data from banking apps, in a database. It takes exercise data (steps, exercise time) and financial data (transaction history, spending amount) as input and stores this data in a standardized format. Specifically, it actively collects data through a data collection API and performs standardization processing using a Python script.

[1532] Step 3:

[1533] The server integrates QR code payment data, purchase data, health data, and financial data stored in the database and manages them as a single dataset. Its input consists of individual data obtained from each data source, and it outputs this as an integrated dataset. Specifically, it uses a data conversion script (Python) to unify the data format and manage it centrally.

[1534] Step 4:

[1535] The server uses integrated data to analyze users' consumption trends, health status, and financial behavior using AI models (such as TensorFlow and PyTorch). It takes the integrated dataset as input and outputs evaluation results for consumption trends, health status, and financial behavior. Specifically, it supplies data to the AI ​​model and performs calculations to obtain the analysis results.

[1536] Step 5:

[1537] The server generates future health, financial, and security risk scenarios for users based on the analysis results. It uses the analysis results as input and outputs future scenarios. Specifically, it generates predictive scenarios using an AI model and visualizes them in text, image, and video formats. Plotly and FFmpeg are used for visualization.

[1538] Step 6:

[1539] The server sends the generated scenario to the user's smartphone and displays it intuitively on the device. The input is a visualized scenario, which is sent via a REST API and displayed using a user interface built with React Native. Specifically, the server displays the scenario data on the device and builds an interface that is easy for the user to understand.

[1540] Step 7:

[1541] The server and terminal will propose specific behavioral changes and security measures to the user based on the generated scenario. Using the generated scenario and its analysis results as input, it will output proposed behavioral changes and security measures. Specifically, it will use OpenAI GPT-3 to generate the proposed content and display it on the terminal in text format.

[1542] Step 8:

[1543] The user reviews the presented future scenario and suggestions, and understands the need for action. The system receives the scenario and suggestions displayed on the device as input and outputs specific actions to implement the improvement measures. These actions might include the user taking measures such as "not clicking on suspicious email links" or "changing passwords regularly."

[1544] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1545] The Future Self Simulator, the present invention, is a system that integrates a user's QR code payment data, purchase data, health data, and financial data, and analyzes them using AI. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides even more personalized services. The specific method for implementing this system is described below.

[1546] 1. Data Collection

[1547] server

[1548] When a user makes a QR code payment at a supermarket, the payment data is automatically sent to the server.

[1549] The server saves user payment data to the database in real time.

[1550] For example, when a user pays for food using a QR code, the product information, price, and purchase date and time are saved.

[1551] 2. Data Integration

[1552] server

[1553] The server integrates the collected QR code payment data, purchase data, health data, and financial data.

[1554] Standardize data from different formats and manage it as a single dataset.

[1555] For example, exercise data obtained from a user's fitness app could be integrated with spending data obtained from a banking app.

[1556] 3. Data Analysis

[1557] server

[1558] Based on integrated data, AI models are used to analyze consumer trends, health status, and financial behavior.

[1559] The analysis reveals the user's current lifestyle and financial behavior.

[1560] For example, we can evaluate the health risks and monthly spending patterns of users who frequently purchase certain foods.

[1561] 4. Generating future scenarios

[1562] server

[1563] The AI ​​model generates multiple scenarios for future health and financial status based on current data. During this process, an emotion engine recognizes the user's emotions and adaptively generates scenarios.

[1564] This allows for the provision of scenarios that take into account the user's psychological state.

[1565] For example, if a user is feeling stressed, the system will generate a scenario that includes suggestions for relaxation and stress relief.

[1566] 5. Sending and displaying visual content

[1567] server

[1568] The generated visual content is sent to the user's device.

[1569] The content is displayed on the user's smartphone or computer.

[1570] terminal

[1571] The device displays the received visual content with an intuitive user interface.

[1572] Users can realistically see what their future self will look like and what their health condition will be.

[1573] For example, an image is displayed that realistically recreates what your body shape and financial situation might look like 10 years from now if you continue the program.

[1574] 6. Proposals for behavioral change

[1575] server

[1576] The server generates specific behavioral change suggestions for the user based on the generated scenario. The suggestions are also adaptively adjusted based on the user's emotions recognized by the emotion engine.

[1577] The proposal will be sent to the user's device in text format.

[1578] terminal

[1579] The device displays the proposed solutions to the user and presents actionable improvement measures in stages.

[1580] A personalized approach is taken to ensure that users can easily understand the process.

[1581] For example, if a user is feeling down, suggestions will be displayed to start with small, easily achievable goals.

[1582] 7. User behavior

[1583] User

[1584] The user reviews the future scenarios and suggestions presented on their device and understands the need for action.

[1585] I will take action to review my lifestyle and financial behavior in accordance with the proposed improvement measures.

[1586] For example, take concrete actions such as "add vegetables to your daily meals" or "create a monthly budget."

[1587] The above describes the configuration for implementing the Future Self Simulator. Through this system, users can visualize their future health and financial situation in concrete terms, and gain motivation to re-evaluate their current actions. Furthermore, the introduction of an emotion engine enables more personalized suggestions that take the user's feelings into consideration.

[1588] The following describes the processing flow.

[1589] Step 1:

[1590] Server: Receives user QR code payment data. Specifically, it retrieves payment information from the QR code payment system via API, links it to the user ID, and stores it.

[1591] Step 2:

[1592] Server: Stores received QR code payment data in a database. Records detailed information such as the name of the purchased item, price, and date and time of purchase.

[1593] Step 3:

[1594] Server: Integrates data from multiple data sources. Centralizes user purchase data, health data, and financial data, and standardizes data formats.

[1595] Step 4:

[1596] Server: Analyzes consumption trends, health status, and financial behavior based on integrated data. Uses AI models to evaluate users' current lifestyles and financial behavior.

[1597] Step 5:

[1598] Server: Uses an emotion engine to recognize the user's emotions. It collects and analyzes emotion data from the user's voice, facial expressions, text input, etc.

[1599] Step 6:

[1600] Server: Based on the analysis results, it generates multiple scenarios for the user's future health and financial status. In this process, the emotion engine adaptively adjusts the scenarios according to the user's emotions as perceived.

[1601] Step 7:

[1602] Server: Visualizes the generated scenarios. Utilizes generative AI technology to realistically represent scenarios in text, image, and video formats.

[1603] Step 8:

[1604] Server: Sends visualized scenarios to the user's device. Sends data to smartphones and PCs via API.

[1605] Step 9:

[1606] Terminal: Displays received visual content. An intuitive user interface allows users to check their future health and financial status.

[1607] Step 10:

[1608] Server: Based on future scenarios, it generates specific behavioral change suggestions for the user. Based on the user's emotions recognized by the emotion engine, it adaptively adjusts the suggestions.

[1609] Step 11:

[1610] Terminal: Displays the proposed content to the user. Specific improvement measures are presented step-by-step, and the system is designed to be easy for the user to understand.

[1611] Step 12:

[1612] User: Review the presented future scenarios and proposed solutions, and implement necessary behavioral changes. Develop a concrete action plan and put it into action.

[1613] (Example 2)

[1614] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1615] In modern society, it is crucial for many users to properly manage their health and financial situation and plan for the future. However, it is difficult to comprehensively grasp information from multiple data sources and make predictions about the future. Furthermore, suggestions and scenarios that do not take into account individual emotional states have the problem of not being able to adequately respond to users' feelings and behavioral changes. To solve these problems, there is a need for a system that provides more advanced and personalized future predictions and action suggestions.

[1616] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, health data, and financial data from multiple data sources, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for recognizing the user's current emotional state using an emotion engine and reflecting this in the scenario generation, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, means for intuitively displaying the visualized scenarios through a user interface, means for generating suggestions for behavioral change to the user and adaptively adjusting the suggestion content based on emotions, and means for transmitting the suggestion content in text format to the user's terminal. As a result, the user can comprehensively understand their own consumption trends, health status, and financial status, and based on these, specifically predict future health and financial scenarios. Furthermore, by incorporating emotion recognition, users can receive actionable suggestions that take their feelings into consideration, thereby improving the rate of behavioral change implementation.

[1617] "QR code payment data" refers to information related to transactions using QR codes, including details such as product information, price, purchase date and time, and purchase location.

[1618] A "database" is a system or software for efficiently storing, managing, and retrieving structured information.

[1619] A "data source" is the system, application, or device from which data is generated or collected.

[1620] "Purchase data" refers to data that includes all information about transactions and purchases made by a user, such as product name, price, and purchase date and time.

[1621] "Health data" refers to data related to a user's health status and fitness activities, including information such as exercise volume, weight, and heart rate.

[1622] "Financial data" refers to data related to a user's economic activities and financial situation, including information such as income, expenses, savings, and investments.

[1623] "Integration" is the process of combining data of different formats and types obtained from multiple data sources into a single dataset.

[1624] "Consumption trends" refer to patterns or tendencies that show what kinds of products and services users purchase and how frequently.

[1625] "Health status" refers to the user's current physical and mental health condition.

[1626] "Financial behavior" refers to a user's patterns of financial actions, such as income, expenses, savings, and investments.

[1627] A "scenario" is a prediction or assumption of future events or circumstances, and may include multiple predictions about the user's health and financial status.

[1628] An "emotion engine" is an algorithm or mechanism for recognizing and analyzing a user's emotional state.

[1629] "Visualization" is the process of representing data and information as images or videos in a way that is easy for users to intuitively understand.

[1630] "User interface" is a general term for the interactive screens and methods of operation that users use to interact with a system.

[1631] "Behavioral change" refers to users taking specific actions to improve their lifestyle habits and behavioral patterns.

[1632] A "proposal" is a specific set of actions or advice designed to encourage users to change their behavior.

[1633] "Adaptive" refers to the ability to make flexible changes or adjustments according to the situation or conditions.

[1634] The Future Self Simulator, the present invention, is a system that integrates a user's QR code payment data, purchase data, health data, and financial data, and analyzes them using AI. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides even more personalized services. The specific method for implementing this system is described below.

[1635] Data collection

[1636] The server automatically receives payment data from the POS system when a user makes a QR code payment at a supermarket. The received data includes details such as product information, price, purchase date and time, and purchase location. The data is immediately stored in the database. For this reason, a common relational database (e.g., MySQL or PostgreSQL) is used as the database system.

[1637] For example, if a user purchases vegetables and beverages at a supermarket, the transaction information is sent to the server and stored in the database as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Beverages ¥150".

[1638] Data integration

[1639] The server periodically collects purchase data, health data (e.g., data from fitness trackers), and financial data (transaction history from banking apps) from multiple data sources, and performs a process of standardizing and integrating data in different formats. ETL (Extract, Transform, Load) tools (e.g., Apache NiFi or Talend) are used for standardization.

[1640] For example, the server integrates exercise data such as "2023-10-01 07:00 AM Jogging 5km" and purchase data such as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Drinks ¥150" and manages them as a single dataset.

[1641] Data analysis

[1642] The server sends the integrated dataset to an AI analysis module, where it performs analysis using machine learning models (e.g., time series analysis or predictive models). For the analysis, programming languages ​​such as Python and R are used, and machine learning frameworks such as TensorFlow and PyTorch are utilized.

[1643] As a concrete example, the server might analyze the data and conclude that "the user purchases junk food at least three times a week, and their monthly food expenses are likely to exceed 30,000 yen."

[1644] Generating future scenarios

[1645] Based on the analysis results, the server sends prompts to the generating AI model to create scenarios for future health and financial situations. The generating AI model uses natural language generation models such as GPT-3 and BERT. Additionally, an emotion engine is used to recognize the user's current emotional state and incorporate it into the scenario generation.

[1646] An example of a prompt message that might be generated is: "Based on the user's health and purchase data from the past year, predict their health status 10 years from now and suggest lifestyle changes the user should adopt to avoid health risks."

[1647] Sending and displaying visual content

[1648] The server is designed to create visual content that visually represents the generated scenario (e.g., graphs showing future body shape and economic situation) and send it to the user's device. Data visualization libraries such as D3.js and Chart.js are used for visualization.

[1649] The device displays the received visual content through a user interface, rendering it in a way that the user can intuitively understand. For example, a "health prediction graph for 10 years from now" or an "estimated future savings image" might be displayed on the smartphone screen.

[1650] Proposals for behavioral change

[1651] The server generates specific behavioral change suggestions from the generated scenarios and visual content, and adaptively adjusts the suggestions based on the user's emotional state as recognized by the emotion engine. The generated suggestions are sent to the user's device in text format.

[1652] The device displays the received suggestions and presents personalized actions that are easy for the user to take. For example, it might display a specific suggestion such as "Add vegetables to one meal a day."

[1653] User behavior

[1654] Users review future scenarios and suggestions displayed on their devices and select actions to improve their lifestyle and financial behavior. They then execute these actions and add the results as feedback to their fitness tracker or financial app.

[1655] Through the above steps, the Future Self Simulator will be able to comprehensively understand the user's consumption trends, health status, and financial situation, specifically predict future health and financial scenarios, and provide actionable suggestions.

[1656] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1657] Step 1: Data Collection

[1658] The server automatically receives payment data from the POS system when a user makes a QR code payment at a supermarket. The input data includes details such as product information, price, purchase date and time, and purchase location. This data is immediately saved to the database using SQL queries. For example, if a user purchases vegetables and a beverage, it will be saved as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Beverage ¥150".

[1659] Step 2: Integration of the certificate

[1660] The server periodically collects purchase data, health data, and financial data from multiple data sources (e.g., fitness trackers and banking apps). The input data is raw data obtained from each data source. An ETL tool (e.g., Apache NiFi) is used to standardize the data in different formats and integrate it into a single dataset. The data is stored in a database in a unified format. For example, exercise data such as "2023-10-01 07:00 AM Jogging 5km" is integrated with purchase data such as "2023-10-01 10:00 AM Supermarket A Vegetables ¥200 Drinks ¥150".

[1661] Step 3: Data Analysis

[1662] The server sends the integrated dataset to the analysis module. The input data consists of integrated lifestyle and consumption behavior data. For analysis, Python and R programs are used, and machine learning frameworks such as TensorFlow and PyTorch are employed to perform time series analysis and predictive models. The output data is a report on the user's consumption trends, health status, and financial behavior. For example, insights such as "the user buys junk food more than three times a week and is likely to spend more than 30,000 yen on food per month" can be obtained.

[1663] Step 4: Generating Future Scenarios

[1664] The server sends the analysis results as prompts to the generating AI model. The input data consists of a summary of the analysis results and the user's current emotional state. The generating AI model (e.g., GPT-3) is used to generate scenarios for future health and financial situations. The emotion engine considers the user's emotional state and reflects it in the scenarios. The output data consists of multiple future scenarios. For example, a scenario is generated that suggests relaxation methods for a stressed user.

[1665] Step 5: Send and display visual content

[1666] The server creates content that visually represents the generated scenarios. The input data is the generated scenarios. Using data visualization libraries such as D3.js or Chart.js, the scenarios are converted into graphs and images. The output data is sent to the user's device as visual content. The device displays the received visual content through its user interface. For example, a smartphone might display a "health prediction graph for 10 years from now" or an "estimated future savings image."

[1667] Step 6: Proposing behavioral change

[1668] The server generates behavioral change suggestions from the generated scenarios and visual content. The input data consists of scenarios and visual content. The emotion engine adjusts the suggestions based on the user's recognized emotions. The generated suggestions are sent to the user's device in text format. The device displays the received suggestions and presents easy-to-follow, step-by-step actions. For example, a specific suggestion such as "Add vegetables to one meal a day" might be displayed.

[1669] Step 7: User Behavior

[1670] The user reviews future scenarios and suggestions displayed on their device and selects actions to improve their lifestyle and financial behavior based on them. The input data consists of the displayed scenarios and suggestions. The user performs the suggested actions and records the results in a fitness tracker or financial app. For example, the user might take the action of "increasing their daily jogging distance by 1km" and record the result on their device.

[1671] (Application Example 2)

[1672] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1673] Conventional data analysis systems can analyze users' consumption trends, health status, and financial behavior, but they lack the ability to suggest behavioral changes that reflect individual emotions. Furthermore, when visually representing analysis results, they are often limited to 2D displays, making it difficult for users to intuitively understand them. To address these challenges, there is a need for behavioral change suggestions that take user emotions into account, as well as intuitive displays using 3D graphics.

[1674] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving QR code payment data, means for storing the received QR code payment data in a database, means for integrating user purchase data, health data, and financial data from multiple data sources, means for analyzing the user's consumption trends, health status, and financial behavior based on the integrated data, means for generating multiple scenarios of the user's future health status and financial status based on the analysis results, means for visualizing the generated scenarios in text, image, and video formats, means for transmitting the visualized scenarios to the user's terminal, means for generating suggestions for behavioral change to the user, means for displaying part or all of the generated scenarios in 3D graphics, and means for generating suggestions for behavioral change based on the user's emotions using an emotion engine. This makes it possible to provide users with personalized, emotion-aware suggestions for specific behavioral change, and to allow them to intuitively understand the analysis results using 3D graphics.

[1675] "QR code payment data" refers to transaction information generated when a user makes a payment for goods or services using a QR code.

[1676] A "database" refers to a system for efficiently storing, managing, searching, and updating collected data.

[1677] "Data sources" refer to various original sources or suppliers that provide information such as a user's purchase history, health data, and financial transaction information.

[1678] "Purchase data" refers to transaction information when a user purchases goods or services.

[1679] "Health data" refers to information about a user's health, including data such as exercise habits, diet, weight, and blood pressure.

[1680] "Financial data" refers to data about a user's financial situation, such as income, expenses, savings, investments, and debt.

[1681] "Integrating" refers to the process of combining data from multiple different data sources into a single, consistent format.

[1682] "Consumption trends" refer to habits and patterns derived from users' purchasing behavior.

[1683] "Health status" refers to the overall situation and assessment of the user's current health.

[1684] "Financial activity" refers to financial transactions and actions related to a user's income, expenses, savings, etc.

[1685] A "scenario" refers to a prediction or plan for the future that takes specific conditions into account.

[1686] "Visualizing" refers to the act of representing information visually in the form of text, images, videos, and other media.

[1687] "Terminal" refers to electronic devices such as computers, smartphones, and tablets that users directly use.

[1688] "Suggestions for behavioral change" refer to specific guidance or advice aimed at improving or altering a user's current behavior.

[1689] "3D graphics" refers to computer graphics that display information to the user in a three-dimensional form.

[1690] An "emotion engine" refers to a computational model or system that determines a user's emotional state and generates responses and suggestions based on those emotions.

[1691] The embodiments for carrying out this invention will be described in detail below.

[1692] 1. Data Collection

[1693] When a user makes a QR code payment, the server automatically receives the data and stores it in a database. For example, when a user makes a QR code payment at a supermarket, the product information, price, and purchase date and time are saved in the database.

[1694] 2. Data Integration

[1695] The server integrates QR code payment data, purchase data, health data, and financial data collected from multiple data sources. It standardizes data in different formats and manages it as a single dataset. For example, it integrates exercise data obtained from a fitness app with spending data obtained from a banking app.

[1696] 3. Data Analysis

[1697] The server uses integrated data and AI models to analyze users' consumption trends, health status, and financial behavior, and generates multiple scenarios based on this analysis. Generative AI models are used for the analysis. For example, it evaluates the health risks of users who frequently purchase certain foods and their monthly spending patterns.

[1698] 4. Generating future scenarios

[1699] The AI ​​model generates multiple scenarios for future health and financial status based on current data. In this process, an emotion engine recognizes the user's emotions and provides scenarios that take their psychological state into consideration. For example, if the user is feeling stressed, it generates scenarios that include suggestions for relaxation and stress relief.

[1700] 5. Sending and displaying visual content

[1701] The server sends the generated visual content to the user's device. The device then intuitively displays the received visual content using 3D graphics. This allows the user to realistically see their future appearance, health, and financial situation. For example, an image is displayed that realistically recreates their physique and financial situation 10 years from now if they continue the program.

[1702] 6. Proposals for behavioral change

[1703] The server generates specific behavioral change suggestions for the user based on the generated scenario. The suggestions are adaptively adjusted based on the user's emotions as recognized by the emotion engine. The suggestions are sent to the user's device in text format and displayed in a way that is easy for the user to understand. For example, if the user is feeling down, suggestions to start with small, easily achievable goals will be displayed.

[1704] As a concrete example, a user can view a scenario based on spending 1500 yen, exercising for 30 minutes, and having a monthly income of 50000 yen. This scenario predicts their future health and financial situation, and uses an emotion engine to suggest behavioral changes to reduce stress. Furthermore, by inputting prompts like the following into the generative AI model, appropriate future scenarios are provided.

[1705] Example of a prompt:

[1706] "Input user purchase data, health data, and financial data to predict future health and financial status. Also, generate behavioral change suggestions when users are experiencing stress."

[1707] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1708] Step 1:

[1709] The server receives payment data when a user makes a QR code payment. The input includes transaction information generated by the QR code payment, such as product information, price, and purchase date and time. The server receives this data and stores it in a database. The output is the stored transaction information.

[1710] Step 2:

[1711] The server integrates data collected from multiple data sources. Inputs include QR code payment data, purchase data, health data, and financial data. It converts data in different formats into a unified format and integrates it into a single dataset. Specifically, it retrieves exercise data from a fitness app and spending data from a banking app. The output is a single, integrated dataset.

[1712] Step 3:

[1713] The server analyzes users' consumption trends, health status, and financial behavior based on an integrated dataset. The integrated dataset is included as input. The data is fed into an AI model for analysis, evaluating user behavior patterns and risks. Specifically, a generative AI model is used to assess the health risks and monthly spending patterns of users who frequently purchase certain foods. The output is the analysis results.

[1714] Step 4:

[1715] The server generates multiple scenarios for the user's future health and financial status based on the analysis results. The input includes the analysis results. Using an AI model and emotion engine, it generates future scenarios based on the user's current data and emotions. Specifically, if the user is experiencing stress, it generates scenarios that include suggestions for relaxation and stress relief. The output is the multiple scenarios generated.

[1716] Step 5:

[1717] The server sends the generated visual content to the user's device. The input includes multiple generated scenarios. These scenarios are visualized in text, image, and video formats and sent to the user's device. Specific actions include images that 3D-render the user's physique and financial situation 10 years later if they continue their current actions. The output is the visual content sent to the user's device.

[1718] Step 6:

[1719] The device intuitively displays received visual content using 3D graphics. The input includes visual content. The device displays this content, allowing the user to see their future self, health, and financial situation. Specifically, the user views the 3D graphics and intuitively understands future scenarios. The output is the displayed 3D graphics.

[1720] Step 7:

[1721] The server generates specific behavioral change suggestions for the user based on the generated scenario. Input includes the generated scenario and the user's emotional information. Using an emotional engine, it generates behavioral change suggestions adapted to the user's emotions and sends them to the user's device in text format. For example, if the user is feeling down, it will display suggestions to start with small, easily achievable goals. The output is the text of the behavioral change suggestions.

[1722] Step 8:

[1723] The user reviews the future scenarios and suggestions presented on the device and understands the need for action. Input includes displayed 3D graphics and suggested text for behavioral change. Based on this, the user takes action to review their lifestyle and financial behavior. Specific actions include "adding vegetables to daily meals" or "creating a monthly budget." The output is the result of the user's actions.

[1724] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1725] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1726] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1727] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1728] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1729] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1730] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1731] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1732] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1733] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1734] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1735] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1736] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1737] 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.

[1738] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1739] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1740] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1741] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1742] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1743] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1744] All documents, patent applications, and technical sta...

Claims

1. A means of receiving QR code payment data, A means of storing received QR code payment data in a database, A means of integrating user purchase data, health data, and financial data from multiple data sources, A means of analyzing users' consumption trends, health status, and financial behavior based on integrated data, A means for generating multiple scenarios of the user's future health and financial status based on the analysis results, A means of visualizing the generated scenario in text, image, and video formats, A means of sending a visualized scenario to the user's terminal, A means of generating suggestions for behavioral change for users, A system that includes this.

2. The system according to claim 1, further comprising means for intuitively displaying the generated scenario through a user interface.

3. The system according to claim 1, further comprising means for displaying the generated proposal content to the user in text format and presenting it step by step.

Images