System

Abstract

A system is provided.SOLUTION: The system includes a means for inputting user information, a means for setting cooperation with a financial institute, a means for acquiring transaction data from the financial institute, a means for integrating and standardizing the acquired data, a means for predicting the transition of assets by using a generation AI, a means for visualizing and displaying the integrated data, and a means for providing investment advice to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's investment environment, many people hold multiple financial assets, including bank deposits, stocks, virtual currencies, and real estate. However, managing these assets all in one place is cumbersome, and linking and integrating data across different platforms is difficult. Another issue is the lack of appropriate tools to understand asset trends and overall status in real time and make appropriate investment decisions. This leaves many investors without sufficient information, making efficient asset management and risk management difficult. [Means for solving the problem]

[0005] The present invention provides a system for centrally managing multiple financial assets held by a user. Specifically, it provides a means for users to input their own financial information and set up connections with financial institutions. The system has the function of automatically acquiring transaction data from financial institutions, standardizing it, and integrating it. It also provides a means for predicting asset trends using generative AI and visualizing and displaying the results. Furthermore, it has the function of providing optimal investment advice to users, allowing them to understand their asset status in real time and make appropriate investment decisions. This system eliminates the complexity of managing financial assets and enables efficient asset management.

[0006] "User information" refers to basic personal information and information related to financial assets of users who use the system.

[0007] A "financial institution" is an institution that provides financial services, such as a bank, securities company, or virtual currency exchange.

[0008] "Transaction data" refers to records of specific transactions, such as deposits, withdrawals, purchases and sales, conducted by a financial institution.

[0009] "Standardization" is the process of converting data provided in multiple different formats into a consistent, uniform format.

[0010] "Generative AI" is a type of artificial intelligence, a technology that has the ability to generate predictions and suggestions based on past data.

[0011] "Asset trends" refers to information that shows how the value and breakdown of assets change over a certain period of time.

[0012] "Visualization" is the technique of displaying data and information in a visually easy-to-understand format, such as graphs and charts.

[0013] "Investment advice" refers to advice that recommends optimal investment actions based on the user's asset status and market conditions.

[0014] "Authentication information" refers to the identification and security information that allows a user to securely access a system.

[0015] A "dashboard" is a screen in the system's user interface that displays multiple pieces of information and data in a unified manner. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] System Overview

[0038] This invention is a system that centrally manages multiple financial assets held by a user and provides asset trend forecasts and investment advice using generative AI. This system has the following functions: input of user information, linkage with financial institutions, automatic collection and standardization of transaction data, data visualization, predictions using generative AI, and provision of investment advice.

[0039] User Operation

[0040] When users first access the service, they enter their personal information and create an account. Next, they enter information about each financial asset and provide an API key and authentication information to set up a connection with a financial institution. Users can check their asset status in real time through the dashboard screen. They can also review their own investment strategies based on investment advice provided by generative AI.

[0041] Device behavior

[0042] The device is responsible for sending the information entered by the user to the server. It also displays the integrated data and forecast results received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up the connection, the device transmits that information to the server. The dashboard displays a graph of monthly asset trends and a chart of the portfolio's diversification ratio.

[0043] Server Operation

[0044] The server performs the following main processes based on the information sent by the user.

[0045] 1. Data collection and integration: The server automatically collects transaction data and asset balance information through the financial institution's API. This process is performed periodically to ensure that the latest data is always obtained.

[0046] 2. Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into a single unified format, thereby integrating information on different financial assets.

[0047] 3. Use of generative AI: The server uses generative AI to predict future asset trends based on the user's trading history and market data. For example, it can analyze past stock trading history and predict future price fluctuations.

[0048] 4. Data visualization: The integrated data and forecast results generated on the server are generated as graphs and charts for visualization, allowing users to grasp the increase or decrease in assets and investment risks at a glance.

[0049] 5. Providing investment advice: The server generates optimal investment advice based on the user's financial situation and market trends. For example, if the generative AI recommends the purchase of a specific stock, it will also provide the reasons and risk assessment.

[0050] Specific examples

[0051] Assume a user has multiple bank accounts, stocks, and cryptocurrencies. After the user registers with the system and configures the link settings for each financial asset, the server immediately collects and standardizes all transaction data. The generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard, and the user can adjust their portfolio based on the investment advice.

[0052] In this way, the system of the present invention centrally manages multiple financial assets held by the user, enabling efficient asset management. Users can grasp the trends in their assets in real time and make optimal investment decisions based on the advice of generative AI.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The user enters personal information to create an account, providing information such as name, email address, and password, and then presses the "Register" button. The device then sends this information to the server.

[0056] Step 2:

[0057] The server receives the user information, stores it in a database, generates a user ID and authentication token, and sends a confirmation email to the user to confirm registration.

[0058] Step 3:

[0059] Users enter information about multiple financial assets, such as bank accounts, stocks, and virtual currencies, including API keys and authentication information. Once the information is complete, they press the "Link" button, and the device sends the information to the server.

[0060] Step 4:

[0061] The server connects to each financial institution's API based on the information provided by the user, sends requests to acquire transaction data and balance information, receives responses from the financial institutions, and stores them in a database.

[0062] Step 5:

[0063] The server periodically calls the financial institution's API at automatically scheduled times to collect new transaction data and balance information, ensuring that the latest data is always maintained.

[0064] Step 6:

[0065] The server converts the acquired data into a standard format and integrates it, bringing together data in different formats to organize the user's total asset status.

[0066] Step 7:

[0067] The server uses generative AI to analyze the integrated data and predict asset trends. It estimates future asset fluctuations based on the user's past trading history and market data.

[0068] Step 8:

[0069] The server generates graphs and charts to visualize the data based on the analysis results, allowing users to intuitively understand their asset status.

[0070] Step 9:

[0071] The server provides optimal investment advice to users, proposing specific investment actions and recommending risk management based on the analysis results of the generative AI.

[0072] Step 10:

[0073] The terminal displays the integrated data, forecast results, and investment advice received from the server on a dashboard screen. After logging in, users can check the updated data in real time.

[0074] Step 11:

[0075] Users can view their financial situation and investment advice on the dashboard, and add new financial information as needed. The device then sends the new information back to the server, and the cycle repeats.

[0076] Example 1

[0077] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0078] In conventional asset management systems, the integration and standardization of transaction data obtained from different financial institutions was cumbersome, making it difficult for users to centrally manage all of their assets. In addition, there was a lack of support for users to make optimal investment decisions, as the systems did not adequately predict future asset trends or provide investment advice.

[0079] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0080] In this invention, the server includes means for periodically collecting transaction data and asset information using APIs of financial institutions, means for standardizing the collected data and converting it into a single format, and means for predicting future asset trends from transaction history and market data using generative AI. This allows users to centrally manage assets from multiple financial institutions and receive accurate asset trend predictions and optimal investment advice using generative AI.

[0081] "User information" refers to personal identification information entered by a user when using the system, including name, email address, password, etc.

[0082] "Integration with financial institutions" refers to the connection settings required for the system to send and receive data between the financial institution designated by the user and the system, and is a process that includes providing API keys and authentication information.

[0083] "Transaction data" refers to a user's transaction history and asset balance information obtained from financial institutions.

[0084] "Data standardization" refers to the process of converting data collected in different formats into one unified format.

[0085] A "generative AI model" is an artificial intelligence model used to predict future asset trends based on trading history and market data.

[0086] "Visualization and display" refers to the process of converting the integrated data and prediction results into a visually easy-to-understand format (e.g., graphs and charts) and providing them to users.

[0087] "Investment advice" refers to optimal investment strategies and recommendations provided by generative AI based on the user's financial situation and market trends.

[0088] A "terminal" refers to a device (e.g., a PC or smartphone) that a user uses to input information, and is responsible for sending and receiving data with the server.

[0089] The "server" is the central computer in the system that acquires data from financial institutions, analyzes the data using generative AI, and visualizes it.

[0090] MODE FOR CARRYING OUT THE INVENTION

[0091] This invention is a system that centrally manages multiple financial assets held by a user and provides asset trend forecasts and investment advice using a generative AI model. This system has the following functions: input of user information, collaboration with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using a generative AI model, and provision of investment advice.

[0092] User Operation

[0093] When users first access the service, they enter their personal information to create an account. Next, they enter information about each financial asset and provide API keys and authentication information to set up connections with financial institutions. Users can check their asset status in real time through the dashboard screen. They can also review their own investment strategies based on investment advice provided by the generative AI model.

[0094] Device behavior

[0095] The device sends the information entered by the user to the server. It also displays the integrated data and forecast results received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up the connection, the device transmits that information to the server. The dashboard displays a graph of monthly asset trends and a chart of the portfolio's diversification ratio.

[0096] Server Operation

[0097] The server performs the following main processes based on the information sent by the user.

[0098] Data collection and integration:

[0099] The server automatically collects transaction data and asset balance information through the financial institution's API. This process is performed periodically to ensure the latest data is always obtained. For example, calling a bank's API to obtain the latest account balance.

[0100] Data standardization and integration:

[0101] The collected data is provided in different formats, so the server standardizes it and converts it into a single unified format, integrating information on different financial assets. For example, bank balance information and stock trading history are converted into the same format.

[0102] Use of generative AI models:

[0103] The server uses the generative AI model to predict future asset trends based on the user's trading history and market data. For example, it analyzes past stock trading history to predict future price fluctuations.

[0104] Data visualization:

[0105] The server generates the integrated data and forecast results as graphs and charts for visualization, allowing users to grasp the increase or decrease in assets and investment risk at a glance. For example, the portfolio diversification rate can be displayed as a pie chart.

[0106] Providing investment advice:

[0107] The server generates optimal investment advice based on the user's financial situation and market trends. For example, when the generative AI model recommends the purchase of a particular stock, it also presents the reason and risk assessment.

[0108] Specific examples

[0109] Assume a user has multiple bank accounts, stocks, and cryptocurrencies. After the user registers with the system and configures the connections for each financial asset, the server immediately collects and standardizes all transaction data. A generative AI model then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard, allowing users to adjust their portfolios based on investment advice.

[0110] For example, use the following as your prompt:

[0111] "Please predict my asset trends for the next three months based on stock trading data from the past year. Also, please provide optimal investment advice along with a risk assessment."

[0112] In this way, the system of the present invention centrally manages multiple financial assets held by the user, enabling efficient asset management. Users can grasp the trends in their assets in real time and make optimal investment decisions based on the advice of the generated AI model.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1: User registration and initial setup

[0115] Input: A user enters their name, email address, and password into a web form.

[0116] Data processing: The terminal sends the entered information to the server, which registers the information in a database.

[0117] Output: An account is created for the user and credentials are generated.

[0118] What it does: When a user submits a form, the device sends the information to the server, which adds the new user to its database. Once registration is complete, authentication information is generated and a confirmation email is sent to the user.

[0119] Step 2: Setting up a connection with your financial institution

[0120] Input: The user enters the API key and authentication information to set up the connection with the financial institution.

[0121] Data processing: The terminal sends the entered authentication information to the server, which stores it. The server also calls the financial institution's API to initialize the connection.

[0122] Output: The integration is now set up and ready to retrieve transaction data from financial institutions.

[0123] How it works: When a user enters their authentication information and presses the link button, the device sends that information to the server, which then calls the financial institution's API to establish the link and securely stores the authentication information.

[0124] Step 3: Collect and link transaction data

[0125] Input: The server periodically calls the financial institution's API.

[0126] Data processing: The server obtains transaction data and asset balance information from financial institutions and standardizes it into the data format of the centralized management system.

[0127] Output: Centralized transaction data and asset balance information.

[0128] How it works: The server calls the API on a scheduled basis, normalizes the data it receives, converts it into a unified format, and stores it in a database.

[0129] Step 4: Data analysis and predictions using generative AI models

[0130] Input: Normalized transaction data and asset balance information.

[0131] Data processing: The server analyzes the data using a generative AI model to predict asset trends. Specifically, it simulates future price fluctuations and asset increases and decreases based on past data.

[0132] Output: Forecast data of future asset trends.

[0133] How it works: The server inputs data into a generative AI model, which then uses that data to predict future asset trends, such as stock price fluctuations over the next three months.

[0134] Step 5: Visualize the data and create a dashboard

[0135] Inputs: Forecast data and consolidated transaction data.

[0136] Data processing: The server generates graphs and charts to visualize the data and displays them in the form of a dashboard.

[0137] Output: Visualized data (graphs, charts, etc.) displayed on a dashboard screen.

[0138] How it works: The server converts forecast data and trading data into graphs and charts and sends them to the terminal, which then displays them on the dashboard screen, allowing users to check their asset status in real time.

[0139] Step 6: Providing investment advice

[0140] Input: Forecast data and user asset status data.

[0141] Data processing: The server uses a generative AI model to analyze the user's asset status and market trends, and generates optimal investment advice.

[0142] Output: Investment advice and risk assessment.

[0143] How it works: The server uses the generative AI model to generate investment advice based on the analysis results and sends it to the device, which then displays it on a dashboard for immediate user confirmation.

[0144] In this way, the system of the present invention centrally manages multiple financial assets held by a user through multiple processing steps, thereby realizing efficient asset management.

[0145] (Application example 1)

[0146] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0147] Existing financial asset management systems have difficulty integrating and standardizing a wide variety of data in different formats, requiring users to perform tedious tasks to centrally manage multiple financial institutions and asset information. Furthermore, specialized knowledge is required to make investment decisions, and there is a need for systems that utilize generative AI to provide investment advice in real time. Furthermore, electronic payment services lack functionality for the integrated management of various payment methods and financial assets, creating a need for systems that can help users understand their asset status in real time and develop optimal investment strategies.

[0148] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0149] In this invention, the server includes means for inputting user information, means for setting up a connection with a financial institution, means for acquiring transaction data from the financial institution, means for integrating and standardizing the acquired data, means for predicting asset trends using generative AI, means for visualizing and displaying the integrated data, means for providing investment advice to the user, means for centrally managing multiple financial assets in the electronic payment service, and means for predicting asset trends from transaction data using generative AI and providing investment advice in real time. This allows users to centrally manage multiple financial assets and instantly receive investment advice from the generative AI, thereby realizing efficient and intelligent asset management and investment decisions.

[0150] "User information" refers to data such as personal information and authentication information entered by system users.

[0151] A "financial institution" is an institution that provides financial services, such as a bank, securities company, or credit card company.

[0152] "Linkage settings" refers to the procedure for setting up a user to exchange data with a financial institution.

[0153] "Transaction data" refers to data such as deposit transactions, payment history, and investment transactions obtained from financial institutions.

[0154] "Integration" is the process of combining data provided in different formats into one standard format.

[0155] "Standardization" is the process of converting integrated data into a single, unified format.

[0156] "Generative AI" is artificial intelligence that uses machine learning and deep learning technologies to analyze data and generate future predictions and advice.

[0157] "Asset trend forecasting" refers to predicting future asset fluctuations based on collected trading data and market data.

[0158] "Visualization" refers to the display of data and prediction results in a visual format such as a graph or chart.

[0159] "Investment advice" is information that suggests how and in which assets to invest based on the user's asset status and market trends.

[0160] "Electronic payment services" are financial transaction services conducted over the Internet or mobile devices.

[0161] "Centralized management" refers to consolidating and managing multiple financial assets and data in one place.

[0162] "Real-time" refers to data processing and information provision occurring immediately.

[0163] System Overview

[0164] This invention is a system that centrally manages multiple financial assets held by a user and provides asset trend forecasts and investment advice using generative AI. This system is provided to users primarily via a smartphone app and has the following functions: input of user information, linkage with financial institutions, automatic collection and standardization of transaction data, data visualization, predictions using generative AI, and provision of investment advice.

[0165] User Operation

[0166] When users first access the service, they enter their personal information and create an account. Next, they enter information about their financial assets and provide API keys and authentication information to set up connections with financial institutions. Users can check their asset status in real time through the dashboard screen. They can also review their own investment strategies based on investment advice provided by generative AI.

[0167] Device behavior

[0168] The device is responsible for sending the information entered by the user to the server. It also displays the integrated data and forecast results received from the server on the dashboard screen. For example, when a user enters bank account and credit card information and sets up the connection, the device transmits that information to the server. The dashboard displays a graph of monthly asset trends and a chart of the portfolio's diversification ratio.

[0169] Server Operation

[0170] The server performs the following main processes based on the information sent by the user.

[0171] 1. Data collection and integration: The server automatically collects transaction data and asset balance information through the financial institution's API. This process is performed periodically to ensure that the latest data is always obtained.

[0172] 2. Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into a single unified format, thereby integrating information on different financial assets.

[0173] 3. Use of generative AI: The server uses generative AI to predict future asset trends based on the user's trading history and market data. For example, it can analyze past trading history and predict future price fluctuations.

[0174] 4. Data visualization: The integrated data and forecast results generated on the server are generated as graphs and charts for visualization, allowing users to grasp the increase or decrease in assets and investment risks at a glance.

[0175] 5. Providing investment advice: The server generates optimal investment advice based on the user's financial situation and market trends. For example, if the generative AI recommends the purchase of a specific stock, it will also provide the reasons and risk assessment.

[0176] Specific examples

[0177] Assume a user has multiple bank accounts, credit cards, and cryptocurrencies. After the user registers with the system and configures the linkage settings for each financial asset, the server immediately collects and standardizes all transaction data. The generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard, and the user can adjust their portfolio based on the investment advice.

[0178] This system centralizes the management of multiple financial assets held by users, enabling efficient asset management. Users can grasp the progress of their assets in real time and make optimal investment decisions based on advice from generative AI.

[0179] Example prompts to input to a generative AI model:

[0180] Data: Bank Account A, Date: 2023-01-01, Amount: -1000.50, Category: Food

[0181] Data: Credit Card B, Date: 2023-01-02, Amount: -200.75, Category: Transportation Expenses

[0182] This gives users a powerful tool to efficiently manage their assets and make investment decisions.

[0183] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0184] Step 1:

[0185] Users launch the smartphone app, enter their personal information, and create an account.

[0186] Input: User information (name, email address, password, etc.)

[0187] Process: The information entered by the user is sent to the server and a new account is created.

[0188] Output: Account creation completion email, notification, login information

[0189] Step 2:

[0190] The user sets up collaboration with each financial institution and inputs information about their financial assets.

[0191] Input: Financial institution information (bank account, credit card information, API key, etc.)

[0192] Processing: The terminal uses the financial institution's API to transmit the user's authentication information to the server and establishes a connection with the financial institution.

[0193] Output: Notification of completion of link with financial institution

[0194] Step 3:

[0195] The server automatically collects transaction data from financial institutions with which it has set up ties.

[0196] Input: Financial institution information (bank account, credit card information, etc.)

[0197] Processing: The server periodically calls the API to obtain transaction data from the financial institution.

[0198] Output: Transaction data (transaction history)

[0199] Step 4:

[0200] The server standardizes the collected transaction data and converts and integrates it into a single unified format.

[0201] Input: Transaction data (transaction history in various formats)

[0202] Processing: The server parses the transaction data and converts it into a standard format (e.g., date, amount, category, etc.).

[0203] Output: Normalized transaction data

[0204] Step 5:

[0205] The server sends the standardized data to the generative AI, which then predicts asset trends.

[0206] Input: Normalized transaction data

[0207] Processing: The server sends the data to the generative AI, which predicts future asset trends based on past trading data and market data.

[0208] Output: Asset forecast data (e.g., asset forecast for the next three months)

[0209] Step 6:

[0210] The server visualizes the asset trend prediction results from the generative AI and displays them on a dashboard.

[0211] Input: Asset transition forecast data

[0212] Processing: The server converts the prediction results into graphs and charts and displays them visually on a dashboard screen.

[0213] Output: Visualized asset trend graph and portfolio diversification ratio chart

[0214] Step 7:

[0215] The server uses generative AI to generate investment advice suited to the user and provides it in real time.

[0216] Input: Asset transition forecast data, user asset status

[0217] Processing: The server generates an optimal investment strategy based on generative AI and presents it to the user, along with the reasons and risk assessment.

[0218] Output: Investment advice information (e.g., recommendations to buy or sell specific financial assets)

[0219] Step 8:

[0220] Users can check the status of their assets and investment advice from generative AI through the dashboard and adjust their portfolios.

[0221] Input: visualized data and investment advice

[0222] Action: User reviews the dashboard and revises investment strategy based on the information provided.

[0223] Output: User's investment strategy (e.g., selection of new investments and portfolio rebalancing)

[0224] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0225] System Overview

[0226] This invention is a system that centrally manages multiple financial assets held by a user and uses generative AI to predict asset trends and provide investment advice. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide personalized investment advice based on emotions. This system has the following functions: input of user information, linkage with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using generative AI, emotion recognition, and provision of emotion-based investment advice.

[0227] User Operation

[0228] When users first access the service, they enter their personal information and create an account. Next, they set up a connection with a financial institution and enter information about each of their financial assets. Next, they perform initial setup so that the emotion engine can recognize the user's emotions. Through the dashboard screen, users can check their asset status in real time and receive optimal investment advice based on their emotions.

[0229] Device behavior

[0230] The device is responsible for sending the information entered by the user to the server. It also displays the data, prediction results, and emotion-based investment advice received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up connectivity, the device transmits that information to the server. At the same time, the emotion engine recognizes the user's emotions in real time and reflects them on the dashboard.

[0231] Server Operation

[0232] The server performs the following main processes based on the information sent by the user.

[0233] 1. Data collection and integration: The server automatically collects transaction data and balance information through the financial institution's API, ensuring that the latest data is always available.

[0234] 2. Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into a single unified format, integrating information on different financial assets.

[0235] 3. Use of generative AI: The server uses generative AI to predict future asset trends based on the user's trading history and market data. For example, it can analyze past stock trading history and predict future price fluctuations.

[0236] 4. Using the emotion engine: The server uses the emotion engine to collect the user's emotion data, which allows it to understand the user's current emotional state.

[0237] 5. Emotion-based adjustment: The server adjusts the dashboard display and investment advice based on the user's emotions recognized by the emotion engine. If the user is feeling anxious, the server personalizes the advice to match their emotions, such as displaying low-risk investment suggestions.

[0238] 6. Data visualization: The server generates integrated data, prediction results, and sentiment data as graphs and charts for visualization, allowing users to intuitively understand their asset status.

[0239] 7. Providing investment advice: The server generates optimal investment advice based on the user's financial situation and emotional data. For example, when the generative AI recommends the purchase of a particular stock, it provides advice that takes into account the user's emotions in addition to the reasons and risk assessment.

[0240] Specific examples

[0241] Assume that a user holds multiple bank accounts, stocks, and cryptocurrencies. When the user initially registers with the system and configures the link settings for each financial asset, the server immediately collects and standardizes all transaction data. The generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard. Furthermore, if the user's emotions are unstable, personalization based on emotions is performed, such as suggesting low-risk investment ideas.

[0242] In this way, the system of the present invention centrally manages multiple financial assets held by a user, enabling efficient asset management. Users can grasp asset trends in real time and make optimal investment decisions based on advice from generative AI. In addition, the introduction of an emotion engine allows users to receive personalized investment advice tailored to their emotions.

[0243] The processing flow will be explained below.

[0244] Step 1:

[0245] The user enters personal information to create an account, providing information such as name, email address, and password, and then presses the "Register" button. The device then sends this information to the server.

[0246] Step 2:

[0247] The server receives the user information, stores it in a database, generates a user ID and authentication token, and sends a confirmation email to the user to confirm registration.

[0248] Step 3:

[0249] Users enter information about multiple financial assets, such as bank accounts, stocks, and virtual currencies, including API keys and authentication information. Once the information is complete, they press the "Link" button, and the device sends the information to the server.

[0250] Step 4:

[0251] The server connects to each financial institution's API based on the information provided by the user, sends requests to acquire transaction data and balance information, receives responses from the financial institutions, and stores them in a database.

[0252] Step 5:

[0253] The server periodically calls the financial institution's API at automatically scheduled times to collect new transaction data and balance information, ensuring that the latest data is always maintained.

[0254] Step 6:

[0255] The server converts the acquired data into a standard format and integrates it, bringing together data in different formats to organize the user's total asset status.

[0256] Step 7:

[0257] The server uses generative AI to analyze the integrated data and predict asset trends. It estimates future asset fluctuations based on the user's past trading history and market data.

[0258] Step 8:

[0259] The server uses an emotion engine to collect user emotion data, analyze the user's facial expressions and input information in real time, and evaluate the user's emotional state.

[0260] Step 9:

[0261] The server adjusts the dashboard display and investment advice based on the user's emotions recognized by the emotion engine. For example, if the user is feeling anxious, it will prioritize displaying low-risk investment ideas and information that will give them a sense of security.

[0262] Step 10:

[0263] The server combines the analysis results of the generative AI and the evaluation results of the emotion engine to generate optimal investment advice, suggesting specific investment actions and recommending risk management.

[0264] Step 11:

[0265] The terminal receives integrated data, forecast results, and sentiment-based investment advice from the server and displays them on a dashboard screen. After logging in, users can view updated data in real time.

[0266] Step 12:

[0267] Users can view their asset status and investment advice on the dashboard, add new financial asset information as needed, and consider investment behavior based on their emotions. The device then sends the new information back to the server, and the cycle repeats.

[0268] Example 2

[0269] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0270] Conventional financial asset management systems lack the functionality to unify the management of multiple financial assets held by users, and integrating and standardizing data provided by different financial institutions is time-consuming. Furthermore, it is difficult to provide personalized investment advice that takes into account the user's emotions and individual circumstances. This makes it difficult for users to grasp the current state of their assets and make effective investment decisions.

[0271] The identification process by the identification 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 inputting user information, means for setting up a link with a financial institution, means for acquiring transaction data from the financial institution, means for integrating and standardizing the acquired data, means for predicting asset trends using generative artificial intelligence, means for visualizing and displaying the integrated data, means for collecting user emotion data, means for adjusting investment advice based on the emotion data, and means for providing personalized investment advice to the user. This makes it possible to centrally manage multiple financial assets held by a user and provide personalized investment advice based on emotions.

[0272] "User information" refers to personal information and information related to financial assets held by a user that the user inputs into the system.

[0273] "Collaboration with financial institutions" refers to a mechanism in which the system connects with various financial institutions via API in order to collect users' financial asset data.

[0274] "Transaction data" refers to data including the transaction history and balance information of a user at a financial institution.

[0275] "Data integration" is the process of converting and centralizing data collected from different financial institutions into a single unified format.

[0276] "Standardization" is the process of standardizing collected data into a predetermined format and arranging it in a form that is easy to analyze.

[0277] "Generative AI" is an AI technology used to analyze past data and predict future outcomes.

[0278] "Asset trend prediction" refers to using generative artificial intelligence to predict future fluctuations in a user's financial assets.

[0279] "Data visualization" refers to the display of integrated data and prediction results in visual formats such as graphs and charts.

[0280] "Emotion data" refers to data that indicates the user's emotional state and is collected by the emotion engine.

[0281] An "emotion engine" is a technology for recognizing a user's emotions and collecting that data.

[0282] "Personalized investment advice" is investment advice that is customized to take into account a user's individual circumstances and emotional state.

[0283] System Overview

[0284] This invention is a system that centrally manages multiple financial assets held by a user and uses generative artificial intelligence to predict asset trends and provide investment advice. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide personalized investment advice based on emotions. This system has the following functions: input of user information, collaboration with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using generative artificial intelligence, emotion recognition, and provision of emotion-based investment advice.

[0285] User Operation

[0286] When users first access the service, they enter their personal information and create an account. Next, they set up a connection with a financial institution and enter information about each of their financial assets. Next, they perform initial setup so that the emotion engine can recognize the user's emotions. Through the dashboard screen, users can check their asset status in real time and receive optimal investment advice based on their emotions.

[0287] Device behavior

[0288] The device is responsible for sending the information entered by the user to the server. It also displays the data, prediction results, and emotion-based investment advice received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up connectivity, the device transmits that information to the server. At the same time, the emotion engine recognizes the user's emotions in real time and reflects them on the dashboard.

[0289] Server Operation

[0290] The server performs the following main processes based on the information sent by the user.

[0291] Data collection and integration: The server automatically collects transaction data and balance information through the financial institution's API, ensuring that the latest data is always available.

[0292] Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into one unified format. Information on different financial assets is integrated.

[0293] Use of generative artificial intelligence: The server uses generative artificial intelligence to predict future asset trends based on the user's trading history and market data. For example, it can analyze past stock trading history and predict future price fluctuations.

[0294] Use of emotion engine: The server uses the emotion engine to collect the user's emotion data, which allows it to understand the user's current emotional state.

[0295] Emotion-based adjustment: The server adjusts the dashboard display and investment advice based on the user's emotions recognized by the emotion engine. If the user is feeling anxious, the server personalizes the content and advice based on the user's emotions, for example, by displaying investment suggestions with low risk.

[0296] Data visualization: The server generates integrated data, prediction results, and sentiment data as graphs and charts for visualization, allowing users to intuitively understand their asset status.

[0297] Providing investment advice: The server generates optimal investment advice based on the user's financial situation and emotional data. For example, when the generative AI recommends the purchase of a particular stock, it provides advice that takes into account the user's emotions in addition to the reasons and risk assessment.

[0298] Specific examples

[0299] Assume that a user holds multiple bank accounts, stocks, and cryptocurrencies. When the user initially registers with the system and configures the link settings for each financial asset, the server immediately collects and standardizes all transaction data. Generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard. Furthermore, if the user's emotions are unstable, the system personalizes the system based on their emotions, suggesting low-risk investment ideas.

[0300] Prompt Sentence Examples

[0301] 1. "Enter the user's bank account information, stock information, and cryptocurrency information and send it to the server."

[0302] 2. The server connects to the financial institution's API and periodically collects transaction data.

[0303] 3. "The server uses generative artificial intelligence to predict asset trends for the next three months."

[0304] 4. "Recognize users' sentiment data in real time and provide sentiment-based investment advice."

[0305] As described above, the system of the present invention centrally manages multiple financial assets held by a user, enabling efficient asset management. Users can grasp asset trends in real time and make optimal investment decisions based on advice from generative AI. Furthermore, by incorporating an emotion engine, users can receive personalized investment advice tailored to their emotions.

[0306] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0307] Step 1:

[0308] User performs initial registration: The user enters personal information and financial asset information to create an account in the system. Specifically, the user enters the required information in the account creation form and presses the submit button. The input data includes name, email address, password, and detailed information about financial assets (bank accounts, stocks, virtual currencies, etc.). This information is sent from the device to the server. The server stores the received information in a database.

[0309] Step 2:

[0310] Setting up integration with financial institutions: The user sets up API integration with each financial institution. This setup involves entering the financial institution's API key and authentication information to establish integration with the system. The API key and authentication information entered by the user are sent from the device to the server, which uses this information to connect with the financial institution and complete the necessary authentication process. If authentication is successful, the server saves the integration setting information in its database.

[0311] Step 3:

[0312] Collection of transaction data: The server automatically collects user transaction data and balance information through the financial institution's API. This process is performed periodically. For example, the server retrieves data from the API using a periodic task scheduler. The input data is the transaction history and balance information provided by the financial institution, and the server saves the received data in temporary storage. It is then stored in a database.

[0313] Step 4:

[0314] Data standardization and integration: The server standardizes the collected data, converts it into a unified format, and integrates it. Specifically, the server receives data in different formats (JSON, XML, etc.) and converts it into a standard format (e.g., JSON). The input data is the collected transaction data, and the results of the format conversion and data standardization performed by the server are stored in a database as an integrated data set.

[0315] Step 5:

[0316] Initial setting of the emotion engine: The user performs the initial setting required for the emotion engine of the system to collect emotion data. The user answers a series of questions on the emotion engine's initial setting screen, including stress level, risk tolerance, and emotional state regarding past investments. The input data is the user's answers, which are sent from the terminal to the server and set as the initial parameters of the emotion engine.

[0317] Step 6:

[0318] Data analysis and prediction: The server uses generative AI to predict future asset trends based on the user's trading data and market data. The server inputs the user's trading history and market data into the generative AI model, which then generates a predicted asset trend. The input data is the user's financial trading data and market data, and the output data is the prediction result from the generative AI model. The predicted result is stored in a database.

[0319] Step 7:

[0320] Emotion recognition and adjustment: The device sends the user's emotional data to the server in real time. The server uses an emotion engine to analyze the received emotional data and understand the user's current emotional state. The input data is the emotional information sent from the device, and the server adjusts the dashboard display content and investment advice based on the emotion engine's analysis. The output data is the adjusted investment advice and dashboard display content.

[0321] Step 8:

[0322] Data visualization: The terminal displays the integrated data and prediction results received from the server as graphs and charts. The input data is the analysis results and prediction data sent from the server, and the terminal visualizes the data based on this. Specifically, line graphs, bar graphs, etc. are displayed on the dashboard screen, allowing the user to intuitively understand the asset status.

[0323] Step 9:

[0324] Providing investment advice: The server generates optimal investment advice based on the user's financial situation and emotional data, and the device displays the results. The input data is the user's financial situation and emotional data, which the server analyzes and uses generative AI to create investment advice. The generated investment advice is stored in a database and sent to the device. The device displays the received advice on the dashboard screen.

[0325] (Application example 2)

[0326] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0327] In modern society, it is difficult for individuals to hold multiple financial assets, manage them centrally, and efficiently invest and pay. Collecting and standardizing transaction data, predicting asset trends, and providing investment advice are particularly burdensome. Providing appropriate advice based on users' emotions and spending patterns is even more challenging. Therefore, there is a need for a system that can handle these complex tasks in an integrated and automated manner and provide users with easy-to-understand, useful information.

[0328] The specific processing 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 inputting user information, means for establishing a connection with a financial institution, means for acquiring transaction data from the financial institution, means for integrating and standardizing the acquired data, means for predicting asset trends using generative AI, means for visualizing and displaying the integrated data, means for providing investment advice to the user, means for recognizing the user's emotions, means for adjusting the investment advice based on the emotions, means for recording the user's payment behavior and learning the user's consumption patterns, and means for providing payment advice based on the consumption patterns. This enables the user to centrally manage multiple financial assets and receive efficient asset management and personalized payment advice in real time.

[0329] The "means for inputting user information" is an interface for inputting the user's personal information and authentication information into the system.

[0330] The "means for setting up linkage with financial institutions" refers to the setting means for linking the system with financial institutions such as banks and securities companies.

[0331] "Means for obtaining transaction data from financial institutions" refers to means for automatically obtaining transaction data using a financial institution's API or other methods.

[0332] "Means for integrating and standardizing acquired data" refers to processing means for centralizing transaction data collected from multiple financial institutions and converting it into a unified format.

[0333] "Means of predicting asset trends using generative AI" refers to a means of predicting future asset fluctuations using generative AI based on past trading data and market information.

[0334] The "means for visualizing and displaying integrated data" refers to a means for displaying data converted into a unified format in a visual form such as a graph or chart.

[0335] The "means for providing investment advice to a user" refers to a means for providing optimal investment advice to a user based on predicted asset trends and market information.

[0336] "Means for recognizing user emotions" refers to a means for analyzing and recognizing the user's emotional state from facial expressions, voice, and input data.

[0337] The "means for tailoring investment advice based on emotions" refers to a means for tailoring and personalizing the content of investment advice based on the recognized emotions of a user.

[0338] "Means for recording users' payment behavior and learning consumption patterns" refers to a means for recording users' daily payment data and learning consumption patterns using generative AI.

[0339] The "means for providing payment advice based on consumption patterns" is a means for providing optimal payment methods and saving methods to users based on learned consumption patterns.

[0340] System Overview

[0341] This invention is a system that centrally manages multiple financial assets and payment behaviors held by a user, and uses generative AI and an emotion engine to predict asset trends and provide personalized investment and payment advice. The system has the following functions: input of user information, connection with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using generative AI, emotion recognition, emotion-based investment advice, consumption learning, and payment advice provision.

[0342] Server Operation

[0343] Data collection and integration features

[0344] The server automatically collects user transaction data and payment data through APIs of financial institutions and payment services, using API connection modules and OCR technology.

[0345] Data standardization and integration capabilities

[0346] The server converts the collected data into a standard format and integrates it into a centralized database, using Python data engineering libraries (pandas, numpy) in the process.

[0347] Generative AI prediction function

[0348] The server uses generative AI (TENSORFLOW (registered trademark), Keras) to predict the user's asset trends and payment patterns based on past trading data and market information.

[0349] Emotion recognition function using emotion engine

[0350] The server collects user emotional data through camera and voice input and analyzes it using an emotion recognition engine (OpenCV, facial expression analysis model).

[0351] Emotion-based personalization

[0352] The server generates investment advice and payment advice according to the user's emotional state based on the emotional data, using a personalization engine.

[0353] Data visualization features

[0354] The server analyzes the integrated data, prediction results, and sentiment data, and generates graphs and charts for visualization. This process uses data visualization libraries (matplotlib, seaborn).

[0355] Device behavior

[0356] The terminal, specifically the user's smartphone, sends the information entered by the user and transaction data to the server, and displays the data, prediction results, and emotion recognition results received from the server on the dashboard screen.

[0357] Specific examples

[0358] If a user has multiple bank accounts and credit cards, they can set up the linking of these financial assets during initial registration. The server automatically collects and standardizes transaction data, and uses generative AI to predict asset trends and payment patterns for the next three months.

[0359] If a user notices that they have spent a lot in a particular week, they can scan the receipt using their smartphone camera. The server extracts the data using OCR technology and analyzes it using generative AI and an emotion engine. As a result, the system identifies the reasons for the excessive spending and suggests specific ways to save money.

[0360] If the emotion engine detects the user's anxiety, it will suggest low-risk investment advice or savings strategies to reduce the user's psychological burden.

[0361] Prompt Sentence Examples

[0362] "Generate next month's spending forecast and savings advice based on May's payment data."

[0363] "We suggest optimal payment methods when users feel unsure."

[0364] In this way, the server and terminal can cooperate to efficiently manage a user's diverse financial assets and payment behavior, and provide personalized investment and payment advice in real time.

[0365] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0366] Step 1:

[0367] User registration and input

[0368] A user creates an account by entering personal information using a smartphone device, including name, email address, password, etc. The entered information is sent from the device to a server and stored in a database.

[0369] Input: User's personal information

[0370] Output: User information stored in the server database

[0371] Step 2:

[0372] Setting up collaboration with financial institutions

[0373] Users input their bank account and credit card information to link the system with financial institutions. The server receives the information sent from the device and connects it to each financial institution's API, making it possible to automatically collect transaction data.

[0374] Input: User's financial institution information

[0375] Output: Financial institution API connection information

[0376] Step 3:

[0377] Automatic collection of transaction data

[0378] The server periodically collects transaction data from financial institutions using the configured API. The data is obtained in JSON format or similar and stored in the server's database.

[0379] Input: Transaction data obtained from financial institution APIs

[0380] Output: Transaction data stored in the server database

[0381] Step 4:

[0382] Data integration and standardization

[0383] The server converts the collected transaction data into a standard format and centrally consolidates it, using data engineering libraries such as pandas and numpy.

[0384] Input: Raw transaction data captured

[0385] Output: Standardized and consolidated transaction data

[0386] Step 5:

[0387] Asset trend prediction using generative AI

[0388] The server uses generative AI (TensorFlow, Keras) to predict future asset trends based on standardized data, using past trading data and market data for learning.

[0389] Input: Standardized and consolidated transaction data

[0390] Output: Predicted asset trend data

[0391] Step 6:

[0392] Emotion recognition

[0393] Users input their facial expressions and voice using the smartphone's camera and microphone. The server analyzes the collected emotional data using an emotion recognition engine (OpenCV, facial expression analysis model) to understand the user's emotional patterns.

[0394] Input: User's facial expression data and voice data

[0395] Output: Parsed emotional state data

[0396] Step 7:

[0397] Personalized investment advice

[0398] The server generates investment advice for the user based on the asset transition data and emotional state data. In this process, a personalization engine is used to provide appropriate advice tailored to the user's emotional state.

[0399] Input: Asset transition data, emotional state data

[0400] Output: Personalized investment advice

[0401] Step 8:

[0402] Recording payment behavior and learning spending patterns

[0403] Users record their daily payment data on their smartphones, and the server collects this data and uses generative AI to learn consumption patterns.

[0404] Input: User payment data

[0405] Output: Learned consumption patterns

[0406] Step 9:

[0407] Providing payment advice

[0408] The server then provides users with optimal payment methods and advice on saving based on their learned consumption patterns, enabling them to effectively manage their consumption.

[0409] Input: Learned consumption patterns

[0410] Output: Personalized payment advice

[0411] Through these steps, users can efficiently manage their assets and consumption and receive personalized advice in real time.

[0412] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0413] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0414] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0415] [Second embodiment]

[0416] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0417] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0418] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0419] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0420] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0421] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0422] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0423] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0424] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0425] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0426] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0427] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0428] System Overview

[0429] This invention is a system that centrally manages multiple financial assets held by a user and provides asset trend forecasts and investment advice using generative AI. This system has the following functions: input of user information, linkage with financial institutions, automatic collection and standardization of transaction data, data visualization, predictions using generative AI, and provision of investment advice.

[0430] User Operation

[0431] When users first access the service, they enter their personal information and create an account. Next, they enter information about each financial asset and provide an API key and authentication information to set up a connection with a financial institution. Users can check their asset status in real time through the dashboard screen. They can also review their own investment strategies based on investment advice provided by generative AI.

[0432] Device behavior

[0433] The device is responsible for sending the information entered by the user to the server. It also displays the integrated data and forecast results received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up the connection, the device transmits that information to the server. The dashboard displays a graph of monthly asset trends and a chart of the portfolio's diversification ratio.

[0434] Server Operation

[0435] The server performs the following main processes based on the information sent by the user.

[0436] 1. Data collection and integration: The server automatically collects transaction data and asset balance information through the financial institution's API. This process is performed periodically to ensure that the latest data is always obtained.

[0437] 2. Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into a single unified format, thereby integrating information on different financial assets.

[0438] 3. Use of generative AI: The server uses generative AI to predict future asset trends based on the user's trading history and market data. For example, it can analyze past stock trading history and predict future price fluctuations.

[0439] 4. Data visualization: The integrated data and forecast results generated on the server are generated as graphs and charts for visualization, allowing users to grasp the increase or decrease in assets and investment risks at a glance.

[0440] 5. Providing investment advice: The server generates optimal investment advice based on the user's financial situation and market trends. For example, if the generative AI recommends the purchase of a specific stock, it will also provide the reasons and risk assessment.

[0441] Specific examples

[0442] Assume a user has multiple bank accounts, stocks, and cryptocurrencies. After the user registers with the system and configures the link settings for each financial asset, the server immediately collects and standardizes all transaction data. The generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard, and the user can adjust their portfolio based on the investment advice.

[0443] In this way, the system of the present invention centrally manages multiple financial assets held by the user, enabling efficient asset management. Users can grasp the trends in their assets in real time and make optimal investment decisions based on the advice of generative AI.

[0444] The processing flow will be explained below.

[0445] Step 1:

[0446] The user enters personal information to create an account, providing information such as name, email address, and password, and then presses the "Register" button. The device then sends this information to the server.

[0447] Step 2:

[0448] The server receives the user information, stores it in a database, generates a user ID and authentication token, and sends a confirmation email to the user to confirm registration.

[0449] Step 3:

[0450] Users enter information about multiple financial assets, such as bank accounts, stocks, and virtual currencies, including API keys and authentication information. Once the information is complete, they press the "Link" button, and the device sends the information to the server.

[0451] Step 4:

[0452] The server connects to each financial institution's API based on the information provided by the user, sends requests to acquire transaction data and balance information, receives responses from the financial institutions, and stores them in a database.

[0453] Step 5:

[0454] The server periodically calls the financial institution's API at automatically scheduled times to collect new transaction data and balance information, ensuring that the latest data is always maintained.

[0455] Step 6:

[0456] The server converts the acquired data into a standard format and integrates it, bringing together data in different formats to organize the user's total asset status.

[0457] Step 7:

[0458] The server uses generative AI to analyze the integrated data and predict asset trends. It estimates future asset fluctuations based on the user's past trading history and market data.

[0459] Step 8:

[0460] The server generates graphs and charts to visualize the data based on the analysis results, allowing users to intuitively understand their asset status.

[0461] Step 9:

[0462] The server provides optimal investment advice to users, proposing specific investment actions and recommending risk management based on the analysis results of the generative AI.

[0463] Step 10:

[0464] The terminal displays the integrated data, forecast results, and investment advice received from the server on a dashboard screen. After logging in, users can check the updated data in real time.

[0465] Step 11:

[0466] Users can view their financial situation and investment advice on the dashboard, and add new financial information as needed. The device then sends the new information back to the server, and the cycle repeats.

[0467] Example 1

[0468] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0469] In conventional asset management systems, the integration and standardization of transaction data obtained from different financial institutions was cumbersome, making it difficult for users to centrally manage all of their assets. In addition, there was a lack of support for users to make optimal investment decisions, as the systems did not adequately predict future asset trends or provide investment advice.

[0470] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0471] In this invention, the server includes means for periodically collecting transaction data and asset information using APIs of financial institutions, means for standardizing the collected data and converting it into a single format, and means for predicting future asset trends from transaction history and market data using generative AI. This allows users to centrally manage assets from multiple financial institutions and receive accurate asset trend predictions and optimal investment advice using generative AI.

[0472] "User information" refers to personal identification information entered by a user when using the system, including name, email address, password, etc.

[0473] "Integration with financial institutions" refers to the connection settings required for the system to send and receive data between the financial institution designated by the user and the system, and is a process that includes providing API keys and authentication information.

[0474] "Transaction data" refers to a user's transaction history and asset balance information obtained from financial institutions.

[0475] "Data standardization" refers to the process of converting data collected in different formats into one unified format.

[0476] A "generative AI model" is an artificial intelligence model used to predict future asset trends based on trading history and market data.

[0477] "Visualization and display" refers to the process of converting the integrated data and prediction results into a visually easy-to-understand format (e.g., graphs and charts) and providing them to users.

[0478] "Investment advice" refers to optimal investment strategies and recommendations provided by generative AI based on the user's financial situation and market trends.

[0479] A "terminal" refers to a device (e.g., a PC or smartphone) that a user uses to input information, and is responsible for sending and receiving data with the server.

[0480] The "server" is the central computer in the system that acquires data from financial institutions, analyzes the data using generative AI, and visualizes it.

[0481] MODE FOR CARRYING OUT THE INVENTION

[0482] This invention is a system that centrally manages multiple financial assets held by a user and provides asset trend forecasts and investment advice using a generative AI model. This system has the following functions: input of user information, collaboration with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using a generative AI model, and provision of investment advice.

[0483] User Operation

[0484] When users first access the service, they enter their personal information to create an account. Next, they enter information about each financial asset and provide API keys and authentication information to set up connections with financial institutions. Users can check their asset status in real time through the dashboard screen. They can also review their own investment strategies based on investment advice provided by the generative AI model.

[0485] Device behavior

[0486] The device sends the information entered by the user to the server. It also displays the integrated data and forecast results received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up the connection, the device transmits that information to the server. The dashboard displays a graph of monthly asset trends and a chart of the portfolio's diversification ratio.

[0487] Server Operation

[0488] The server performs the following main processes based on the information sent by the user.

[0489] Data collection and integration:

[0490] The server automatically collects transaction data and asset balance information through the financial institution's API. This process is performed periodically to ensure the latest data is always obtained. For example, calling a bank's API to obtain the latest account balance.

[0491] Data standardization and integration:

[0492] The collected data is provided in different formats, so the server standardizes it and converts it into a single unified format, integrating information on different financial assets. For example, bank balance information and stock trading history are converted into the same format.

[0493] Use of generative AI models:

[0494] The server uses the generative AI model to predict future asset trends based on the user's trading history and market data. For example, it analyzes past stock trading history to predict future price fluctuations.

[0495] Data visualization:

[0496] The server generates the integrated data and forecast results as graphs and charts for visualization, allowing users to grasp the increase or decrease in assets and investment risk at a glance. For example, the portfolio diversification rate can be displayed as a pie chart.

[0497] Providing investment advice:

[0498] The server generates optimal investment advice based on the user's financial situation and market trends. For example, when the generative AI model recommends the purchase of a particular stock, it also presents the reason and risk assessment.

[0499] Specific examples

[0500] Assume a user has multiple bank accounts, stocks, and cryptocurrencies. After the user registers with the system and configures the connections for each financial asset, the server immediately collects and standardizes all transaction data. A generative AI model then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard, allowing users to adjust their portfolios based on investment advice.

[0501] For example, use the following as your prompt:

[0502] "Please predict my asset trends for the next three months based on stock trading data from the past year. Also, please provide optimal investment advice along with a risk assessment."

[0503] In this way, the system of the present invention centrally manages multiple financial assets held by the user, enabling efficient asset management. Users can grasp the trends in their assets in real time and make optimal investment decisions based on the advice of the generated AI model.

[0504] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0505] Step 1: User registration and initial setup

[0506] Input: A user enters their name, email address, and password into a web form.

[0507] Data processing: The terminal sends the entered information to the server, which registers the information in a database.

[0508] Output: An account is created for the user and credentials are generated.

[0509] What it does: When a user submits a form, the device sends the information to the server, which adds the new user to its database. Once registration is complete, authentication information is generated and a confirmation email is sent to the user.

[0510] Step 2: Setting up a connection with your financial institution

[0511] Input: The user enters the API key and authentication information to set up the connection with the financial institution.

[0512] Data processing: The terminal sends the entered authentication information to the server, which stores it. The server also calls the financial institution's API to initialize the connection.

[0513] Output: The integration is now set up and ready to retrieve transaction data from financial institutions.

[0514] How it works: When a user enters their authentication information and presses the link button, the device sends that information to the server, which then calls the financial institution's API to establish the link and securely stores the authentication information.

[0515] Step 3: Collect and link transaction data

[0516] Input: The server periodically calls the financial institution's API.

[0517] Data processing: The server obtains transaction data and asset balance information from financial institutions and standardizes it into the data format of the centralized management system.

[0518] Output: Centralized transaction data and asset balance information.

[0519] How it works: The server calls the API on a scheduled basis, normalizes the data it receives, converts it into a unified format, and stores it in a database.

[0520] Step 4: Data analysis and predictions using generative AI models

[0521] Input: Normalized transaction data and asset balance information.

[0522] Data processing: The server analyzes the data using a generative AI model to predict asset trends. Specifically, it simulates future price fluctuations and asset increases and decreases based on past data.

[0523] Output: Forecast data of future asset trends.

[0524] How it works: The server inputs data into a generative AI model, which then uses that data to predict future asset trends, such as stock price fluctuations over the next three months.

[0525] Step 5: Visualize the data and create a dashboard

[0526] Inputs: Forecast data and consolidated transaction data.

[0527] Data processing: The server generates graphs and charts to visualize the data and displays them in the form of a dashboard.

[0528] Output: Visualized data (graphs, charts, etc.) displayed on a dashboard screen.

[0529] How it works: The server converts forecast data and trading data into graphs and charts and sends them to the terminal, which then displays them on the dashboard screen, allowing users to check their asset status in real time.

[0530] Step 6: Providing investment advice

[0531] Input: Forecast data and user asset status data.

[0532] Data processing: The server uses a generative AI model to analyze the user's asset status and market trends, and generates optimal investment advice.

[0533] Output: Investment advice and risk assessment.

[0534] How it works: The server uses the generative AI model to generate investment advice based on the analysis results and sends it to the device, which then displays it on a dashboard for immediate user confirmation.

[0535] In this way, the system of the present invention centrally manages multiple financial assets held by a user through multiple processing steps, thereby realizing efficient asset management.

[0536] (Application example 1)

[0537] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0538] Existing financial asset management systems have difficulty integrating and standardizing a wide variety of data in different formats, requiring users to perform tedious tasks to centrally manage multiple financial institutions and asset information. Furthermore, specialized knowledge is required to make investment decisions, and there is a need for systems that utilize generative AI to provide investment advice in real time. Furthermore, electronic payment services lack functionality for the integrated management of various payment methods and financial assets, creating a need for systems that can help users understand their asset status in real time and develop optimal investment strategies.

[0539] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0540] In this invention, the server includes means for inputting user information, means for setting up a connection with a financial institution, means for acquiring transaction data from the financial institution, means for integrating and standardizing the acquired data, means for predicting asset trends using generative AI, means for visualizing and displaying the integrated data, means for providing investment advice to the user, means for centrally managing multiple financial assets in the electronic payment service, and means for predicting asset trends from transaction data using generative AI and providing investment advice in real time. This allows users to centrally manage multiple financial assets and instantly receive investment advice from the generative AI, thereby realizing efficient and intelligent asset management and investment decisions.

[0541] "User information" refers to data such as personal information and authentication information entered by system users.

[0542] A "financial institution" is an institution that provides financial services, such as a bank, securities company, or credit card company.

[0543] "Linkage settings" refers to the procedure for setting up a user to exchange data with a financial institution.

[0544] "Transaction data" refers to data such as deposit transactions, payment history, and investment transactions obtained from financial institutions.

[0545] "Integration" is the process of combining data provided in different formats into one standard format.

[0546] "Standardization" is the process of converting integrated data into a single, unified format.

[0547] "Generative AI" is artificial intelligence that uses machine learning and deep learning technologies to analyze data and generate future predictions and advice.

[0548] "Asset trend forecasting" refers to predicting future asset fluctuations based on collected trading data and market data.

[0549] "Visualization" refers to the display of data and prediction results in a visual format such as a graph or chart.

[0550] "Investment advice" is information that suggests how and in which assets to invest based on the user's asset status and market trends.

[0551] "Electronic payment services" are financial transaction services conducted over the Internet or mobile devices.

[0552] "Centralized management" refers to consolidating and managing multiple financial assets and data in one place.

[0553] "Real-time" refers to data processing and information provision occurring immediately.

[0554] System Overview

[0555] This invention is a system that centrally manages multiple financial assets held by a user and provides asset trend forecasts and investment advice using generative AI. This system is provided to users primarily via a smartphone app and has the following functions: input of user information, linkage with financial institutions, automatic collection and standardization of transaction data, data visualization, predictions using generative AI, and provision of investment advice.

[0556] User Operation

[0557] When users first access the service, they enter their personal information and create an account. Next, they enter information about their financial assets and provide API keys and authentication information to set up connections with financial institutions. Users can check their asset status in real time through the dashboard screen. They can also review their own investment strategies based on investment advice provided by generative AI.

[0558] Device behavior

[0559] The device is responsible for sending the information entered by the user to the server. It also displays the integrated data and forecast results received from the server on the dashboard screen. For example, when a user enters bank account and credit card information and sets up the connection, the device transmits that information to the server. The dashboard displays a graph of monthly asset trends and a chart of the portfolio's diversification ratio.

[0560] Server Operation

[0561] The server performs the following main processes based on the information sent by the user.

[0562] 1. Data collection and integration: The server automatically collects transaction data and asset balance information through the financial institution's API. This process is performed periodically to ensure that the latest data is always obtained.

[0563] 2. Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into a single unified format, thereby integrating information on different financial assets.

[0564] 3. Use of generative AI: The server uses generative AI to predict future asset trends based on the user's trading history and market data. For example, it can analyze past trading history and predict future price fluctuations.

[0565] 4. Data visualization: The integrated data and forecast results generated on the server are generated as graphs and charts for visualization, allowing users to grasp the increase or decrease in assets and investment risks at a glance.

[0566] 5. Providing investment advice: The server generates optimal investment advice based on the user's financial situation and market trends. For example, if the generative AI recommends the purchase of a specific stock, it will also provide the reasons and risk assessment.

[0567] Specific examples

[0568] Assume a user has multiple bank accounts, credit cards, and cryptocurrencies. After the user registers with the system and configures the linkage settings for each financial asset, the server immediately collects and standardizes all transaction data. The generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard, and the user can adjust their portfolio based on the investment advice.

[0569] This system centralizes the management of multiple financial assets held by users, enabling efficient asset management. Users can grasp the progress of their assets in real time and make optimal investment decisions based on advice from generative AI.

[0570] Example prompts to input to a generative AI model:

[0571] Data: Bank Account A, Date: 2023-01-01, Amount: -1000.50, Category: Food

[0572] Data: Credit Card B, Date: 2023-01-02, Amount: -200.75, Category: Transportation Expenses

[0573] This gives users a powerful tool to efficiently manage their assets and make investment decisions.

[0574] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0575] Step 1:

[0576] Users launch the smartphone app, enter their personal information, and create an account.

[0577] Input: User information (name, email address, password, etc.)

[0578] Process: The information entered by the user is sent to the server and a new account is created.

[0579] Output: Account creation completion email, notification, login information

[0580] Step 2:

[0581] The user sets up collaboration with each financial institution and inputs information about their financial assets.

[0582] Input: Financial institution information (bank account, credit card information, API key, etc.)

[0583] Processing: The terminal uses the financial institution's API to transmit the user's authentication information to the server and establishes a connection with the financial institution.

[0584] Output: Notification of completion of link with financial institution

[0585] Step 3:

[0586] The server automatically collects transaction data from financial institutions with which it has set up ties.

[0587] Input: Financial institution information (bank account, credit card information, etc.)

[0588] Processing: The server periodically calls the API to obtain transaction data from the financial institution.

[0589] Output: Transaction data (transaction history)

[0590] Step 4:

[0591] The server standardizes the collected transaction data and converts and integrates it into a single unified format.

[0592] Input: Transaction data (transaction history in various formats)

[0593] Processing: The server parses the transaction data and converts it into a standard format (e.g., date, amount, category, etc.).

[0594] Output: Normalized transaction data

[0595] Step 5:

[0596] The server sends the standardized data to the generative AI, which then predicts asset trends.

[0597] Input: Normalized transaction data

[0598] Processing: The server sends the data to the generative AI, which predicts future asset trends based on past trading data and market data.

[0599] Output: Asset forecast data (e.g., asset forecast for the next three months)

[0600] Step 6:

[0601] The server visualizes the asset trend prediction results from the generative AI and displays them on a dashboard.

[0602] Input: Asset transition forecast data

[0603] Processing: The server converts the prediction results into graphs and charts and displays them visually on a dashboard screen.

[0604] Output: Visualized asset trend graph and portfolio diversification ratio chart

[0605] Step 7:

[0606] The server uses generative AI to generate investment advice suited to the user and provides it in real time.

[0607] Input: Asset transition forecast data, user asset status

[0608] Processing: The server generates an optimal investment strategy based on generative AI and presents it to the user, along with the reasons and risk assessment.

[0609] Output: Investment advice information (e.g., recommendations to buy or sell specific financial assets)

[0610] Step 8:

[0611] Users can check the status of their assets and investment advice from generative AI through the dashboard and adjust their portfolios.

[0612] Input: visualized data and investment advice

[0613] Action: User reviews the dashboard and revises investment strategy based on the information provided.

[0614] Output: User's investment strategy (e.g., selection of new investments and portfolio rebalancing)

[0615] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0616] System Overview

[0617] This invention is a system that centrally manages multiple financial assets held by a user and uses generative AI to predict asset trends and provide investment advice. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide personalized investment advice based on emotions. This system has the following functions: input of user information, linkage with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using generative AI, emotion recognition, and provision of emotion-based investment advice.

[0618] User Operation

[0619] When users first access the service, they enter their personal information and create an account. Next, they set up a connection with a financial institution and enter information about each of their financial assets. Next, they perform initial setup so that the emotion engine can recognize the user's emotions. Through the dashboard screen, users can check their asset status in real time and receive optimal investment advice based on their emotions.

[0620] Device behavior

[0621] The device is responsible for sending the information entered by the user to the server. It also displays the data, prediction results, and emotion-based investment advice received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up connectivity, the device transmits that information to the server. At the same time, the emotion engine recognizes the user's emotions in real time and reflects them on the dashboard.

[0622] Server Operation

[0623] The server performs the following main processes based on the information sent by the user.

[0624] 1. Data collection and integration: The server automatically collects transaction data and balance information through the financial institution's API, ensuring that the latest data is always available.

[0625] 2. Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into a single unified format, integrating information on different financial assets.

[0626] 3. Use of generative AI: The server uses generative AI to predict future asset trends based on the user's trading history and market data. For example, it can analyze past stock trading history and predict future price fluctuations.

[0627] 4. Using the emotion engine: The server uses the emotion engine to collect the user's emotion data, which allows it to understand the user's current emotional state.

[0628] 5. Emotion-based adjustment: The server adjusts the dashboard display and investment advice based on the user's emotions recognized by the emotion engine. If the user is feeling anxious, the server personalizes the advice to match their emotions, such as displaying low-risk investment suggestions.

[0629] 6. Data visualization: The server generates integrated data, prediction results, and sentiment data as graphs and charts for visualization, allowing users to intuitively understand their asset status.

[0630] 7. Providing investment advice: The server generates optimal investment advice based on the user's financial situation and emotional data. For example, when the generative AI recommends the purchase of a particular stock, it provides advice that takes into account the user's emotions in addition to the reasons and risk assessment.

[0631] Specific examples

[0632] Assume that a user holds multiple bank accounts, stocks, and cryptocurrencies. When the user initially registers with the system and configures the link settings for each financial asset, the server immediately collects and standardizes all transaction data. The generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard. Furthermore, if the user's emotions are unstable, personalization based on emotions is performed, such as suggesting low-risk investment ideas.

[0633] In this way, the system of the present invention centrally manages multiple financial assets held by a user, enabling efficient asset management. Users can grasp asset trends in real time and make optimal investment decisions based on advice from generative AI. In addition, the introduction of an emotion engine allows users to receive personalized investment advice tailored to their emotions.

[0634] The processing flow will be explained below.

[0635] Step 1:

[0636] The user enters personal information to create an account, providing information such as name, email address, and password, and then presses the "Register" button. The device then sends this information to the server.

[0637] Step 2:

[0638] The server receives the user information, stores it in a database, generates a user ID and authentication token, and sends a confirmation email to the user to confirm registration.

[0639] Step 3:

[0640] Users enter information about multiple financial assets, such as bank accounts, stocks, and virtual currencies, including API keys and authentication information. Once the information is complete, they press the "Link" button, and the device sends the information to the server.

[0641] Step 4:

[0642] The server connects to each financial institution's API based on the information provided by the user, sends requests to acquire transaction data and balance information, receives responses from the financial institutions, and stores them in a database.

[0643] Step 5:

[0644] The server periodically calls the financial institution's API at automatically scheduled times to collect new transaction data and balance information, ensuring that the latest data is always maintained.

[0645] Step 6:

[0646] The server converts the acquired data into a standard format and integrates it, bringing together data in different formats to organize the user's total asset status.

[0647] Step 7:

[0648] The server uses generative AI to analyze the integrated data and predict asset trends. It estimates future asset fluctuations based on the user's past trading history and market data.

[0649] Step 8:

[0650] The server uses an emotion engine to collect user emotion data, analyze the user's facial expressions and input information in real time, and evaluate the user's emotional state.

[0651] Step 9:

[0652] The server adjusts the dashboard display and investment advice based on the user's emotions recognized by the emotion engine. For example, if the user is feeling anxious, it will prioritize displaying low-risk investment ideas and information that will give them a sense of security.

[0653] Step 10:

[0654] The server combines the analysis results of the generative AI and the evaluation results of the emotion engine to generate optimal investment advice, suggesting specific investment actions and recommending risk management.

[0655] Step 11:

[0656] The terminal receives integrated data, forecast results, and sentiment-based investment advice from the server and displays them on a dashboard screen. After logging in, users can view updated data in real time.

[0657] Step 12:

[0658] Users can view their asset status and investment advice on the dashboard, add new financial asset information as needed, and consider investment behavior based on their emotions. The device then sends the new information back to the server, and the cycle repeats.

[0659] Example 2

[0660] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0661] Conventional financial asset management systems lack the functionality to unify the management of multiple financial assets held by users, and integrating and standardizing data provided by different financial institutions is time-consuming. Furthermore, it is difficult to provide personalized investment advice that takes into account the user's emotions and individual circumstances. This makes it difficult for users to grasp the current state of their assets and make effective investment decisions.

[0662] The identification process by the identification 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 inputting user information, means for setting up a link with a financial institution, means for acquiring transaction data from the financial institution, means for integrating and standardizing the acquired data, means for predicting asset trends using generative artificial intelligence, means for visualizing and displaying the integrated data, means for collecting user emotion data, means for adjusting investment advice based on the emotion data, and means for providing personalized investment advice to the user. This makes it possible to centrally manage multiple financial assets held by a user and provide personalized investment advice based on emotions.

[0663] "User information" refers to personal information and information related to financial assets held by a user that the user inputs into the system.

[0664] "Collaboration with financial institutions" refers to a mechanism in which the system connects with various financial institutions via API in order to collect users' financial asset data.

[0665] "Transaction data" refers to data including the transaction history and balance information of a user at a financial institution.

[0666] "Data integration" is the process of converting and centralizing data collected from different financial institutions into a single unified format.

[0667] "Standardization" is the process of standardizing collected data into a predetermined format and arranging it in a form that is easy to analyze.

[0668] "Generative AI" is an AI technology used to analyze past data and predict future outcomes.

[0669] "Asset trend prediction" refers to using generative artificial intelligence to predict future fluctuations in a user's financial assets.

[0670] "Data visualization" refers to the display of integrated data and prediction results in visual formats such as graphs and charts.

[0671] "Emotion data" refers to data that indicates the user's emotional state and is collected by the emotion engine.

[0672] An "emotion engine" is a technology for recognizing a user's emotions and collecting that data.

[0673] "Personalized investment advice" is investment advice that is customized to take into account a user's individual circumstances and emotional state.

[0674] System Overview

[0675] This invention is a system that centrally manages multiple financial assets held by a user and uses generative artificial intelligence to predict asset trends and provide investment advice. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide personalized investment advice based on emotions. This system has the following functions: input of user information, collaboration with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using generative artificial intelligence, emotion recognition, and provision of emotion-based investment advice.

[0676] User Operation

[0677] When users first access the service, they enter their personal information and create an account. Next, they set up a connection with a financial institution and enter information about each of their financial assets. Next, they perform initial setup so that the emotion engine can recognize the user's emotions. Through the dashboard screen, users can check their asset status in real time and receive optimal investment advice based on their emotions.

[0678] Device behavior

[0679] The device is responsible for sending the information entered by the user to the server. It also displays the data, prediction results, and emotion-based investment advice received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up connectivity, the device transmits that information to the server. At the same time, the emotion engine recognizes the user's emotions in real time and reflects them on the dashboard.

[0680] Server Operation

[0681] The server performs the following main processes based on the information sent by the user.

[0682] Data collection and integration: The server automatically collects transaction data and balance information through the financial institution's API, ensuring that the latest data is always available.

[0683] Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into one unified format. Information on different financial assets is integrated.

[0684] Use of generative artificial intelligence: The server uses generative artificial intelligence to predict future asset trends based on the user's trading history and market data. For example, it can analyze past stock trading history and predict future price fluctuations.

[0685] Use of emotion engine: The server uses the emotion engine to collect the user's emotion data, which allows it to understand the user's current emotional state.

[0686] Emotion-based adjustment: The server adjusts the dashboard display and investment advice based on the user's emotions recognized by the emotion engine. If the user is feeling anxious, the server personalizes the content and advice based on the user's emotions, for example, by displaying investment suggestions with low risk.

[0687] Data visualization: The server generates integrated data, prediction results, and sentiment data as graphs and charts for visualization, allowing users to intuitively understand their asset status.

[0688] Providing investment advice: The server generates optimal investment advice based on the user's financial situation and emotional data. For example, when the generative AI recommends the purchase of a particular stock, it provides advice that takes into account the user's emotions in addition to the reasons and risk assessment.

[0689] Specific examples

[0690] Assume that a user holds multiple bank accounts, stocks, and cryptocurrencies. When the user initially registers with the system and configures the link settings for each financial asset, the server immediately collects and standardizes all transaction data. Generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard. Furthermore, if the user's emotions are unstable, the system personalizes the system based on their emotions, suggesting low-risk investment ideas.

[0691] Prompt Sentence Examples

[0692] 1. "Enter the user's bank account information, stock information, and cryptocurrency information and send it to the server."

[0693] 2. The server connects to the financial institution's API and periodically collects transaction data.

[0694] 3. "The server uses generative artificial intelligence to predict asset trends for the next three months."

[0695] 4. "Recognize users' sentiment data in real time and provide sentiment-based investment advice."

[0696] As described above, the system of the present invention centrally manages multiple financial assets held by a user, enabling efficient asset management. Users can grasp asset trends in real time and make optimal investment decisions based on advice from generative AI. Furthermore, by incorporating an emotion engine, users can receive personalized investment advice tailored to their emotions.

[0697] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0698] Step 1:

[0699] User performs initial registration: The user enters personal information and financial asset information to create an account in the system. Specifically, the user enters the required information in the account creation form and presses the submit button. The input data includes name, email address, password, and detailed information about financial assets (bank accounts, stocks, virtual currencies, etc.). This information is sent from the device to the server. The server stores the received information in a database.

[0700] Step 2:

[0701] Setting up integration with financial institutions: The user sets up API integration with each financial institution. This setup involves entering the financial institution's API key and authentication information to establish integration with the system. The API key and authentication information entered by the user are sent from the device to the server, which uses this information to connect with the financial institution and complete the necessary authentication process. If authentication is successful, the server saves the integration setting information in its database.

[0702] Step 3:

[0703] Collection of transaction data: The server automatically collects user transaction data and balance information through the financial institution's API. This process is performed periodically. For example, the server retrieves data from the API using a periodic task scheduler. The input data is the transaction history and balance information provided by the financial institution, and the server saves the received data in temporary storage. It is then stored in a database.

[0704] Step 4:

[0705] Data standardization and integration: The server standardizes the collected data, converts it into a unified format, and integrates it. Specifically, the server receives data in different formats (JSON, XML, etc.) and converts it into a standard format (e.g., JSON). The input data is the collected transaction data, and the results of the format conversion and data standardization performed by the server are stored in a database as an integrated data set.

[0706] Step 5:

[0707] Initial setting of the emotion engine: The user performs the initial setting required for the emotion engine of the system to collect emotion data. The user answers a series of questions on the emotion engine's initial setting screen, including stress level, risk tolerance, and emotional state regarding past investments. The input data is the user's answers, which are sent from the terminal to the server and set as the initial parameters of the emotion engine.

[0708] Step 6:

[0709] Data analysis and prediction: The server uses generative AI to predict future asset trends based on the user's trading data and market data. The server inputs the user's trading history and market data into the generative AI model, which then generates a predicted asset trend. The input data is the user's financial trading data and market data, and the output data is the prediction result from the generative AI model. The predicted result is stored in a database.

[0710] Step 7:

[0711] Emotion recognition and adjustment: The device sends the user's emotional data to the server in real time. The server uses an emotion engine to analyze the received emotional data and understand the user's current emotional state. The input data is the emotional information sent from the device, and the server adjusts the dashboard display content and investment advice based on the emotion engine's analysis. The output data is the adjusted investment advice and dashboard display content.

[0712] Step 8:

[0713] Data visualization: The terminal displays the integrated data and prediction results received from the server as graphs and charts. The input data is the analysis results and prediction data sent from the server, and the terminal visualizes the data based on this. Specifically, line graphs, bar graphs, etc. are displayed on the dashboard screen, allowing the user to intuitively understand the asset status.

[0714] Step 9:

[0715] Providing investment advice: The server generates optimal investment advice based on the user's financial situation and emotional data, and the device displays the results. The input data is the user's financial situation and emotional data, which the server analyzes and uses generative AI to create investment advice. The generated investment advice is stored in a database and sent to the device. The device displays the received advice on the dashboard screen.

[0716] (Application example 2)

[0717] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0718] In modern society, it is difficult for individuals to hold multiple financial assets, manage them centrally, and efficiently invest and pay. Collecting and standardizing transaction data, predicting asset trends, and providing investment advice are particularly burdensome. Providing appropriate advice based on users' emotions and spending patterns is even more challenging. Therefore, there is a need for a system that can handle these complex tasks in an integrated and automated manner and provide users with easy-to-understand, useful information.

[0719] The specific processing 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 inputting user information, means for establishing a connection with a financial institution, means for acquiring transaction data from the financial institution, means for integrating and standardizing the acquired data, means for predicting asset trends using generative AI, means for visualizing and displaying the integrated data, means for providing investment advice to the user, means for recognizing the user's emotions, means for adjusting the investment advice based on the emotions, means for recording the user's payment behavior and learning the user's consumption patterns, and means for providing payment advice based on the consumption patterns. This enables the user to centrally manage multiple financial assets and receive efficient asset management and personalized payment advice in real time.

[0720] The "means for inputting user information" is an interface for inputting the user's personal information and authentication information into the system.

[0721] The "means for setting up linkage with financial institutions" refers to the setting means for linking the system with financial institutions such as banks and securities companies.

[0722] "Means for obtaining transaction data from financial institutions" refers to means for automatically obtaining transaction data using a financial institution's API or other methods.

[0723] "Means for integrating and standardizing acquired data" refers to processing means for centralizing transaction data collected from multiple financial institutions and converting it into a unified format.

[0724] "Means of predicting asset trends using generative AI" refers to a means of predicting future asset fluctuations using generative AI based on past trading data and market information.

[0725] The "means for visualizing and displaying integrated data" refers to a means for displaying data converted into a unified format in a visual form such as a graph or chart.

[0726] The "means for providing investment advice to a user" refers to a means for providing optimal investment advice to a user based on predicted asset trends and market information.

[0727] "Means for recognizing user emotions" refers to a means for analyzing and recognizing the user's emotional state from facial expressions, voice, and input data.

[0728] The "means for tailoring investment advice based on emotions" refers to a means for tailoring and personalizing the content of investment advice based on the recognized emotions of a user.

[0729] "Means for recording users' payment behavior and learning consumption patterns" refers to a means for recording users' daily payment data and learning consumption patterns using generative AI.

[0730] The "means for providing payment advice based on consumption patterns" is a means for providing optimal payment methods and saving methods to users based on learned consumption patterns.

[0731] System Overview

[0732] This invention is a system that centrally manages multiple financial assets and payment behaviors held by a user, and uses generative AI and an emotion engine to predict asset trends and provide personalized investment and payment advice. The system has the following functions: input of user information, connection with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using generative AI, emotion recognition, emotion-based investment advice, consumption learning, and payment advice provision.

[0733] Server Operation

[0734] Data collection and integration features

[0735] The server automatically collects user transaction data and payment data through APIs of financial institutions and payment services, using API connection modules and OCR technology.

[0736] Data standardization and integration capabilities

[0737] The server converts the collected data into a standard format and integrates it into a centralized database, using Python data engineering libraries (pandas, numpy) in the process.

[0738] Generative AI prediction function

[0739] The server uses generative AI (TensorFlow, Keras) to predict the user's asset trends and payment patterns based on past trading data and market information.

[0740] Emotion recognition function using emotion engine

[0741] The server collects user emotional data through camera and voice input and analyzes it using an emotion recognition engine (OpenCV, facial expression analysis model).

[0742] Emotion-based personalization

[0743] The server generates investment advice and payment advice according to the user's emotional state based on the emotional data, using a personalization engine.

[0744] Data visualization features

[0745] The server analyzes the integrated data, prediction results, and sentiment data, and generates graphs and charts for visualization. This process uses data visualization libraries (matplotlib, seaborn).

[0746] Device behavior

[0747] The terminal, specifically the user's smartphone, sends the information entered by the user and transaction data to the server, and displays the data, prediction results, and emotion recognition results received from the server on the dashboard screen.

[0748] Specific examples

[0749] If a user has multiple bank accounts and credit cards, they can set up the linking of these financial assets during initial registration. The server automatically collects and standardizes transaction data, and uses generative AI to predict asset trends and payment patterns for the next three months.

[0750] If a user notices that they have spent a lot in a particular week, they can scan the receipt using their smartphone camera. The server extracts the data using OCR technology and analyzes it using generative AI and an emotion engine. As a result, the system identifies the reasons for the excessive spending and suggests specific ways to save money.

[0751] If the emotion engine detects the user's anxiety, it will suggest low-risk investment advice or savings strategies to reduce the user's psychological burden.

[0752] Prompt Sentence Examples

[0753] "Generate next month's spending forecast and savings advice based on May's payment data."

[0754] "We suggest optimal payment methods when users feel unsure."

[0755] In this way, the server and terminal can cooperate to efficiently manage a user's diverse financial assets and payment behavior, and provide personalized investment and payment advice in real time.

[0756] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0757] Step 1:

[0758] User registration and input

[0759] A user creates an account by entering personal information using a smartphone device, including name, email address, password, etc. The entered information is sent from the device to a server and stored in a database.

[0760] Input: User's personal information

[0761] Output: User information stored in the server database

[0762] Step 2:

[0763] Setting up collaboration with financial institutions

[0764] Users input their bank account and credit card information to link the system with financial institutions. The server receives the information sent from the device and connects it to each financial institution's API, making it possible to automatically collect transaction data.

[0765] Input: User's financial institution information

[0766] Output: Financial institution API connection information

[0767] Step 3:

[0768] Automatic collection of transaction data

[0769] The server periodically collects transaction data from financial institutions using the configured API. The data is obtained in JSON format or similar and stored in the server's database.

[0770] Input: Transaction data obtained from financial institution APIs

[0771] Output: Transaction data stored in the server database

[0772] Step 4:

[0773] Data integration and standardization

[0774] The server converts the collected transaction data into a standard format and centrally consolidates it, using data engineering libraries such as pandas and numpy.

[0775] Input: Raw transaction data captured

[0776] Output: Standardized and consolidated transaction data

[0777] Step 5:

[0778] Asset trend prediction using generative AI

[0779] The server uses generative AI (TensorFlow, Keras) to predict future asset trends based on standardized data, using past trading data and market data for learning.

[0780] Input: Standardized and consolidated transaction data

[0781] Output: Predicted asset trend data

[0782] Step 6:

[0783] Emotion recognition

[0784] Users input their facial expressions and voice using the smartphone's camera and microphone. The server analyzes the collected emotional data using an emotion recognition engine (OpenCV, facial expression analysis model) to understand the user's emotional patterns.

[0785] Input: User's facial expression data and voice data

[0786] Output: Parsed emotional state data

[0787] Step 7:

[0788] Personalized investment advice

[0789] The server generates investment advice for the user based on the asset transition data and emotional state data. In this process, a personalization engine is used to provide appropriate advice tailored to the user's emotional state.

[0790] Input: Asset transition data, emotional state data

[0791] Output: Personalized investment advice

[0792] Step 8:

[0793] Recording payment behavior and learning spending patterns

[0794] Users record their daily payment data on their smartphones, and the server collects this data and uses generative AI to learn consumption patterns.

[0795] Input: User payment data

[0796] Output: Learned consumption patterns

[0797] Step 9:

[0798] Providing payment advice

[0799] The server then provides users with optimal payment methods and advice on saving based on their learned consumption patterns, enabling them to effectively manage their consumption.

[0800] Input: Learned consumption patterns

[0801] Output: Personalized payment advice

[0802] Through these steps, users can efficiently manage their assets and consumption and receive personalized advice in real time.

[0803] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0804] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0805] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0806] [Third embodiment]

[0807] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0808] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0809] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0810] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0811] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0812] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0813] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0814] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0815] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0816] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0817] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0818] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0819] System Overview

[0820] This invention is a system that centrally manages multiple financial assets held by a user and provides asset trend forecasts and investment advice using generative AI. This system has the following functions: input of user information, linkage with financial institutions, automatic collection and standardization of transaction data, data visualization, predictions using generative AI, and provision of investment advice.

[0821] User Operation

[0822] When users first access the service, they enter their personal information and create an account. Next, they enter information about each financial asset and provide an API key and authentication information to set up a connection with a financial institution. Users can check their asset status in real time through the dashboard screen. They can also review their own investment strategies based on investment advice provided by generative AI.

[0823] Device behavior

[0824] The device is responsible for sending the information entered by the user to the server. It also displays the integrated data and forecast results received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up the connection, the device transmits that information to the server. The dashboard displays a graph of monthly asset trends and a chart of the portfolio's diversification ratio.

[0825] Server Operation

[0826] The server performs the following main processes based on the information sent by the user.

[0827] 1. Data collection and integration: The server automatically collects transaction data and asset balance information through the financial institution's API. This process is performed periodically to ensure that the latest data is always obtained.

[0828] 2. Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into a single unified format, thereby integrating information on different financial assets.

[0829] 3. Use of generative AI: The server uses generative AI to predict future asset trends based on the user's trading history and market data. For example, it can analyze past stock trading history and predict future price fluctuations.

[0830] 4. Data visualization: The integrated data and forecast results generated on the server are generated as graphs and charts for visualization, allowing users to grasp the increase or decrease in assets and investment risks at a glance.

[0831] 5. Providing investment advice: The server generates optimal investment advice based on the user's financial situation and market trends. For example, if the generative AI recommends the purchase of a specific stock, it will also provide the reasons and risk assessment.

[0832] Specific examples

[0833] Assume a user has multiple bank accounts, stocks, and cryptocurrencies. After the user registers with the system and configures the link settings for each financial asset, the server immediately collects and standardizes all transaction data. The generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard, and the user can adjust their portfolio based on the investment advice.

[0834] In this way, the system of the present invention centrally manages multiple financial assets held by the user, enabling efficient asset management. Users can grasp the trends in their assets in real time and make optimal investment decisions based on the advice of generative AI.

[0835] The processing flow will be explained below.

[0836] Step 1:

[0837] The user enters personal information to create an account, providing information such as name, email address, and password, and then presses the "Register" button. The device then sends this information to the server.

[0838] Step 2:

[0839] The server receives the user information, stores it in a database, generates a user ID and authentication token, and sends a confirmation email to the user to confirm registration.

[0840] Step 3:

[0841] Users enter information about multiple financial assets, such as bank accounts, stocks, and virtual currencies, including API keys and authentication information. Once the information is complete, they press the "Link" button, and the device sends the information to the server.

[0842] Step 4:

[0843] The server connects to each financial institution's API based on the information provided by the user, sends requests to acquire transaction data and balance information, receives responses from the financial institutions, and stores them in a database.

[0844] Step 5:

[0845] The server periodically calls the financial institution's API at automatically scheduled times to collect new transaction data and balance information, ensuring that the latest data is always maintained.

[0846] Step 6:

[0847] The server converts the acquired data into a standard format and integrates it, bringing together data in different formats to organize the user's total asset status.

[0848] Step 7:

[0849] The server uses generative AI to analyze the integrated data and predict asset trends. It estimates future asset fluctuations based on the user's past trading history and market data.

[0850] Step 8:

[0851] The server generates graphs and charts to visualize the data based on the analysis results, allowing users to intuitively understand their asset status.

[0852] Step 9:

[0853] The server provides optimal investment advice to users, proposing specific investment actions and recommending risk management based on the analysis results of the generative AI.

[0854] Step 10:

[0855] The terminal displays the integrated data, forecast results, and investment advice received from the server on a dashboard screen. After logging in, users can check the updated data in real time.

[0856] Step 11:

[0857] Users can view their financial situation and investment advice on the dashboard, and add new financial information as needed. The device then sends the new information back to the server, and the cycle repeats.

[0858] Example 1

[0859] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0860] In conventional asset management systems, the integration and standardization of transaction data obtained from different financial institutions was cumbersome, making it difficult for users to centrally manage all of their assets. In addition, there was a lack of support for users to make optimal investment decisions, as the systems did not adequately predict future asset trends or provide investment advice.

[0861] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0862] In this invention, the server includes means for periodically collecting transaction data and asset information using APIs of financial institutions, means for standardizing the collected data and converting it into a single format, and means for predicting future asset trends from transaction history and market data using generative AI. This allows users to centrally manage assets from multiple financial institutions and receive accurate asset trend predictions and optimal investment advice using generative AI.

[0863] "User information" refers to personal identification information entered by a user when using the system, including name, email address, password, etc.

[0864] "Integration with financial institutions" refers to the connection settings required for the system to send and receive data between the financial institution designated by the user and the system, and is a process that includes providing API keys and authentication information.

[0865] "Transaction data" refers to a user's transaction history and asset balance information obtained from financial institutions.

[0866] "Data standardization" refers to the process of converting data collected in different formats into one unified format.

[0867] A "generative AI model" is an artificial intelligence model used to predict future asset trends based on trading history and market data.

[0868] "Visualization and display" refers to the process of converting the integrated data and prediction results into a visually easy-to-understand format (e.g., graphs and charts) and providing them to users.

[0869] "Investment advice" refers to optimal investment strategies and recommendations provided by generative AI based on the user's financial situation and market trends.

[0870] A "terminal" refers to a device (e.g., a PC or smartphone) that a user uses to input information, and is responsible for sending and receiving data with the server.

[0871] The "server" is the central computer in the system that acquires data from financial institutions, analyzes the data using generative AI, and visualizes it.

[0872] MODE FOR CARRYING OUT THE INVENTION

[0873] This invention is a system that centrally manages multiple financial assets held by a user and provides asset trend forecasts and investment advice using a generative AI model. This system has the following functions: input of user information, collaboration with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using a generative AI model, and provision of investment advice.

[0874] User Operation

[0875] When users first access the service, they enter their personal information to create an account. Next, they enter information about each financial asset and provide API keys and authentication information to set up connections with financial institutions. Users can check their asset status in real time through the dashboard screen. They can also review their own investment strategies based on investment advice provided by the generative AI model.

[0876] Device behavior

[0877] The device sends the information entered by the user to the server. It also displays the integrated data and forecast results received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up the connection, the device transmits that information to the server. The dashboard displays a graph of monthly asset trends and a chart of the portfolio's diversification ratio.

[0878] Server Operation

[0879] The server performs the following main processes based on the information sent by the user.

[0880] Data collection and integration:

[0881] The server automatically collects transaction data and asset balance information through the financial institution's API. This process is performed periodically to ensure the latest data is always obtained. For example, calling a bank's API to obtain the latest account balance.

[0882] Data standardization and integration:

[0883] The collected data is provided in different formats, so the server standardizes it and converts it into a single unified format, integrating information on different financial assets. For example, bank balance information and stock trading history are converted into the same format.

[0884] Use of generative AI models:

[0885] The server uses the generative AI model to predict future asset trends based on the user's trading history and market data. For example, it analyzes past stock trading history to predict future price fluctuations.

[0886] Data visualization:

[0887] The server generates the integrated data and forecast results as graphs and charts for visualization, allowing users to grasp the increase or decrease in assets and investment risk at a glance. For example, the portfolio diversification rate can be displayed as a pie chart.

[0888] Providing investment advice:

[0889] The server generates optimal investment advice based on the user's financial situation and market trends. For example, when the generative AI model recommends the purchase of a particular stock, it also presents the reason and risk assessment.

[0890] Specific examples

[0891] Assume a user has multiple bank accounts, stocks, and cryptocurrencies. After the user registers with the system and configures the connections for each financial asset, the server immediately collects and standardizes all transaction data. A generative AI model then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard, allowing users to adjust their portfolios based on investment advice.

[0892] For example, use the following as your prompt:

[0893] "Please predict my asset trends for the next three months based on stock trading data from the past year. Also, please provide optimal investment advice along with a risk assessment."

[0894] In this way, the system of the present invention centrally manages multiple financial assets held by the user, enabling efficient asset management. Users can grasp the trends in their assets in real time and make optimal investment decisions based on the advice of the generated AI model.

[0895] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0896] Step 1: User registration and initial setup

[0897] Input: A user enters their name, email address, and password into a web form.

[0898] Data processing: The terminal sends the entered information to the server, which registers the information in a database.

[0899] Output: An account is created for the user and credentials are generated.

[0900] What it does: When a user submits a form, the device sends the information to the server, which adds the new user to its database. Once registration is complete, authentication information is generated and a confirmation email is sent to the user.

[0901] Step 2: Setting up a connection with your financial institution

[0902] Input: The user enters the API key and authentication information to set up the connection with the financial institution.

[0903] Data processing: The terminal sends the entered authentication information to the server, which stores it. The server also calls the financial institution's API to initialize the connection.

[0904] Output: The integration is now set up and ready to retrieve transaction data from financial institutions.

[0905] How it works: When a user enters their authentication information and presses the link button, the device sends that information to the server, which then calls the financial institution's API to establish the link and securely stores the authentication information.

[0906] Step 3: Collect and link transaction data

[0907] Input: The server periodically calls the financial institution's API.

[0908] Data processing: The server obtains transaction data and asset balance information from financial institutions and standardizes it into the data format of the centralized management system.

[0909] Output: Centralized transaction data and asset balance information.

[0910] How it works: The server calls the API on a scheduled basis, normalizes the data it receives, converts it into a unified format, and stores it in a database.

[0911] Step 4: Data analysis and predictions using generative AI models

[0912] Input: Normalized transaction data and asset balance information.

[0913] Data processing: The server analyzes the data using a generative AI model to predict asset trends. Specifically, it simulates future price fluctuations and asset increases and decreases based on past data.

[0914] Output: Forecast data of future asset trends.

[0915] How it works: The server inputs data into a generative AI model, which then uses that data to predict future asset trends, such as stock price fluctuations over the next three months.

[0916] Step 5: Visualize the data and create a dashboard

[0917] Inputs: Forecast data and consolidated transaction data.

[0918] Data processing: The server generates graphs and charts to visualize the data and displays them in the form of a dashboard.

[0919] Output: Visualized data (graphs, charts, etc.) displayed on a dashboard screen.

[0920] How it works: The server converts forecast data and trading data into graphs and charts and sends them to the terminal, which then displays them on the dashboard screen, allowing users to check their asset status in real time.

[0921] Step 6: Providing investment advice

[0922] Input: Forecast data and user asset status data.

[0923] Data processing: The server uses a generative AI model to analyze the user's asset status and market trends, and generates optimal investment advice.

[0924] Output: Investment advice and risk assessment.

[0925] How it works: The server uses the generative AI model to generate investment advice based on the analysis results and sends it to the device, which then displays it on a dashboard for immediate user confirmation.

[0926] In this way, the system of the present invention centrally manages multiple financial assets held by a user through multiple processing steps, thereby realizing efficient asset management.

[0927] (Application example 1)

[0928] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0929] Existing financial asset management systems have difficulty integrating and standardizing a wide variety of data in different formats, requiring users to perform tedious tasks to centrally manage multiple financial institutions and asset information. Furthermore, specialized knowledge is required to make investment decisions, and there is a need for systems that utilize generative AI to provide investment advice in real time. Furthermore, electronic payment services lack functionality for the integrated management of various payment methods and financial assets, creating a need for systems that can help users understand their asset status in real time and develop optimal investment strategies.

[0930] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0931] In this invention, the server includes means for inputting user information, means for setting up a connection with a financial institution, means for acquiring transaction data from the financial institution, means for integrating and standardizing the acquired data, means for predicting asset trends using generative AI, means for visualizing and displaying the integrated data, means for providing investment advice to the user, means for centrally managing multiple financial assets in the electronic payment service, and means for predicting asset trends from transaction data using generative AI and providing investment advice in real time. This allows users to centrally manage multiple financial assets and instantly receive investment advice from the generative AI, thereby realizing efficient and intelligent asset management and investment decisions.

[0932] "User information" refers to data such as personal information and authentication information entered by system users.

[0933] A "financial institution" is an institution that provides financial services, such as a bank, securities company, or credit card company.

[0934] "Linkage settings" refers to the procedure for setting up a user to exchange data with a financial institution.

[0935] "Transaction data" refers to data such as deposit transactions, payment history, and investment transactions obtained from financial institutions.

[0936] "Integration" is the process of combining data provided in different formats into one standard format.

[0937] "Standardization" is the process of converting integrated data into a single, unified format.

[0938] "Generative AI" is artificial intelligence that uses machine learning and deep learning technologies to analyze data and generate future predictions and advice.

[0939] "Asset trend forecasting" refers to predicting future asset fluctuations based on collected trading data and market data.

[0940] "Visualization" refers to the display of data and prediction results in a visual format such as a graph or chart.

[0941] "Investment advice" is information that suggests how and in which assets to invest based on the user's asset status and market trends.

[0942] "Electronic payment services" are financial transaction services conducted over the Internet or mobile devices.

[0943] "Centralized management" refers to consolidating and managing multiple financial assets and data in one place.

[0944] "Real-time" refers to data processing and information provision occurring immediately.

[0945] System Overview

[0946] This invention is a system that centrally manages multiple financial assets held by a user and provides asset trend forecasts and investment advice using generative AI. This system is provided to users primarily via a smartphone app and has the following functions: input of user information, linkage with financial institutions, automatic collection and standardization of transaction data, data visualization, predictions using generative AI, and provision of investment advice.

[0947] User Operation

[0948] When users first access the service, they enter their personal information and create an account. Next, they enter information about their financial assets and provide API keys and authentication information to set up connections with financial institutions. Users can check their asset status in real time through the dashboard screen. They can also review their own investment strategies based on investment advice provided by generative AI.

[0949] Device behavior

[0950] The device is responsible for sending the information entered by the user to the server. It also displays the integrated data and forecast results received from the server on the dashboard screen. For example, when a user enters bank account and credit card information and sets up the connection, the device transmits that information to the server. The dashboard displays a graph of monthly asset trends and a chart of the portfolio's diversification ratio.

[0951] Server Operation

[0952] The server performs the following main processes based on the information sent by the user.

[0953] 1. Data collection and integration: The server automatically collects transaction data and asset balance information through the financial institution's API. This process is performed periodically to ensure that the latest data is always obtained.

[0954] 2. Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into a single unified format, thereby integrating information on different financial assets.

[0955] 3. Use of generative AI: The server uses generative AI to predict future asset trends based on the user's trading history and market data. For example, it can analyze past trading history and predict future price fluctuations.

[0956] 4. Data visualization: The integrated data and forecast results generated on the server are generated as graphs and charts for visualization, allowing users to grasp the increase or decrease in assets and investment risks at a glance.

[0957] 5. Providing investment advice: The server generates optimal investment advice based on the user's financial situation and market trends. For example, if the generative AI recommends the purchase of a specific stock, it will also provide the reasons and risk assessment.

[0958] Specific examples

[0959] Assume a user has multiple bank accounts, credit cards, and cryptocurrencies. After the user registers with the system and configures the linkage settings for each financial asset, the server immediately collects and standardizes all transaction data. The generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard, and the user can adjust their portfolio based on the investment advice.

[0960] This system centralizes the management of multiple financial assets held by users, enabling efficient asset management. Users can grasp the progress of their assets in real time and make optimal investment decisions based on advice from generative AI.

[0961] Example prompts to input to a generative AI model:

[0962] Data: Bank Account A, Date: 2023-01-01, Amount: -1000.50, Category: Food

[0963] Data: Credit Card B, Date: 2023-01-02, Amount: -200.75, Category: Transportation Expenses

[0964] This gives users a powerful tool to efficiently manage their assets and make investment decisions.

[0965] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0966] Step 1:

[0967] Users launch the smartphone app, enter their personal information, and create an account.

[0968] Input: User information (name, email address, password, etc.)

[0969] Process: The information entered by the user is sent to the server and a new account is created.

[0970] Output: Account creation completion email, notification, login information

[0971] Step 2:

[0972] The user sets up collaboration with each financial institution and inputs information about their financial assets.

[0973] Input: Financial institution information (bank account, credit card information, API key, etc.)

[0974] Processing: The terminal uses the financial institution's API to transmit the user's authentication information to the server and establishes a connection with the financial institution.

[0975] Output: Notification of completion of link with financial institution

[0976] Step 3:

[0977] The server automatically collects transaction data from financial institutions with which it has set up ties.

[0978] Input: Financial institution information (bank account, credit card information, etc.)

[0979] Processing: The server periodically calls the API to obtain transaction data from the financial institution.

[0980] Output: Transaction data (transaction history)

[0981] Step 4:

[0982] The server standardizes the collected transaction data and converts and integrates it into a single unified format.

[0983] Input: Transaction data (transaction history in various formats)

[0984] Processing: The server parses the transaction data and converts it into a standard format (e.g., date, amount, category, etc.).

[0985] Output: Normalized transaction data

[0986] Step 5:

[0987] The server sends the standardized data to the generative AI, which then predicts asset trends.

[0988] Input: Normalized transaction data

[0989] Processing: The server sends the data to the generative AI, which predicts future asset trends based on past trading data and market data.

[0990] Output: Asset forecast data (e.g., asset forecast for the next three months)

[0991] Step 6:

[0992] The server visualizes the asset trend prediction results from the generative AI and displays them on a dashboard.

[0993] Input: Asset transition forecast data

[0994] Processing: The server converts the prediction results into graphs and charts and displays them visually on a dashboard screen.

[0995] Output: Visualized asset trend graph and portfolio diversification ratio chart

[0996] Step 7:

[0997] The server uses generative AI to generate investment advice suited to the user and provides it in real time.

[0998] Input: Asset transition forecast data, user asset status

[0999] Processing: The server generates an optimal investment strategy based on generative AI and presents it to the user, along with the reasons and risk assessment.

[1000] Output: Investment advice information (e.g., recommendations to buy or sell specific financial assets)

[1001] Step 8:

[1002] Users can check the status of their assets and investment advice from generative AI through the dashboard and adjust their portfolios.

[1003] Input: visualized data and investment advice

[1004] Action: User reviews the dashboard and revises investment strategy based on the information provided.

[1005] Output: User's investment strategy (e.g., selection of new investments and portfolio rebalancing)

[1006] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1007] System Overview

[1008] This invention is a system that centrally manages multiple financial assets held by a user and uses generative AI to predict asset trends and provide investment advice. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide personalized investment advice based on emotions. This system has the following functions: input of user information, linkage with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using generative AI, emotion recognition, and provision of emotion-based investment advice.

[1009] User Operation

[1010] When users first access the service, they enter their personal information and create an account. Next, they set up a connection with a financial institution and enter information about each of their financial assets. Next, they perform initial setup so that the emotion engine can recognize the user's emotions. Through the dashboard screen, users can check their asset status in real time and receive optimal investment advice based on their emotions.

[1011] Device behavior

[1012] The device is responsible for sending the information entered by the user to the server. It also displays the data, prediction results, and emotion-based investment advice received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up connectivity, the device transmits that information to the server. At the same time, the emotion engine recognizes the user's emotions in real time and reflects them on the dashboard.

[1013] Server Operation

[1014] The server performs the following main processes based on the information sent by the user.

[1015] 1. Data collection and integration: The server automatically collects transaction data and balance information through the financial institution's API, ensuring that the latest data is always available.

[1016] 2. Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into a single unified format, integrating information on different financial assets.

[1017] 3. Use of generative AI: The server uses generative AI to predict future asset trends based on the user's trading history and market data. For example, it can analyze past stock trading history and predict future price fluctuations.

[1018] 4. Using the emotion engine: The server uses the emotion engine to collect the user's emotion data, which allows it to understand the user's current emotional state.

[1019] 5. Emotion-based adjustment: The server adjusts the dashboard display and investment advice based on the user's emotions recognized by the emotion engine. If the user is feeling anxious, the server personalizes the advice to match their emotions, such as displaying low-risk investment suggestions.

[1020] 6. Data visualization: The server generates integrated data, prediction results, and sentiment data as graphs and charts for visualization, allowing users to intuitively understand their asset status.

[1021] 7. Providing investment advice: The server generates optimal investment advice based on the user's financial situation and emotional data. For example, when the generative AI recommends the purchase of a particular stock, it provides advice that takes into account the user's emotions in addition to the reasons and risk assessment.

[1022] Specific examples

[1023] Assume that a user holds multiple bank accounts, stocks, and cryptocurrencies. When the user initially registers with the system and configures the link settings for each financial asset, the server immediately collects and standardizes all transaction data. The generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard. Furthermore, if the user's emotions are unstable, personalization based on emotions is performed, such as suggesting low-risk investment ideas.

[1024] In this way, the system of the present invention centrally manages multiple financial assets held by a user, enabling efficient asset management. Users can grasp asset trends in real time and make optimal investment decisions based on advice from generative AI. In addition, the introduction of an emotion engine allows users to receive personalized investment advice tailored to their emotions.

[1025] The processing flow will be explained below.

[1026] Step 1:

[1027] The user enters personal information to create an account, providing information such as name, email address, and password, and then presses the "Register" button. The device then sends this information to the server.

[1028] Step 2:

[1029] The server receives the user information, stores it in a database, generates a user ID and authentication token, and sends a confirmation email to the user to confirm registration.

[1030] Step 3:

[1031] Users enter information about multiple financial assets, such as bank accounts, stocks, and virtual currencies, including API keys and authentication information. Once the information is complete, they press the "Link" button, and the device sends the information to the server.

[1032] Step 4:

[1033] The server connects to each financial institution's API based on the information provided by the user, sends requests to acquire transaction data and balance information, receives responses from the financial institutions, and stores them in a database.

[1034] Step 5:

[1035] The server periodically calls the financial institution's API at automatically scheduled times to collect new transaction data and balance information, ensuring that the latest data is always maintained.

[1036] Step 6:

[1037] The server converts the acquired data into a standard format and integrates it, bringing together data in different formats to organize the user's total asset status.

[1038] Step 7:

[1039] The server uses generative AI to analyze the integrated data and predict asset trends. It estimates future asset fluctuations based on the user's past trading history and market data.

[1040] Step 8:

[1041] The server uses an emotion engine to collect user emotion data, analyze the user's facial expressions and input information in real time, and evaluate the user's emotional state.

[1042] Step 9:

[1043] The server adjusts the dashboard display and investment advice based on the user's emotions recognized by the emotion engine. For example, if the user is feeling anxious, it will prioritize displaying low-risk investment ideas and information that will give them a sense of security.

[1044] Step 10:

[1045] The server combines the analysis results of the generative AI and the evaluation results of the emotion engine to generate optimal investment advice, suggesting specific investment actions and recommending risk management.

[1046] Step 11:

[1047] The terminal receives integrated data, forecast results, and sentiment-based investment advice from the server and displays them on a dashboard screen. After logging in, users can view updated data in real time.

[1048] Step 12:

[1049] Users can view their asset status and investment advice on the dashboard, add new financial asset information as needed, and consider investment behavior based on their emotions. The device then sends the new information back to the server, and the cycle repeats.

[1050] Example 2

[1051] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1052] Conventional financial asset management systems lack the functionality to unify the management of multiple financial assets held by users, and integrating and standardizing data provided by different financial institutions is time-consuming. Furthermore, it is difficult to provide personalized investment advice that takes into account the user's emotions and individual circumstances. This makes it difficult for users to grasp the current state of their assets and make effective investment decisions.

[1053] The identification process by the identification 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 inputting user information, means for setting up a link with a financial institution, means for acquiring transaction data from the financial institution, means for integrating and standardizing the acquired data, means for predicting asset trends using generative artificial intelligence, means for visualizing and displaying the integrated data, means for collecting user emotion data, means for adjusting investment advice based on the emotion data, and means for providing personalized investment advice to the user. This makes it possible to centrally manage multiple financial assets held by a user and provide personalized investment advice based on emotions.

[1054] "User information" refers to personal information and information related to financial assets held by a user that the user inputs into the system.

[1055] "Collaboration with financial institutions" refers to a mechanism in which the system connects with various financial institutions via API in order to collect users' financial asset data.

[1056] "Transaction data" refers to data including the transaction history and balance information of a user at a financial institution.

[1057] "Data integration" is the process of converting and centralizing data collected from different financial institutions into a single unified format.

[1058] "Standardization" is the process of standardizing collected data into a predetermined format and arranging it in a form that is easy to analyze.

[1059] "Generative AI" is an AI technology used to analyze past data and predict future outcomes.

[1060] "Asset trend prediction" refers to using generative artificial intelligence to predict future fluctuations in a user's financial assets.

[1061] "Data visualization" refers to the display of integrated data and prediction results in visual formats such as graphs and charts.

[1062] "Emotion data" refers to data that indicates the user's emotional state and is collected by the emotion engine.

[1063] An "emotion engine" is a technology for recognizing a user's emotions and collecting that data.

[1064] "Personalized investment advice" is investment advice that is customized to take into account a user's individual circumstances and emotional state.

[1065] System Overview

[1066] This invention is a system that centrally manages multiple financial assets held by a user and uses generative artificial intelligence to predict asset trends and provide investment advice. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide personalized investment advice based on emotions. This system has the following functions: input of user information, collaboration with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using generative artificial intelligence, emotion recognition, and provision of emotion-based investment advice.

[1067] User Operation

[1068] When users first access the service, they enter their personal information and create an account. Next, they set up a connection with a financial institution and enter information about each of their financial assets. Next, they perform initial setup so that the emotion engine can recognize the user's emotions. Through the dashboard screen, users can check their asset status in real time and receive optimal investment advice based on their emotions.

[1069] Device behavior

[1070] The device is responsible for sending the information entered by the user to the server. It also displays the data, prediction results, and emotion-based investment advice received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up connectivity, the device transmits that information to the server. At the same time, the emotion engine recognizes the user's emotions in real time and reflects them on the dashboard.

[1071] Server Operation

[1072] The server performs the following main processes based on the information sent by the user.

[1073] Data collection and integration: The server automatically collects transaction data and balance information through the financial institution's API, ensuring that the latest data is always available.

[1074] Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into one unified format. Information on different financial assets is integrated.

[1075] Use of generative artificial intelligence: The server uses generative artificial intelligence to predict future asset trends based on the user's trading history and market data. For example, it can analyze past stock trading history and predict future price fluctuations.

[1076] Use of emotion engine: The server uses the emotion engine to collect the user's emotion data, which allows it to understand the user's current emotional state.

[1077] Emotion-based adjustment: The server adjusts the dashboard display and investment advice based on the user's emotions recognized by the emotion engine. If the user is feeling anxious, the server personalizes the content and advice based on the user's emotions, for example, by displaying investment suggestions with low risk.

[1078] Data visualization: The server generates integrated data, prediction results, and sentiment data as graphs and charts for visualization, allowing users to intuitively understand their asset status.

[1079] Providing investment advice: The server generates optimal investment advice based on the user's financial situation and emotional data. For example, when the generative AI recommends the purchase of a particular stock, it provides advice that takes into account the user's emotions in addition to the reasons and risk assessment.

[1080] Specific examples

[1081] Assume that a user holds multiple bank accounts, stocks, and cryptocurrencies. When the user initially registers with the system and configures the link settings for each financial asset, the server immediately collects and standardizes all transaction data. Generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard. Furthermore, if the user's emotions are unstable, the system personalizes the system based on their emotions, suggesting low-risk investment ideas.

[1082] Prompt Sentence Examples

[1083] 1. "Enter the user's bank account information, stock information, and cryptocurrency information and send it to the server."

[1084] 2. The server connects to the financial institution's API and periodically collects transaction data.

[1085] 3. "The server uses generative artificial intelligence to predict asset trends for the next three months."

[1086] 4. "Recognize users' sentiment data in real time and provide sentiment-based investment advice."

[1087] As described above, the system of the present invention centrally manages multiple financial assets held by a user, enabling efficient asset management. Users can grasp asset trends in real time and make optimal investment decisions based on advice from generative AI. Furthermore, by incorporating an emotion engine, users can receive personalized investment advice tailored to their emotions.

[1088] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1089] Step 1:

[1090] User performs initial registration: The user enters personal information and financial asset information to create an account in the system. Specifically, the user enters the required information in the account creation form and presses the submit button. The input data includes name, email address, password, and detailed information about financial assets (bank accounts, stocks, virtual currencies, etc.). This information is sent from the device to the server. The server stores the received information in a database.

[1091] Step 2:

[1092] Setting up integration with financial institutions: The user sets up API integration with each financial institution. This setup involves entering the financial institution's API key and authentication information to establish integration with the system. The API key and authentication information entered by the user are sent from the device to the server, which uses this information to connect with the financial institution and complete the necessary authentication process. If authentication is successful, the server saves the integration setting information in its database.

[1093] Step 3:

[1094] Collection of transaction data: The server automatically collects user transaction data and balance information through the financial institution's API. This process is performed periodically. For example, the server retrieves data from the API using a periodic task scheduler. The input data is the transaction history and balance information provided by the financial institution, and the server saves the received data in temporary storage. It is then stored in a database.

[1095] Step 4:

[1096] Data standardization and integration: The server standardizes the collected data, converts it into a unified format, and integrates it. Specifically, the server receives data in different formats (JSON, XML, etc.) and converts it into a standard format (e.g., JSON). The input data is the collected transaction data, and the results of the format conversion and data standardization performed by the server are stored in a database as an integrated data set.

[1097] Step 5:

[1098] Initial setting of the emotion engine: The user performs the initial setting required for the emotion engine of the system to collect emotion data. The user answers a series of questions on the emotion engine's initial setting screen, including stress level, risk tolerance, and emotional state regarding past investments. The input data is the user's answers, which are sent from the terminal to the server and set as the initial parameters of the emotion engine.

[1099] Step 6:

[1100] Data analysis and prediction: The server uses generative AI to predict future asset trends based on the user's trading data and market data. The server inputs the user's trading history and market data into the generative AI model, which then generates a predicted asset trend. The input data is the user's financial trading data and market data, and the output data is the prediction result from the generative AI model. The predicted result is stored in a database.

[1101] Step 7:

[1102] Emotion recognition and adjustment: The device sends the user's emotional data to the server in real time. The server uses an emotion engine to analyze the received emotional data and understand the user's current emotional state. The input data is the emotional information sent from the device, and the server adjusts the dashboard display content and investment advice based on the emotion engine's analysis. The output data is the adjusted investment advice and dashboard display content.

[1103] Step 8:

[1104] Data visualization: The terminal displays the integrated data and prediction results received from the server as graphs and charts. The input data is the analysis results and prediction data sent from the server, and the terminal visualizes the data based on this. Specifically, line graphs, bar graphs, etc. are displayed on the dashboard screen, allowing the user to intuitively understand the asset status.

[1105] Step 9:

[1106] Providing investment advice: The server generates optimal investment advice based on the user's financial situation and emotional data, and the device displays the results. The input data is the user's financial situation and emotional data, which the server analyzes and uses generative AI to create investment advice. The generated investment advice is stored in a database and sent to the device. The device displays the received advice on the dashboard screen.

[1107] (Application example 2)

[1108] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1109] In modern society, it is difficult for individuals to hold multiple financial assets, manage them centrally, and efficiently invest and pay. Collecting and standardizing transaction data, predicting asset trends, and providing investment advice are particularly burdensome. Providing appropriate advice based on users' emotions and spending patterns is even more challenging. Therefore, there is a need for a system that can handle these complex tasks in an integrated and automated manner and provide users with easy-to-understand, useful information.

[1110] The specific processing 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 inputting user information, means for establishing a connection with a financial institution, means for acquiring transaction data from the financial institution, means for integrating and standardizing the acquired data, means for predicting asset trends using generative AI, means for visualizing and displaying the integrated data, means for providing investment advice to the user, means for recognizing the user's emotions, means for adjusting the investment advice based on the emotions, means for recording the user's payment behavior and learning the user's consumption patterns, and means for providing payment advice based on the consumption patterns. This enables the user to centrally manage multiple financial assets and receive efficient asset management and personalized payment advice in real time.

[1111] The "means for inputting user information" is an interface for inputting the user's personal information and authentication information into the system.

[1112] The "means for setting up linkage with financial institutions" refers to the setting means for linking the system with financial institutions such as banks and securities companies.

[1113] "Means for obtaining transaction data from financial institutions" refers to means for automatically obtaining transaction data using a financial institution's API or other methods.

[1114] "Means for integrating and standardizing acquired data" refers to processing means for centralizing transaction data collected from multiple financial institutions and converting it into a unified format.

[1115] "Means of predicting asset trends using generative AI" refers to a means of predicting future asset fluctuations using generative AI based on past trading data and market information.

[1116] The "means for visualizing and displaying integrated data" refers to a means for displaying data converted into a unified format in a visual form such as a graph or chart.

[1117] The "means for providing investment advice to a user" refers to a means for providing optimal investment advice to a user based on predicted asset trends and market information.

[1118] "Means for recognizing user emotions" refers to a means for analyzing and recognizing the user's emotional state from facial expressions, voice, and input data.

[1119] The "means for tailoring investment advice based on emotions" refers to a means for tailoring and personalizing the content of investment advice based on the recognized emotions of a user.

[1120] "Means for recording users' payment behavior and learning consumption patterns" refers to a means for recording users' daily payment data and learning consumption patterns using generative AI.

[1121] The "means for providing payment advice based on consumption patterns" is a means for providing optimal payment methods and saving methods to users based on learned consumption patterns.

[1122] System Overview

[1123] This invention is a system that centrally manages multiple financial assets and payment behaviors held by a user, and uses generative AI and an emotion engine to predict asset trends and provide personalized investment and payment advice. The system has the following functions: input of user information, connection with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using generative AI, emotion recognition, emotion-based investment advice, consumption learning, and payment advice provision.

[1124] Server Operation

[1125] Data collection and integration features

[1126] The server automatically collects user transaction data and payment data through APIs of financial institutions and payment services, using API connection modules and OCR technology.

[1127] Data standardization and integration capabilities

[1128] The server converts the collected data into a standard format and integrates it into a centralized database, using Python data engineering libraries (pandas, numpy) in the process.

[1129] Generative AI prediction function

[1130] The server uses generative AI (TensorFlow, Keras) to predict the user's asset trends and payment patterns based on past trading data and market information.

[1131] Emotion recognition function using emotion engine

[1132] The server collects user emotional data through camera and voice input and analyzes it using an emotion recognition engine (OpenCV, facial expression analysis model).

[1133] Emotion-based personalization

[1134] The server generates investment advice and payment advice according to the user's emotional state based on the emotional data, using a personalization engine.

[1135] Data visualization features

[1136] The server analyzes the integrated data, prediction results, and sentiment data, and generates graphs and charts for visualization. This process uses data visualization libraries (matplotlib, seaborn).

[1137] Device behavior

[1138] The terminal, specifically the user's smartphone, sends the information entered by the user and transaction data to the server, and displays the data, prediction results, and emotion recognition results received from the server on the dashboard screen.

[1139] Specific examples

[1140] If a user has multiple bank accounts and credit cards, they can set up the linking of these financial assets during initial registration. The server automatically collects and standardizes transaction data, and uses generative AI to predict asset trends and payment patterns for the next three months.

[1141] If a user notices that they have spent a lot in a particular week, they can scan the receipt using their smartphone camera. The server extracts the data using OCR technology and analyzes it using generative AI and an emotion engine. As a result, the system identifies the reasons for the excessive spending and suggests specific ways to save money.

[1142] If the emotion engine detects the user's anxiety, it will suggest low-risk investment advice or savings strategies to reduce the user's psychological burden.

[1143] Prompt Sentence Examples

[1144] "Generate next month's spending forecast and savings advice based on May's payment data."

[1145] "We suggest optimal payment methods when users feel unsure."

[1146] In this way, the server and terminal can cooperate to efficiently manage a user's diverse financial assets and payment behavior, and provide personalized investment and payment advice in real time.

[1147] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1148] Step 1:

[1149] User registration and input

[1150] A user creates an account by entering personal information using a smartphone device, including name, email address, password, etc. The entered information is sent from the device to a server and stored in a database.

[1151] Input: User's personal information

[1152] Output: User information stored in the server database

[1153] Step 2:

[1154] Setting up collaboration with financial institutions

[1155] Users input their bank account and credit card information to link the system with financial institutions. The server receives the information sent from the device and connects it to each financial institution's API, making it possible to automatically collect transaction data.

[1156] Input: User's financial institution information

[1157] Output: Financial institution API connection information

[1158] Step 3:

[1159] Automatic collection of transaction data

[1160] The server periodically collects transaction data from financial institutions using the configured API. The data is obtained in JSON format or similar and stored in the server's database.

[1161] Input: Transaction data obtained from financial institution APIs

[1162] Output: Transaction data stored in the server database

[1163] Step 4:

[1164] Data integration and standardization

[1165] The server converts the collected transaction data into a standard format and centrally consolidates it, using data engineering libraries such as pandas and numpy.

[1166] Input: Raw transaction data captured

[1167] Output: Standardized and consolidated transaction data

[1168] Step 5:

[1169] Asset trend prediction using generative AI

[1170] The server uses generative AI (TensorFlow, Keras) to predict future asset trends based on standardized data, using past trading data and market data for learning.

[1171] Input: Standardized and consolidated transaction data

[1172] Output: Predicted asset trend data

[1173] Step 6:

[1174] Emotion recognition

[1175] Users input their facial expressions and voice using the smartphone's camera and microphone. The server analyzes the collected emotional data using an emotion recognition engine (OpenCV, facial expression analysis model) to understand the user's emotional patterns.

[1176] Input: User's facial expression data and voice data

[1177] Output: Parsed emotional state data

[1178] Step 7:

[1179] Personalized investment advice

[1180] The server generates investment advice for the user based on the asset transition data and emotional state data. In this process, a personalization engine is used to provide appropriate advice tailored to the user's emotional state.

[1181] Input: Asset transition data, emotional state data

[1182] Output: Personalized investment advice

[1183] Step 8:

[1184] Recording payment behavior and learning spending patterns

[1185] Users record their daily payment data on their smartphones, and the server collects this data and uses generative AI to learn consumption patterns.

[1186] Input: User payment data

[1187] Output: Learned consumption patterns

[1188] Step 9:

[1189] Providing payment advice

[1190] The server then provides users with optimal payment methods and advice on saving based on their learned consumption patterns, enabling them to effectively manage their consumption.

[1191] Input: Learned consumption patterns

[1192] Output: Personalized payment advice

[1193] Through these steps, users can efficiently manage their assets and consumption and receive personalized advice in real time.

[1194] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1195] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1196] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1197] [Fourth embodiment]

[1198] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1199] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1200] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1201] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1202] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1203] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1204] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1205] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1206] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1207] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1208] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1209] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1210] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1211] System Overview

[1212] This invention is a system that centrally manages multiple financial assets held by a user and provides asset trend forecasts and investment advice using generative AI. This system has the following functions: input of user information, linkage with financial institutions, automatic collection and standardization of transaction data, data visualization, predictions using generative AI, and provision of investment advice.

[1213] User Operation

[1214] When users first access the service, they enter their personal information and create an account. Next, they enter information about each financial asset and provide an API key and authentication information to set up a connection with a financial institution. Users can check their asset status in real time through the dashboard screen. They can also review their own investment strategies based on investment advice provided by generative AI.

[1215] Device behavior

[1216] The device is responsible for sending the information entered by the user to the server. It also displays the integrated data and forecast results received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up the connection, the device transmits that information to the server. The dashboard displays a graph of monthly asset trends and a chart of the portfolio's diversification ratio.

[1217] Server Operation

[1218] The server performs the following main processes based on the information sent by the user.

[1219] 1. Data collection and integration: The server automatically collects transaction data and asset balance information through the financial institution's API. This process is performed periodically to ensure that the latest data is always obtained.

[1220] 2. Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into a single unified format, thereby integrating information on different financial assets.

[1221] 3. Use of generative AI: The server uses generative AI to predict future asset trends based on the user's trading history and market data. For example, it can analyze past stock trading history and predict future price fluctuations.

[1222] 4. Data visualization: The integrated data and forecast results generated on the server are generated as graphs and charts for visualization, allowing users to grasp the increase or decrease in assets and investment risks at a glance.

[1223] 5. Providing investment advice: The server generates optimal investment advice based on the user's financial situation and market trends. For example, if the generative AI recommends the purchase of a specific stock, it will also provide the reasons and risk assessment.

[1224] Specific examples

[1225] Assume a user has multiple bank accounts, stocks, and cryptocurrencies. After the user registers with the system and configures the link settings for each financial asset, the server immediately collects and standardizes all transaction data. The generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard, and the user can adjust their portfolio based on the investment advice.

[1226] In this way, the system of the present invention centrally manages multiple financial assets held by the user, enabling efficient asset management. Users can grasp the trends in their assets in real time and make optimal investment decisions based on the advice of generative AI.

[1227] The processing flow will be explained below.

[1228] Step 1:

[1229] The user enters personal information to create an account, providing information such as name, email address, and password, and then presses the "Register" button. The device then sends this information to the server.

[1230] Step 2:

[1231] The server receives the user information, stores it in a database, generates a user ID and authentication token, and sends a confirmation email to the user to confirm registration.

[1232] Step 3:

[1233] Users enter information about multiple financial assets, such as bank accounts, stocks, and virtual currencies, including API keys and authentication information. Once the information is complete, they press the "Link" button, and the device sends the information to the server.

[1234] Step 4:

[1235] The server connects to each financial institution's API based on the information provided by the user, sends requests to acquire transaction data and balance information, receives responses from the financial institutions, and stores them in a database.

[1236] Step 5:

[1237] The server periodically calls the financial institution's API at automatically scheduled times to collect new transaction data and balance information, ensuring that the latest data is always maintained.

[1238] Step 6:

[1239] The server converts the acquired data into a standard format and integrates it, bringing together data in different formats to organize the user's total asset status.

[1240] Step 7:

[1241] The server uses generative AI to analyze the integrated data and predict asset trends. It estimates future asset fluctuations based on the user's past trading history and market data.

[1242] Step 8:

[1243] The server generates graphs and charts to visualize the data based on the analysis results, allowing users to intuitively understand their asset status.

[1244] Step 9:

[1245] The server provides optimal investment advice to users, proposing specific investment actions and recommending risk management based on the analysis results of the generative AI.

[1246] Step 10:

[1247] The terminal displays the integrated data, forecast results, and investment advice received from the server on a dashboard screen. After logging in, users can check the updated data in real time.

[1248] Step 11:

[1249] Users can view their financial situation and investment advice on the dashboard, and add new financial information as needed. The device then sends the new information back to the server, and the cycle repeats.

[1250] Example 1

[1251] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1252] In conventional asset management systems, the integration and standardization of transaction data obtained from different financial institutions was cumbersome, making it difficult for users to centrally manage all of their assets. In addition, there was a lack of support for users to make optimal investment decisions, as the systems did not adequately predict future asset trends or provide investment advice.

[1253] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1254] In this invention, the server includes means for periodically collecting transaction data and asset information using APIs of financial institutions, means for standardizing the collected data and converting it into a single format, and means for predicting future asset trends from transaction history and market data using generative AI. This allows users to centrally manage assets from multiple financial institutions and receive accurate asset trend predictions and optimal investment advice using generative AI.

[1255] "User information" refers to personal identification information entered by a user when using the system, including name, email address, password, etc.

[1256] "Integration with financial institutions" refers to the connection settings required for the system to send and receive data between the financial institution designated by the user and the system, and is a process that includes providing API keys and authentication information.

[1257] "Transaction data" refers to a user's transaction history and asset balance information obtained from financial institutions.

[1258] "Data standardization" refers to the process of converting data collected in different formats into one unified format.

[1259] A "generative AI model" is an artificial intelligence model used to predict future asset trends based on trading history and market data.

[1260] "Visualization and display" refers to the process of converting the integrated data and prediction results into a visually easy-to-understand format (e.g., graphs and charts) and providing them to users.

[1261] "Investment advice" refers to optimal investment strategies and recommendations provided by generative AI based on the user's financial situation and market trends.

[1262] A "terminal" refers to a device (e.g., a PC or smartphone) that a user uses to input information, and is responsible for sending and receiving data with the server.

[1263] The "server" is the central computer in the system that acquires data from financial institutions, analyzes the data using generative AI, and visualizes it.

[1264] MODE FOR CARRYING OUT THE INVENTION

[1265] This invention is a system that centrally manages multiple financial assets held by a user and provides asset trend forecasts and investment advice using a generative AI model. This system has the following functions: input of user information, collaboration with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using a generative AI model, and provision of investment advice.

[1266] User Operation

[1267] When users first access the service, they enter their personal information to create an account. Next, they enter information about each financial asset and provide API keys and authentication information to set up connections with financial institutions. Users can check their asset status in real time through the dashboard screen. They can also review their own investment strategies based on investment advice provided by the generative AI model.

[1268] Device behavior

[1269] The device sends the information entered by the user to the server. It also displays the integrated data and forecast results received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up the connection, the device transmits that information to the server. The dashboard displays a graph of monthly asset trends and a chart of the portfolio's diversification ratio.

[1270] Server Operation

[1271] The server performs the following main processes based on the information sent by the user.

[1272] Data collection and integration:

[1273] The server automatically collects transaction data and asset balance information through the financial institution's API. This process is performed periodically to ensure the latest data is always obtained. For example, calling a bank's API to obtain the latest account balance.

[1274] Data standardization and integration:

[1275] The collected data is provided in different formats, so the server standardizes it and converts it into a single unified format, integrating information on different financial assets. For example, bank balance information and stock trading history are converted into the same format.

[1276] Use of generative AI models:

[1277] The server uses the generative AI model to predict future asset trends based on the user's trading history and market data. For example, it analyzes past stock trading history to predict future price fluctuations.

[1278] Data visualization:

[1279] The server generates the integrated data and forecast results as graphs and charts for visualization, allowing users to grasp the increase or decrease in assets and investment risk at a glance. For example, the portfolio diversification rate can be displayed as a pie chart.

[1280] Providing investment advice:

[1281] The server generates optimal investment advice based on the user's financial situation and market trends. For example, when the generative AI model recommends the purchase of a particular stock, it also presents the reason and risk assessment.

[1282] Specific examples

[1283] Assume a user has multiple bank accounts, stocks, and cryptocurrencies. After the user registers with the system and configures the connections for each financial asset, the server immediately collects and standardizes all transaction data. A generative AI model then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard, allowing users to adjust their portfolios based on investment advice.

[1284] For example, use the following as your prompt:

[1285] "Please predict my asset trends for the next three months based on stock trading data from the past year. Also, please provide optimal investment advice along with a risk assessment."

[1286] In this way, the system of the present invention centrally manages multiple financial assets held by the user, enabling efficient asset management. Users can grasp the trends in their assets in real time and make optimal investment decisions based on the advice of the generated AI model.

[1287] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1288] Step 1: User registration and initial setup

[1289] Input: A user enters their name, email address, and password into a web form.

[1290] Data processing: The terminal sends the entered information to the server, which registers the information in a database.

[1291] Output: An account is created for the user and credentials are generated.

[1292] What it does: When a user submits a form, the device sends the information to the server, which adds the new user to its database. Once registration is complete, authentication information is generated and a confirmation email is sent to the user.

[1293] Step 2: Setting up a connection with your financial institution

[1294] Input: The user enters the API key and authentication information to set up the connection with the financial institution.

[1295] Data processing: The terminal sends the entered authentication information to the server, which stores it. The server also calls the financial institution's API to initialize the connection.

[1296] Output: The integration is now set up and ready to retrieve transaction data from financial institutions.

[1297] How it works: When a user enters their authentication information and presses the link button, the device sends that information to the server, which then calls the financial institution's API to establish the link and securely stores the authentication information.

[1298] Step 3: Collect and link transaction data

[1299] Input: The server periodically calls the financial institution's API.

[1300] Data processing: The server obtains transaction data and asset balance information from financial institutions and standardizes it into the data format of the centralized management system.

[1301] Output: Centralized transaction data and asset balance information.

[1302] How it works: The server calls the API on a scheduled basis, normalizes the data it receives, converts it into a unified format, and stores it in a database.

[1303] Step 4: Data analysis and predictions using generative AI models

[1304] Input: Normalized transaction data and asset balance information.

[1305] Data processing: The server analyzes the data using a generative AI model to predict asset trends. Specifically, it simulates future price fluctuations and asset increases and decreases based on past data.

[1306] Output: Forecast data of future asset trends.

[1307] How it works: The server inputs data into a generative AI model, which then uses that data to predict future asset trends, such as stock price fluctuations over the next three months.

[1308] Step 5: Visualize the data and create a dashboard

[1309] Inputs: Forecast data and consolidated transaction data.

[1310] Data processing: The server generates graphs and charts to visualize the data and displays them in the form of a dashboard.

[1311] Output: Visualized data (graphs, charts, etc.) displayed on a dashboard screen.

[1312] How it works: The server converts forecast data and trading data into graphs and charts and sends them to the terminal, which then displays them on the dashboard screen, allowing users to check their asset status in real time.

[1313] Step 6: Providing investment advice

[1314] Input: Forecast data and user asset status data.

[1315] Data processing: The server uses a generative AI model to analyze the user's asset status and market trends, and generates optimal investment advice.

[1316] Output: Investment advice and risk assessment.

[1317] How it works: The server uses the generative AI model to generate investment advice based on the analysis results and sends it to the device, which then displays it on a dashboard for immediate user confirmation.

[1318] In this way, the system of the present invention centrally manages multiple financial assets held by a user through multiple processing steps, thereby realizing efficient asset management.

[1319] (Application example 1)

[1320] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1321] Existing financial asset management systems have difficulty integrating and standardizing a wide variety of data in different formats, requiring users to perform tedious tasks to centrally manage multiple financial institutions and asset information. Furthermore, specialized knowledge is required to make investment decisions, and there is a need for systems that utilize generative AI to provide investment advice in real time. Furthermore, electronic payment services lack functionality for the integrated management of various payment methods and financial assets, creating a need for systems that can help users understand their asset status in real time and develop optimal investment strategies.

[1322] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1323] In this invention, the server includes means for inputting user information, means for setting up a connection with a financial institution, means for acquiring transaction data from the financial institution, means for integrating and standardizing the acquired data, means for predicting asset trends using generative AI, means for visualizing and displaying the integrated data, means for providing investment advice to the user, means for centrally managing multiple financial assets in the electronic payment service, and means for predicting asset trends from transaction data using generative AI and providing investment advice in real time. This allows users to centrally manage multiple financial assets and instantly receive investment advice from the generative AI, thereby realizing efficient and intelligent asset management and investment decisions.

[1324] "User information" refers to data such as personal information and authentication information entered by system users.

[1325] A "financial institution" is an institution that provides financial services, such as a bank, securities company, or credit card company.

[1326] "Linkage settings" refers to the procedure for setting up a user to exchange data with a financial institution.

[1327] "Transaction data" refers to data such as deposit transactions, payment history, and investment transactions obtained from financial institutions.

[1328] "Integration" is the process of combining data provided in different formats into one standard format.

[1329] "Standardization" is the process of converting integrated data into a single, unified format.

[1330] "Generative AI" is artificial intelligence that uses machine learning and deep learning technologies to analyze data and generate future predictions and advice.

[1331] "Asset trend forecasting" refers to predicting future asset fluctuations based on collected trading data and market data.

[1332] "Visualization" refers to the display of data and prediction results in a visual format such as a graph or chart.

[1333] "Investment advice" is information that suggests how and in which assets to invest based on the user's asset status and market trends.

[1334] "Electronic payment services" are financial transaction services conducted over the Internet or mobile devices.

[1335] "Centralized management" refers to consolidating and managing multiple financial assets and data in one place.

[1336] "Real-time" refers to data processing and information provision occurring immediately.

[1337] System Overview

[1338] This invention is a system that centrally manages multiple financial assets held by a user and provides asset trend forecasts and investment advice using generative AI. This system is provided to users primarily via a smartphone app and has the following functions: input of user information, linkage with financial institutions, automatic collection and standardization of transaction data, data visualization, predictions using generative AI, and provision of investment advice.

[1339] User Operation

[1340] When users first access the service, they enter their personal information and create an account. Next, they enter information about their financial assets and provide API keys and authentication information to set up connections with financial institutions. Users can check their asset status in real time through the dashboard screen. They can also review their own investment strategies based on investment advice provided by generative AI.

[1341] Device behavior

[1342] The device is responsible for sending the information entered by the user to the server. It also displays the integrated data and forecast results received from the server on the dashboard screen. For example, when a user enters bank account and credit card information and sets up the connection, the device transmits that information to the server. The dashboard displays a graph of monthly asset trends and a chart of the portfolio's diversification ratio.

[1343] Server Operation

[1344] The server performs the following main processes based on the information sent by the user.

[1345] 1. Data collection and integration: The server automatically collects transaction data and asset balance information through the financial institution's API. This process is performed periodically to ensure that the latest data is always obtained.

[1346] 2. Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into a single unified format, thereby integrating information on different financial assets.

[1347] 3. Use of generative AI: The server uses generative AI to predict future asset trends based on the user's trading history and market data. For example, it can analyze past trading history and predict future price fluctuations.

[1348] 4. Data visualization: The integrated data and forecast results generated on the server are generated as graphs and charts for visualization, allowing users to grasp the increase or decrease in assets and investment risks at a glance.

[1349] 5. Providing investment advice: The server generates optimal investment advice based on the user's financial situation and market trends. For example, if the generative AI recommends the purchase of a specific stock, it will also provide the reasons and risk assessment.

[1350] Specific examples

[1351] Assume a user has multiple bank accounts, credit cards, and cryptocurrencies. After the user registers with the system and configures the linkage settings for each financial asset, the server immediately collects and standardizes all transaction data. The generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard, and the user can adjust their portfolio based on the investment advice.

[1352] This system centralizes the management of multiple financial assets held by users, enabling efficient asset management. Users can grasp the progress of their assets in real time and make optimal investment decisions based on advice from generative AI.

[1353] Example prompts to input to a generative AI model:

[1354] Data: Bank Account A, Date: 2023-01-01, Amount: -1000.50, Category: Food

[1355] Data: Credit Card B, Date: 2023-01-02, Amount: -200.75, Category: Transportation Expenses

[1356] This gives users a powerful tool to efficiently manage their assets and make investment decisions.

[1357] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1358] Step 1:

[1359] Users launch the smartphone app, enter their personal information, and create an account.

[1360] Input: User information (name, email address, password, etc.)

[1361] Process: The information entered by the user is sent to the server and a new account is created.

[1362] Output: Account creation completion email, notification, login information

[1363] Step 2:

[1364] The user sets up collaboration with each financial institution and inputs information about their financial assets.

[1365] Input: Financial institution information (bank account, credit card information, API key, etc.)

[1366] Processing: The terminal uses the financial institution's API to transmit the user's authentication information to the server and establishes a connection with the financial institution.

[1367] Output: Notification of completion of link with financial institution

[1368] Step 3:

[1369] The server automatically collects transaction data from financial institutions with which it has set up ties.

[1370] Input: Financial institution information (bank account, credit card information, etc.)

[1371] Processing: The server periodically calls the API to obtain transaction data from the financial institution.

[1372] Output: Transaction data (transaction history)

[1373] Step 4:

[1374] The server standardizes the collected transaction data and converts and integrates it into a single unified format.

[1375] Input: Transaction data (transaction history in various formats)

[1376] Processing: The server parses the transaction data and converts it into a standard format (e.g., date, amount, category, etc.).

[1377] Output: Normalized transaction data

[1378] Step 5:

[1379] The server sends the standardized data to the generative AI, which then predicts asset trends.

[1380] Input: Normalized transaction data

[1381] Processing: The server sends the data to the generative AI, which predicts future asset trends based on past trading data and market data.

[1382] Output: Asset forecast data (e.g., asset forecast for the next three months)

[1383] Step 6:

[1384] The server visualizes the asset trend prediction results from the generative AI and displays them on a dashboard.

[1385] Input: Asset transition forecast data

[1386] Processing: The server converts the prediction results into graphs and charts and displays them visually on a dashboard screen.

[1387] Output: Visualized asset trend graph and portfolio diversification ratio chart

[1388] Step 7:

[1389] The server uses generative AI to generate investment advice suited to the user and provides it in real time.

[1390] Input: Asset transition forecast data, user asset status

[1391] Processing: The server generates an optimal investment strategy based on generative AI and presents it to the user, along with the reasons and risk assessment.

[1392] Output: Investment advice information (e.g., recommendations to buy or sell specific financial assets)

[1393] Step 8:

[1394] Users can check the status of their assets and investment advice from generative AI through the dashboard and adjust their portfolios.

[1395] Input: visualized data and investment advice

[1396] Action: User reviews the dashboard and revises investment strategy based on the information provided.

[1397] Output: User's investment strategy (e.g., selection of new investments and portfolio rebalancing)

[1398] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1399] System Overview

[1400] This invention is a system that centrally manages multiple financial assets held by a user and uses generative AI to predict asset trends and provide investment advice. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide personalized investment advice based on emotions. This system has the following functions: input of user information, linkage with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using generative AI, emotion recognition, and provision of emotion-based investment advice.

[1401] User Operation

[1402] When users first access the service, they enter their personal information and create an account. Next, they set up a connection with a financial institution and enter information about each of their financial assets. Next, they perform initial setup so that the emotion engine can recognize the user's emotions. Through the dashboard screen, users can check their asset status in real time and receive optimal investment advice based on their emotions.

[1403] Device behavior

[1404] The device is responsible for sending the information entered by the user to the server. It also displays the data, prediction results, and emotion-based investment advice received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up connectivity, the device transmits that information to the server. At the same time, the emotion engine recognizes the user's emotions in real time and reflects them on the dashboard.

[1405] Server Operation

[1406] The server performs the following main processes based on the information sent by the user.

[1407] 1. Data collection and integration: The server automatically collects transaction data and balance information through the financial institution's API, ensuring that the latest data is always available.

[1408] 2. Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into a single unified format, integrating information on different financial assets.

[1409] 3. Use of generative AI: The server uses generative AI to predict future asset trends based on the user's trading history and market data. For example, it can analyze past stock trading history and predict future price fluctuations.

[1410] 4. Using the emotion engine: The server uses the emotion engine to collect the user's emotion data, which allows it to understand the user's current emotional state.

[1411] 5. Emotion-based adjustment: The server adjusts the dashboard display and investment advice based on the user's emotions recognized by the emotion engine. If the user is feeling anxious, the server personalizes the advice to match their emotions, such as displaying low-risk investment suggestions.

[1412] 6. Data visualization: The server generates integrated data, prediction results, and sentiment data as graphs and charts for visualization, allowing users to intuitively understand their asset status.

[1413] 7. Providing investment advice: The server generates optimal investment advice based on the user's financial situation and emotional data. For example, when the generative AI recommends the purchase of a particular stock, it provides advice that takes into account the user's emotions in addition to the reasons and risk assessment.

[1414] Specific examples

[1415] Assume that a user holds multiple bank accounts, stocks, and cryptocurrencies. When the user initially registers with the system and configures the link settings for each financial asset, the server immediately collects and standardizes all transaction data. The generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard. Furthermore, if the user's emotions are unstable, personalization based on emotions is performed, such as suggesting low-risk investment ideas.

[1416] In this way, the system of the present invention centrally manages multiple financial assets held by a user, enabling efficient asset management. Users can grasp asset trends in real time and make optimal investment decisions based on advice from generative AI. In addition, the introduction of an emotion engine allows users to receive personalized investment advice tailored to their emotions.

[1417] The processing flow will be explained below.

[1418] Step 1:

[1419] The user enters personal information to create an account, providing information such as name, email address, and password, and then presses the "Register" button. The device then sends this information to the server.

[1420] Step 2:

[1421] The server receives the user information, stores it in a database, generates a user ID and authentication token, and sends a confirmation email to the user to confirm registration.

[1422] Step 3:

[1423] Users enter information about multiple financial assets, such as bank accounts, stocks, and virtual currencies, including API keys and authentication information. Once the information is complete, they press the "Link" button, and the device sends the information to the server.

[1424] Step 4:

[1425] The server connects to each financial institution's API based on the information provided by the user, sends requests to acquire transaction data and balance information, receives responses from the financial institutions, and stores them in a database.

[1426] Step 5:

[1427] The server periodically calls the financial institution's API at automatically scheduled times to collect new transaction data and balance information, ensuring that the latest data is always maintained.

[1428] Step 6:

[1429] The server converts the acquired data into a standard format and integrates it, bringing together data in different formats to organize the user's total asset status.

[1430] Step 7:

[1431] The server uses generative AI to analyze the integrated data and predict asset trends. It estimates future asset fluctuations based on the user's past trading history and market data.

[1432] Step 8:

[1433] The server uses an emotion engine to collect user emotion data, analyze the user's facial expressions and input information in real time, and evaluate the user's emotional state.

[1434] Step 9:

[1435] The server adjusts the dashboard display and investment advice based on the user's emotions recognized by the emotion engine. For example, if the user is feeling anxious, it will prioritize displaying low-risk investment ideas and information that will give them a sense of security.

[1436] Step 10:

[1437] The server combines the analysis results of the generative AI and the evaluation results of the emotion engine to generate optimal investment advice, suggesting specific investment actions and recommending risk management.

[1438] Step 11:

[1439] The terminal receives integrated data, forecast results, and sentiment-based investment advice from the server and displays them on a dashboard screen. After logging in, users can view updated data in real time.

[1440] Step 12:

[1441] Users can view their asset status and investment advice on the dashboard, add new financial asset information as needed, and consider investment behavior based on their emotions. The device then sends the new information back to the server, and the cycle repeats.

[1442] Example 2

[1443] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1444] Conventional financial asset management systems lack the functionality to unify the management of multiple financial assets held by users, and integrating and standardizing data provided by different financial institutions is time-consuming. Furthermore, it is difficult to provide personalized investment advice that takes into account the user's emotions and individual circumstances. This makes it difficult for users to grasp the current state of their assets and make effective investment decisions.

[1445] The identification process by the identification 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 inputting user information, means for setting up a link with a financial institution, means for acquiring transaction data from the financial institution, means for integrating and standardizing the acquired data, means for predicting asset trends using generative artificial intelligence, means for visualizing and displaying the integrated data, means for collecting user emotion data, means for adjusting investment advice based on the emotion data, and means for providing personalized investment advice to the user. This makes it possible to centrally manage multiple financial assets held by a user and provide personalized investment advice based on emotions.

[1446] "User information" refers to personal information and information related to financial assets held by a user that the user inputs into the system.

[1447] "Collaboration with financial institutions" refers to a mechanism in which the system connects with various financial institutions via API in order to collect users' financial asset data.

[1448] "Transaction data" refers to data including the transaction history and balance information of a user at a financial institution.

[1449] "Data integration" is the process of converting and centralizing data collected from different financial institutions into a single unified format.

[1450] "Standardization" is the process of standardizing collected data into a predetermined format and arranging it in a form that is easy to analyze.

[1451] "Generative AI" is an AI technology used to analyze past data and predict future outcomes.

[1452] "Asset trend prediction" refers to using generative artificial intelligence to predict future fluctuations in a user's financial assets.

[1453] "Data visualization" refers to the display of integrated data and prediction results in visual formats such as graphs and charts.

[1454] "Emotion data" refers to data that indicates the user's emotional state and is collected by the emotion engine.

[1455] An "emotion engine" is a technology for recognizing a user's emotions and collecting that data.

[1456] "Personalized investment advice" is investment advice that is customized to take into account a user's individual circumstances and emotional state.

[1457] System Overview

[1458] This invention is a system that centrally manages multiple financial assets held by a user and uses generative artificial intelligence to predict asset trends and provide investment advice. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide personalized investment advice based on emotions. This system has the following functions: input of user information, collaboration with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using generative artificial intelligence, emotion recognition, and provision of emotion-based investment advice.

[1459] User Operation

[1460] When users first access the service, they enter their personal information and create an account. Next, they set up a connection with a financial institution and enter information about each of their financial assets. Next, they perform initial setup so that the emotion engine can recognize the user's emotions. Through the dashboard screen, users can check their asset status in real time and receive optimal investment advice based on their emotions.

[1461] Device behavior

[1462] The device is responsible for sending the information entered by the user to the server. It also displays the data, prediction results, and emotion-based investment advice received from the server on the dashboard screen. For example, when a user enters bank account and stock information and sets up connectivity, the device transmits that information to the server. At the same time, the emotion engine recognizes the user's emotions in real time and reflects them on the dashboard.

[1463] Server Operation

[1464] The server performs the following main processes based on the information sent by the user.

[1465] Data collection and integration: The server automatically collects transaction data and balance information through the financial institution's API, ensuring that the latest data is always available.

[1466] Data standardization and integration: As the collected data is provided in different formats, the server standardizes it and converts it into one unified format. Information on different financial assets is integrated.

[1467] Use of generative artificial intelligence: The server uses generative artificial intelligence to predict future asset trends based on the user's trading history and market data. For example, it can analyze past stock trading history and predict future price fluctuations.

[1468] Use of emotion engine: The server uses the emotion engine to collect the user's emotion data, which allows it to understand the user's current emotional state.

[1469] Emotion-based adjustment: The server adjusts the dashboard display and investment advice based on the user's emotions recognized by the emotion engine. If the user is feeling anxious, the server personalizes the content and advice based on the user's emotions, for example, by displaying investment suggestions with low risk.

[1470] Data visualization: The server generates integrated data, prediction results, and sentiment data as graphs and charts for visualization, allowing users to intuitively understand their asset status.

[1471] Providing investment advice: The server generates optimal investment advice based on the user's financial situation and emotional data. For example, when the generative AI recommends the purchase of a particular stock, it provides advice that takes into account the user's emotions in addition to the reasons and risk assessment.

[1472] Specific examples

[1473] Assume that a user holds multiple bank accounts, stocks, and cryptocurrencies. When the user initially registers with the system and configures the link settings for each financial asset, the server immediately collects and standardizes all transaction data. Generative AI then analyzes this data and predicts asset trends for the next three months. The prediction results are visually displayed on a dashboard. Furthermore, if the user's emotions are unstable, the system personalizes the system based on their emotions, suggesting low-risk investment ideas.

[1474] Prompt Sentence Examples

[1475] 1. "Enter the user's bank account information, stock information, and cryptocurrency information and send it to the server."

[1476] 2. The server connects to the financial institution's API and periodically collects transaction data.

[1477] 3. "The server uses generative artificial intelligence to predict asset trends for the next three months."

[1478] 4. "Recognize users' sentiment data in real time and provide sentiment-based investment advice."

[1479] As described above, the system of the present invention centrally manages multiple financial assets held by a user, enabling efficient asset management. Users can grasp asset trends in real time and make optimal investment decisions based on advice from generative AI. Furthermore, by incorporating an emotion engine, users can receive personalized investment advice tailored to their emotions.

[1480] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1481] Step 1:

[1482] User performs initial registration: The user enters personal information and financial asset information to create an account in the system. Specifically, the user enters the required information in the account creation form and presses the submit button. The input data includes name, email address, password, and detailed information about financial assets (bank accounts, stocks, virtual currencies, etc.). This information is sent from the device to the server. The server stores the received information in a database.

[1483] Step 2:

[1484] Setting up integration with financial institutions: The user sets up API integration with each financial institution. This setup involves entering the financial institution's API key and authentication information to establish integration with the system. The API key and authentication information entered by the user are sent from the device to the server, which uses this information to connect with the financial institution and complete the necessary authentication process. If authentication is successful, the server saves the integration setting information in its database.

[1485] Step 3:

[1486] Collection of transaction data: The server automatically collects user transaction data and balance information through the financial institution's API. This process is performed periodically. For example, the server retrieves data from the API using a periodic task scheduler. The input data is the transaction history and balance information provided by the financial institution, and the server saves the received data in temporary storage. It is then stored in a database.

[1487] Step 4:

[1488] Data standardization and integration: The server standardizes the collected data, converts it into a unified format, and integrates it. Specifically, the server receives data in different formats (JSON, XML, etc.) and converts it into a standard format (e.g., JSON). The input data is the collected transaction data, and the results of the format conversion and data standardization performed by the server are stored in a database as an integrated data set.

[1489] Step 5:

[1490] Initial setting of the emotion engine: The user performs the initial setting required for the emotion engine of the system to collect emotion data. The user answers a series of questions on the emotion engine's initial setting screen, including stress level, risk tolerance, and emotional state regarding past investments. The input data is the user's answers, which are sent from the terminal to the server and set as the initial parameters of the emotion engine.

[1491] Step 6:

[1492] Data analysis and prediction: The server uses generative AI to predict future asset trends based on the user's trading data and market data. The server inputs the user's trading history and market data into the generative AI model, which then generates a predicted asset trend. The input data is the user's financial trading data and market data, and the output data is the prediction result from the generative AI model. The predicted result is stored in a database.

[1493] Step 7:

[1494] Emotion recognition and adjustment: The device sends the user's emotional data to the server in real time. The server uses an emotion engine to analyze the received emotional data and understand the user's current emotional state. The input data is the emotional information sent from the device, and the server adjusts the dashboard display content and investment advice based on the emotion engine's analysis. The output data is the adjusted investment advice and dashboard display content.

[1495] Step 8:

[1496] Data visualization: The terminal displays the integrated data and prediction results received from the server as graphs and charts. The input data is the analysis results and prediction data sent from the server, and the terminal visualizes the data based on this. Specifically, line graphs, bar graphs, etc. are displayed on the dashboard screen, allowing the user to intuitively understand the asset status.

[1497] Step 9:

[1498] Providing investment advice: The server generates optimal investment advice based on the user's financial situation and emotional data, and the device displays the results. The input data is the user's financial situation and emotional data, which the server analyzes and uses generative AI to create investment advice. The generated investment advice is stored in a database and sent to the device. The device displays the received advice on the dashboard screen.

[1499] (Application example 2)

[1500] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1501] In modern society, it is difficult for individuals to hold multiple financial assets, manage them centrally, and efficiently invest and pay. Collecting and standardizing transaction data, predicting asset trends, and providing investment advice are particularly burdensome. Providing appropriate advice based on users' emotions and spending patterns is even more challenging. Therefore, there is a need for a system that can handle these complex tasks in an integrated and automated manner and provide users with easy-to-understand, useful information.

[1502] The specific processing 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 inputting user information, means for establishing a connection with a financial institution, means for acquiring transaction data from the financial institution, means for integrating and standardizing the acquired data, means for predicting asset trends using generative AI, means for visualizing and displaying the integrated data, means for providing investment advice to the user, means for recognizing the user's emotions, means for adjusting the investment advice based on the emotions, means for recording the user's payment behavior and learning the user's consumption patterns, and means for providing payment advice based on the consumption patterns. This enables the user to centrally manage multiple financial assets and receive efficient asset management and personalized payment advice in real time.

[1503] The "means for inputting user information" is an interface for inputting the user's personal information and authentication information into the system.

[1504] The "means for setting up linkage with financial institutions" refers to the setting means for linking the system with financial institutions such as banks and securities companies.

[1505] "Means for obtaining transaction data from financial institutions" refers to means for automatically obtaining transaction data using a financial institution's API or other methods.

[1506] "Means for integrating and standardizing acquired data" refers to processing means for centralizing transaction data collected from multiple financial institutions and converting it into a unified format.

[1507] "Means of predicting asset trends using generative AI" refers to a means of predicting future asset fluctuations using generative AI based on past trading data and market information.

[1508] The "means for visualizing and displaying integrated data" refers to a means for displaying data converted into a unified format in a visual form such as a graph or chart.

[1509] The "means for providing investment advice to a user" refers to a means for providing optimal investment advice to a user based on predicted asset trends and market information.

[1510] "Means for recognizing user emotions" refers to a means for analyzing and recognizing the user's emotional state from facial expressions, voice, and input data.

[1511] The "means for tailoring investment advice based on emotions" refers to a means for tailoring and personalizing the content of investment advice based on the recognized emotions of a user.

[1512] "Means for recording users' payment behavior and learning consumption patterns" refers to a means for recording users' daily payment data and learning consumption patterns using generative AI.

[1513] The "means for providing payment advice based on consumption patterns" is a means for providing optimal payment methods and saving methods to users based on learned consumption patterns.

[1514] System Overview

[1515] This invention is a system that centrally manages multiple financial assets and payment behaviors held by a user, and uses generative AI and an emotion engine to predict asset trends and provide personalized investment and payment advice. The system has the following functions: input of user information, connection with financial institutions, automatic collection and standardization of transaction data, data visualization, prediction using generative AI, emotion recognition, emotion-based investment advice, consumption learning, and payment advice provision.

[1516] Server Operation

[1517] Data collection and integration features

[1518] The server automatically collects user transaction data and payment data through APIs of financial institutions and payment services, using API connection modules and OCR technology.

[1519] Data standardization and integration capabilities

[1520] The server converts the collected data into a standard format and integrates it into a centralized database, using Python data engineering libraries (pandas, numpy) in the process.

[1521] Generative AI prediction function

[1522] The server uses generative AI (TensorFlow, Keras) to predict the user's asset trends and payment patterns based on past trading data and market information.

[1523] Emotion recognition function using emotion engine

[1524] The server collects user emotional data through camera and voice input and analyzes it using an emotion recognition engine (OpenCV, facial expression analysis model).

[1525] Emotion-based personalization

[1526] The server generates investment advice and payment advice according to the user's emotional state based on the emotional data, using a personalization engine.

[1527] Data visualization features

[1528] The server analyzes the integrated data, prediction results, and sentiment data, and generates graphs and charts for visualization. This process uses data visualization libraries (matplotlib, seaborn).

[1529] Device behavior

[1530] The terminal, specifically the user's smartphone, sends the information entered by the user and transaction data to the server, and displays the data, prediction results, and emotion recognition results received from the server on the dashboard screen.

[1531] Specific examples

[1532] If a user has multiple bank accounts and credit cards, they can set up the linking of these financial assets during initial registration. The server automatically collects and standardizes transaction data, and uses generative AI to predict asset trends and payment patterns for the next three months.

[1533] If a user notices that they have spent a lot in a particular week, they can scan the receipt using their smartphone camera. The server extracts the data using OCR technology and analyzes it using generative AI and an emotion engine. As a result, the system identifies the reasons for the excessive spending and suggests specific ways to save money.

[1534] If the emotion engine detects the user's anxiety, it will suggest low-risk investment advice or savings strategies to reduce the user's psychological burden.

[1535] Prompt Sentence Examples

[1536] "Generate next month's spending forecast and savings advice based on May's payment data."

[1537] "We suggest optimal payment methods when users feel unsure."

[1538] In this way, the server and terminal can cooperate to efficiently manage a user's diverse financial assets and payment behavior, and provide personalized investment and payment advice in real time.

[1539] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1540] Step 1:

[1541] User registration and input

[1542] A user creates an account by entering personal information using a smartphone device, including name, email address, password, etc. The entered information is sent from the device to a server and stored in a database.

[1543] Input: User's personal information

[1544] Output: User information stored in the server database

[1545] Step 2:

[1546] Setting up collaboration with financial institutions

[1547] Users input their bank account and credit card information to link the system with financial institutions. The server receives the information sent from the device and connects it to each financial institution's API, making it possible to automatically collect transaction data.

[1548] Input: User's financial institution information

[1549] Output: Financial institution API connection information

[1550] Step 3:

[1551] Automatic collection of transaction data

[1552] The server periodically collects transaction data from financial institutions using the configured API. The data is obtained in JSON format or similar and stored in the server's database.

[1553] Input: Transaction data obtained from financial institution APIs

[1554] Output: Transaction data stored in the server database

[1555] Step 4:

[1556] Data integration and standardization

[1557] The server converts the collected transaction data into a standard format and centrally consolidates it, using data engineering libraries such as pandas and numpy.

[1558] Input: Raw transaction data captured

[1559] Output: Standardized and consolidated transaction data

[1560] Step 5:

[1561] Asset trend prediction using generative AI

[1562] The server uses generative AI (TensorFlow, Keras) to predict future asset trends based on standardized data, using past trading data and market data for learning.

[1563] Input: Standardized and consolidated transaction data

[1564] Output: Predicted asset trend data

[1565] Step 6:

[1566] Emotion recognition

[1567] Users input their facial expressions and voice using the smartphone's camera and microphone. The server analyzes the collected emotional data using an emotion recognition engine (OpenCV, facial expression analysis model) to understand the user's emotional patterns.

[1568] Input: User's facial expression data and voice data

[1569] Output: Parsed emotional state data

[1570] Step 7:

[1571] Personalized investment advice

[1572] The server generates investment advice for the user based on the asset transition data and emotional state data. In this process, a personalization engine is used to provide appropriate advice tailored to the user's emotional state.

[1573] Input: Asset transition data, emotional state data

[1574] Output: Personalized investment advice

[1575] Step 8:

[1576] Recording payment behavior and learning spending patterns

[1577] Users record their daily payment data on their smartphones, and the server collects this data and uses generative AI to learn consumption patterns.

[1578] Input: User payment data

[1579] Output: Learned consumption patterns

[1580] Step 9:

[1581] Providing payment advice

[1582] The server then provides users with optimal payment methods and advice on saving based on their learned consumption patterns, enabling them to effectively manage their consumption.

[1583] Input: Learned consumption patterns

[1584] Output: Personalized payment advice

[1585] Through these steps, users can efficiently manage their assets and consumption and receive personalized advice in real time.

[1586] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1587] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1588] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1589] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1590] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1591] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1592] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1593] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1594] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1595] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1596] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1597] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1598] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1599] 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.

[1600] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1601] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1602] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1603] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1604] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1605] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1606] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1607] The following is further disclosed regarding the above embodiment.

[1608] (Claim 1)

[1609] means for inputting user information;

[1610] means for setting up collaboration with financial institutions;

[1611] a means for obtaining transaction data from financial institutions;

[1612] a means to integrate and standardize the data obtained;

[1613] A means of predicting asset trends using generative AI,

[1614] a means for visualizing and displaying the integrated data;

[1615] means for providing investment advice to users;

[1616] A system including:

[1617] (Claim 2)

[1618] 10. The system of claim 1, further comprising means for automatically obtaining transaction data from financial institutions on a periodic basis.

[1619] (Claim 3)

[1620] 10. The system of claim 1, further comprising means for generating and authenticating user authentication information.

[1621] "Example 1"

[1622] (Claim 1)

[1623] means for inputting user information;

[1624] means for setting up collaboration with financial institutions;

[1625] a means for obtaining transaction data from financial institutions;

[1626] a means to integrate and standardize the data obtained;

[1627] A means of forecasting asset trends using generative AI models;

[1628] a means for visualizing and displaying the integrated data;

[1629] means for providing investment advice to users;

[1630] A means for transmitting input information from the terminal to a server and receiving integrated data and prediction results from the server;

[1631] The server periodically collects transaction data and asset information using the financial institution's API,

[1632] A means by which the server standardizes and converts the collected data into a single format;

[1633] A method to predict future asset trends based on trading history and market data using generative AI,

[1634] A means to convert the generated data and prediction results into graphs and charts for display;

[1635] A system including:

[1636] (Claim 2)

[1637] 10. The system of claim 1, further comprising means for automatically obtaining transaction data from financial institutions on a periodic basis.

[1638] (Claim 3)

[1639] 10. The system of claim 1, further comprising means for generating and authenticating user authentication information.

[1640] "Application Example 1"

[1641] (Claim 1)

[1642] means for inputting user information;

[1643] means for setting up collaboration with financial institutions;

[1644] a means for obtaining transaction data from financial institutions;

[1645] a means to integrate and standardize the data obtained;

[1646] A means of predicting asset trends using generative AI,

[1647] a means for visualizing and displaying the integrated data;

[1648] means for providing investment advice to users;

[1649] A means for centrally managing multiple financial assets in electronic payment services;

[1650] A means to use generative AI to predict asset trends from trading data and provide investment advice in real time,

[1651] A system including:

[1652] (Claim 2)

[1653] 10. The system of claim 1, further comprising means for automatically obtaining transaction data from financial institutions on a periodic basis.

[1654] (Claim 3)

[1655] 10. The system of claim 1, further comprising means for generating and authenticating user authentication information.

[1656] "Example 2: Combining Emotion Engines"

[1657] (Claim 1)

[1658] means for inputting user information;

[1659] means for setting up collaboration with financial institutions;

[1660] a means for obtaining transaction data from financial institutions;

[1661] a means to integrate and standardize the data obtained;

[1662] A means for predicting asset trends using generative artificial intelligence;

[1663] a means for visualizing and displaying the integrated data;

[1664] means for collecting user emotion data;

[1665] a means for adjusting investment advice based on sentiment data;

[1666] means for providing personalized investment advice to users;

[1667] A system including:

[1668] (Claim 2)

[1669] 10. The system of claim 1, further comprising means for automatically obtaining transaction data from financial institutions on a periodic basis.

[1670] (Claim 3)

[1671] 10. The system of claim 1, further comprising means for generating and authenticating user authentication information.

[1672] "Application example 2 when combining emotion engines"

[1673] (Claim 1)

[1674] means for inputting user information;

[1675] means for setting up collaboration with financial institutions;

[1676] a means for obtaining transaction data from financial institutions;

[1677] a means to integrate and standardize the data obtained;

[1678] A means of predicting asset trends using generative AI,

[1679] a means for visualizing and displaying the integrated data;

[1680] means for providing investment advice to users;

[1681] means for recognizing a user's emotion;

[1682] a means of adjusting investment advice based on emotions;

[1683] means for recording user payment behavior and learning consumption patterns;

[1684] a means for providing payment advice based on spending patterns;

[1685] A system including:

[1686] (Claim 2)

[1687] 10. The system of claim 1, further comprising means for automatically obtaining transaction data from financial institutions on a periodic basis.

[1688] (Claim 3)

[1689] 10. The system of claim 1, further comprising means for generating and authenticating user authentication information. [Explanation of symbols]

[1690] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for inputting user information; means for setting up collaboration with financial institutions; a means for obtaining transaction data from financial institutions; a means to integrate and standardize the data obtained; A means of predicting asset trends using generative AI, a means for visualizing and displaying the integrated data; means for providing investment advice to users; A system including:

2. The system of claim 1 , further comprising means for automatically obtaining transaction data from financial institutions on a periodic basis.

3. The system of claim 1 further comprising means for generating and authenticating user authentication information.

Images