system

Abstract

We provide the system. [Solution] A means for collecting users' financial data, A means for aggregating and integrating the financial data, A generation engine means that analyzes aggregated financial data to generate financial advice, A means of presenting the generated financial advice to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, it is very important for users to understand their own financial situation and receive appropriate financial advice. However, various financial data such as those of banks, insurance, and loans exist in a scattered manner, and manually aggregating and analyzing them places a great burden on users. In addition, it is often difficult for users without financial expertise to appropriately analyze this data by themselves. Furthermore, when consulting an expert, consulting multiple times involves psychological and economic burdens. Due to such problems, there is a demand for a system that allows users to easily receive financial advice.

Means for Solving the Problems

[0005] This invention provides a system that collects users' financial data, centrally aggregates and analyzes this data, and then provides appropriate financial advice. Specifically,

[0006] 1. Provide a means to collect users' financial data.

[0007] 2. Provide means for aggregating and integrating the financial data,

[0008] 3. Provide a generation engine means that analyzes aggregated financial data and generates financial advice.

[0009] 4. Provide a means to present the generated financial advice to the user.

[0010] This allows users to receive appropriate advice based on centrally aggregated financial data. By using this system, users are freed from managing dispersed financial data and can easily obtain expert financial advice.

[0011] "User" refers to an individual or legal entity that provides data in order to receive the system's functions or services.

[0012] "Financial data" refers to a collection of information related to a user's financial situation, such as a user's bank account data, insurance contract data, and loan contract data.

[0013] "Means of collection" refers to the processes, devices, and software used to capture specific information or data.

[0014] "Means of aggregation and integration" refer to processes, devices, or software used to centrally consolidate multiple dispersed data sets.

[0015] "Generative engine means" refers to algorithms and software programs that analyze data and generate useful information and advice from it.

[0016] "To analyze" refers to the process of evaluating the collected data to find patterns and meanings.

[0017] "Financial advice" refers to specific instructions and suggestions provided to improve the user's financial situation.

[0018] "Means of presentation" refers to the means and methods for visually or auditorily presenting the generated advice and information to the user.

Brief Description of the Drawings

[0019] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0020] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0021] First, let's explain the terminology used in the following explanation.

[0022] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0032] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0039] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0040] This invention is a system that collects users' financial data, integrates and analyzes it centrally, and provides users with appropriate financial advice. This system mainly consists of three elements: a user terminal, a server, and a generation engine.

[0041] First, the user launches the application to obtain financial advice and requests it. The user's device sends this request to the server. The request includes the user's identification information.

[0042] The server collects the following data based on the user's identification information.

[0043] 1. Bank data: Includes information such as bank account details, transaction history, and balance.

[0044] 2. Insurance data: Includes information such as insurance contract details, premiums, and coverage details.

[0045] 3. Loan data: Includes information such as loan agreement details, outstanding balance, and interest rate.

[0046] The server executes multiple API requests and retrieves this data. Next, the server centrally aggregates the retrieved data to create a unified dataset showing the user's financial status.

[0047] The generation engine receives this integrated dataset and performs data analysis. This analysis includes evaluating the data, assessing the balance between income and expenses, assessing loan risk, and evaluating the appropriateness of insurance. The generation engine uses natural language processing techniques to generate financial advice in a format that is easy for users to understand.

[0048] The advice generated by the generation engine is sent back to the user's terminal via the server. The user's terminal displays this in an appropriate format and provides it to the user.

[0049] As a concrete example, when a user wants to understand their asset status, the system works as follows:

[0050] 1. The user launches the application and submits an advice request.

[0051] 2. The server sequentially retrieves bank data, insurance data, and loan data based on the user's ID.

[0052] 3. The server centrally aggregates this data and generates an integrated dataset.

[0053] 4. The generation engine analyzes this dataset and generates financial advice such as, "Your current income and expenses are well balanced, but you have insufficient emergency savings, so we recommend you increase your savings a little more."

[0054] 5. The server sends this advice to the user's terminal.

[0055] 6. The user terminal will display advice on the screen so that the user can confirm it.

[0056] In this way, users can easily obtain specific advice based on their own financial situation.

[0057] The following describes the processing flow.

[0058] Step 1:

[0059] Users launch a mobile or web application and log in to receive financial advice.

[0060] Step 2:

[0061] The user clicks the "Request Advice" button. This action sends an advice request from the user's terminal to the server.

[0062] Step 3:

[0063] The user's terminal sends a request to the server that includes user identification information (such as a user ID).

[0064] Step 4:

[0065] The server receives the user ID and sequentially sends data retrieval requests to multiple external API services (such as banks, insurance companies, and loan services).

[0066] Step 5:

[0067] The server collects data using the following steps:

[0068] To retrieve bank data, a request is sent to https: / / api.bank.com / userdata. This will return bank account information, transaction history, balance, etc.

[0069] To retrieve insurance data, a request is sent to https: / / api.insurance.com / userdata. This will return information such as insurance policy details, premiums, and coverage details.

[0070] To retrieve loan data, send a request to https: / / api.loan.com / userdata. This will return loan contract information, outstanding balance, interest rate, etc.

[0071] Step 6:

[0072] The data acquired by the server is centrally aggregated and integrated to create a unified dataset. This dataset includes banking data, insurance data, and loan data.

[0073] Step 7:

[0074] The server sends the integrated dataset to the generation engine.

[0075] Step 8:

[0076] The generation engine analyzes the integrated dataset to assess the user's financial situation. This assessment includes:

[0077] Assessment of the current balance of income and expenses

[0078] Loan risk assessment

[0079] Assessment of insurance suitability

[0080] Step 9:

[0081] The generation engine uses natural language processing technology to generate financial advice in a way that is easy for the user to understand. For example, it might generate advice such as, "Your current balance of income and expenses is good, but you lack sufficient emergency savings, so we recommend increasing your savings."

[0082] Step 10:

[0083] The generation engine sends the generated financial advice back to the server.

[0084] Step 11:

[0085] The server sends the financial advice received from the generation engine to the user's terminal.

[0086] Step 12:

[0087] The user's terminal displays the transmitted financial advice on its screen. This allows the user to see specific advice based on their own financial situation.

[0088] (Example 1)

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

[0090] In modern society, many users manage various financial data provided by multiple financial institutions and insurance companies, but it is difficult to centrally manage and analyze this data and obtain appropriate financial advice. This challenge is particularly evident when information such as income, expenses, loan agreements, and insurance policies are dispersed. Users want to accurately understand their financial situation and receive specific advice to improve it, but current systems lack methods to efficiently provide this.

[0091] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0092] In this invention, the server includes means for a user to request financial advice, means for collecting financial data based on the user's identification information, means for integrating the collected financial data, means for analyzing the integrated financial data to generate financial advice, and means for displaying the generated financial advice. This makes it possible for users to obtain specific and easy-to-understand financial advice from centrally managed financial data.

[0093] "Means for users to request financial advice" refers to the interface and related functions that allow users to request financial advice through the application.

[0094] "Means of collecting financial data based on user identification information" refers to a mechanism that automatically acquires relevant financial data from banks, insurance companies, lenders, etc., using user identification information such as IDs.

[0095] "Means for integrating collected financial data" refers to a function that centrally organizes and aggregates user financial data collected from multiple data sources to generate an integrated dataset.

[0096] "Means of analyzing integrated financial data to generate financial advice" refers to algorithms and engines that analyze aggregated financial data and generate specific and appropriate financial advice for users.

[0097] "Means for displaying generated financial advice" refers to an interface and functionality for sending the generated advice to the user's terminal and presenting it in a visual format on the application screen.

[0098] "Bank data" refers to information about a user's bank account, including transaction history and balance.

[0099] "Insurance data" refers to information about the insurance policies a user has contracted, such as premiums and coverage details.

[0100] "Loan contract data" refers to information about loan agreements entered into by users, such as outstanding balance and interest rates.

[0101] "Natural language processing technology" refers to the technology that enables computers to understand and generate human language, and specifically includes the use of text analysis and generative AI models.

[0102] This invention is a system that collects users' financial data, integrates and analyzes it centrally, and provides users with appropriate financial advice. This system mainly consists of three elements: a user terminal, a server, and a generation engine.

[0103] First, the user launches the application to obtain financial advice and requests it. The user's device sends this request to the server. The request includes the user's identification information.

[0104] The server collects the following data based on the user's identification information.

[0105] 1. Bank data: Includes information such as bank account details, transaction history, and balance.

[0106] 2. Insurance data: Includes information such as insurance contract details, premiums, and coverage details.

[0107] 3. Loan agreement data: Includes information such as loan agreement details, outstanding balance, and interest rate.

[0108] The server executes multiple API requests to retrieve this data. For example, it can utilize banking APIs, insurance data APIs, and loan data APIs. The server then centrally aggregates the retrieved data to create a unified dataset showing the user's financial situation. This dataset is stored in a database server (e.g., MySQL® or PostgreSQL).

[0109] The generation engine receives this integrated dataset and performs data analysis. This analysis includes evaluating the data, assessing the balance between income and expenses, assessing loan risk, and evaluating the appropriateness of insurance. The generation engine uses natural language processing techniques (e.g., Google® Cloud Natural Language API and OpenAI® GPT model) to generate financial advice in a format that is easy for users to understand.

[0110] The advice generated by the generation engine is sent back to the user's terminal via the server. The user's terminal displays this in an appropriate format and provides it to the user. The application's user interface (e.g., React.js, Flutter®, React Native) provides the information in a visually easy-to-understand manner.

[0111] As a concrete example, when a user wants to understand their asset status, the system works as follows:

[0112] 1. The user launches the application and submits an advice request.

[0113] 2. The server sequentially retrieves bank data, insurance data, and loan contract data based on the user's ID.

[0114] 3. The server centrally aggregates this data and generates an integrated dataset.

[0115] 4. The generation engine analyzes this dataset and generates financial advice such as, "Your current income and expenses are well balanced, but you have insufficient emergency savings, so we recommend you increase your savings a little more."

[0116] 5. The server sends this advice to the user's terminal.

[0117] 6. The user terminal will display advice on the screen so that the user can confirm it.

[0118] Example of a prompt:

[0119] User: Please evaluate my assets.

[0120] Server: We are collecting data, please wait a moment.

[0121] Server: Data collection and integration complete. Generating advice.

[0122] Server: Your income and expenses are well balanced, but your emergency savings are low, so I recommend increasing your savings a bit more.

[0123] User terminal: Advice displayed. "Your income and expenses are well balanced, but your emergency savings are low, so we recommend you increase your savings a little more."

[0124] In this way, users can easily obtain specific advice based on their own financial situation.

[0125] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0126] Program processing flow

[0127] Step 1: User Request

[0128] The user launches the application, types "Please appraise my assets," and presses the submit button. The input data consists of the user's identification information (e.g., user ID) and the request content. This causes the user's terminal to send the request and identification information to the server.

[0129] Input: User identification information, advice request

[0130] Output: Sending a request to the server

[0131] Step 2: Data collection by the server

[0132] Based on the received identification information, the server collects the user's financial data using bank APIs, insurance APIs, loan APIs, etc. Specifically, the server sends API requests and retrieves the necessary information (transaction history, insurance contract information, loan contract information, etc.) from each data source.

[0133] Input: User identification information

[0134] Output: Collected financial data (bank data, insurance data, loan data)

[0135] Step 3: Server-based data integration

[0136] The server temporarily stores the collected financial data in storage and then integrates it to generate a single unified dataset. This includes data preprocessing and cleaning.

[0137] Input: Collected financial data

[0138] Output: Integrated financial dataset

[0139] Step 4: Analysis by the generation engine

[0140] The generation engine receives an integrated dataset and performs analyses such as income and expenditure balance assessment, loan risk assessment, and insurance suitability assessment. It also uses natural language processing technology to generate financial advice in a format that is easy for users to understand.

[0141] Input: Integrated financial dataset

[0142] Output: Generated financial advice

[0143] Step 5: Server sends advice

[0144] The server receives the financial advice generated by the generation engine and sends it to the user's terminal. The advice is then converted to an appropriate format (e.g., JSON).

[0145] Input: Generated financial advice

[0146] Output: Sending advice to the user terminal

[0147] Step 6: Advice display via user terminal

[0148] The user's device receives advice sent from the server and displays it to the user in a visually easy-to-understand format. For example, a message such as "Your income and expenses are well balanced, but your emergency savings are low, so we recommend you increase your savings a little more" might appear on the smartphone screen.

[0149] Input: Financial advice sent from the server

[0150] Output: Display of advice

[0151] This process allows users to quickly and accurately receive specific advice based on their financial data.

[0152] (Application Example 1)

[0153] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0154] In modern society, many users find it difficult to manage and understand the multiple financial data points provided by financial institutions, insurance companies, and loan companies. This makes it challenging to properly grasp their financial situation and create effective financial plans. Furthermore, there is a lack of systems that allow users to understand and respond immediately to real-time changes in their financial situation. Therefore, there is a need for a system that allows users to comprehensively manage their own financial status and receive immediate advice.

[0155] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0156] In this invention, the server includes means for collecting users' financial data, means for aggregating and integrating said financial data, means for a generation engine that analyzes the aggregated financial data to generate financial advice, means for presenting the generated financial advice to the user in real time through an application installed on their smartphone, and means for notifying the user when their financial situation changes using a status notification function. As a result, users can grasp their financial situation in real time and receive timely and accurate financial advice.

[0157] "Means of collecting users' financial data" refers to a system for obtaining financial information provided by users from multiple financial institutions, insurance companies, and loan companies.

[0158] "Means for aggregating and integrating the financial data" refers to a method of centrally compiling acquired financial information and integrating the data in order to understand the user's overall financial situation.

[0159] A "generative engine that analyzes aggregated financial data to generate financial advice" refers to an algorithm and process for analyzing integrated financial data and providing advice to users in an easily understandable format based on that analysis.

[0160] "A means of presenting generated financial advice to users in real time through an application installed on their smartphone" refers to a technology that notifies users of instantly generated financial advice via an application installed on their smartphone.

[0161] "A means of notifying users when their financial status changes using a status notification function" refers to a mechanism that uses a pre-configured notification function to inform users in real time when there is a significant change in their financial status.

[0162] This invention is a system that collects and integrates users' financial data and provides real-time financial advice. The system consists of the following elements:

[0163] System Overview:

[0164] 1. User terminal:

[0165] It is a smartphone used by the user, and applications are installed on it.

[0166] 2. Server:

[0167] A backend system that processes data requests sent from user terminals and collects and integrates users' financial data.

[0168] 3. Generation Engine:

[0169] Designing an algorithm that analyzes aggregated financial data and generates financial advice for users.

[0170] 4. Notification system:

[0171] It monitors changes in financial status in real time and sends notifications to users as needed.

[0172] Data collection:

[0173] The server collects the following data based on the user ID.

[0174] Bank data: Bank account information, transaction history, and balance.

[0175] Insurance data: Details of the insurance contract, premiums, and coverage.

[0176] Loan data: Loan agreement information, balance, and interest rate.

[0177] The server automatically retrieves this data from multiple financial institutions using RESTful APIs. Secure communication is ensured by providing the necessary API endpoints and authentication keys.

[0178] Data integration:

[0179] The server centrally aggregates the acquired financial data and generates integrated datasets for each user. This allows for the unified management of information obtained from multiple data sources.

[0180] Data analysis and advice generation:

[0181] The generation engine analyzes the integrated dataset using natural language processing technology. Specifically, it performs data evaluation, income and expenditure balance assessment, loan risk assessment, and insurance suitability assessment. Based on the analysis results, it generates financial advice like the example below.

[0182] Example of a prompt:

[0183] "Requesting advice based on financial data for user ID: 12345: Bank balance: 500,000 yen, Insurance policies: 2, Loan balance: 600,000 yen"

[0184] Offering advice:

[0185] The generated financial advice is sent back to the user's terminal via the server. The user's terminal displays the advice on the screen in real time for the user to review. In addition, a status notification function is used to immediately notify the user when there are changes in the financial situation.

[0186] As a concrete example, if a user sends a request through the application saying, "I want to know my asset status," the following process will be executed.

[0187] An advice message is generated and displayed on the user's smartphone stating, "Your total balance is good, but your debt is a little high. Please review your repayment plan."

[0188] This system allows users to always have an up-to-date understanding of their financial situation and receive accurate and timely advice.

[0189] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0190] Step 1:

[0191] The user launches a smartphone application and requests financial advice.

[0192] Input: User ID and request information.

[0193] Specific operation: The user terminal sends the user ID and request to the server.

[0194] Step 2:

[0195] The server retrieves bank data, insurance data, and loan data based on the user ID.

[0196] Input: User ID.

[0197] Specific operation: The server uses a RESTful API to retrieve data from financial institutions, insurance companies, and loan companies.

[0198] Output: Bank data, insurance data, loan data.

[0199] Step 3:

[0200] The system centrally aggregates the data acquired by the servers and generates an integrated dataset.

[0201] Input: Bank data, insurance data, loan data.

[0202] Specific operation: The server integrates the data and compiles it into a dataset in a standard format.

[0203] Output: Integrated dataset.

[0204] Step 4:

[0205] The generation engine analyzes the integrated dataset and generates financial advice.

[0206] Input: Integrated dataset.

[0207] Specific operation: The generation engine uses natural language processing techniques to analyze data and generate advice.

[0208] Output: Financial advice.

[0209] Step 5:

[0210] The generated financial advice is sent to the user's terminal via the server.

[0211] Input: Financial advice.

[0212] Specific operation: The server sends the generated advice to the user's terminal.

[0213] Output: Financial advice is displayed on the user's terminal.

[0214] Step 6:

[0215] The user terminal displays advice on the screen in real time and uses a status notification function to notify the user when the financial situation changes.

[0216] Input: Financial advice and information on changes in financial condition.

[0217] Specific operation: The user's terminal displays advice and sends real-time notifications when there are changes in the financial situation.

[0218] Output: Users receive advice in real time and are notified in a timely manner.

[0219] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0220] This invention provides a system that collects, integrates, and analyzes users' financial data to offer financial advice, and also includes a function to recognize users' emotions. The system consists of a user terminal, a server, a generation engine, and an emotion engine.

[0221] First, the user requests financial advice by launching the application and logging in. This request is sent from the user's device to the server. The request includes the user's identification information.

[0222] The server collects the following data based on the user's identification information.

[0223] 1. Bank data: Bank account information, transaction history, balance, etc.

[0224] 2. Insurance data: Insurance contract information, premiums, coverage details, etc.

[0225] 3. Loan data: Loan contract information, outstanding balance, interest rate, etc.

[0226] The server executes multiple API requests to retrieve this data. The server then centrally aggregates the retrieved financial data to create a unified dataset. This unified dataset is then sent to the generation engine.

[0227] The generation engine analyzes the integrated dataset to assess the user's financial situation. This assessment process includes data evaluation, income and expenditure balance assessment, loan risk assessment, and insurance suitability assessment. Then, using natural language processing technology, it generates financial advice in a format that is easy for the user to understand.

[0228] The emotion engine functions as a means of recognizing the user's emotions. It employs technology to identify emotions from the user's tone of voice, facial expressions, and text input. This emotional information is fed back to the generation engine and considered along with the analysis results.

[0229] For example, if a user is feeling anxious about unexpected expenses, the emotion engine recognizes that anxiety. The generation engine then reflects this emotional information and generates more reassuring advice, such as, "Your current financial situation is good, but we recommend saving some more to be prepared for unexpected expenses."

[0230] The advice generated by the generation engine is sent to the user terminal via the server. The user terminal displays this advice on the screen, and the user can review it.

[0231] Thus, the present invention makes it possible to provide the most appropriate and acceptable advice to the user by taking into account not only the user's financial situation but also their emotions at that time.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] Users launch a mobile or web application and log in to receive financial advice.

[0235] Step 2:

[0236] The user clicks the "Request Advice" button. This action sends an advice request from the user's terminal to the server.

[0237] Step 3:

[0238] The user's terminal sends a request to the server that includes user identification information (such as a user ID).

[0239] Step 4:

[0240] The server receives the user ID and sequentially sends data retrieval requests to multiple external API services (such as banks, insurance companies, and loan services).

[0241] Step 5:

[0242] The server collects data using the following steps:

[0243] To retrieve bank data, a request is sent to https: / / api.bank.com / userdata. This will return bank account information, transaction history, balance, etc.

[0244] To retrieve insurance data, a request is sent to https: / / api.insurance.com / userdata. This will return information such as insurance policy details, premiums, and coverage details.

[0245] To retrieve loan data, send a request to https: / / api.loan.com / userdata. This will return loan contract information, outstanding balance, interest rate, etc.

[0246] Step 6:

[0247] The data acquired by the server is centrally aggregated and integrated to create a unified dataset. This dataset includes banking data, insurance data, and loan data.

[0248] Step 7:

[0249] The user's device sends emotional data (such as tone of voice, facial expressions, and text input) to the emotion engine.

[0250] Step 8:

[0251] The emotion engine analyzes the user's emotional data to recognize the user's current emotional state. This information is then used for subsequent analysis.

[0252] Step 9:

[0253] The server sends the integrated dataset and sentiment data from the sentiment engine to the generation engine.

[0254] Step 10:

[0255] The generation engine analyzes the integrated dataset to assess the user's financial situation. This assessment includes:

[0256] Assessment of the current balance of income and expenses

[0257] Loan risk assessment

[0258] Assessment of insurance suitability

[0259] Step 11:

[0260] The generation engine uses natural language processing technology to generate financial advice in a way that is easy for the user to understand. It also considers sentiment data from the sentiment engine to adjust the content and presentation of the advice.

[0261] Step 12:

[0262] The generation engine sends the generated financial advice back to the server.

[0263] Step 13:

[0264] The server sends the advice it received from the generation engine to the user's terminal.

[0265] Step 14:

[0266] The user's terminal displays the transmitted financial advice on the screen. This allows the user to see specific advice based on their financial situation, as well as receive thoughtful advice that takes their emotions into consideration.

[0267] (Example 2)

[0268] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0269] Traditional financial advisory systems often only consider the user's financial situation, failing to provide advice that takes into account their emotions and psychological state. As a result, there was a lack of appropriate advice that was easily accepted by users. Furthermore, by ignoring emotional aspects such as stress and anxiety, advice was often not followed.

[0270] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0271] In this invention, the server includes means for collecting the user's financial data, means for aggregating and integrating the financial data, means for analyzing the aggregated financial data to generate financial advice, means for presenting the generated financial advice to the user, means for recognizing the user's emotions, and means for adjusting the financial advice based on the recognized emotional information. This makes it possible to provide advice that takes into account not only the user's financial situation but also their emotional state at any given time.

[0272] A "user" is an individual or organization that uses the system to receive financial advice.

[0273] "Financial data" refers to data that includes information about a user's bank accounts, insurance policies, and loan agreements.

[0274] "Collection method" refers to the function of obtaining users' financial data from various data sources.

[0275] "Integration means" refers to a function that centrally aggregates different types of financial data and creates an integrated dataset.

[0276] "Generative means" refers to technology that analyzes integrated financial data and creates advice for users.

[0277] "Presentation means" refers to the function of displaying and providing advice created by the generation means to the user.

[0278] "Emotion recognition means" refers to technology that recognizes emotions from the user's voice, facial expressions, text input, etc.

[0279] "Adjustment mechanisms" refer to functions that appropriately modify the generated financial advice in accordance with the perceived emotional information.

[0280] The present invention is a system that collects, integrates, and analyzes the financial data of users, and further recognizes the emotions of users to generate and provide financial advice. This system is composed of a "user terminal", a "server", a "generation engine", and an "emotion engine".

[0281] Overview of Hardware and Software:

[0282] The user terminal includes devices such as smartphones, tablets, and personal computers. These terminals are installed with applications for requesting and receiving financial advice.

[0283] The server uses a cloud environment or an on-premises server. It performs data collection, aggregation, and integration, transmits data to the generation engine and the emotion engine, and provides advice.

[0284] The generation engine is a software module that analyzes the aggregated financial data and generates financial advice. It mainly uses natural language processing technology to generate advice.

[0285] The emotion engine is a software module that recognizes the emotions of users using voice recognition, facial expression recognition, and text analysis.

[0286] Details of System Operation:

[0287] 1. The user launches the application and logs in. Thereby, the identification information of the user is obtained.

[0288] 2. The user terminal provides an interface for requesting financial advice, and the user enters specific requirements (e.g., "worried about sudden expenses").

[0289] 3. Based on the identification information of the user, the server collects financial data from the following data sources: [[ID=z39]]

[0290] Retrieve bank account information, transaction history, and balance from bank APIs.

[0291] Retrieve insurance contract information, premiums, and coverage details from the insurance API.

[0292] Retrieve loan contract information, outstanding balance, and interest rate from the loan API.

[0293] 4. The server integrates this data to create a centralized financial dataset.

[0294] 5. The server sends the dataset to the generation engine.

[0295] 6. The generation engine analyzes the dataset and evaluates the user's financial situation:

[0296] Evaluation of the balance between income and expenses

[0297] Loan risk assessment

[0298] Assessment of insurance suitability

[0299] 7. The generation engine uses natural language processing technology to generate financial advice.

[0300] 8. Simultaneously, the emotion engine analyzes the user's voice, facial expressions, and text input to recognize their emotional state:

[0301] Voice tone analysis

[0302] facial expression recognition

[0303] Text analysis

[0304] 9. The emotion engine feeds back the recognized emotion information to the generation engine.

[0305] 10. The generation engine reflects emotional information and generates appropriate and reassuring advice for the user.

[0306] 11. The server sends the generated advice to the user terminal.

[0307] 12. The user terminal displays the advice on the screen and notifies the user.

[0308] Specific example:

[0309] When the user inputs the prompt text "worried about sudden expenses", the server collects and integrates bank data (account balance and transaction history), insurance data (insurance contract details, insurance premiums), and loan data (remaining debt, interest rate). The generation engine analyzes these data to evaluate the user's financial situation. At the same time, the emotion engine recognizes anxiety from the user's voice and expression. Finally, the generation engine generates advice that gives a sense of reassurance such as "Your current financial situation is good, but it is recommended that you save some more money to cope with unexpected expenses." and displays it on the terminal.

[0310] Thus, the present invention provides comprehensive financial advice that takes into account not only financial data but also the user's emotional state.

[0311] The flow of the specific process in Example 2 will be described with reference to FIG. 13.

[0312] Step 1:

[0313] The user launches the application and enters login information (user ID, password).

[0314] Input: User ID, password

[0315] Output: Authentication request

[0316] Step 2:

[0317] The server receives the authentication request and verifies the authentication information. If the authentication is successful, it returns the dashboard screen.

[0318] Input: Authentication Request

[0319] Output: Authentication results, dashboard screen

[0320] Step 3:

[0321] Users request financial advice from the dashboard screen and enter specific prompts such as "I'm worried about unexpected expenses."

[0322] Input: Prompt message

[0323] Output: Financial advice request

[0324] Step 4:

[0325] The user's terminal sends a financial advice request to the server.

[0326] Input: Financial advice request

[0327] Output: Sending a request to the server

[0328] Step 5:

[0329] Based on the user's identification information, the server collects financial data from the following data sources:

[0330] Retrieve bank account information, transaction history, and balance from bank APIs.

[0331] Retrieve insurance contract information, premiums, and coverage details from the insurance API.

[0332] Retrieve loan contract information, outstanding balance, and interest rate from the loan API.

[0333] Input: User identification information

[0334] Output: Various financial data collected

[0335] Step 6:

[0336] The server integrates various acquired financial data to create a unified financial dataset.

[0337] Input: Collected financial data

[0338] Output: Integrated financial dataset

[0339] Step 7:

[0340] The server sends the integrated dataset to the generation engine.

[0341] Input: Integrated financial dataset

[0342] Output: Sending the dataset to the generation engine

[0343] Step 8:

[0344] The generation engine analyzes the integrated dataset to assess the user's financial situation. Specifically, it evaluates the balance between income and expenses, assesses loan risk, and evaluates the appropriateness of insurance.

[0345] Input: Integrated financial dataset

[0346] Output: Initial advice

[0347] Step 9:

[0348] The emotion engine recognizes the user's emotions. It analyzes the user's voice tone, facial expressions, text input, etc., to generate emotional information.

[0349] Input: User's voice tone, facial expression, and text input

[0350] Output: Emotional information

[0351] Step 10:

[0352] The emotion engine feeds back the recognized emotion information to the generation engine.

[0353] Input: Emotional information

[0354] Output: Feedback to the generation engine

[0355] Step 11:

[0356] The generation engine incorporates emotional information to produce the final financial advice.

[0357] Input: Initial advice, emotional information

[0358] Output: Final Financial Advice

[0359] Step 12:

[0360] The generation engine sends the final financial advice it has generated to the server.

[0361] Input: Final Financial Advice

[0362] Output: Sending advice to the server

[0363] Step 13:

[0364] The server sends the final financial advice to the user's terminal.

[0365] Input: Final Financial Advice

[0366] Output: Sending advice to the user's terminal

[0367] Step 14:

[0368] The user's terminal displays the received advice on its screen.

[0369] Input: Final Financial Advice

[0370] Output: Screen display

[0371] Step 15:

[0372] The user reviews the financial advice displayed on the screen and decides on their next course of action.

[0373] Input: Advice displayed on screen

[0374] Output: User decision

[0375] (Application Example 2)

[0376] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0377] Traditional financial advisory systems relied solely on the user's financial data, failing to consider their emotions. This made it difficult to provide appropriate advice to users who were feeling anxious about their current financial situation. Furthermore, there was a lack of systems capable of providing emotionally responsive advice, resulting in a lack of services that considered the user's psychological state.

[0378] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0379] In this invention, the server includes means for collecting user financial data, means for aggregating and integrating the financial data, means for collecting and analyzing emotional data, means for generating financial advice that takes emotional data into consideration, and means for presenting the generated financial advice to the user. This makes it possible to provide advice that takes into account not only the user's financial situation but also their emotions at that time.

[0380] "Means for collecting users' financial data" refers to devices or programs for obtaining users' deposit account information, insurance contract information, and loan contract information from various financial institutions and services.

[0381] "Means for aggregating and integrating financial data" refers to a device or program that centrally compiles acquired user financial data and creates a dataset in a unified format.

[0382] A "generation engine means" is a device or program that analyzes aggregated financial data, evaluates the user's financial situation, and then generates appropriate financial advice.

[0383] "An emotion engine means for collecting and analyzing user emotion data" refers to a device or program for identifying and analyzing emotions from a user's voice tone, facial expressions, text input, etc.

[0384] "Means for generating financial advice that takes emotional data into consideration" refers to a device or program for generating financial advice that reflects the user's mental state, based on emotional data identified by an emotional engine.

[0385] "Means for presenting generated financial advice to the user" refers to a device or program that displays and allows the user to confirm the financial advice obtained by the generation engine and emotion engine on the user's terminal.

[0386] This invention is a system that collects users' financial and emotional data, integrates and analyzes them, and provides appropriate financial advice. The system consists of a user terminal, a server, a generation engine, and an emotional engine.

[0387] Hardware and software configuration

[0388] 1. User terminal:

[0389] smartphone

[0390] Installed applications (Android®, iOS)

[0391] 2. Server:

[0392] Cloud servers (AWS®, GCP, etc.)

[0393] 3. Software:

[0394] API integration module (acquires data from various financial institutions)

[0395] Emotion recognition engine (Google Cloud Speech-to-Text API, OpenCV)

[0396] Data analysis engine (GOOGLE TENSOR®, FLOW®, PyTorch)

[0397] Natural Language Processing Engine (OpenAI GPT)

[0398] Processing flow

[0399] 1. User Authentication and Login

[0400] Users log in using a smartphone app. Login information is sent to the server, where the user's identity is verified.

[0401] 2. Data Collection

[0402] The server uses an API integration module based on login information to collect users' financial data, such as banking data, insurance data, and loan data. This data is centrally aggregated to create an integrated dataset.

[0403] 3. Emotion recognition

[0404] The system collects the user's voice tone and facial expressions using the smartphone's microphone and camera. The voice data is converted to text using the Google Cloud Speech-to-Text API, and the facial expression data is analyzed using OpenCV. This data is then processed by an emotion engine to identify the user's emotions.

[0405] 4. Data Analysis

[0406] The integrated financial and sentiment datasets are analyzed using TensorFlow. Considering the user's financial status and emotional state, an appropriate financial advice generator produces relevant financial advice.

[0407] 5. Providing financial advice

[0408] Using a natural language processing engine (OpenAI GPT), the analysis results are converted into a format that is easy for the user to understand. The server sends the generated advice to the user's terminal, where the user can review it.

[0409] Specific examples and prompt statements

[0410] For example, if a user is worried about unexpected expenses, a response can be generated using a prompt message like the following.

[0411] Voice and facial expression input

[0412] User's voice: "I'm worried about unexpected expenses lately."

[0413] Facial expression: A tense face

[0414] App analysis and response

[0415] Emotional Engine Result: Anxiety

[0416] Financial data analysis results: Savings are not sufficient, but there is a monthly surplus of approximately 10,000 yen.

[0417] advice:

[0418] "Considering your current financial situation, I recommend setting aside a portion of your monthly surplus to prepare for unexpected expenses. Specifically, you could start by saving 3,000 yen per month."

[0419] Prompt example

[0420] User's voice: "I'm worried about unexpected expenses lately."

[0421] User's facial expression: A tense expression

[0422] Financial data:

[0423] Bank account balance: 500,000

[0424] Monthly income: 300,000

[0425] Monthly expenses: 200,000

[0426] Loan: Car loan, remaining balance 100,000 yen, monthly payment 10,000 yen.

[0427] Based on the analysis results, what kind of financial advice will you provide to the user?

[0428] Thus, by considering not only the user's financial data but also their emotions at that time, the present invention makes it possible to provide more personalized and appropriate financial advice.

[0429] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0430] Step 1:

[0431] User authentication and login

[0432] The user launches the application on their smartphone and enters their login information (user ID and password). The submitted login information is sent to the server and stored as user identification information.

[0433] Input: User ID, Password

[0434] Output: User identification authentication result

[0435] Step 2:

[0436] Data collection

[0437] Based on authenticated user identification information, the server uses an API integration module to retrieve user financial data (bank data, insurance data, loan data) from various financial institutions. This data is centrally aggregated on the server, creating an integrated dataset.

[0438] Input: User identification information

[0439] Output: Integrated financial dataset

[0440] Step 3:

[0441] emotion recognition

[0442] The system uses the microphone and camera on the user's device to collect the user's voice and facial expressions. The voice data is transcribed using the Google Cloud Speech-to-Text API, and the facial expression data is analyzed using OpenCV. An emotion engine then identifies the user's emotions from this data.

[0443] Input: User's voice and facial expression data

[0444] Output: Identified sentiment data

[0445] Step 4:

[0446] Data Analysis

[0447] The server analyzes an integrated financial dataset and identified sentiment data using TensorFlow. Considering the financial status and the user's sentiment state, the generative engine generates appropriate financial advice using a generative AI model.

[0448] Input: Integrated financial dataset, identified sentiment data

[0449] Output: Generated financial advice

[0450] Step 5:

[0451] Providing financial advice

[0452] The generated financial advice is converted into a user-friendly format using a natural language processing engine (OpenAI GPT). The server then sends the converted financial advice to the user's terminal, allowing the user to review it and decide on their next course of action.

[0453] Input: Generated financial advice

[0454] Output: Financial advice presented to the user

[0455] In this way, this system analyzes the user's financial and emotional data through multiple steps and provides optimal financial advice tailored to each individual's situation.

[0456] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0457] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0458] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0459] [Second Embodiment]

[0460] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0461] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0462] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0463] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0464] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0465] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0466] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0467] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0468] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0469] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0470] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0471] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0472] This invention is a system that collects users' financial data, integrates and analyzes it centrally, and provides users with appropriate financial advice. This system mainly consists of three elements: a user terminal, a server, and a generation engine.

[0473] First, the user launches the application to obtain financial advice and requests it. The user's device sends this request to the server. The request includes the user's identification information.

[0474] The server collects the following data based on the user's identification information.

[0475] 1. Bank data: Includes information such as bank account details, transaction history, and balance.

[0476] 2. Insurance data: Includes information such as insurance contract details, premiums, and coverage details.

[0477] 3. Loan data: Includes information such as loan agreement details, outstanding balance, and interest rate.

[0478] The server executes multiple API requests and retrieves this data. Next, the server centrally aggregates the retrieved data to create a unified dataset showing the user's financial status.

[0479] The generation engine receives this integrated dataset and performs data analysis. This analysis includes evaluating the data, assessing the balance between income and expenses, assessing loan risk, and evaluating the appropriateness of insurance. The generation engine uses natural language processing techniques to generate financial advice in a format that is easy for users to understand.

[0480] The advice generated by the generation engine is sent back to the user's terminal via the server. The user's terminal displays this in an appropriate format and provides it to the user.

[0481] As a concrete example, when a user wants to understand their asset status, the system works as follows:

[0482] 1. The user launches the application and submits an advice request.

[0483] 2. The server sequentially retrieves bank data, insurance data, and loan data based on the user's ID.

[0484] 3. The server centrally aggregates this data and generates an integrated dataset.

[0485] 4. The generation engine analyzes this dataset and generates financial advice such as, "Your current income and expenses are well balanced, but you have insufficient emergency savings, so we recommend you increase your savings a little more."

[0486] 5. The server sends this advice to the user's terminal.

[0487] 6. The user terminal will display advice on the screen so that the user can confirm it.

[0488] In this way, users can easily obtain specific advice based on their own financial situation.

[0489] The following describes the processing flow.

[0490] Step 1:

[0491] Users launch a mobile or web application and log in to receive financial advice.

[0492] Step 2:

[0493] The user clicks the "Request Advice" button. This action sends an advice request from the user's terminal to the server.

[0494] Step 3:

[0495] The user's terminal sends a request to the server that includes user identification information (such as a user ID).

[0496] Step 4:

[0497] The server receives the user ID and sequentially sends data retrieval requests to multiple external API services (such as banks, insurance companies, and loan services).

[0498] Step 5:

[0499] The server collects data using the following steps:

[0500] To retrieve bank data, a request is sent to https: / / api.bank.com / userdata. This will return bank account information, transaction history, balance, etc.

[0501] To retrieve insurance data, a request is sent to https: / / api.insurance.com / userdata. This will return information such as insurance policy details, premiums, and coverage details.

[0502] To retrieve loan data, send a request to https: / / api.loan.com / userdata. This will return loan contract information, outstanding balance, interest rate, etc.

[0503] Step 6:

[0504] The data acquired by the server is centrally aggregated and integrated to create a unified dataset. This dataset includes banking data, insurance data, and loan data.

[0505] Step 7:

[0506] The server sends the integrated dataset to the generation engine.

[0507] Step 8:

[0508] The generation engine analyzes the integrated dataset to assess the user's financial situation. This assessment includes:

[0509] Assessment of the current balance of income and expenses

[0510] Loan risk assessment

[0511] Assessment of insurance suitability

[0512] Step 9:

[0513] The generation engine uses natural language processing technology to generate financial advice in a way that is easy for the user to understand. For example, it might generate advice such as, "Your current balance of income and expenses is good, but you lack sufficient emergency savings, so we recommend increasing your savings."

[0514] Step 10:

[0515] The generation engine sends the generated financial advice back to the server.

[0516] Step 11:

[0517] The server sends the financial advice received from the generation engine to the user's terminal.

[0518] Step 12:

[0519] The user's terminal displays the transmitted financial advice on its screen. This allows the user to see specific advice based on their own financial situation.

[0520] (Example 1)

[0521] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0522] In modern society, many users manage various financial data provided by multiple financial institutions and insurance companies, but it is difficult to centrally manage and analyze this data and obtain appropriate financial advice. This challenge is particularly evident when information such as income, expenses, loan agreements, and insurance policies are dispersed. Users want to accurately understand their financial situation and receive specific advice to improve it, but current systems lack methods to efficiently provide this.

[0523] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0524] In this invention, the server includes means for a user to request financial advice, means for collecting financial data based on the user's identification information, means for integrating the collected financial data, means for analyzing the integrated financial data to generate financial advice, and means for displaying the generated financial advice. This makes it possible for users to obtain specific and easy-to-understand financial advice from centrally managed financial data.

[0525] "Means for users to request financial advice" refers to the interface and related functions that allow users to request financial advice through the application.

[0526] "Means of collecting financial data based on user identification information" refers to a mechanism that automatically acquires relevant financial data from banks, insurance companies, lenders, etc., using user identification information such as IDs.

[0527] "Means for integrating collected financial data" refers to a function that centrally organizes and aggregates user financial data collected from multiple data sources to generate an integrated dataset.

[0528] "Means of analyzing integrated financial data to generate financial advice" refers to algorithms and engines that analyze aggregated financial data and generate specific and appropriate financial advice for users.

[0529] "Means for displaying generated financial advice" refers to an interface and functionality for sending the generated advice to the user's terminal and presenting it in a visual format on the application screen.

[0530] "Bank data" refers to information about a user's bank account, including transaction history and balance.

[0531] "Insurance data" refers to information about the insurance policies a user has contracted, such as premiums and coverage details.

[0532] "Loan contract data" refers to information about loan agreements entered into by users, such as outstanding balance and interest rates.

[0533] "Natural language processing technology" refers to the technology that enables computers to understand and generate human language, and specifically includes the use of text analysis and generative AI models.

[0534] This invention is a system that collects users' financial data, integrates and analyzes it centrally, and provides users with appropriate financial advice. This system mainly consists of three elements: a user terminal, a server, and a generation engine.

[0535] First, the user launches the application to obtain financial advice and requests it. The user's device sends this request to the server. The request includes the user's identification information.

[0536] The server collects the following data based on the user's identification information.

[0537] 1. Bank data: Includes information such as bank account details, transaction history, and balance.

[0538] 2. Insurance data: Includes information such as insurance contract details, premiums, and coverage details.

[0539] 3. Loan agreement data: Includes information such as loan agreement details, outstanding balance, and interest rate.

[0540] The server executes multiple API requests to retrieve this data. For example, it can utilize banking APIs, insurance data APIs, and loan data APIs. The server then centrally aggregates the retrieved data to create a unified dataset showing the user's financial situation. This dataset is stored in a database server (e.g., MySQL or PostgreSQL).

[0541] The generation engine receives this integrated dataset and performs data analysis. This analysis includes evaluating the data, assessing the balance between income and expenses, assessing loan risk, and evaluating the appropriateness of insurance. The generation engine uses natural language processing techniques (e.g., Google Cloud Natural Language API or OpenAI's GPT model) to generate financial advice in a format that is easy for users to understand.

[0542] The advice generated by the generation engine is sent back to the user's terminal via the server. The user's terminal displays this in an appropriate format and provides it to the user. The application's user interface (e.g., React.js, Flutter, React Native) provides the information in a visually easy-to-understand manner.

[0543] As a concrete example, when a user wants to understand their asset status, the system works as follows:

[0544] 1. The user launches the application and submits an advice request.

[0545] 2. The server sequentially retrieves bank data, insurance data, and loan contract data based on the user's ID.

[0546] 3. The server centrally aggregates this data and generates an integrated dataset.

[0547] 4. The generation engine analyzes this dataset and generates financial advice such as, "Your current income and expenses are well balanced, but you have insufficient emergency savings, so we recommend you increase your savings a little more."

[0548] 5. The server sends this advice to the user's terminal.

[0549] 6. The user terminal will display advice on the screen so that the user can confirm it.

[0550] Example of a prompt:

[0551] User: Please evaluate my assets.

[0552] Server: We are collecting data, please wait a moment.

[0553] Server: Data collection and integration complete. Generating advice.

[0554] Server: Your income and expenses are well balanced, but your emergency savings are low, so I recommend increasing your savings a bit more.

[0555] User terminal: Advice displayed. "Your income and expenses are well balanced, but your emergency savings are low, so we recommend you increase your savings a little more."

[0556] In this way, users can easily obtain specific advice based on their own financial situation.

[0557] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0558] Program processing flow

[0559] Step 1: User Request

[0560] The user launches the application, types "Please appraise my assets," and presses the submit button. The input data consists of the user's identification information (e.g., user ID) and the request content. This causes the user's terminal to send the request and identification information to the server.

[0561] Input: User identification information, advice request

[0562] Output: Sending a request to the server

[0563] Step 2: Data collection by the server

[0564] Based on the received identification information, the server collects the user's financial data using bank APIs, insurance APIs, loan APIs, etc. Specifically, the server sends API requests and retrieves the necessary information (transaction history, insurance contract information, loan contract information, etc.) from each data source.

[0565] Input: User identification information

[0566] Output: Collected financial data (bank data, insurance data, loan data)

[0567] Step 3: Server-based data integration

[0568] The server temporarily stores the collected financial data in storage and then integrates it to generate a single unified dataset. This includes data preprocessing and cleaning.

[0569] Input: Collected financial data

[0570] Output: Integrated financial dataset

[0571] Step 4: Analysis by the generation engine

[0572] The generation engine receives an integrated dataset and performs analyses such as income and expenditure balance assessment, loan risk assessment, and insurance suitability assessment. It also uses natural language processing technology to generate financial advice in a format that is easy for users to understand.

[0573] Input: Integrated financial dataset

[0574] Output: Generated financial advice

[0575] Step 5: Server sends advice

[0576] The server receives the financial advice generated by the generation engine and sends it to the user's terminal. The advice is then converted to an appropriate format (e.g., JSON).

[0577] Input: Generated financial advice

[0578] Output: Sending advice to the user terminal

[0579] Step 6: Advice display via user terminal

[0580] The user's device receives advice sent from the server and displays it to the user in a visually easy-to-understand format. For example, a message such as "Your income and expenses are well balanced, but your emergency savings are low, so we recommend you increase your savings a little more" might appear on the smartphone screen.

[0581] Input: Financial advice sent from the server

[0582] Output: Display of advice

[0583] This process allows users to quickly and accurately receive specific advice based on their financial data.

[0584] (Application Example 1)

[0585] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0586] In modern society, many users find it difficult to manage and understand the multiple financial data points provided by financial institutions, insurance companies, and loan companies. This makes it challenging to properly grasp their financial situation and create effective financial plans. Furthermore, there is a lack of systems that allow users to understand and respond immediately to real-time changes in their financial situation. Therefore, there is a need for a system that allows users to comprehensively manage their own financial status and receive immediate advice.

[0587] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0588] In this invention, the server includes means for collecting users' financial data, means for aggregating and integrating said financial data, means for a generation engine that analyzes the aggregated financial data to generate financial advice, means for presenting the generated financial advice to the user in real time through an application installed on their smartphone, and means for notifying the user when their financial situation changes using a status notification function. As a result, users can grasp their financial situation in real time and receive timely and accurate financial advice.

[0589] "Means of collecting users' financial data" refers to a system for obtaining financial information provided by users from multiple financial institutions, insurance companies, and loan companies.

[0590] "Means for aggregating and integrating the financial data" refers to a method of centrally compiling acquired financial information and integrating the data in order to understand the user's overall financial situation.

[0591] A "generative engine that analyzes aggregated financial data to generate financial advice" refers to an algorithm and process for analyzing integrated financial data and providing advice to users in an easily understandable format based on that analysis.

[0592] "A means of presenting generated financial advice to users in real time through an application installed on their smartphone" refers to a technology that notifies users of instantly generated financial advice via an application installed on their smartphone.

[0593] "A means of notifying users when their financial status changes using a status notification function" refers to a mechanism that uses a pre-configured notification function to inform users in real time when there is a significant change in their financial status.

[0594] This invention is a system that collects and integrates users' financial data and provides real-time financial advice. The system consists of the following elements:

[0595] System Overview:

[0596] 1. User terminal:

[0597] It is a smartphone used by the user, and applications are installed on it.

[0598] 2. Server:

[0599] A backend system that processes data requests sent from user terminals and collects and integrates users' financial data.

[0600] 3. Generation Engine:

[0601] Designing an algorithm that analyzes aggregated financial data and generates financial advice for users.

[0602] 4. Notification system:

[0603] It monitors changes in financial status in real time and sends notifications to users as needed.

[0604] Data collection:

[0605] The server collects the following data based on the user ID.

[0606] Bank data: Bank account information, transaction history, and balance.

[0607] Insurance data: Details of the insurance contract, premiums, and coverage.

[0608] Loan data: Loan agreement information, balance, and interest rate.

[0609] The server automatically retrieves this data from multiple financial institutions using RESTful APIs. Secure communication is ensured by providing the necessary API endpoints and authentication keys.

[0610] Data integration:

[0611] The server centrally aggregates the acquired financial data and generates integrated datasets for each user. This allows for the unified management of information obtained from multiple data sources.

[0612] Data analysis and advice generation:

[0613] The generation engine analyzes the integrated dataset using natural language processing technology. Specifically, it performs data evaluation, income and expenditure balance assessment, loan risk assessment, and insurance suitability assessment. Based on the analysis results, it generates financial advice like the example below.

[0614] Example of a prompt:

[0615] "Requesting advice based on financial data for user ID: 12345: Bank balance: 500,000 yen, Insurance policies: 2, Loan balance: 600,000 yen"

[0616] Offering advice:

[0617] The generated financial advice is sent back to the user's terminal via the server. The user's terminal displays the advice on the screen in real time for the user to review. In addition, a status notification function is used to immediately notify the user when there are changes in the financial situation.

[0618] As a concrete example, if a user sends a request through the application saying, "I want to know my asset status," the following process will be executed.

[0619] An advice message is generated and displayed on the user's smartphone stating, "Your total balance is good, but your debt is a little high. Please review your repayment plan."

[0620] This system allows users to always have an up-to-date understanding of their financial situation and receive accurate and timely advice.

[0621] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0622] Step 1:

[0623] The user launches a smartphone application and requests financial advice.

[0624] Input: User ID and request information.

[0625] Specific operation: The user terminal sends the user ID and request to the server.

[0626] Step 2:

[0627] The server retrieves bank data, insurance data, and loan data based on the user ID.

[0628] Input: User ID.

[0629] Specific operation: The server uses a RESTful API to retrieve data from financial institutions, insurance companies, and loan companies.

[0630] Output: Bank data, insurance data, loan data.

[0631] Step 3:

[0632] The system centrally aggregates the data acquired by the servers and generates an integrated dataset.

[0633] Input: Bank data, insurance data, loan data.

[0634] Specific operation: The server integrates the data and compiles it into a dataset in a standard format.

[0635] Output: Integrated dataset.

[0636] Step 4:

[0637] The generation engine analyzes the integrated dataset and generates financial advice.

[0638] Input: Integrated dataset.

[0639] Specific operation: The generation engine uses natural language processing techniques to analyze data and generate advice.

[0640] Output: Financial advice.

[0641] Step 5:

[0642] The generated financial advice is sent to the user's terminal via the server.

[0643] Input: Financial advice.

[0644] Specific operation: The server sends the generated advice to the user's terminal.

[0645] Output: Financial advice is displayed on the user's terminal.

[0646] Step 6:

[0647] The user terminal displays advice on the screen in real time and uses a status notification function to notify the user when the financial situation changes.

[0648] Input: Financial advice and information on changes in financial condition.

[0649] Specific operation: The user's terminal displays advice and sends real-time notifications when there are changes in the financial situation.

[0650] Output: Users receive advice in real time and are notified in a timely manner.

[0651] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0652] This invention provides a system that collects, integrates, and analyzes users' financial data to offer financial advice, and also includes a function to recognize users' emotions. The system consists of a user terminal, a server, a generation engine, and an emotion engine.

[0653] First, the user requests financial advice by launching the application and logging in. This request is sent from the user's device to the server. The request includes the user's identification information.

[0654] The server collects the following data based on the user's identification information.

[0655] 1. Bank data: Bank account information, transaction history, balance, etc.

[0656] 2. Insurance data: Insurance contract information, premiums, coverage details, etc.

[0657] 3. Loan data: Loan contract information, outstanding balance, interest rate, etc.

[0658] The server executes multiple API requests to retrieve this data. The server then centrally aggregates the retrieved financial data to create a unified dataset. This unified dataset is then sent to the generation engine.

[0659] The generation engine analyzes the integrated dataset to assess the user's financial situation. This assessment process includes data evaluation, income and expenditure balance assessment, loan risk assessment, and insurance suitability assessment. Then, using natural language processing technology, it generates financial advice in a format that is easy for the user to understand.

[0660] The emotion engine functions as a means of recognizing the user's emotions. It employs technology to identify emotions from the user's tone of voice, facial expressions, and text input. This emotional information is fed back to the generation engine and considered along with the analysis results.

[0661] For example, if a user is feeling anxious about unexpected expenses, the emotion engine recognizes that anxiety. The generation engine then reflects this emotional information and generates more reassuring advice, such as, "Your current financial situation is good, but we recommend saving some more to be prepared for unexpected expenses."

[0662] The advice generated by the generation engine is sent to the user terminal via the server. The user terminal displays this advice on the screen, and the user can review it.

[0663] Thus, the present invention makes it possible to provide the most appropriate and acceptable advice to the user by taking into account not only the user's financial situation but also their emotions at that time.

[0664] The following describes the processing flow.

[0665] Step 1:

[0666] Users launch a mobile or web application and log in to receive financial advice.

[0667] Step 2:

[0668] The user clicks the "Request Advice" button. This action sends an advice request from the user's terminal to the server.

[0669] Step 3:

[0670] The user's terminal sends a request to the server that includes user identification information (such as a user ID).

[0671] Step 4:

[0672] The server receives the user ID and sequentially sends data retrieval requests to multiple external API services (such as banks, insurance companies, and loan services).

[0673] Step 5:

[0674] The server collects data using the following steps:

[0675] To retrieve bank data, a request is sent to https: / / api.bank.com / userdata. This will return bank account information, transaction history, balance, etc.

[0676] To retrieve insurance data, a request is sent to https: / / api.insurance.com / userdata. This will return information such as insurance policy details, premiums, and coverage details.

[0677] To retrieve loan data, send a request to https: / / api.loan.com / userdata. This will return loan contract information, outstanding balance, interest rate, etc.

[0678] Step 6:

[0679] The data acquired by the server is centrally aggregated and integrated to create a unified dataset. This dataset includes banking data, insurance data, and loan data.

[0680] Step 7:

[0681] The user's device sends emotional data (such as tone of voice, facial expressions, and text input) to the emotion engine.

[0682] Step 8:

[0683] The emotion engine analyzes the user's emotional data to recognize the user's current emotional state. This information is then used for subsequent analysis.

[0684] Step 9:

[0685] The server sends the integrated dataset and sentiment data from the sentiment engine to the generation engine.

[0686] Step 10:

[0687] The generation engine analyzes the integrated dataset to assess the user's financial situation. This assessment includes:

[0688] Assessment of the current balance of income and expenses

[0689] Loan risk assessment

[0690] Assessment of insurance suitability

[0691] Step 11:

[0692] The generation engine uses natural language processing technology to generate financial advice in a way that is easy for the user to understand. It also considers sentiment data from the sentiment engine to adjust the content and presentation of the advice.

[0693] Step 12:

[0694] The generation engine sends the generated financial advice back to the server.

[0695] Step 13:

[0696] The server sends the advice it received from the generation engine to the user's terminal.

[0697] Step 14:

[0698] The user's terminal displays the transmitted financial advice on the screen. This allows the user to see specific advice based on their financial situation, as well as receive thoughtful advice that takes their emotions into consideration.

[0699] (Example 2)

[0700] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0701] Traditional financial advisory systems often only consider the user's financial situation, failing to provide advice that takes into account their emotions and psychological state. As a result, there was a lack of appropriate advice that was easily accepted by users. Furthermore, by ignoring emotional aspects such as stress and anxiety, advice was often not followed.

[0702] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0703] In this invention, the server includes means for collecting the user's financial data, means for aggregating and integrating the financial data, means for analyzing the aggregated financial data to generate financial advice, means for presenting the generated financial advice to the user, means for recognizing the user's emotions, and means for adjusting the financial advice based on the recognized emotional information. This makes it possible to provide advice that takes into account not only the user's financial situation but also their emotional state at any given time.

[0704] A "user" is an individual or organization that uses the system to receive financial advice.

[0705] "Financial data" refers to data that includes information about a user's bank accounts, insurance policies, and loan agreements.

[0706] "Collection method" refers to the function of obtaining users' financial data from various data sources.

[0707] "Integration means" refers to a function that centrally aggregates different types of financial data and creates an integrated dataset.

[0708] "Generative means" refers to technology that analyzes integrated financial data and creates advice for users.

[0709] "Presentation means" refers to the function of displaying and providing advice created by the generation means to the user.

[0710] "Emotion recognition means" refers to technology that recognizes emotions from the user's voice, facial expressions, text input, etc.

[0711] "Adjustment mechanisms" refer to functions that appropriately modify the generated financial advice in accordance with the perceived emotional information.

[0712] This invention relates to a system that collects, integrates, and analyzes users' financial data, and further recognizes users' emotions to generate and provide financial advice. This system consists of a "user terminal," a "server," a "generation engine," and an "emotion engine."

[0713] Hardware and software overview:

[0714] User devices include smartphones, tablets, and personal computers. These devices have applications installed for requesting and receiving financial advice.

[0715] The servers utilize cloud environments or on-premises servers. They collect, aggregate, and integrate data, send it to the generation and sentiment engines, and provide advice.

[0716] The generation engine is a software module that analyzes aggregated financial data and generates financial advice. It primarily uses natural language processing techniques to generate advice.

[0717] The emotion engine is a software module that recognizes a user's emotions using speech recognition, facial expression recognition, and text analysis.

[0718] System operation details:

[0719] 1. The user launches the application and logs in. This allows the user's identification information to be obtained.

[0720] 2. The user terminal provides an interface for requesting financial advice, and the user enters a specific request (e.g., "I'm worried about unexpected expenses").

[0721] 3. Based on the user's identification information, the server collects financial data from the following data sources:

[0722] Retrieve bank account information, transaction history, and balance from bank APIs.

[0723] Retrieve insurance contract information, premiums, and coverage details from the insurance API.

[0724] Retrieve loan contract information, outstanding balance, and interest rate from the loan API.

[0725] 4. The server integrates this data to create a centralized financial dataset.

[0726] 5. The server sends the dataset to the generation engine.

[0727] 6. The generation engine analyzes the dataset and evaluates the user's financial situation:

[0728] Evaluation of the balance between income and expenses

[0729] Loan risk assessment

[0730] Assessment of insurance suitability

[0731] 7. The generation engine uses natural language processing technology to generate financial advice.

[0732] 8. Simultaneously, the emotion engine analyzes the user's voice, facial expressions, and text input to recognize their emotional state:

[0733] Voice tone analysis

[0734] facial expression recognition

[0735] Text analysis

[0736] 9. The emotion engine feeds back the recognized emotion information to the generation engine.

[0737] 10. The generation engine reflects emotional information and generates appropriate and reassuring advice for the user.

[0738] 11. The server sends the generated advice to the user's terminal.

[0739] 12. The user terminal displays advice on the screen and notifies the user.

[0740] Specific example:

[0741] When a user enters the prompt "I'm worried about unexpected expenses," the server collects and integrates bank data (account balance and transaction history), insurance data (insurance policy details and premiums), and loan data (outstanding balance and interest rates). The generation engine analyzes this data to assess the user's financial situation. Simultaneously, the emotion engine recognizes anxiety from the user's voice and facial expressions. Finally, the generation engine generates reassuring advice such as "Your current financial situation is good, but we recommend saving some more to be prepared for unexpected expenses," and displays it on the device.

[0742] Thus, the present invention provides comprehensive financial advice that takes into account not only financial data but also the user's emotional state.

[0743] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0744] Step 1:

[0745] The user launches the application and enters their login information (user ID, password).

[0746] Input: User ID, Password

[0747] Output: Authentication Request

[0748] Step 2:

[0749] The server receives the authentication request and verifies the authentication information. If authentication is successful, it returns the dashboard screen.

[0750] Input: Authentication Request

[0751] Output: Authentication results, dashboard screen

[0752] Step 3:

[0753] Users request financial advice from the dashboard screen and enter specific prompts such as "I'm worried about unexpected expenses."

[0754] Input: Prompt message

[0755] Output: Financial advice request

[0756] Step 4:

[0757] The user's terminal sends a financial advice request to the server.

[0758] Input: Financial advice request

[0759] Output: Sending a request to the server

[0760] Step 5:

[0761] Based on the user's identification information, the server collects financial data from the following data sources:

[0762] Retrieve bank account information, transaction history, and balance from bank APIs.

[0763] Retrieve insurance contract information, premiums, and coverage details from the insurance API.

[0764] Retrieve loan contract information, outstanding balance, and interest rate from the loan API.

[0765] Input: User identification information

[0766] Output: Various financial data collected

[0767] Step 6:

[0768] The server integrates various acquired financial data to create a unified financial dataset.

[0769] Input: Collected financial data

[0770] Output: Integrated financial dataset

[0771] Step 7:

[0772] The server sends the integrated dataset to the generation engine.

[0773] Input: Integrated financial dataset

[0774] Output: Sending the dataset to the generation engine

[0775] Step 8:

[0776] The generation engine analyzes the integrated dataset to assess the user's financial situation. Specifically, it evaluates the balance between income and expenses, assesses loan risk, and evaluates the appropriateness of insurance.

[0777] Input: Integrated financial dataset

[0778] Output: Initial advice

[0779] Step 9:

[0780] The emotion engine recognizes the user's emotions. It analyzes the user's voice tone, facial expressions, text input, etc., to generate emotional information.

[0781] Input: User's voice tone, facial expression, and text input

[0782] Output: Emotional information

[0783] Step 10:

[0784] The emotion engine feeds back the recognized emotion information to the generation engine.

[0785] Input: Emotional information

[0786] Output: Feedback to the generation engine

[0787] Step 11:

[0788] The generation engine incorporates emotional information to produce the final financial advice.

[0789] Input: Initial advice, emotional information

[0790] Output: Final Financial Advice

[0791] Step 12:

[0792] The generation engine sends the final financial advice it has generated to the server.

[0793] Input: Final Financial Advice

[0794] Output: Sending advice to the server

[0795] Step 13:

[0796] The server sends the final financial advice to the user's terminal.

[0797] Input: Final Financial Advice

[0798] Output: Sending advice to the user's terminal

[0799] Step 14:

[0800] The user's terminal displays the received advice on its screen.

[0801] Input: Final Financial Advice

[0802] Output: Screen display

[0803] Step 15:

[0804] The user reviews the financial advice displayed on the screen and decides on their next course of action.

[0805] Input: Advice displayed on screen

[0806] Output: User decision

[0807] (Application Example 2)

[0808] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0809] Traditional financial advisory systems relied solely on the user's financial data, failing to consider their emotions. This made it difficult to provide appropriate advice to users who were feeling anxious about their current financial situation. Furthermore, there was a lack of systems capable of providing emotionally responsive advice, resulting in a lack of services that considered the user's psychological state.

[0810] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0811] In this invention, the server includes means for collecting user financial data, means for aggregating and integrating the financial data, means for collecting and analyzing emotional data, means for generating financial advice that takes emotional data into consideration, and means for presenting the generated financial advice to the user. This makes it possible to provide advice that takes into account not only the user's financial situation but also their emotions at that time.

[0812] "Means for collecting users' financial data" refers to devices or programs for obtaining users' deposit account information, insurance contract information, and loan contract information from various financial institutions and services.

[0813] "Means for aggregating and integrating financial data" refers to a device or program that centrally compiles acquired user financial data and creates a dataset in a unified format.

[0814] A "generation engine means" is a device or program that analyzes aggregated financial data, evaluates the user's financial situation, and then generates appropriate financial advice.

[0815] "An emotion engine means for collecting and analyzing user emotion data" refers to a device or program for identifying and analyzing emotions from a user's voice tone, facial expressions, text input, etc.

[0816] "Means for generating financial advice that takes emotional data into consideration" refers to a device or program for generating financial advice that reflects the user's mental state, based on emotional data identified by an emotional engine.

[0817] "Means for presenting generated financial advice to the user" refers to a device or program that displays and allows the user to confirm the financial advice obtained by the generation engine and emotion engine on the user's terminal.

[0818] This invention is a system that collects users' financial and emotional data, integrates and analyzes them, and provides appropriate financial advice. The system consists of a user terminal, a server, a generation engine, and an emotional engine.

[0819] Hardware and software configuration

[0820] 1. User terminal:

[0821] smartphone

[0822] Installed applications (Android, iOS)

[0823] 2. Server:

[0824] Cloud servers (AWS, GCP, etc.)

[0825] 3. Software:

[0826] API integration module (acquires data from various financial institutions)

[0827] Emotion recognition engine (Google Cloud Speech-to-Text API, OpenCV)

[0828] Data analysis engine (Google TensorFlow, PyTorch)

[0829] Natural Language Processing Engine (OpenAI GPT)

[0830] Processing flow

[0831] 1. User Authentication and Login

[0832] Users log in using a smartphone app. Login information is sent to the server, where the user's identity is verified.

[0833] 2. Data Collection

[0834] The server uses an API integration module based on login information to collect users' financial data, such as banking data, insurance data, and loan data. This data is centrally aggregated to create an integrated dataset.

[0835] 3. Emotion recognition

[0836] The system collects the user's voice tone and facial expressions using the smartphone's microphone and camera. The voice data is converted to text using the Google Cloud Speech-to-Text API, and the facial expression data is analyzed using OpenCV. This data is then processed by an emotion engine to identify the user's emotions.

[0837] 4. Data Analysis

[0838] The integrated financial and sentiment datasets are analyzed using TensorFlow. Considering the user's financial status and emotional state, an appropriate financial advice generator produces relevant financial advice.

[0839] 5. Providing financial advice

[0840] Using a natural language processing engine (OpenAI GPT), the analysis results are converted into a format that is easy for the user to understand. The server sends the generated advice to the user's terminal, where the user can review it.

[0841] Specific examples and prompt statements

[0842] For example, if a user is worried about unexpected expenses, a response can be generated using a prompt message like the following.

[0843] Voice and facial expression input

[0844] User's voice: "I'm worried about unexpected expenses lately."

[0845] Facial expression: A tense face

[0846] App analysis and response

[0847] Emotional Engine Result: Anxiety

[0848] Financial data analysis results: Savings are not sufficient, but there is a monthly surplus of approximately 10,000 yen.

[0849] advice:

[0850] "Considering your current financial situation, I recommend setting aside a portion of your monthly surplus to prepare for unexpected expenses. Specifically, you could start by saving 3,000 yen per month."

[0851] Prompt example

[0852] User's voice: "I'm worried about unexpected expenses lately."

[0853] User's facial expression: A tense expression

[0854] Financial data:

[0855] Bank account balance: 500,000

[0856] Monthly income: 300,000

[0857] Monthly expenses: 200,000

[0858] Loan: Car loan, remaining balance 100,000 yen, monthly payment 10,000 yen.

[0859] Based on the analysis results, what kind of financial advice will you provide to the user?

[0860] Thus, by considering not only the user's financial data but also their emotions at that time, the present invention makes it possible to provide more personalized and appropriate financial advice.

[0861] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0862] Step 1:

[0863] User authentication and login

[0864] The user launches the application on their smartphone and enters their login information (user ID and password). The submitted login information is sent to the server and stored as user identification information.

[0865] Input: User ID, Password

[0866] Output: User identification authentication result

[0867] Step 2:

[0868] Data collection

[0869] Based on authenticated user identification information, the server uses an API integration module to retrieve user financial data (bank data, insurance data, loan data) from various financial institutions. This data is centrally aggregated on the server, creating an integrated dataset.

[0870] Input: User identification information

[0871] Output: Integrated financial dataset

[0872] Step 3:

[0873] emotion recognition

[0874] The system uses the microphone and camera on the user's device to collect the user's voice and facial expressions. The voice data is transcribed using the Google Cloud Speech-to-Text API, and the facial expression data is analyzed using OpenCV. An emotion engine then identifies the user's emotions from this data.

[0875] Input: User's voice and facial expression data

[0876] Output: Identified sentiment data

[0877] Step 4:

[0878] Data Analysis

[0879] The server analyzes an integrated financial dataset and identified sentiment data using TensorFlow. Considering the financial status and the user's sentiment state, the generative engine generates appropriate financial advice using a generative AI model.

[0880] Input: Integrated financial dataset, identified sentiment data

[0881] Output: Generated financial advice

[0882] Step 5:

[0883] Providing financial advice

[0884] The generated financial advice is converted into a user-friendly format using a natural language processing engine (OpenAI GPT). The server then sends the converted financial advice to the user's terminal, allowing the user to review it and decide on their next course of action.

[0885] Input: Generated financial advice

[0886] Output: Financial advice presented to the user

[0887] In this way, this system analyzes the user's financial and emotional data through multiple steps and provides optimal financial advice tailored to each individual's situation.

[0888] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0889] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0890] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0891] [Third Embodiment]

[0892] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0893] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0894] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0895] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0896] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0897] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0898] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0899] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0900] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0901] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0902] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0903] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0904] This invention is a system that collects users' financial data, integrates and analyzes it centrally, and provides users with appropriate financial advice. This system mainly consists of three elements: a user terminal, a server, and a generation engine.

[0905] First, the user launches the application to obtain financial advice and requests it. The user's device sends this request to the server. The request includes the user's identification information.

[0906] The server collects the following data based on the user's identification information.

[0907] 1. Bank data: Includes information such as bank account details, transaction history, and balance.

[0908] 2. Insurance data: Includes information such as insurance contract details, premiums, and coverage details.

[0909] 3. Loan data: Includes information such as loan agreement details, outstanding balance, and interest rate.

[0910] The server executes multiple API requests and retrieves this data. Next, the server centrally aggregates the retrieved data to create a unified dataset showing the user's financial status.

[0911] The generation engine receives this integrated dataset and performs data analysis. This analysis includes evaluating the data, assessing the balance between income and expenses, assessing loan risk, and evaluating the appropriateness of insurance. The generation engine uses natural language processing techniques to generate financial advice in a format that is easy for users to understand.

[0912] The advice generated by the generation engine is sent back to the user's terminal via the server. The user's terminal displays this in an appropriate format and provides it to the user.

[0913] As a concrete example, when a user wants to understand their asset status, the system works as follows:

[0914] 1. The user launches the application and submits an advice request.

[0915] 2. The server sequentially retrieves bank data, insurance data, and loan data based on the user's ID.

[0916] 3. The server centrally aggregates this data and generates an integrated dataset.

[0917] 4. The generation engine analyzes this dataset and generates financial advice such as, "Your current income and expenses are well balanced, but you have insufficient emergency savings, so we recommend you increase your savings a little more."

[0918] 5. The server sends this advice to the user's terminal.

[0919] 6. The user terminal will display advice on the screen so that the user can confirm it.

[0920] In this way, users can easily obtain specific advice based on their own financial situation.

[0921] The following describes the processing flow.

[0922] Step 1:

[0923] Users launch a mobile or web application and log in to receive financial advice.

[0924] Step 2:

[0925] The user clicks the "Request Advice" button. This action sends an advice request from the user's terminal to the server.

[0926] Step 3:

[0927] The user's terminal sends a request to the server that includes user identification information (such as a user ID).

[0928] Step 4:

[0929] The server receives the user ID and sequentially sends data retrieval requests to multiple external API services (such as banks, insurance companies, and loan services).

[0930] Step 5:

[0931] The server collects data using the following steps:

[0932] To retrieve bank data, a request is sent to https: / / api.bank.com / userdata. This will return bank account information, transaction history, balance, etc.

[0933] To retrieve insurance data, a request is sent to https: / / api.insurance.com / userdata. This will return information such as insurance policy details, premiums, and coverage details.

[0934] To retrieve loan data, send a request to https: / / api.loan.com / userdata. This will return loan contract information, outstanding balance, interest rate, etc.

[0935] Step 6:

[0936] The data acquired by the server is centrally aggregated and integrated to create a unified dataset. This dataset includes banking data, insurance data, and loan data.

[0937] Step 7:

[0938] The server sends the integrated dataset to the generation engine.

[0939] Step 8:

[0940] The generation engine analyzes the integrated dataset to assess the user's financial situation. This assessment includes:

[0941] Assessment of the current balance of income and expenses

[0942] Loan risk assessment

[0943] Assessment of insurance suitability

[0944] Step 9:

[0945] The generation engine uses natural language processing technology to generate financial advice in a way that is easy for the user to understand. For example, it might generate advice such as, "Your current balance of income and expenses is good, but you lack sufficient emergency savings, so we recommend increasing your savings."

[0946] Step 10:

[0947] The generation engine sends the generated financial advice back to the server.

[0948] Step 11:

[0949] The server sends the financial advice received from the generation engine to the user's terminal.

[0950] Step 12:

[0951] The user's terminal displays the transmitted financial advice on its screen. This allows the user to see specific advice based on their own financial situation.

[0952] (Example 1)

[0953] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0954] In modern society, many users manage various financial data provided by multiple financial institutions and insurance companies, but it is difficult to centrally manage and analyze this data and obtain appropriate financial advice. This challenge is particularly evident when information such as income, expenses, loan agreements, and insurance policies are dispersed. Users want to accurately understand their financial situation and receive specific advice to improve it, but current systems lack methods to efficiently provide this.

[0955] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0956] In this invention, the server includes means for a user to request financial advice, means for collecting financial data based on the user's identification information, means for integrating the collected financial data, means for analyzing the integrated financial data to generate financial advice, and means for displaying the generated financial advice. This makes it possible for users to obtain specific and easy-to-understand financial advice from centrally managed financial data.

[0957] "Means for users to request financial advice" refers to the interface and related functions that allow users to request financial advice through the application.

[0958] "Means of collecting financial data based on user identification information" refers to a mechanism that automatically acquires relevant financial data from banks, insurance companies, lenders, etc., using user identification information such as IDs.

[0959] "Means for integrating collected financial data" refers to a function that centrally organizes and aggregates user financial data collected from multiple data sources to generate an integrated dataset.

[0960] "Means of analyzing integrated financial data to generate financial advice" refers to algorithms and engines that analyze aggregated financial data and generate specific and appropriate financial advice for users.

[0961] "Means for displaying generated financial advice" refers to an interface and functionality for sending the generated advice to the user's terminal and presenting it in a visual format on the application screen.

[0962] "Bank data" refers to information about a user's bank account, including transaction history and balance.

[0963] "Insurance data" refers to information about the insurance policies a user has contracted, such as premiums and coverage details.

[0964] "Loan contract data" refers to information about loan agreements entered into by users, such as outstanding balance and interest rates.

[0965] "Natural language processing technology" refers to the technology that enables computers to understand and generate human language, and specifically includes the use of text analysis and generative AI models.

[0966] This invention is a system that collects users' financial data, integrates and analyzes it centrally, and provides users with appropriate financial advice. This system mainly consists of three elements: a user terminal, a server, and a generation engine.

[0967] First, the user launches the application to obtain financial advice and requests it. The user's device sends this request to the server. The request includes the user's identification information.

[0968] The server collects the following data based on the user's identification information.

[0969] 1. Bank data: Includes information such as bank account details, transaction history, and balance.

[0970] 2. Insurance data: Includes information such as insurance contract details, premiums, and coverage details.

[0971] 3. Loan agreement data: Includes information such as loan agreement details, outstanding balance, and interest rate.

[0972] The server executes multiple API requests to retrieve this data. For example, it can utilize banking APIs, insurance data APIs, and loan data APIs. The server then centrally aggregates the retrieved data to create a unified dataset showing the user's financial situation. This dataset is stored in a database server (e.g., MySQL or PostgreSQL).

[0973] The generation engine receives this integrated dataset and performs data analysis. This analysis includes evaluating the data, assessing the balance between income and expenses, assessing loan risk, and evaluating the appropriateness of insurance. The generation engine uses natural language processing techniques (e.g., Google Cloud Natural Language API or OpenAI's GPT model) to generate financial advice in a format that is easy for users to understand.

[0974] The advice generated by the generation engine is sent back to the user's terminal via the server. The user's terminal displays this in an appropriate format and provides it to the user. The application's user interface (e.g., React.js, Flutter, React Native) provides the information in a visually easy-to-understand manner.

[0975] As a concrete example, when a user wants to understand their asset status, the system works as follows:

[0976] 1. The user launches the application and submits an advice request.

[0977] 2. The server sequentially retrieves bank data, insurance data, and loan contract data based on the user's ID.

[0978] 3. The server centrally aggregates this data and generates an integrated dataset.

[0979] 4. The generation engine analyzes this dataset and generates financial advice such as, "Your current income and expenses are well balanced, but you have insufficient emergency savings, so we recommend you increase your savings a little more."

[0980] 5. The server sends this advice to the user's terminal.

[0981] 6. The user terminal will display advice on the screen so that the user can confirm it.

[0982] Example of a prompt:

[0983] User: Please evaluate my assets.

[0984] Server: We are collecting data, please wait a moment.

[0985] Server: Data collection and integration complete. Generating advice.

[0986] Server: Your income and expenses are well balanced, but your emergency savings are low, so I recommend increasing your savings a bit more.

[0987] User terminal: Advice displayed. "Your income and expenses are well balanced, but your emergency savings are low, so we recommend you increase your savings a little more."

[0988] In this way, users can easily obtain specific advice based on their own financial situation.

[0989] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0990] Program processing flow

[0991] Step 1: User Request

[0992] The user launches the application, types "Please appraise my assets," and presses the submit button. The input data consists of the user's identification information (e.g., user ID) and the request content. This causes the user's terminal to send the request and identification information to the server.

[0993] Input: User identification information, advice request

[0994] Output: Sending a request to the server

[0995] Step 2: Data collection by the server

[0996] Based on the received identification information, the server collects the user's financial data using bank APIs, insurance APIs, loan APIs, etc. Specifically, the server sends API requests and retrieves the necessary information (transaction history, insurance contract information, loan contract information, etc.) from each data source.

[0997] Input: User identification information

[0998] Output: Collected financial data (bank data, insurance data, loan data)

[0999] Step 3: Server-based data integration

[1000] The server temporarily stores the collected financial data in storage and then integrates it to generate a single unified dataset. This includes data preprocessing and cleaning.

[1001] Input: Collected financial data

[1002] Output: Integrated financial dataset

[1003] Step 4: Analysis by the generation engine

[1004] The generation engine receives an integrated dataset and performs analyses such as income and expenditure balance assessment, loan risk assessment, and insurance suitability assessment. It also uses natural language processing technology to generate financial advice in a format that is easy for users to understand.

[1005] Input: Integrated financial dataset

[1006] Output: Generated financial advice

[1007] Step 5: Server sends advice

[1008] The server receives the financial advice generated by the generation engine and sends it to the user's terminal. The advice is then converted to an appropriate format (e.g., JSON).

[1009] Input: Generated financial advice

[1010] Output: Sending advice to the user terminal

[1011] Step 6: Advice display via user terminal

[1012] The user's device receives advice sent from the server and displays it to the user in a visually easy-to-understand format. For example, a message such as "Your income and expenses are well balanced, but your emergency savings are low, so we recommend you increase your savings a little more" might appear on the smartphone screen.

[1013] Input: Financial advice sent from the server

[1014] Output: Display of advice

[1015] This process allows users to quickly and accurately receive specific advice based on their financial data.

[1016] (Application Example 1)

[1017] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1018] In modern society, many users find it difficult to manage and understand the multiple financial data points provided by financial institutions, insurance companies, and loan companies. This makes it challenging to properly grasp their financial situation and create effective financial plans. Furthermore, there is a lack of systems that allow users to understand and respond immediately to real-time changes in their financial situation. Therefore, there is a need for a system that allows users to comprehensively manage their own financial status and receive immediate advice.

[1019] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1020] In this invention, the server includes means for collecting users' financial data, means for aggregating and integrating said financial data, means for a generation engine that analyzes the aggregated financial data to generate financial advice, means for presenting the generated financial advice to the user in real time through an application installed on their smartphone, and means for notifying the user when their financial situation changes using a status notification function. As a result, users can grasp their financial situation in real time and receive timely and accurate financial advice.

[1021] "Means of collecting users' financial data" refers to a system for obtaining financial information provided by users from multiple financial institutions, insurance companies, and loan companies.

[1022] "Means for aggregating and integrating the financial data" refers to a method of centrally compiling acquired financial information and integrating the data in order to understand the user's overall financial situation.

[1023] A "generative engine that analyzes aggregated financial data to generate financial advice" refers to an algorithm and process for analyzing integrated financial data and providing advice to users in an easily understandable format based on that analysis.

[1024] "A means of presenting generated financial advice to users in real time through an application installed on their smartphone" refers to a technology that notifies users of instantly generated financial advice via an application installed on their smartphone.

[1025] "A means of notifying users when their financial status changes using a status notification function" refers to a mechanism that uses a pre-configured notification function to inform users in real time when there is a significant change in their financial status.

[1026] This invention is a system that collects and integrates users' financial data and provides real-time financial advice. The system consists of the following elements:

[1027] System Overview:

[1028] 1. User terminal:

[1029] It is a smartphone used by the user, and applications are installed on it.

[1030] 2. Server:

[1031] A backend system that processes data requests sent from user terminals and collects and integrates users' financial data.

[1032] 3. Generation Engine:

[1033] Designing an algorithm that analyzes aggregated financial data and generates financial advice for users.

[1034] 4. Notification system:

[1035] It monitors changes in financial status in real time and sends notifications to users as needed.

[1036] Data collection:

[1037] The server collects the following data based on the user ID.

[1038] Bank data: Bank account information, transaction history, and balance.

[1039] Insurance data: Details of the insurance contract, premiums, and coverage.

[1040] Loan data: Loan agreement information, balance, and interest rate.

[1041] The server automatically retrieves this data from multiple financial institutions using RESTful APIs. Secure communication is ensured by providing the necessary API endpoints and authentication keys.

[1042] Data integration:

[1043] The server centrally aggregates the acquired financial data and generates integrated datasets for each user. This allows for the unified management of information obtained from multiple data sources.

[1044] Data analysis and advice generation:

[1045] The generation engine analyzes the integrated dataset using natural language processing technology. Specifically, it performs data evaluation, income and expenditure balance assessment, loan risk assessment, and insurance suitability assessment. Based on the analysis results, it generates financial advice like the example below.

[1046] Example of a prompt:

[1047] "Requesting advice based on financial data for user ID: 12345: Bank balance: 500,000 yen, Insurance policies: 2, Loan balance: 600,000 yen"

[1048] Offering advice:

[1049] The generated financial advice is sent back to the user's terminal via the server. The user's terminal displays the advice on the screen in real time for the user to review. In addition, a status notification function is used to immediately notify the user when there are changes in the financial situation.

[1050] As a concrete example, if a user sends a request through the application saying, "I want to know my asset status," the following process will be executed.

[1051] An advice message is generated and displayed on the user's smartphone stating, "Your total balance is good, but your debt is a little high. Please review your repayment plan."

[1052] This system allows users to always have an up-to-date understanding of their financial situation and receive accurate and timely advice.

[1053] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1054] Step 1:

[1055] The user launches a smartphone application and requests financial advice.

[1056] Input: User ID and request information.

[1057] Specific operation: The user terminal sends the user ID and request to the server.

[1058] Step 2:

[1059] The server retrieves bank data, insurance data, and loan data based on the user ID.

[1060] Input: User ID.

[1061] Specific operation: The server uses a RESTful API to retrieve data from financial institutions, insurance companies, and loan companies.

[1062] Output: Bank data, insurance data, loan data.

[1063] Step 3:

[1064] The system centrally aggregates the data acquired by the servers and generates an integrated dataset.

[1065] Input: Bank data, insurance data, loan data.

[1066] Specific operation: The server integrates the data and compiles it into a dataset in a standard format.

[1067] Output: Integrated dataset.

[1068] Step 4:

[1069] The generation engine analyzes the integrated dataset and generates financial advice.

[1070] Input: Integrated dataset.

[1071] Specific operation: The generation engine uses natural language processing techniques to analyze data and generate advice.

[1072] Output: Financial advice.

[1073] Step 5:

[1074] The generated financial advice is sent to the user's terminal via the server.

[1075] Input: Financial advice.

[1076] Specific operation: The server sends the generated advice to the user's terminal.

[1077] Output: Financial advice is displayed on the user's terminal.

[1078] Step 6:

[1079] The user terminal displays advice on the screen in real time and uses a status notification function to notify the user when the financial situation changes.

[1080] Input: Financial advice and information on changes in financial condition.

[1081] Specific operation: The user's terminal displays advice and sends real-time notifications when there are changes in the financial situation.

[1082] Output: Users receive advice in real time and are notified in a timely manner.

[1083] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1084] This invention provides a system that collects, integrates, and analyzes users' financial data to offer financial advice, and also includes a function to recognize users' emotions. The system consists of a user terminal, a server, a generation engine, and an emotion engine.

[1085] First, the user requests financial advice by launching the application and logging in. This request is sent from the user's device to the server. The request includes the user's identification information.

[1086] The server collects the following data based on the user's identification information.

[1087] 1. Bank data: Bank account information, transaction history, balance, etc.

[1088] 2. Insurance data: Insurance contract information, premiums, coverage details, etc.

[1089] 3. Loan data: Loan contract information, outstanding balance, interest rate, etc.

[1090] The server executes multiple API requests to retrieve this data. The server then centrally aggregates the retrieved financial data to create a unified dataset. This unified dataset is then sent to the generation engine.

[1091] The generation engine analyzes the integrated dataset to assess the user's financial situation. This assessment process includes data evaluation, income and expenditure balance assessment, loan risk assessment, and insurance suitability assessment. Then, using natural language processing technology, it generates financial advice in a format that is easy for the user to understand.

[1092] The emotion engine functions as a means of recognizing the user's emotions. It employs technology to identify emotions from the user's tone of voice, facial expressions, and text input. This emotional information is fed back to the generation engine and considered along with the analysis results.

[1093] For example, if a user is feeling anxious about unexpected expenses, the emotion engine recognizes that anxiety. The generation engine then reflects this emotional information and generates more reassuring advice, such as, "Your current financial situation is good, but we recommend saving some more to be prepared for unexpected expenses."

[1094] The advice generated by the generation engine is sent to the user terminal via the server. The user terminal displays this advice on the screen, and the user can review it.

[1095] Thus, the present invention makes it possible to provide the most appropriate and acceptable advice to the user by taking into account not only the user's financial situation but also their emotions at that time.

[1096] The following describes the processing flow.

[1097] Step 1:

[1098] Users launch a mobile or web application and log in to receive financial advice.

[1099] Step 2:

[1100] The user clicks the "Request Advice" button. This action sends an advice request from the user's terminal to the server.

[1101] Step 3:

[1102] The user's terminal sends a request to the server that includes user identification information (such as a user ID).

[1103] Step 4:

[1104] The server receives the user ID and sequentially sends data retrieval requests to multiple external API services (such as banks, insurance companies, and loan services).

[1105] Step 5:

[1106] The server collects data using the following steps:

[1107] To retrieve bank data, a request is sent to https: / / api.bank.com / userdata. This will return bank account information, transaction history, balance, etc.

[1108] To retrieve insurance data, a request is sent to https: / / api.insurance.com / userdata. This will return information such as insurance policy details, premiums, and coverage details.

[1109] To retrieve loan data, send a request to https: / / api.loan.com / userdata. This will return loan contract information, outstanding balance, interest rate, etc.

[1110] Step 6:

[1111] The data acquired by the server is centrally aggregated and integrated to create a unified dataset. This dataset includes banking data, insurance data, and loan data.

[1112] Step 7:

[1113] The user's device sends emotional data (such as tone of voice, facial expressions, and text input) to the emotion engine.

[1114] Step 8:

[1115] The emotion engine analyzes the user's emotional data to recognize the user's current emotional state. This information is then used for subsequent analysis.

[1116] Step 9:

[1117] The server sends the integrated dataset and sentiment data from the sentiment engine to the generation engine.

[1118] Step 10:

[1119] The generation engine analyzes the integrated dataset to assess the user's financial situation. This assessment includes:

[1120] Assessment of the current balance of income and expenses

[1121] Loan risk assessment

[1122] Assessment of insurance suitability

[1123] Step 11:

[1124] The generation engine uses natural language processing technology to generate financial advice in a way that is easy for the user to understand. It also considers sentiment data from the sentiment engine to adjust the content and presentation of the advice.

[1125] Step 12:

[1126] The generation engine sends the generated financial advice back to the server.

[1127] Step 13:

[1128] The server sends the advice it received from the generation engine to the user's terminal.

[1129] Step 14:

[1130] The user's terminal displays the transmitted financial advice on the screen. This allows the user to see specific advice based on their financial situation, as well as receive thoughtful advice that takes their emotions into consideration.

[1131] (Example 2)

[1132] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1133] Traditional financial advisory systems often only consider the user's financial situation, failing to provide advice that takes into account their emotions and psychological state. As a result, there was a lack of appropriate advice that was easily accepted by users. Furthermore, by ignoring emotional aspects such as stress and anxiety, advice was often not followed.

[1134] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1135] In this invention, the server includes means for collecting the user's financial data, means for aggregating and integrating the financial data, means for analyzing the aggregated financial data to generate financial advice, means for presenting the generated financial advice to the user, means for recognizing the user's emotions, and means for adjusting the financial advice based on the recognized emotional information. This makes it possible to provide advice that takes into account not only the user's financial situation but also their emotional state at any given time.

[1136] A "user" is an individual or organization that uses the system to receive financial advice.

[1137] "Financial data" refers to data that includes information about a user's bank accounts, insurance policies, and loan agreements.

[1138] "Collection method" refers to the function of obtaining users' financial data from various data sources.

[1139] "Integration means" refers to a function that centrally aggregates different types of financial data and creates an integrated dataset.

[1140] "Generative means" refers to technology that analyzes integrated financial data and creates advice for users.

[1141] "Presentation means" refers to the function of displaying and providing advice created by the generation means to the user.

[1142] "Emotion recognition means" refers to technology that recognizes emotions from the user's voice, facial expressions, text input, etc.

[1143] "Adjustment mechanisms" refer to functions that appropriately modify the generated financial advice in accordance with the perceived emotional information.

[1144] This invention relates to a system that collects, integrates, and analyzes users' financial data, and further recognizes users' emotions to generate and provide financial advice. This system consists of a "user terminal," a "server," a "generation engine," and an "emotion engine."

[1145] Hardware and software overview:

[1146] User devices include smartphones, tablets, and personal computers. These devices have applications installed for requesting and receiving financial advice.

[1147] The servers utilize cloud environments or on-premises servers. They collect, aggregate, and integrate data, send it to the generation and sentiment engines, and provide advice.

[1148] The generation engine is a software module that analyzes aggregated financial data and generates financial advice. It primarily uses natural language processing techniques to generate advice.

[1149] The emotion engine is a software module that recognizes a user's emotions using speech recognition, facial expression recognition, and text analysis.

[1150] System operation details:

[1151] 1. The user launches the application and logs in. This allows the user's identification information to be obtained.

[1152] 2. The user terminal provides an interface for requesting financial advice, and the user enters a specific request (e.g., "I'm worried about unexpected expenses").

[1153] 3. Based on the user's identification information, the server collects financial data from the following data sources:

[1154] Retrieve bank account information, transaction history, and balance from bank APIs.

[1155] Retrieve insurance contract information, premiums, and coverage details from the insurance API.

[1156] Retrieve loan contract information, outstanding balance, and interest rate from the loan API.

[1157] 4. The server integrates this data to create a centralized financial dataset.

[1158] 5. The server sends the dataset to the generation engine.

[1159] 6. The generation engine analyzes the dataset and evaluates the user's financial situation:

[1160] Evaluation of the balance between income and expenses

[1161] Loan risk assessment

[1162] Assessment of insurance suitability

[1163] 7. The generation engine uses natural language processing technology to generate financial advice.

[1164] 8. Simultaneously, the emotion engine analyzes the user's voice, facial expressions, and text input to recognize their emotional state:

[1165] Voice tone analysis

[1166] facial expression recognition

[1167] Text analysis

[1168] 9. The emotion engine feeds back the recognized emotion information to the generation engine.

[1169] 10. The generation engine reflects emotional information and generates appropriate and reassuring advice for the user.

[1170] 11. The server sends the generated advice to the user's terminal.

[1171] 12. The user terminal displays advice on the screen and notifies the user.

[1172] Specific example:

[1173] When a user enters the prompt "I'm worried about unexpected expenses," the server collects and integrates bank data (account balance and transaction history), insurance data (insurance policy details and premiums), and loan data (outstanding balance and interest rates). The generation engine analyzes this data to assess the user's financial situation. Simultaneously, the emotion engine recognizes anxiety from the user's voice and facial expressions. Finally, the generation engine generates reassuring advice such as "Your current financial situation is good, but we recommend saving some more to be prepared for unexpected expenses," and displays it on the device.

[1174] Thus, the present invention provides comprehensive financial advice that takes into account not only financial data but also the user's emotional state.

[1175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1176] Step 1:

[1177] The user launches the application and enters their login information (user ID, password).

[1178] Input: User ID, Password

[1179] Output: Authentication Request

[1180] Step 2:

[1181] The server receives the authentication request and verifies the authentication information. If authentication is successful, it returns the dashboard screen.

[1182] Input: Authentication Request

[1183] Output: Authentication results, dashboard screen

[1184] Step 3:

[1185] Users request financial advice from the dashboard screen and enter specific prompts such as "I'm worried about unexpected expenses."

[1186] Input: Prompt message

[1187] Output: Financial advice request

[1188] Step 4:

[1189] The user's terminal sends a financial advice request to the server.

[1190] Input: Financial advice request

[1191] Output: Sending a request to the server

[1192] Step 5:

[1193] Based on the user's identification information, the server collects financial data from the following data sources:

[1194] Retrieve bank account information, transaction history, and balance from bank APIs.

[1195] Retrieve insurance contract information, premiums, and coverage details from the insurance API.

[1196] Retrieve loan contract information, outstanding balance, and interest rate from the loan API.

[1197] Input: User identification information

[1198] Output: Various financial data collected

[1199] Step 6:

[1200] The server integrates various acquired financial data to create a unified financial dataset.

[1201] Input: Collected financial data

[1202] Output: Integrated financial dataset

[1203] Step 7:

[1204] The server sends the integrated dataset to the generation engine.

[1205] Input: Integrated financial dataset

[1206] Output: Sending the dataset to the generation engine

[1207] Step 8:

[1208] The generation engine analyzes the integrated dataset to assess the user's financial situation. Specifically, it evaluates the balance between income and expenses, assesses loan risk, and evaluates the appropriateness of insurance.

[1209] Input: Integrated financial dataset

[1210] Output: Initial advice

[1211] Step 9:

[1212] The emotion engine recognizes the user's emotions. It analyzes the user's voice tone, facial expressions, text input, etc., to generate emotional information.

[1213] Input: User's voice tone, facial expression, and text input

[1214] Output: Emotional information

[1215] Step 10:

[1216] The emotion engine feeds back the recognized emotion information to the generation engine.

[1217] Input: Emotional information

[1218] Output: Feedback to the generation engine

[1219] Step 11:

[1220] The generation engine incorporates emotional information to produce the final financial advice.

[1221] Input: Initial advice, emotional information

[1222] Output: Final Financial Advice

[1223] Step 12:

[1224] The generation engine sends the final financial advice it has generated to the server.

[1225] Input: Final Financial Advice

[1226] Output: Sending advice to the server

[1227] Step 13:

[1228] The server sends the final financial advice to the user's terminal.

[1229] Input: Final Financial Advice

[1230] Output: Sending advice to the user's terminal

[1231] Step 14:

[1232] The user's terminal displays the received advice on its screen.

[1233] Input: Final Financial Advice

[1234] Output: Screen display

[1235] Step 15:

[1236] The user reviews the financial advice displayed on the screen and decides on their next course of action.

[1237] Input: Advice displayed on screen

[1238] Output: User decision

[1239] (Application Example 2)

[1240] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1241] Traditional financial advisory systems relied solely on the user's financial data, failing to consider their emotions. This made it difficult to provide appropriate advice to users who were feeling anxious about their current financial situation. Furthermore, there was a lack of systems capable of providing emotionally responsive advice, resulting in a lack of services that considered the user's psychological state.

[1242] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1243] In this invention, the server includes means for collecting user financial data, means for aggregating and integrating the financial data, means for collecting and analyzing emotional data, means for generating financial advice that takes emotional data into consideration, and means for presenting the generated financial advice to the user. This makes it possible to provide advice that takes into account not only the user's financial situation but also their emotions at that time.

[1244] "Means for collecting users' financial data" refers to devices or programs for obtaining users' deposit account information, insurance contract information, and loan contract information from various financial institutions and services.

[1245] "Means for aggregating and integrating financial data" refers to a device or program that centrally compiles acquired user financial data and creates a dataset in a unified format.

[1246] A "generation engine means" is a device or program that analyzes aggregated financial data, evaluates the user's financial situation, and then generates appropriate financial advice.

[1247] "An emotion engine means for collecting and analyzing user emotion data" refers to a device or program for identifying and analyzing emotions from a user's voice tone, facial expressions, text input, etc.

[1248] "Means for generating financial advice that takes emotional data into consideration" refers to a device or program for generating financial advice that reflects the user's mental state, based on emotional data identified by an emotional engine.

[1249] "Means for presenting generated financial advice to the user" refers to a device or program that displays and allows the user to confirm the financial advice obtained by the generation engine and emotion engine on the user's terminal.

[1250] This invention is a system that collects users' financial and emotional data, integrates and analyzes them, and provides appropriate financial advice. The system consists of a user terminal, a server, a generation engine, and an emotional engine.

[1251] Hardware and software configuration

[1252] 1. User terminal:

[1253] smartphone

[1254] Installed applications (Android, iOS)

[1255] 2. Server:

[1256] Cloud servers (AWS, GCP, etc.)

[1257] 3. Software:

[1258] API integration module (acquires data from various financial institutions)

[1259] Emotion recognition engine (Google Cloud Speech-to-Text API, OpenCV)

[1260] Data analysis engine (Google TensorFlow, PyTorch)

[1261] Natural Language Processing Engine (OpenAI GPT)

[1262] Processing flow

[1263] 1. User Authentication and Login

[1264] Users log in using a smartphone app. Login information is sent to the server, where the user's identity is verified.

[1265] 2. Data Collection

[1266] The server uses an API integration module based on login information to collect users' financial data, such as banking data, insurance data, and loan data. This data is centrally aggregated to create an integrated dataset.

[1267] 3. Emotion recognition

[1268] The system collects the user's voice tone and facial expressions using the smartphone's microphone and camera. The voice data is converted to text using the Google Cloud Speech-to-Text API, and the facial expression data is analyzed using OpenCV. This data is then processed by an emotion engine to identify the user's emotions.

[1269] 4. Data Analysis

[1270] The integrated financial and sentiment datasets are analyzed using TensorFlow. Considering the user's financial status and emotional state, an appropriate financial advice generator produces relevant financial advice.

[1271] 5. Providing financial advice

[1272] Using a natural language processing engine (OpenAI GPT), the analysis results are converted into a format that is easy for the user to understand. The server sends the generated advice to the user's terminal, where the user can review it.

[1273] Specific examples and prompt statements

[1274] For example, if a user is worried about unexpected expenses, a response can be generated using a prompt message like the following.

[1275] Voice and facial expression input

[1276] User's voice: "I'm worried about unexpected expenses lately."

[1277] Facial expression: A tense face

[1278] App analysis and response

[1279] Emotional Engine Result: Anxiety

[1280] Financial data analysis results: Savings are not sufficient, but there is a monthly surplus of approximately 10,000 yen.

[1281] advice:

[1282] "Considering your current financial situation, I recommend setting aside a portion of your monthly surplus to prepare for unexpected expenses. Specifically, you could start by saving 3,000 yen per month."

[1283] Prompt example

[1284] User's voice: "I'm worried about unexpected expenses lately."

[1285] User's facial expression: A tense expression

[1286] Financial data:

[1287] Bank account balance: 500,000

[1288] Monthly income: 300,000

[1289] Monthly expenses: 200,000

[1290] Loan: Car loan, remaining balance 100,000 yen, monthly payment 10,000 yen.

[1291] Based on the analysis results, what kind of financial advice will you provide to the user?

[1292] Thus, by considering not only the user's financial data but also their emotions at that time, the present invention makes it possible to provide more personalized and appropriate financial advice.

[1293] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1294] Step 1:

[1295] User authentication and login

[1296] The user launches the application on their smartphone and enters their login information (user ID and password). The submitted login information is sent to the server and stored as user identification information.

[1297] Input: User ID, Password

[1298] Output: User identification authentication result

[1299] Step 2:

[1300] Data collection

[1301] Based on authenticated user identification information, the server uses an API integration module to retrieve user financial data (bank data, insurance data, loan data) from various financial institutions. This data is centrally aggregated on the server, creating an integrated dataset.

[1302] Input: User identification information

[1303] Output: Integrated financial dataset

[1304] Step 3:

[1305] emotion recognition

[1306] The system uses the microphone and camera on the user's device to collect the user's voice and facial expressions. The voice data is transcribed using the Google Cloud Speech-to-Text API, and the facial expression data is analyzed using OpenCV. An emotion engine then identifies the user's emotions from this data.

[1307] Input: User's voice and facial expression data

[1308] Output: Identified sentiment data

[1309] Step 4:

[1310] Data Analysis

[1311] The server analyzes an integrated financial dataset and identified sentiment data using TensorFlow. Considering the financial status and the user's sentiment state, the generative engine generates appropriate financial advice using a generative AI model.

[1312] Input: Integrated financial dataset, identified sentiment data

[1313] Output: Generated financial advice

[1314] Step 5:

[1315] Providing financial advice

[1316] The generated financial advice is converted into a user-friendly format using a natural language processing engine (OpenAI GPT). The server then sends the converted financial advice to the user's terminal, allowing the user to review it and decide on their next course of action.

[1317] Input: Generated financial advice

[1318] Output: Financial advice presented to the user

[1319] In this way, this system analyzes the user's financial and emotional data through multiple steps and provides optimal financial advice tailored to each individual's situation.

[1320] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1321] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1322] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1323] [Fourth Embodiment]

[1324] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1325] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1326] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1327] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1328] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1329] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1330] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1331] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1332] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1333] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1334] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1335] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1336] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1337] This invention is a system that collects users' financial data, integrates and analyzes it centrally, and provides users with appropriate financial advice. This system mainly consists of three elements: a user terminal, a server, and a generation engine.

[1338] First, the user launches the application to obtain financial advice and requests it. The user's device sends this request to the server. The request includes the user's identification information.

[1339] The server collects the following data based on the user's identification information.

[1340] 1. Bank data: Includes information such as bank account details, transaction history, and balance.

[1341] 2. Insurance data: Includes information such as insurance contract details, premiums, and coverage details.

[1342] 3. Loan data: Includes information such as loan agreement details, outstanding balance, and interest rate.

[1343] The server executes multiple API requests and retrieves this data. Next, the server centrally aggregates the retrieved data to create a unified dataset showing the user's financial status.

[1344] The generation engine receives this integrated dataset and performs data analysis. This analysis includes evaluating the data, assessing the balance between income and expenses, assessing loan risk, and evaluating the appropriateness of insurance. The generation engine uses natural language processing techniques to generate financial advice in a format that is easy for users to understand.

[1345] The advice generated by the generation engine is sent back to the user's terminal via the server. The user's terminal displays this in an appropriate format and provides it to the user.

[1346] As a concrete example, when a user wants to understand their asset status, the system works as follows:

[1347] 1. The user launches the application and submits an advice request.

[1348] 2. The server sequentially retrieves bank data, insurance data, and loan data based on the user's ID.

[1349] 3. The server centrally aggregates this data and generates an integrated dataset.

[1350] 4. The generation engine analyzes this dataset and generates financial advice such as, "Your current income and expenses are well balanced, but you have insufficient emergency savings, so we recommend you increase your savings a little more."

[1351] 5. The server sends this advice to the user's terminal.

[1352] 6. The user terminal will display advice on the screen so that the user can confirm it.

[1353] In this way, users can easily obtain specific advice based on their own financial situation.

[1354] The following describes the processing flow.

[1355] Step 1:

[1356] Users launch a mobile or web application and log in to receive financial advice.

[1357] Step 2:

[1358] The user clicks the "Request Advice" button. This action sends an advice request from the user's terminal to the server.

[1359] Step 3:

[1360] The user's terminal sends a request to the server that includes user identification information (such as a user ID).

[1361] Step 4:

[1362] The server receives the user ID and sequentially sends data retrieval requests to multiple external API services (such as banks, insurance companies, and loan services).

[1363] Step 5:

[1364] The server collects data using the following steps:

[1365] To retrieve bank data, a request is sent to https: / / api.bank.com / userdata. This will return bank account information, transaction history, balance, etc.

[1366] To retrieve insurance data, a request is sent to https: / / api.insurance.com / userdata. This will return information such as insurance policy details, premiums, and coverage details.

[1367] To retrieve loan data, send a request to https: / / api.loan.com / userdata. This will return loan contract information, outstanding balance, interest rate, etc.

[1368] Step 6:

[1369] The data acquired by the server is centrally aggregated and integrated to create a unified dataset. This dataset includes banking data, insurance data, and loan data.

[1370] Step 7:

[1371] The server sends the integrated dataset to the generation engine.

[1372] Step 8:

[1373] The generation engine analyzes the integrated dataset to assess the user's financial situation. This assessment includes:

[1374] Assessment of the current balance of income and expenses

[1375] Loan risk assessment

[1376] Assessment of insurance suitability

[1377] Step 9:

[1378] The generation engine uses natural language processing technology to generate financial advice in a way that is easy for the user to understand. For example, it might generate advice such as, "Your current balance of income and expenses is good, but you lack sufficient emergency savings, so we recommend increasing your savings."

[1379] Step 10:

[1380] The generation engine sends the generated financial advice back to the server.

[1381] Step 11:

[1382] The server sends the financial advice received from the generation engine to the user's terminal.

[1383] Step 12:

[1384] The user's terminal displays the transmitted financial advice on its screen. This allows the user to see specific advice based on their own financial situation.

[1385] (Example 1)

[1386] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1387] In modern society, many users manage various financial data provided by multiple financial institutions and insurance companies, but it is difficult to centrally manage and analyze this data and obtain appropriate financial advice. This challenge is particularly evident when information such as income, expenses, loan agreements, and insurance policies are dispersed. Users want to accurately understand their financial situation and receive specific advice to improve it, but current systems lack methods to efficiently provide this.

[1388] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1389] In this invention, the server includes means for a user to request financial advice, means for collecting financial data based on the user's identification information, means for integrating the collected financial data, means for analyzing the integrated financial data to generate financial advice, and means for displaying the generated financial advice. This makes it possible for users to obtain specific and easy-to-understand financial advice from centrally managed financial data.

[1390] "Means for users to request financial advice" refers to the interface and related functions that allow users to request financial advice through the application.

[1391] "Means of collecting financial data based on user identification information" refers to a mechanism that automatically acquires relevant financial data from banks, insurance companies, lenders, etc., using user identification information such as IDs.

[1392] "Means for integrating collected financial data" refers to a function that centrally organizes and aggregates user financial data collected from multiple data sources to generate an integrated dataset.

[1393] "Means of analyzing integrated financial data to generate financial advice" refers to algorithms and engines that analyze aggregated financial data and generate specific and appropriate financial advice for users.

[1394] "Means for displaying generated financial advice" refers to an interface and functionality for sending the generated advice to the user's terminal and presenting it in a visual format on the application screen.

[1395] "Bank data" refers to information about a user's bank account, including transaction history and balance.

[1396] "Insurance data" refers to information about the insurance policies a user has contracted, such as premiums and coverage details.

[1397] "Loan contract data" refers to information about loan agreements entered into by users, such as outstanding balance and interest rates.

[1398] "Natural language processing technology" refers to the technology that enables computers to understand and generate human language, and specifically includes the use of text analysis and generative AI models.

[1399] This invention is a system that collects users' financial data, integrates and analyzes it centrally, and provides users with appropriate financial advice. This system mainly consists of three elements: a user terminal, a server, and a generation engine.

[1400] First, the user launches the application to obtain financial advice and requests it. The user's device sends this request to the server. The request includes the user's identification information.

[1401] The server collects the following data based on the user's identification information.

[1402] 1. Bank data: Includes information such as bank account details, transaction history, and balance.

[1403] 2. Insurance data: Includes information such as insurance contract details, premiums, and coverage details.

[1404] 3. Loan agreement data: Includes information such as loan agreement details, outstanding balance, and interest rate.

[1405] The server executes multiple API requests to retrieve this data. For example, it can utilize banking APIs, insurance data APIs, and loan data APIs. The server then centrally aggregates the retrieved data to create a unified dataset showing the user's financial situation. This dataset is stored in a database server (e.g., MySQL or PostgreSQL).

[1406] The generation engine receives this integrated dataset and performs data analysis. This analysis includes evaluating the data, assessing the balance between income and expenses, assessing loan risk, and evaluating the appropriateness of insurance. The generation engine uses natural language processing techniques (e.g., Google Cloud Natural Language API or OpenAI's GPT model) to generate financial advice in a format that is easy for users to understand.

[1407] The advice generated by the generation engine is sent back to the user's terminal via the server. The user's terminal displays this in an appropriate format and provides it to the user. The application's user interface (e.g., React.js, Flutter, React Native) provides the information in a visually easy-to-understand manner.

[1408] As a concrete example, when a user wants to understand their asset status, the system works as follows:

[1409] 1. The user launches the application and submits an advice request.

[1410] 2. The server sequentially retrieves bank data, insurance data, and loan contract data based on the user's ID.

[1411] 3. The server centrally aggregates this data and generates an integrated dataset.

[1412] 4. The generation engine analyzes this dataset and generates financial advice such as, "Your current income and expenses are well balanced, but you have insufficient emergency savings, so we recommend you increase your savings a little more."

[1413] 5. The server sends this advice to the user's terminal.

[1414] 6. The user terminal will display advice on the screen so that the user can confirm it.

[1415] Example of a prompt:

[1416] User: Please evaluate my assets.

[1417] Server: We are collecting data, please wait a moment.

[1418] Server: Data collection and integration complete. Generating advice.

[1419] Server: Your income and expenses are well balanced, but your emergency savings are low, so I recommend increasing your savings a bit more.

[1420] User terminal: Advice displayed. "Your income and expenses are well balanced, but your emergency savings are low, so we recommend you increase your savings a little more."

[1421] In this way, users can easily obtain specific advice based on their own financial situation.

[1422] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1423] Program processing flow

[1424] Step 1: User Request

[1425] The user launches the application, types "Please appraise my assets," and presses the submit button. The input data consists of the user's identification information (e.g., user ID) and the request content. This causes the user's terminal to send the request and identification information to the server.

[1426] Input: User identification information, advice request

[1427] Output: Sending a request to the server

[1428] Step 2: Data collection by the server

[1429] Based on the received identification information, the server collects the user's financial data using bank APIs, insurance APIs, loan APIs, etc. Specifically, the server sends API requests and retrieves the necessary information (transaction history, insurance contract information, loan contract information, etc.) from each data source.

[1430] Input: User identification information

[1431] Output: Collected financial data (bank data, insurance data, loan data)

[1432] Step 3: Server-based data integration

[1433] The server temporarily stores the collected financial data in storage and then integrates it to generate a single unified dataset. This includes data preprocessing and cleaning.

[1434] Input: Collected financial data

[1435] Output: Integrated financial dataset

[1436] Step 4: Analysis by the generation engine

[1437] The generation engine receives an integrated dataset and performs analyses such as income and expenditure balance assessment, loan risk assessment, and insurance suitability assessment. It also uses natural language processing technology to generate financial advice in a format that is easy for users to understand.

[1438] Input: Integrated financial dataset

[1439] Output: Generated financial advice

[1440] Step 5: Server sends advice

[1441] The server receives the financial advice generated by the generation engine and sends it to the user's terminal. The advice is then converted to an appropriate format (e.g., JSON).

[1442] Input: Generated financial advice

[1443] Output: Sending advice to the user terminal

[1444] Step 6: Advice display via user terminal

[1445] The user's device receives advice sent from the server and displays it to the user in a visually easy-to-understand format. For example, a message such as "Your income and expenses are well balanced, but your emergency savings are low, so we recommend you increase your savings a little more" might appear on the smartphone screen.

[1446] Input: Financial advice sent from the server

[1447] Output: Display of advice

[1448] This process allows users to quickly and accurately receive specific advice based on their financial data.

[1449] (Application Example 1)

[1450] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1451] In modern society, many users find it difficult to manage and understand the multiple financial data points provided by financial institutions, insurance companies, and loan companies. This makes it challenging to properly grasp their financial situation and create effective financial plans. Furthermore, there is a lack of systems that allow users to understand and respond immediately to real-time changes in their financial situation. Therefore, there is a need for a system that allows users to comprehensively manage their own financial status and receive immediate advice.

[1452] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1453] In this invention, the server includes means for collecting users' financial data, means for aggregating and integrating said financial data, means for a generation engine that analyzes the aggregated financial data to generate financial advice, means for presenting the generated financial advice to the user in real time through an application installed on their smartphone, and means for notifying the user when their financial situation changes using a status notification function. As a result, users can grasp their financial situation in real time and receive timely and accurate financial advice.

[1454] "Means of collecting users' financial data" refers to a system for obtaining financial information provided by users from multiple financial institutions, insurance companies, and loan companies.

[1455] "Means for aggregating and integrating the financial data" refers to a method of centrally compiling acquired financial information and integrating the data in order to understand the user's overall financial situation.

[1456] A "generative engine that analyzes aggregated financial data to generate financial advice" refers to an algorithm and process for analyzing integrated financial data and providing advice to users in an easily understandable format based on that analysis.

[1457] "A means of presenting generated financial advice to users in real time through an application installed on their smartphone" refers to a technology that notifies users of instantly generated financial advice via an application installed on their smartphone.

[1458] "A means of notifying users when their financial status changes using a status notification function" refers to a mechanism that uses a pre-configured notification function to inform users in real time when there is a significant change in their financial status.

[1459] This invention is a system that collects and integrates users' financial data and provides real-time financial advice. The system consists of the following elements:

[1460] System Overview:

[1461] 1. User terminal:

[1462] It is a smartphone used by the user, and applications are installed on it.

[1463] 2. Server:

[1464] A backend system that processes data requests sent from user terminals and collects and integrates users' financial data.

[1465] 3. Generation Engine:

[1466] Designing an algorithm that analyzes aggregated financial data and generates financial advice for users.

[1467] 4. Notification system:

[1468] It monitors changes in financial status in real time and sends notifications to users as needed.

[1469] Data collection:

[1470] The server collects the following data based on the user ID.

[1471] Bank data: Bank account information, transaction history, and balance.

[1472] Insurance data: Details of the insurance contract, premiums, and coverage.

[1473] Loan data: Loan agreement information, balance, and interest rate.

[1474] The server automatically retrieves this data from multiple financial institutions using RESTful APIs. Secure communication is ensured by providing the necessary API endpoints and authentication keys.

[1475] Data integration:

[1476] The server centrally aggregates the acquired financial data and generates integrated datasets for each user. This allows for the unified management of information obtained from multiple data sources.

[1477] Data analysis and advice generation:

[1478] The generation engine analyzes the integrated dataset using natural language processing technology. Specifically, it performs data evaluation, income and expenditure balance assessment, loan risk assessment, and insurance suitability assessment. Based on the analysis results, it generates financial advice like the example below.

[1479] Example of a prompt:

[1480] "Requesting advice based on financial data for user ID: 12345: Bank balance: 500,000 yen, Insurance policies: 2, Loan balance: 600,000 yen"

[1481] Offering advice:

[1482] The generated financial advice is sent back to the user's terminal via the server. The user's terminal displays the advice on the screen in real time for the user to review. In addition, a status notification function is used to immediately notify the user when there are changes in the financial situation.

[1483] As a concrete example, if a user sends a request through the application saying, "I want to know my asset status," the following process will be executed.

[1484] An advice message is generated and displayed on the user's smartphone stating, "Your total balance is good, but your debt is a little high. Please review your repayment plan."

[1485] This system allows users to always have an up-to-date understanding of their financial situation and receive accurate and timely advice.

[1486] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1487] Step 1:

[1488] The user launches a smartphone application and requests financial advice.

[1489] Input: User ID and request information.

[1490] Specific operation: The user terminal sends the user ID and request to the server.

[1491] Step 2:

[1492] The server retrieves bank data, insurance data, and loan data based on the user ID.

[1493] Input: User ID.

[1494] Specific operation: The server uses a RESTful API to retrieve data from financial institutions, insurance companies, and loan companies.

[1495] Output: Bank data, insurance data, loan data.

[1496] Step 3:

[1497] The system centrally aggregates the data acquired by the servers and generates an integrated dataset.

[1498] Input: Bank data, insurance data, loan data.

[1499] Specific operation: The server integrates the data and compiles it into a dataset in a standard format.

[1500] Output: Integrated dataset.

[1501] Step 4:

[1502] The generation engine analyzes the integrated dataset and generates financial advice.

[1503] Input: Integrated dataset.

[1504] Specific operation: The generation engine uses natural language processing techniques to analyze data and generate advice.

[1505] Output: Financial advice.

[1506] Step 5:

[1507] The generated financial advice is sent to the user's terminal via the server.

[1508] Input: Financial advice.

[1509] Specific operation: The server sends the generated advice to the user's terminal.

[1510] Output: Financial advice is displayed on the user's terminal.

[1511] Step 6:

[1512] The user terminal displays advice on the screen in real time and uses a status notification function to notify the user when the financial situation changes.

[1513] Input: Financial advice and information on changes in financial condition.

[1514] Specific operation: The user's terminal displays advice and sends real-time notifications when there are changes in the financial situation.

[1515] Output: Users receive advice in real time and are notified in a timely manner.

[1516] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1517] This invention provides a system that collects, integrates, and analyzes users' financial data to offer financial advice, and also includes a function to recognize users' emotions. The system consists of a user terminal, a server, a generation engine, and an emotion engine.

[1518] First, the user requests financial advice by launching the application and logging in. This request is sent from the user's device to the server. The request includes the user's identification information.

[1519] The server collects the following data based on the user's identification information.

[1520] 1. Bank data: Bank account information, transaction history, balance, etc.

[1521] 2. Insurance data: Insurance contract information, premiums, coverage details, etc.

[1522] 3. Loan data: Loan contract information, outstanding balance, interest rate, etc.

[1523] The server executes multiple API requests to retrieve this data. The server then centrally aggregates the retrieved financial data to create a unified dataset. This unified dataset is then sent to the generation engine.

[1524] The generation engine analyzes the integrated dataset to assess the user's financial situation. This assessment process includes data evaluation, income and expenditure balance assessment, loan risk assessment, and insurance suitability assessment. Then, using natural language processing technology, it generates financial advice in a format that is easy for the user to understand.

[1525] The emotion engine functions as a means of recognizing the user's emotions. It employs technology to identify emotions from the user's tone of voice, facial expressions, and text input. This emotional information is fed back to the generation engine and considered along with the analysis results.

[1526] For example, if a user is feeling anxious about unexpected expenses, the emotion engine recognizes that anxiety. The generation engine then reflects this emotional information and generates more reassuring advice, such as, "Your current financial situation is good, but we recommend saving some more to be prepared for unexpected expenses."

[1527] The advice generated by the generation engine is sent to the user terminal via the server. The user terminal displays this advice on the screen, and the user can review it.

[1528] Thus, the present invention makes it possible to provide the most appropriate and acceptable advice to the user by taking into account not only the user's financial situation but also their emotions at that time.

[1529] The following describes the processing flow.

[1530] Step 1:

[1531] Users launch a mobile or web application and log in to receive financial advice.

[1532] Step 2:

[1533] The user clicks the "Request Advice" button. This action sends an advice request from the user's terminal to the server.

[1534] Step 3:

[1535] The user's terminal sends a request to the server that includes user identification information (such as a user ID).

[1536] Step 4:

[1537] The server receives the user ID and sequentially sends data retrieval requests to multiple external API services (such as banks, insurance companies, and loan services).

[1538] Step 5:

[1539] The server collects data using the following steps:

[1540] To retrieve bank data, a request is sent to https: / / api.bank.com / userdata. This will return bank account information, transaction history, balance, etc.

[1541] To retrieve insurance data, a request is sent to https: / / api.insurance.com / userdata. This will return information such as insurance policy details, premiums, and coverage details.

[1542] To retrieve loan data, send a request to https: / / api.loan.com / userdata. This will return loan contract information, outstanding balance, interest rate, etc.

[1543] Step 6:

[1544] The data acquired by the server is centrally aggregated and integrated to create a unified dataset. This dataset includes banking data, insurance data, and loan data.

[1545] Step 7:

[1546] The user's device sends emotional data (such as tone of voice, facial expressions, and text input) to the emotion engine.

[1547] Step 8:

[1548] The emotion engine analyzes the user's emotional data to recognize the user's current emotional state. This information is then used for subsequent analysis.

[1549] Step 9:

[1550] The server sends the integrated dataset and sentiment data from the sentiment engine to the generation engine.

[1551] Step 10:

[1552] The generation engine analyzes the integrated dataset to assess the user's financial situation. This assessment includes:

[1553] Assessment of the current balance of income and expenses

[1554] Loan risk assessment

[1555] Assessment of insurance suitability

[1556] Step 11:

[1557] The generation engine uses natural language processing technology to generate financial advice in a way that is easy for the user to understand. It also considers sentiment data from the sentiment engine to adjust the content and presentation of the advice.

[1558] Step 12:

[1559] The generation engine sends the generated financial advice back to the server.

[1560] Step 13:

[1561] The server sends the advice it received from the generation engine to the user's terminal.

[1562] Step 14:

[1563] The user's terminal displays the transmitted financial advice on the screen. This allows the user to see specific advice based on their financial situation, as well as receive thoughtful advice that takes their emotions into consideration.

[1564] (Example 2)

[1565] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1566] Traditional financial advisory systems often only consider the user's financial situation, failing to provide advice that takes into account their emotions and psychological state. As a result, there was a lack of appropriate advice that was easily accepted by users. Furthermore, by ignoring emotional aspects such as stress and anxiety, advice was often not followed.

[1567] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1568] In this invention, the server includes means for collecting the user's financial data, means for aggregating and integrating the financial data, means for analyzing the aggregated financial data to generate financial advice, means for presenting the generated financial advice to the user, means for recognizing the user's emotions, and means for adjusting the financial advice based on the recognized emotional information. This makes it possible to provide advice that takes into account not only the user's financial situation but also their emotional state at any given time.

[1569] A "user" is an individual or organization that uses the system to receive financial advice.

[1570] "Financial data" refers to data that includes information about a user's bank accounts, insurance policies, and loan agreements.

[1571] "Collection method" refers to the function of obtaining users' financial data from various data sources.

[1572] "Integration means" refers to a function that centrally aggregates different types of financial data and creates an integrated dataset.

[1573] "Generative means" refers to technology that analyzes integrated financial data and creates advice for users.

[1574] "Presentation means" refers to the function of displaying and providing advice created by the generation means to the user.

[1575] "Emotion recognition means" refers to technology that recognizes emotions from the user's voice, facial expressions, text input, etc.

[1576] "Adjustment mechanisms" refer to functions that appropriately modify the generated financial advice in accordance with the perceived emotional information.

[1577] This invention relates to a system that collects, integrates, and analyzes users' financial data, and further recognizes users' emotions to generate and provide financial advice. This system consists of a "user terminal," a "server," a "generation engine," and an "emotion engine."

[1578] Hardware and software overview:

[1579] User devices include smartphones, tablets, and personal computers. These devices have applications installed for requesting and receiving financial advice.

[1580] The servers utilize cloud environments or on-premises servers. They collect, aggregate, and integrate data, send it to the generation and sentiment engines, and provide advice.

[1581] The generation engine is a software module that analyzes aggregated financial data and generates financial advice. It primarily uses natural language processing techniques to generate advice.

[1582] The emotion engine is a software module that recognizes a user's emotions using speech recognition, facial expression recognition, and text analysis.

[1583] System operation details:

[1584] 1. The user launches the application and logs in. This allows the user's identification information to be obtained.

[1585] 2. The user terminal provides an interface for requesting financial advice, and the user enters a specific request (e.g., "I'm worried about unexpected expenses").

[1586] 3. Based on the user's identification information, the server collects financial data from the following data sources:

[1587] Retrieve bank account information, transaction history, and balance from bank APIs.

[1588] Retrieve insurance contract information, premiums, and coverage details from the insurance API.

[1589] Retrieve loan contract information, outstanding balance, and interest rate from the loan API.

[1590] 4. The server integrates this data to create a centralized financial dataset.

[1591] 5. The server sends the dataset to the generation engine.

[1592] 6. The generation engine analyzes the dataset and evaluates the user's financial situation:

[1593] Evaluation of the balance between income and expenses

[1594] Loan risk assessment

[1595] Assessment of insurance suitability

[1596] 7. The generation engine uses natural language processing technology to generate financial advice.

[1597] 8. Simultaneously, the emotion engine analyzes the user's voice, facial expressions, and text input to recognize their emotional state:

[1598] Voice tone analysis

[1599] facial expression recognition

[1600] Text analysis

[1601] 9. The emotion engine feeds back the recognized emotion information to the generation engine.

[1602] 10. The generation engine reflects emotional information and generates appropriate and reassuring advice for the user.

[1603] 11. The server sends the generated advice to the user's terminal.

[1604] 12. The user terminal displays advice on the screen and notifies the user.

[1605] Specific example:

[1606] When a user enters the prompt "I'm worried about unexpected expenses," the server collects and integrates bank data (account balance and transaction history), insurance data (insurance policy details and premiums), and loan data (outstanding balance and interest rates). The generation engine analyzes this data to assess the user's financial situation. Simultaneously, the emotion engine recognizes anxiety from the user's voice and facial expressions. Finally, the generation engine generates reassuring advice such as "Your current financial situation is good, but we recommend saving some more to be prepared for unexpected expenses," and displays it on the device.

[1607] Thus, the present invention provides comprehensive financial advice that takes into account not only financial data but also the user's emotional state.

[1608] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1609] Step 1:

[1610] The user launches the application and enters their login information (user ID, password).

[1611] Input: User ID, Password

[1612] Output: Authentication Request

[1613] Step 2:

[1614] The server receives the authentication request and verifies the authentication information. If authentication is successful, it returns the dashboard screen.

[1615] Input: Authentication Request

[1616] Output: Authentication results, dashboard screen

[1617] Step 3:

[1618] Users request financial advice from the dashboard screen and enter specific prompts such as "I'm worried about unexpected expenses."

[1619] Input: Prompt message

[1620] Output: Financial advice request

[1621] Step 4:

[1622] The user's terminal sends a financial advice request to the server.

[1623] Input: Financial advice request

[1624] Output: Sending a request to the server

[1625] Step 5:

[1626] Based on the user's identification information, the server collects financial data from the following data sources:

[1627] Retrieve bank account information, transaction history, and balance from bank APIs.

[1628] Retrieve insurance contract information, premiums, and coverage details from the insurance API.

[1629] Retrieve loan contract information, outstanding balance, and interest rate from the loan API.

[1630] Input: User identification information

[1631] Output: Various financial data collected

[1632] Step 6:

[1633] The server integrates various acquired financial data to create a unified financial dataset.

[1634] Input: Collected financial data

[1635] Output: Integrated financial dataset

[1636] Step 7:

[1637] The server sends the integrated dataset to the generation engine.

[1638] Input: Integrated financial dataset

[1639] Output: Sending the dataset to the generation engine

[1640] Step 8:

[1641] The generation engine analyzes the integrated dataset to assess the user's financial situation. Specifically, it evaluates the balance between income and expenses, assesses loan risk, and evaluates the appropriateness of insurance.

[1642] Input: Integrated financial dataset

[1643] Output: Initial advice

[1644] Step 9:

[1645] The emotion engine recognizes the user's emotions. It analyzes the user's voice tone, facial expressions, text input, etc., to generate emotional information.

[1646] Input: User's voice tone, facial expression, and text input

[1647] Output: Emotional information

[1648] Step 10:

[1649] The emotion engine feeds back the recognized emotion information to the generation engine.

[1650] Input: Emotional information

[1651] Output: Feedback to the generation engine

[1652] Step 11:

[1653] The generation engine incorporates emotional information to produce the final financial advice.

[1654] Input: Initial advice, emotional information

[1655] Output: Final Financial Advice

[1656] Step 12:

[1657] The generation engine sends the final financial advice it has generated to the server.

[1658] Input: Final Financial Advice

[1659] Output: Sending advice to the server

[1660] Step 13:

[1661] The server sends the final financial advice to the user's terminal.

[1662] Input: Final Financial Advice

[1663] Output: Sending advice to the user's terminal

[1664] Step 14:

[1665] The user's terminal displays the received advice on its screen.

[1666] Input: Final Financial Advice

[1667] Output: Screen display

[1668] Step 15:

[1669] The user reviews the financial advice displayed on the screen and decides on their next course of action.

[1670] Input: Advice displayed on screen

[1671] Output: User decision

[1672] (Application Example 2)

[1673] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1674] Traditional financial advisory systems relied solely on the user's financial data, failing to consider their emotions. This made it difficult to provide appropriate advice to users who were feeling anxious about their current financial situation. Furthermore, there was a lack of systems capable of providing emotionally responsive advice, resulting in a lack of services that considered the user's psychological state.

[1675] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1676] In this invention, the server includes means for collecting user financial data, means for aggregating and integrating the financial data, means for collecting and analyzing emotional data, means for generating financial advice that takes emotional data into consideration, and means for presenting the generated financial advice to the user. This makes it possible to provide advice that takes into account not only the user's financial situation but also their emotions at that time.

[1677] "Means for collecting users' financial data" refers to devices or programs for obtaining users' deposit account information, insurance contract information, and loan contract information from various financial institutions and services.

[1678] "Means for aggregating and integrating financial data" refers to a device or program that centrally compiles acquired user financial data and creates a dataset in a unified format.

[1679] A "generation engine means" is a device or program that analyzes aggregated financial data, evaluates the user's financial situation, and then generates appropriate financial advice.

[1680] "An emotion engine means for collecting and analyzing user emotion data" refers to a device or program for identifying and analyzing emotions from a user's voice tone, facial expressions, text input, etc.

[1681] "Means for generating financial advice that takes emotional data into consideration" refers to a device or program for generating financial advice that reflects the user's mental state, based on emotional data identified by an emotional engine.

[1682] "Means for presenting generated financial advice to the user" refers to a device or program that displays and allows the user to confirm the financial advice obtained by the generation engine and emotion engine on the user's terminal.

[1683] This invention is a system that collects users' financial and emotional data, integrates and analyzes them, and provides appropriate financial advice. The system consists of a user terminal, a server, a generation engine, and an emotional engine.

[1684] Hardware and software configuration

[1685] 1. User terminal:

[1686] smartphone

[1687] Installed applications (Android, iOS)

[1688] 2. Server:

[1689] Cloud servers (AWS, GCP, etc.)

[1690] 3. Software:

[1691] API integration module (acquires data from various financial institutions)

[1692] Emotion recognition engine (Google Cloud Speech-to-Text API, OpenCV)

[1693] Data analysis engine (Google TensorFlow, PyTorch)

[1694] Natural Language Processing Engine (OpenAI GPT)

[1695] Processing flow

[1696] 1. User Authentication and Login

[1697] Users log in using a smartphone app. Login information is sent to the server, where the user's identity is verified.

[1698] 2. Data Collection

[1699] The server uses an API integration module based on login information to collect users' financial data, such as banking data, insurance data, and loan data. This data is centrally aggregated to create an integrated dataset.

[1700] 3. Emotion recognition

[1701] The system collects the user's voice tone and facial expressions using the smartphone's microphone and camera. The voice data is converted to text using the Google Cloud Speech-to-Text API, and the facial expression data is analyzed using OpenCV. This data is then processed by an emotion engine to identify the user's emotions.

[1702] 4. Data Analysis

[1703] The integrated financial and sentiment datasets are analyzed using TensorFlow. Considering the user's financial status and emotional state, an appropriate financial advice generator produces relevant financial advice.

[1704] 5. Providing financial advice

[1705] Using a natural language processing engine (OpenAI GPT), the analysis results are converted into a format that is easy for the user to understand. The server sends the generated advice to the user's terminal, where the user can review it.

[1706] Specific examples and prompt statements

[1707] For example, if a user is worried about unexpected expenses, a response can be generated using a prompt message like the following.

[1708] Voice and facial expression input

[1709] User's voice: "I'm worried about unexpected expenses lately."

[1710] Facial expression: A tense face

[1711] App analysis and response

[1712] Emotional Engine Result: Anxiety

[1713] Financial data analysis results: Savings are not sufficient, but there is a monthly surplus of approximately 10,000 yen.

[1714] advice:

[1715] "Considering your current financial situation, I recommend setting aside a portion of your monthly surplus to prepare for unexpected expenses. Specifically, you could start by saving 3,000 yen per month."

[1716] Prompt example

[1717] User's voice: "I'm worried about unexpected expenses lately."

[1718] User's facial expression: A tense expression

[1719] Financial data:

[1720] Bank account balance: 500,000

[1721] Monthly income: 300,000

[1722] Monthly expenses: 200,000

[1723] Loan: Car loan, remaining balance 100,000 yen, monthly payment 10,000 yen.

[1724] Based on the analysis results, what kind of financial advice will you provide to the user?

[1725] Thus, by considering not only the user's financial data but also their emotions at that time, the present invention makes it possible to provide more personalized and appropriate financial advice.

[1726] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1727] Step 1:

[1728] User authentication and login

[1729] The user launches the application on their smartphone and enters their login information (user ID and password). The submitted login information is sent to the server and stored as user identification information.

[1730] Input: User ID, Password

[1731] Output: User identification authentication result

[1732] Step 2:

[1733] Data collection

[1734] Based on authenticated user identification information, the server uses an API integration module to retrieve user financial data (bank data, insurance data, loan data) from various financial institutions. This data is centrally aggregated on the server, creating an integrated dataset.

[1735] Input: User identification information

[1736] Output: Integrated financial dataset

[1737] Step 3:

[1738] emotion recognition

[1739] The system uses the microphone and camera on the user's device to collect the user's voice and facial expressions. The voice data is transcribed using the Google Cloud Speech-to-Text API, and the facial expression data is analyzed using OpenCV. An emotion engine then identifies the user's emotions from this data.

[1740] Input: User's voice and facial expression data

[1741] Output: Identified sentiment data

[1742] Step 4:

[1743] Data Analysis

[1744] The server analyzes an integrated financial dataset and identified sentiment data using TensorFlow. Considering the financial status and the user's sentiment state, the generative engine generates appropriate financial advice using a generative AI model.

[1745] Input: Integrated financial dataset, identified sentiment data

[1746] Output: Generated financial advice

[1747] Step 5:

[1748] Providing financial advice

[1749] The generated financial advice is converted into a user-friendly format using a natural language processing engine (OpenAI GPT). The server then sends the converted financial advice to the user's terminal, allowing the user to review it and decide on their next course of action.

[1750] Input: Generated financial advice

[1751] Output: Financial advice presented to the user

[1752] In this way, this system analyzes the user's financial and emotional data through multiple steps and provides optimal financial advice tailored to each individual's situation.

[1753] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1754] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1755] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1756] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1757] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1758] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1759] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1760] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1761] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1762] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1763] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1764] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1765] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1766] 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.

[1767] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1768] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1769] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1770] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1771] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1772] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1773] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1774] The following is further disclosed regarding the embodiments described above.

[1775] (Claim 1)

[1776] Means of collecting users' financial data,

[1777] A means for aggregating and integrating the financial data,

[1778] A generation engine means that analyzes aggregated financial data to generate financial advice,

[1779] A means of presenting the generated financial advice to the user,

[1780] A system that includes this.

[1781] (Claim 2)

[1782] The system according to claim 1, wherein the financial data includes deposit account data, insurance contract data, and loan contract data.

[1783] (Claim 3)

[1784] The system according to claim 1, wherein the analysis means generates financial advice using natural language processing technology.

[1785] "Example 1"

[1786] (Claim 1)

[1787] A means for users to request financial advice,

[1788] A means of collecting financial data based on user identification information,

[1789] A means of integrating collected financial data,

[1790] A means of analyzing integrated financial data to generate financial advice,

[1791] A means of displaying the generated financial advice,

[1792] A system that includes this.

[1793] (Claim 2)

[1794] The system according to claim 1, wherein the financial data includes bank data, insurance data, and loan agreement data.

[1795] (Claim 3)

[1796] The system according to claim 1, wherein the analysis means generates financial advice using natural language processing technology.

[1797] "Application Example 1"

[1798] (Claim 1)

[1799] Means of collecting users' financial data,

[1800] A means for aggregating and integrating the financial data,

[1801] A generation engine means that analyzes aggregated financial data to generate financial advice,

[1802] A means of presenting generated financial advice to users in real time through an application installed on their smartphones,

[1803] A means of notifying users when their financial status changes using a status notification function,

[1804] A system that includes this.

[1805] (Claim 2)

[1806] The system according to claim 1, wherein the financial data includes deposit account data, insurance contract data, and loan contract data.

[1807] (Claim 3)

[1808] The system according to claim 1, wherein the analysis means generates financial advice using natural language processing technology.

[1809] "Example 2 of combining an emotion engine"

[1810] (Claim 1)

[1811] Means of collecting users' financial data,

[1812] A means for aggregating and integrating the financial data,

[1813] A generation method that analyzes aggregated financial data to generate financial advice,

[1814] A means of presenting the generated financial advice to the user,

[1815] Means for recognizing the user's emotions,

[1816] A means of adjusting financial advice based on recognized emotional information,

[1817] A system that includes this.

[1818] (Claim 2)

[1819] The system according to claim 1, wherein the financial data includes deposit account data, insurance contract data, and loan contract data.

[1820] (Claim 3)

[1821] The system according to claim 1, wherein the analysis means generates financial advice using natural language processing technology.

[1822] "Application example 2 when combining with an emotional engine"

[1823] (Claim 1)

[1824] Means of collecting users' financial data,

[1825] A means for aggregating and integrating the financial data,

[1826] A generation engine means that analyzes aggregated financial data to generate financial advice,

[1827] An emotion engine means for collecting and analyzing user emotion data,

[1828] A means of generating financial advice that takes emotional data into account,

[1829] A means of presenting the generated financial advice to the user,

[1830] A system that includes this.

[1831] (Claim 2)

[1832] The system according to claim 1, wherein the financial data includes deposit account data, insurance contract data, and loan contract data.

[1833] (Claim 3)

[1834] The system according to claim 1, wherein the analysis means generates financial advice using natural language processing technology. [Explanation of symbols]

[1835] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting users' financial data, A means for aggregating and integrating the financial data, A generation engine means that analyzes aggregated financial data to generate financial advice, A means of presenting the generated financial advice to the user, A system that includes this.

2. The system according to claim 1, wherein the financial data includes deposit account data, insurance contract data, and loan contract data.

3. The system according to claim 1, wherein the analysis means generates financial advice using natural language processing technology.

Images