System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting asset data from a user; means for collecting daily market data; means for analyzing the asset data and market data to generate asset formation advice; and means for providing the advice to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional asset formation support systems have the problem of being unable to provide advice that fully reflects the individual circumstances and market trends of each user. Furthermore, they lack feedback based on comparisons with average values ​​for the same age or region, making it impossible to provide specific and reliable guidance for users in asset formation. This makes it difficult for users to find an appropriate asset formation policy, resulting in the issue of inefficient asset formation. [Means for solving the problem]

[0005] This invention solves the above-mentioned problems by providing a system including a means for collecting asset data from users, a means for collecting daily market data, a means for analyzing the asset data and market data to generate asset formation advice, and a means for providing the advice to users. Furthermore, by incorporating a means for generating an individualized asset formation plan based on user input and a statistical analysis means for comparing the data with that of other users of the same age and region, it is possible to provide each user with more specific and reliable advice. As a result, users can clarify their own asset formation policies and efficiently build their assets.

[0006] "User" refers to an individual who uses this system to build assets and save.

[0007] "Asset data" refers to information such as income, expenses, savings, and savings goals provided by the user.

[0008] "Market data" refers to external economic data that fluctuates daily, such as foreign exchange information, stock prices, and economic indicators.

[0009] "Analysis" refers to the process of extracting future predictions and trends using statistical methods and machine learning models based on collected data.

[0010] "Asset formation advice" refers to specific guidelines and strategies recommended to users based on the analysis results to help them achieve their savings goals.

[0011] "Means" refers to the programs, processes, and hardware components required to realize each function of the system.

[0012] "Individualized Wealth Building Plan" refers to a plan for wealth building that is customized to a user's particular circumstances and needs.

[0013] "Statistical analysis methods" refers to methods and algorithms for comparing and analyzing a user's data with the data of other users of the same age and region. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0022] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] In one embodiment of the present invention, a system for supporting asset formation is configured by users, servers, and terminals working together. The processing and specific operations of each component will be explained in natural language below.

[0036] Server Processing

[0037] The server is responsible for the central data processing and analysis of the system.

[0038] 1. Market data collection

[0039] The server periodically accesses the financial API to obtain the latest exchange rates, stock prices, and economic indicators. The collected data is temporarily stored in storage and used for subsequent analysis.

[0040] 2. Data analysis and model updating

[0041] The server analyzes the acquired market data and updates the model for predicting market trends using statistical methods and machine learning models. The results of this analysis are stored in a database and used to generate advice for users.

[0042] 3. Import of personal data

[0043] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user and stores it in a database.

[0044] 4. Analysis of personal data

[0045] The server analyzes the user's income and expenditure balance and savings patterns based on the saved asset data, and compares them with the data of other users of the same age and region.

[0046] 5. Advice Generation

[0047] Based on the analysis results, the server generates specific asset formation advice for the user to achieve their savings target. The advice generated is customized to the user's individual situation.

[0048] 6. Submitting the results

[0049] The server transmits the generated advice to the user's terminal.

[0050] Terminal handling

[0051] The terminal provides the interface with the user and is responsible for inputting data and displaying results.

[0052] 1. Data input from the user

[0053] The terminal provides an interface for the user to input data such as income, expenses, current savings, target savings, etc. The input data is sent to the server.

[0054] 2. Data reception and display

[0055] The device receives the analysis results and advice sent from the server and displays them to the user in an easy-to-read format, such as graphs or charts, which are visually easy to understand.

[0056] User Action

[0057] The user uses a terminal to input data into the system and checks the advice sent from the server.

[0058] 1. Data Entry

[0059] The user inputs his / her income, expenses, current savings amount, and target savings amount through the terminal interface, and sends the data to the server by clicking the send button.

[0060] 2. Check the advice

[0061] Users can check the analysis results and advice displayed on their device and use them to plan their asset-building activities, such as how much to save each month and which investment products to purchase.

[0062] 3. Providing Feedback

[0063] Users can input feedback about the advice provided and submit their wishes and changes to the system. For example, by inputting a wish such as "I want to take more risks," new advice will be provided.

[0064] Specific examples

[0065] Every morning, the server retrieves and analyzes market data such as exchange rates and stock indexes from a specified financial API. The user inputs data such as a monthly income of 300,000 yen, a savings goal of 5 million yen, and current savings of 1 million yen into a smartphone app. The server analyzes this data and generates a result by comparing it with the average savings of people in their 30s. The generated result and advice are sent to the user's device, and the user receives specific guidelines such as saving 30,000 yen per month and purchasing low-risk investment products. The user can provide feedback on the advice and have it reflected in the system, resulting in a more accurate asset formation plan.

[0066] In this way, the present invention can provide specific and reliable advice to help users build assets efficiently.

[0067] The processing flow will be explained below.

[0068] Server Processing Steps

[0069] Step 1:

[0070] The server runs a scheduled job every morning at 7:00 am, accessing the API of economic data providers to obtain market data such as exchange rates, stock indexes, and economic indicators, and stores it in temporary storage.

[0071] Step 2:

[0072] The server analyzes the stored market data using a data analysis module, which uses statistical analysis and machine learning algorithms to predict market trends and stores the results in a database.

[0073] Step 3:

[0074] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user via API and stores it in a database.

[0075] Step 4:

[0076] The server retrieves the user data stored in the database and analyzes it using the asset data analysis module. The user's income and expenditure balance and savings patterns are analyzed and compared with the data of other users of the same age and region.

[0077] Step 5:

[0078] Based on the analysis results, the server generates specific asset formation advice to help users achieve their savings goals. The advice is customized based on each user's situation.

[0079] Step 6:

[0080] The server packages the generated advice in JSON format and sends it to the user's device.

[0081] Terminal processing steps

[0082] Step 1:

[0083] The terminal presents the user with a data entry form, where the user enters information such as income, expenses, current savings, and savings goals.

[0084] Step 2:

[0085] The device receives the user's input data and generates an API request to send it to the server. The API request is encrypted and sent.

[0086] Step 3:

[0087] The device receives the analysis results and advice sent from the server, which are also received as API responses.

[0088] Step 4:

[0089] The device analyzes the data it receives and displays it in a format that is easy for the user to understand, such as a graph, chart, or list.

[0090] User processing steps

[0091] Step 1:

[0092] The user enters income, expenses, current savings amount, and target savings amount into the data input form on the terminal and clicks the submit button.

[0093] Step 2:

[0094] The user checks the analysis results and advice displayed on the device, such as how much they should save each month and which investment products they should choose.

[0095] Step 3:

[0096] The user inputs feedback about the advice provided, such as "I want to take more risks" or "I want to know about safer options," and sends this feedback from the device to the server.

[0097] Through these steps, the system can provide users with personalized asset formation advice and support optimal asset formation.

[0098] Example 1

[0099] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0100] Conventional asset formation support systems have struggled to provide specific and reliable advice tailored to each user's individual circumstances. Furthermore, there was a lack of systems that could accurately reflect daily fluctuating market data and allow users to obtain timely information. Furthermore, it was difficult to generate personalized plans based on a user's income, expenses, and savings, and comparisons with a large amount of user data were not conducted.

[0101] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0102] In this invention, the server includes means for collecting asset data from users, means for collecting daily market data, means for analyzing the asset data and market data to generate asset formation advice, means for providing the advice to users, means for updating a machine learning model using the market data and asset data, a terminal interface for inputting data on the user's income, expenses, savings, and target savings, and means for confirming the analysis results and advice displayed on the terminal. This allows users to receive specific and reliable advice tailored to their individual circumstances. Furthermore, by reflecting market data that fluctuates daily in a timely manner, asset formation based on the latest information is possible. Furthermore, by comparing user data with data on other users of the same age and region, more accurate analysis and advice can be provided.

[0103] The "means for collecting asset data from a user" refers to a means for inputting, receiving, and storing asset data such as a user's income, expenses, savings amount, and target savings amount.

[0104] "Means of collecting daily market data" refers to the use of financial APIs to regularly obtain and store market data such as foreign exchange information, stock prices, and economic indicators.

[0105] The "means for analyzing the asset data and market data to generate asset formation advice" refers to a means for analyzing the acquired asset data and market data and using statistical techniques and machine learning models to generate specific asset formation advice for the user.

[0106] The "means for providing the advice to the user" refers to means for transmitting information to the user's terminal through an interface for providing the generated advice to the user.

[0107] "Means for updating machine learning models using market data and asset data" refers to means for updating predictive models using machine learning algorithms based on regularly collected market data and asset data from users.

[0108] A "terminal interface for inputting user's income, expenditure, savings, and savings goal data" is a terminal that provides a graphical interface for a user to input personal data such as income, expenditure, current savings, and savings goal.

[0109] "Means for checking the analysis results and advice displayed on the terminal" refers to a terminal function for receiving the analysis results and advice sent from the server and visually displaying them.

[0110] This invention provides a system that supports asset formation through cooperation between users, servers, and terminals. The specific configuration and operation of this system will be described below.

[0111] Server Roles

[0112] The server is responsible for the central data processing and analysis of this system and uses the following hardware and software:

[0113] Hardware: High-performance servers, SSD storage, network interfaces

[0114] Software: Python, TENSORFLOW (registered trademark), Scikit-learn, Pandas, Jupyter Notebook, MongoDB, RESTful API

[0115] The server collects daily market data using financial APIs. For example, it periodically accesses APIs from Alpha Vantage and Yahoo Finance to obtain the latest exchange rates, stock prices, and economic indicators. This data is temporarily stored in a database such as MongoDB.

[0116] The server then analyzes the collected market data using Python and Jupyter Notebook, preprocessing the data with the Pandas library, and updating machine learning models using TensorFlow and Scikit-learn. The analyzed data is then used to generate recommendations for users.

[0117] Furthermore, the server receives asset data (income, expenses, savings amount, savings target, etc.) sent by the user and stores it in a database. Based on the stored data, the server analyzes the user's income and expenditure balance and savings pattern and performs statistical comparisons. Based on the results, it generates specific asset formation advice for the user and sends it to the user's device via a RESTful API.

[0118] Device Role

[0119] The terminal provides the interface with the user, allowing data entry and displaying results. The terminal uses the following hardware and software:

[0120] Hardware: Smartphones, tablets, computers

[0121] Software: HTML, CSS, JavaScript (registered trademark), AJAX, Chart.js, D3.js

[0122] The terminal provides an interface for users to input data such as income, expenses, current savings, and target savings. These data are retrieved by JavaScript through an HTML form and sent to the server in JSON format using AJAX.

[0123] The device also receives analysis results and advice sent from the server and visually displays them to the user using Chart.js and D3.js, using graphs and charts to help users intuitively understand the information.

[0124] User Roles

[0125] The user uses a terminal interface to input asset data into the system and review the advice provided by the server.

[0126] Users enter their income, expenses, current savings amount, and target savings amount into an HTML form on their device, and then click the submit button to send the data to the server. The analysis results and advice sent from the server are displayed on the device. This allows users to obtain specific asset formation guidelines and implement an asset formation plan that suits their own situation.

[0127] Furthermore, users can provide feedback on the advice provided. For example, they can enter their wishes or changes, such as "I want to take more risks" or "I want more detailed advice," and click the submit button. The server receives this feedback and reflects it in the next advice generation.

[0128] Specific examples

[0129] Every morning, the server retrieves market data such as exchange rates and stock indexes from a specified financial API (e.g., Alpha Vantage) and analyzes it. The user enters data into the smartphone app, such as monthly income of 300,000 yen, savings goal of 5 million yen, and current savings of 1 million yen. This data is sent to the server, which analyzes and compares it to generate specific advice. For example, this advice might include "save 30,000 yen per month and purchase low-risk investment products."

[0130] Examples of prompt statements

[0131] Below is an example of a prompt sentence to input to the generative AI model.

[0132] I'm in my 30s, earn 300,000 yen a month, have a savings goal of 5 million yen, and currently have 1 million yen saved. Please give me some advice on how to build up assets with low risk.

[0133] In this way, the present invention is a system that provides specific and reliable advice to help users build up their assets efficiently.

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Step 1: Gather market data

[0136] Every morning, the server periodically accesses a financial API (e.g., Alpha Vantage, Yahoo Finance) to retrieve exchange rate information, stock prices, and economic indicators. The input is the API key and request parameters, and the output is market data in JSON format. The server temporarily stores this JSON data in MongoDB. Specifically, it sends an API request using a Python library, receives the response, and stores it in the database.

[0137] Step 2: Analyze market data and update the model

[0138] The server analyzes market data using Python scripts and Jupyter Notebook. The input is market data stored in MongoDB, and the output is the analysis results and an updated machine learning model. Specifically, the data is read and preprocessed using the Pandas library, and the model is trained and updated using TensorFlow and Scikit-learn. This analysis data is stored in a database.

[0139] Step 3: Import user data

[0140] The user enters asset data such as income, expenses, savings amount, and savings goal through an HTML form on the device and clicks the submit button. The input is the user's asset data, and the output is JSON format data stored on the server. The device uses JavaScript and AJAX to send the data to the server, which then receives the data and stores it in a database.

[0141] Step 4: Analyzing personal data

[0142] The server analyzes income / expense balances and savings patterns based on the saved user asset data. The input is asset data obtained from the user database, and the output is the results of statistical analysis. Specifically, data is obtained using SQL queries, and statistical analysis such as standard deviation and average values ​​is performed using Python scripts. The results are then compared with data from users of the same age and region.

[0143] Step 5: Generating Advice

[0144] The server generates asset formation advice for the user based on the analysis results. The input is the analysis results of personal data and market data, and the output is a customized advice message. Specifically, it uses machine learning models and natural language generation models (e.g., GPT-3 (registered trademark)) to generate specific guidelines in text that are tailored to the user's situation. The results are stored in a database.

[0145] Step 6: Send and view results

[0146] The server sends the generated advice to the user's device. The input is the generated advice, and the output is the advice message displayed on the user's device. Specifically, the advice is sent in JSON format using a RESTful API, and is received on the device using AJAX. The received advice is displayed visually using Chart.js or D3.js. For example, a text message such as "Save 30,000 yen each month and purchase low-risk investment products" is displayed.

[0147] Through this series of processes, users can receive specific and reliable advice on how to build assets efficiently.

[0148] (Application example 1)

[0149] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0150] Conventional asset formation support systems provide advice based on basic asset data and market data from users, but are unable to reflect feedback on users' daily purchasing behavior or actual spending. As a result, it is difficult to provide real-time advice adapted to individual situations, and users are unable to obtain sufficient information to formulate specific asset formation plans.

[0151] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0152] In this invention, the server includes means for collecting asset data from users, means for collecting daily market data, means for analyzing the asset data and market data to generate asset formation advice, means for providing the advice to users, means for collecting user purchase history and expenditure data, means for analyzing the purchase history, expenditure data, and market data to generate asset formation advice based on purchasing behavior, means for providing the advice to users in real time, and means for updating the advice based on user feedback, thereby making it possible to provide more specific, personalized, real-time advice to users in asset formation.

[0153] "Means for collecting asset data from users" refers to a function that allows users to input asset data such as their income, expenses, savings amount, and target savings amount, and transmit this data to the server.

[0154] "Means of collecting daily market data" refers to the function of regularly collecting market data such as exchange rates, stock prices, and economic indicators from external sources such as financial APIs.

[0155] "Means for analyzing the asset data and market data to generate asset formation advice" refers to a function that performs analysis based on the collected asset data and market data and generates asset formation advice to be provided to the user.

[0156] The "means for providing the advice to the user" refers to a function for transmitting the generated asset formation advice to the user's terminal and displaying it in a visually easy-to-understand format.

[0157] "Means for collecting user purchase history and expenditure data" refers to a function that automatically collects a user's electronic payment transaction history and daily expenditure data and transmits it to a server for analysis.

[0158] "Means for analyzing the purchase history, expenditure data and market data, and generating asset formation advice based on purchasing behavior" refers to a function that comprehensively analyzes a user's purchase history, expenditure data and market data, and generates specific asset formation advice based on individual purchasing behavior.

[0159] The "means for providing the advice to the user in real time" refers to a function that allows advice based on the analysis results to be immediately provided to the user and feedback to be received in real time.

[0160] "Means for updating advice based on user feedback" refers to the function of collecting feedback information from users and appropriately updating and adjusting the advice content generated based on that information.

[0161] This invention configures a system that supports users' asset formation by linking users, servers, and terminals. The processing and specific operations of each component will be described below.

[0162] Server Processing

[0163] The server is responsible for the system's central data processing and analysis. It analyzes asset data and purchase history data obtained from users, along with the latest market data. Market data is obtained from financial APIs, and includes exchange information, stock prices, economic indicators, and more. Statistical methods and machine learning models are used to predict market trends and purchasing behavior. Based on the results of this analysis, the server generates asset formation advice personalized for the user and sends it to the terminal.

[0164] Terminal handling

[0165] The terminal provides an interface for the user and is responsible for inputting data and displaying the results. The user inputs data such as income, expenses, current savings amount, and savings goal, and daily purchase history and expenditure data are also collected. The input data is sent to the server. The analysis results and advice sent from the server are displayed on the terminal in real time. The data is displayed in a visually easy-to-understand format such as graphs and charts.

[0166] User Action

[0167] Users use their devices to input data into the system and check the advice sent from the server. Based on the advice, users plan specific asset formation actions. For example, they are presented with guidelines on how much to save each month and which investment products to purchase. Users also provide feedback on the advice provided and send their wishes and changes to the system. This allows the server to improve the analysis model based on the feedback and provide more accurate advice.

[0168] Specific examples

[0169] Every morning, the server retrieves market data such as exchange rates and stock indexes from a specified financial API. The user enters data into their smartphone, such as monthly income of 300,000 yen, savings goal of 5 million yen, and current savings of 1 million yen. At the same time, the device automatically collects the user's purchase history and expenditure data. The server analyzes this data and generates results that compare the user's savings with the average savings of people in their 30s. The generated results and advice are sent to the user's device in real time as specific guidelines, such as saving 30,000 yen per month or purchasing low-risk investment products. The user can provide feedback on the advice and have it reflected in the system, resulting in an even more accurate asset formation plan.

[0170] Prompt Sentence Examples

[0171] "Input: My monthly income is ¥200,000, my monthly expenses are ¥150,000, my current savings are ¥300,000, and my goal savings is ¥5 million. How can I achieve this in the next five years?

[0172] Output: I recommend you put away 10,000 yen per month in a low-risk mutual fund. This will increase your chances of reaching your goal.

[0173] As a result, the present invention provides a system that helps users to efficiently build assets by automatically tracking their daily expenses and income and providing financial advice in real time.

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] The server periodically accesses the financial API to obtain market data (foreign exchange information, stock prices, economic indicators, etc.). The obtained market data is temporarily stored in storage. The input is market data from the financial API, and the output is the temporarily stored market data.

[0177] Step 2:

[0178] The server analyzes the acquired market data and updates a model for predicting market trends using statistical methods and machine learning models (e.g., Linear Regression). The analyzed data is stored in a database and used to generate advice for users. The input is temporarily stored market data, and the output is the updated results of the analytical model.

[0179] Step 3:

[0180] The user uses a terminal to input asset data such as their income, expenses, current savings amount, and target savings amount. In addition, the user's purchase history and daily expenditure data are also automatically collected through the terminal. The input is the asset data and purchase history data entered by the user into the terminal, and the output is the data sent to the server.

[0181] Step 4:

[0182] The server receives asset data and purchase history data sent from the user and stores them in a database. The input is the asset data and purchase history data sent from the terminal, and the output is the stored data.

[0183] Step 5:

[0184] The server analyzes the saved user asset data and purchase history data in combination with market data. This analysis generates specific advice for the user regarding asset formation. The inputs are market data, the user's asset data, and purchase history data, and the output is the generated advice.

[0185] Step 6:

[0186] The server sends the generated asset formation advice to the user's terminal. The advice is specific and tailored to the user's purchasing behavior and asset data. The input is the generated advice, and the output is the advice sent to the user's terminal.

[0187] Step 7:

[0188] The user checks the analysis results and advice displayed on the terminal and plans asset formation actions based on them. The user inputs feedback about the advice provided and sends it to the system. The input is feedback about the analysis results and advice, and the output is the feedback sent to the server.

[0189] Step 8:

[0190] The server receives feedback from users and updates the analytical model and advice generation logic based on the feedback. The input is the user feedback, and the output is the updated analytical model and advice generation logic.

[0191] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0192] As an embodiment of the present invention, a user, a server, a terminal, and an emotion engine work in cooperation to form an asset formation support system. Specific processing and operations of each component will be described in detail below.

[0193] Server Processing

[0194] The server is responsible for collecting asset and market data, analyzing it, generating advice, and analyzing user sentiment data.

[0195] 1. Market data collection

[0196] The server accesses the financial API at 7:00 every morning to obtain the latest exchange rate information, stock prices, and economic indicators, and stores them in temporary storage.

[0197] 2. Data analysis and model updating

[0198] The server analyzes the collected market data using statistical analysis and machine learning algorithms to predict market trends, and the results are stored in a database.

[0199] 3. Import of personal data

[0200] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user via API and stores it in a database.

[0201] 4. Analysis of personal data

[0202] The server retrieves user data stored in the database and analyzes it using the asset data analysis module. The server analyzes income and expenditure balances and savings patterns, and compares them with data from other users of the same age and region.

[0203] 5. Advice Generation

[0204] Based on the analysis results, the server generates specific asset formation advice to help users achieve their savings goals. The advice generated is customized to fit each user's situation.

[0205] 6. Emotional Data Collection and Analysis

[0206] The server uses an emotion engine to determine the user's emotional state from input data and interaction data (e.g., the user's keystroke speed, mouse click frequency, etc.) The emotion data is stored in a database as part of the analysis.

[0207] 7. Adjusting advice based on emotions

[0208] The server adjusts the asset formation advice based on the user's emotional state. For example, if the user is feeling stressed, the server generates more appropriate advice, such as suggesting low-risk investment methods.

[0209] 8. Submitting the results

[0210] The server sends the generated advice to the user's device, packaged in JSON format or similar.

[0211] Terminal handling

[0212] The terminal provides the interface with the user and is responsible for inputting data and displaying results.

[0213] 1. Data input from the user

[0214] The terminal displays a form for the user to input data such as income, expenses, current savings, target savings, etc. The data input by the user is sent to the server.

[0215] 2. Collecting Emotional Data

[0216] The device also analyzes the user's keystroke speed, mouse click frequency, and emotion using facial recognition, and sends this data to the server.

[0217] 3. Data reception and display

[0218] The terminal receives the analysis results and advice sent from the server and displays them to the user in a visually easy-to-understand format such as graphs and charts.

[0219] User Action

[0220] The user uses a terminal to input data into the system and checks the advice sent from the server.

[0221] 1. Data Entry

[0222] The user enters their income, expenses, current savings amount, and target savings amount into a form on the terminal and clicks the send button to send the data to the server.

[0223] 2. Reflecting emotions

[0224] The user's interactions (such as keystroke speed and mouse click frequency) are analyzed by the emotion engine, and the user's emotional state is reflected in the system.

[0225] 3. Check the advice

[0226] Users can view the analysis results and advice displayed on their device, including specific guidelines on how much they should save each month and which investment products they should choose.

[0227] 4. Providing Feedback

[0228] The user inputs feedback about the advice provided, for example, a preference such as "I want to take more risks," and sends this feedback to the server from the terminal.

[0229] Specific examples

[0230] Every morning at 7am, the server retrieves and analyzes market data such as exchange rates and stock indexes from a financial API. The user inputs data such as a monthly income of 300,000 yen, a savings goal of 5 million yen, and a current savings of 1 million yen into the smartphone app. The server analyzes this data and generates a result by comparing it with the average savings of people in their 30s. The generated result and advice are sent to the user's device, and the user receives specific guidelines such as saving 30,000 yen per month and purchasing low-risk investment products.

[0231] Furthermore, if the user's input speed is slow and they are feeling anxious, the emotion engine will provide advice based on the user's emotional state, such as suggesting low-risk investment methods. This allows users to find the optimal asset formation policy that takes their emotional state into account.

[0232] The processing flow will be explained below.

[0233] Server Processing Steps

[0234] Step 1:

[0235] The server accesses the financial API at 7am every morning to obtain the latest exchange rates, stock prices, and economic indicators, and stores them in temporary storage.

[0236] Step 2:

[0237] The server analyzes the stored market data using a data analysis module, and uses statistical analysis and machine learning algorithms to predict market trends, and stores the results in a database.

[0238] Step 3:

[0239] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user via API and stores it in a database.

[0240] Step 4:

[0241] The server retrieves user data stored in the database and analyzes it using the asset data analysis module. The analysis includes income and expenditure balances and savings patterns, and compares them with data from other users of the same age and region.

[0242] Step 5:

[0243] Based on the analysis results, the server generates specific asset formation advice to help users achieve their savings goals. The advice is customized to each user's situation.

[0244] Step 6:

[0245] The server uses an emotion engine to determine the user's emotional state from their input data and interaction data (e.g., keystroke speed, mouse click frequency, etc.), and the emotional data is stored in a database.

[0246] Step 7:

[0247] The server adjusts asset formation advice based on the user's emotional state. For example, if the user is feeling stressed, the server will suggest low-risk investment methods.

[0248] Step 8:

[0249] The server packages the generated customized advice in JSON format and sends it to the user's device.

[0250] Terminal processing steps

[0251] Step 1:

[0252] The terminal presents the user with a data entry form, where the user enters information such as income, expenses, current savings, and savings goals.

[0253] Step 2:

[0254] The device receives the user's input data and generates an API request to send it to the server. The API request is encrypted and sent.

[0255] Step 3:

[0256] The device collects user interactions (such as keystroke speed, mouse click frequency, and facial recognition data) and sends them to a server.

[0257] Step 4:

[0258] The device receives the analysis results and advice sent from the server and displays them in a user-friendly format (graphs, charts, lists, etc.).

[0259] User processing steps

[0260] Step 1:

[0261] The user enters their income, expenses, current savings amount, target savings amount, etc. into the data input form on the terminal and clicks the submit button.

[0262] Step 2:

[0263] The user checks the analysis results and advice displayed on the device, receiving specific guidance on how much to save each month, which investment products to choose, and so on.

[0264] Step 3:

[0265] The user inputs feedback about the advice provided. For example, the user sends a request such as "I want to take more risks" to the server via the terminal.

[0266] Specific examples

[0267] Server Processing

[0268] Step 1:

[0269] The server retrieves "exchange rates and stock indexes from the API" every morning at 7:00.

[0270] Step 2:

[0271] The server "analyzes the acquired market data using statistical analysis and machine learning algorithms" and "stores the results in a database."

[0272] Step 3:

[0273] The server receives the data sent by the user, including a monthly income of 300,000 yen, a savings goal of 5 million yen, and a current savings amount of 1 million yen, and stores this data in the database.

[0274] Step 4:

[0275] The server performs the process of "analyzing user data stored in a database and comparing it with the average savings amount of people in their 30s."

[0276] Step 5:

[0277] The server "generates asset formation advice based on each user's situation" and "suggests monthly savings of 30,000 yen and low-risk investment products."

[0278] Step 6:

[0279] The server "uses an emotion engine to determine the user's emotional state" and "saves the emotional data in a database."

[0280] Step 7:

[0281] The server adjusts advice based on the user's emotional state, such as suggesting low-risk investment methods if the user is feeling stressed.

[0282] Step 8:

[0283] The server "packages the generated advice in JSON format" and "sends it to the user's device."

[0284] Terminal handling

[0285] Step 1:

[0286] The device "presents the user with a data entry form for income, expenses, savings, and savings goals."

[0287] Step 2:

[0288] The device "generates an API request to send the input data to the server" and "encrypts and sends it."

[0289] Step 3:

[0290] The device "collects user interaction data (such as keystroke speed and mouse click frequency)" and "sends it to the server."

[0291] Step 4:

[0292] The device "displays the analysis results and advice received from the server in graphs and charts."

[0293] User Action

[0294] Step 1:

[0295] The user "enters their income, expenses, current savings amount, and target savings amount, and clicks the submit button."

[0296] Step 2:

[0297] The user "checks the displayed analysis results and advice (saving 30,000 yen per month, low-risk investment products, etc.)."

[0298] Step 3:

[0299] Users "enter feedback about the advice provided" and "submit preferences such as 'I'd like to take more risks.'"

[0300] Through these steps, the system provides users with personalized asset formation advice, and by taking the user's emotional state into consideration, it achieves more accurate support.

[0301] Example 2

[0302] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0303] Conventional asset formation support systems generally provide uniform advice based on data input by users, making it difficult to provide advice that takes into account individual emotions and unique situations. In addition, it is difficult for users to accurately grasp market trends and their own asset status, and it takes a lot of time and effort to find the optimal asset formation strategy.

[0304] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0305] In this invention, the server includes means for receiving asset data from a user, means for periodically recording market data, means for analyzing the asset data and market data to generate asset formation advice, means for notifying the user of the advice, means for collecting user interaction data and analyzing emotion data, and means for adjusting the advice based on the emotion data, thereby enabling the provision of customized advice that takes into account the individual circumstances and emotional state of the user.

[0306] "Asset data" refers to information about assets owned by a user, and specifically includes income, expenses, current savings, target savings, and the like.

[0307] "Market data" is a general term for information collected from financial markets, and includes data such as exchange rates, stock prices, and economic indicators.

[0308] "Means for generating advice" refers to machine learning algorithms and statistical analysis means for analyzing collected asset data and market data and creating appropriate asset formation advice for users.

[0309] The "means for notifying advice" refers to communication means and display means for transmitting the generated advice to the user's terminal and making it available for the user to view.

[0310] "Interaction data" refers to data related to user operations, such as keystroke speed, mouse click frequency, and facial recognition data, when a user operates a device.

[0311] "Emotional data" refers to information about a user's emotional state obtained by analyzing interaction data and facial recognition data.

[0312] "Means for adjusting advice based on emotional data" refers to algorithms and analytical means for taking into account the user's emotional data and providing optimal asset formation advice.

[0313] As an embodiment of the present invention, a user, a server, a terminal, and an emotion engine work in cooperation to form an asset formation support system. Specific processing and operations of each component will be described in detail below.

[0314] Server Processing

[0315] The server is responsible for collecting asset and market data, analyzing it, generating advice, and analyzing user sentiment data.

[0316] 1. Market data collection

[0317] The server automatically runs a Python script every morning at 7:00, connects to a financial API (e.g., Alpha Vantage) using an API access library (e.g., requests), retrieves the latest exchange rates, stock prices, and economic indicators, and stores them in temporary storage (e.g., Redis, memcached).

[0318] 2. Market data analysis and model updates

[0319] The server preprocesses the collected market data using Python data processing libraries such as Pandas and NumPy, and analyzes it using statistical analysis and machine learning algorithms (e.g., ARIMA model, regression). The analysis results are stored in a database (e.g., MySQL (registered trademark)). The machine learning model is also updated regularly.

[0320] 3. Import of personal data

[0321] The server uses a web framework (e.g., Flask, Django) to receive asset data entered by the user via a REST API and store it in a database.

[0322] 4. Analysis of personal data

[0323] The server retrieves the stored user data and performs statistical analysis using Python's analytics module, such as calculating a user's income and expenditure balance and savings patterns using a three-month rolling average and comparing them with data from other users of the same age and region.

[0324] 5. Advice Generation

[0325] Based on the analysis results, the server uses a machine learning model (e.g., random forest) to automatically generate optimal asset formation advice for each user. The advice generated is customized to fit each user's data.

[0326] 6. Emotional Data Collection and Analysis

[0327] The server sends the user's interaction data to an emotion engine (e.g., Microsoft® Azure® Emotion API) to analyze the user's emotional state. The analysis results are stored in a database.

[0328] 7. Adjusting advice based on emotions

[0329] Based on the results of the emotion analysis, the server readjusts the advice to take into account the user's stress and anxiety.

[0330] 8. Submitting the results

[0331] The server packages the generated advice in JSON format and sends it to the user's device as an HTTP response.

[0332] Terminal handling

[0333] The terminal provides the interface with the user and is responsible for inputting data and displaying results.

[0334] 1. Data input from the user

[0335] The device (e.g. smartphone, PC) uses a front-end framework (e.g. React, Vue.js) to display a form for entering income, expenses, current savings amount, target savings amount, etc. The entered data is sent to the server's API via JavaScript.

[0336] 2. Collecting Emotional Data

[0337] The device uses JavaScript to measure the user's keystroke speed and mouse click frequency, and periodically sends the data to a server in the background. It also uses facial recognition software (e.g., OpenCV) via the camera to perform real-time emotion analysis.

[0338] 3. Data reception and display

[0339] The device receives the advice results sent from the server and displays them to the user in a visually easy-to-understand format (e.g., graphs or charts). A JavaScript library (e.g., Chart.js) is used for display.

[0340] User Action

[0341] The user uses a terminal to input data into the system and checks the advice sent from the server.

[0342] 1. Data Entry

[0343] The user enters their income, expenses, current savings amount, and target savings amount into a form on the terminal, and clicks the submit button to send the data to the server.

[0344] 2. Reflecting emotions

[0345] Data such as the user's keystroke speed and mouse click frequency is analyzed by the emotion engine, allowing the system to understand the user's emotional state.

[0346] 3. Check the advice

[0347] Users can view the analysis results and advice displayed on their device, including specific guidelines on how much they should save each month and which investment products they should choose.

[0348] 4. Providing Feedback

[0349] The user fills in the input form with feedback about the advice provided and clicks the submit button to send it to the server, for example, to indicate a preference such as "I would like to take more risks."

[0350] Specific examples

[0351] Every morning at 7am, the server retrieves market data such as exchange rates and stock indexes from a financial API (e.g., Alpha Vantage) and analyzes the data using NumPy and Pandas. The user enters their monthly income of 300,000 yen, savings goal of 5 million yen, and current savings of 1 million yen into the smartphone app. The front end is implemented in React, and the entered data is sent to the server via JavaScript and REST API. The server saves the received data in a MySQL database and analyzes the asset data using a Python script. Based on the results of this analysis, the user is compared with the average savings of people in their 30s and optimal asset formation advice is generated.

[0352] The emotion engine (e.g., Microsoft Azure Emotion API) analyzes the user's keystroke speed and mouse click frequency, and if it determines that the user is feeling anxious, it suggests low-risk investment methods. The server sends this advice in JSON format to the user's device.

[0353] Example prompt sentence:

[0354] "I'm 30 years old and earn 300,000 yen a month. My current savings goal is 5 million yen, but I've only saved 1 million yen. Please tell me how I can achieve my savings goal in the future."

[0355] To this prompt, the generative AI model responds as follows:

[0356] "We recommend that you review your monthly income and expenditures based on your current income and expenditure data and continue to save at least 30,000 yen per month. Also, if you are feeling anxious, consider choosing low-risk investment products and ways to safely increase your assets."

[0357] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0358] Server Processing

[0359] Step 1: Gather market data

[0360] The server automatically runs a Python script every morning at 7:00, connecting to a financial API (e.g., Alpha Vantage) using an API access library (e.g., requests) to retrieve the latest exchange rates, stock prices, and economic indicators. This data is stored in temporary storage (e.g., Redis, memcached). The input is market data retrieved from the API, and the output is the raw market data stored in temporary storage.

[0361] Step 2: Analyze market data and update the model

[0362] The server retrieves market data from temporary storage and preprocesses it using data processing libraries such as Pandas and NumPy. It then analyzes the market data using statistical analysis and machine learning algorithms (e.g., ARIMA model, regression) to predict market trends. It stores the analysis results in a database (e.g., MySQL). The input is the preprocessed market data, and the output is the analysis results stored in the database.

[0363] Step 3: Importing personal data

[0364] The server receives asset data (income, expenses, current savings, target savings, etc.) entered by the user via REST API and stores it in a database. The input is asset data sent by the user from the device, and the output is user data stored in the database.

[0365] Step 4: Analyzing personal data

[0366] The server retrieves user data stored in the database and performs statistical analysis using a Python analysis module. It calculates income / expense balance and savings patterns and compares them with data from other users of the same age and region. The results of this analysis are then stored back in the database. The input is the user's asset data, and the output is the analysis results.

[0367] Step 5: Advice Generation

[0368] The server generates optimal asset formation advice for the user using a machine learning model (e.g., random forest) based on user data and market data. The generated advice is stored in a database. The input is the analyzed market data and user data, and the output is the generated advice.

[0369] Step 6: Collect and analyze emotion data

[0370] The server sends the user's interaction data (keystroke speed, mouse click frequency, etc.) to the emotion engine (e.g., Microsoft Azure Emotion API) to analyze the user's emotional state. The analysis results are also stored in a database. The input is the user's interaction data, and the output is the analyzed emotional data.

[0371] Step 7: Adjust your advice based on emotions

[0372] The server readjusts the advice based on the results of the sentiment analysis. If the user is feeling stressed, it generates customized advice, such as suggesting low-risk investment methods. The adjusted advice is stored in a database. The input is the sentiment analysis result and existing advice, and the output is the adjusted advice.

[0373] Step 8: Sending the results

[0374] The server packages the generated and adjusted advice in JSON format and sends it to the user's device as an HTTP response. The input is the adjusted advice, and the output is the advice sent to the user's device.

[0375] Terminal handling

[0376] Step 1: Data input from the user

[0377] The device (e.g. smartphone, PC) uses a front-end framework (e.g. React, Vue.js) to display a form for inputting income, expenses, current savings, target savings, etc. When the user enters the data and clicks the submit button, the data is sent to the server's API via JavaScript. The input is the asset data entered by the user, and the output is the data sent to the server.

[0378] Step 2: Collecting emotion data

[0379] The device uses JavaScript to measure keystroke speed and mouse click frequency, and periodically sends the data to the server. It also uses face recognition software (e.g., OpenCV) via the camera to perform real-time emotion analysis, and sends the data to the server. The input is the user's interaction data, and the output is the emotion data sent to the server.

[0380] Step 3: Receiving and displaying data

[0381] The terminal receives the advice results sent from the server and displays them to the user in a visually easy-to-understand format such as graphs or charts using a JavaScript library (e.g., Chart.js). The input is the advice data received from the server, and the output is the advice displayed on the terminal.

[0382] User Action

[0383] Step 1: Data entry

[0384] The user enters their income, expenses, current savings amount, and target savings amount into the form on their device and clicks the submit button. This sends the data to the server. The input is the asset data entered by the user, and the output is the data sent to the server.

[0385] Step 2: Reflecting your emotions

[0386] Data such as the user's keystroke speed and mouse click frequency is sent to the server in real time and analyzed by the emotion engine. The input is the user's interaction data, and the output is emotion data stored on the server.

[0387] Step 3: Review the advice

[0388] The user checks the analysis results and advice displayed on the terminal. For example, specific guidelines are provided, such as how much to save each month or which investment product to choose. The input is advice data from the server, and the output is advice displayed on the terminal.

[0389] Step 4: Provide feedback

[0390] The user fills in the input form with feedback about the advice provided and clicks the submit button to send it to the server. For example, the user may indicate their preference for "taking more risks." The input is the feedback entered by the user, and the output is the feedback sent to the server.

[0391] (Application example 2)

[0392] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0393] Conventional asset formation support systems provide advice based solely on the analysis of asset data and market data entered by users. However, because they do not take into account the user's emotional state, they may suggest high-risk investments even when the user is feeling stressed or anxious, which makes it difficult to provide optimal asset formation for the user.

[0394] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0395] In this invention, the server includes means for collecting asset data from a user, means for collecting daily market data, means for analyzing the asset data and market data to generate asset formation advice, means for providing the advice to the user, means for analyzing user emotion data, and means for adjusting the advice based on the emotion data, thereby making it possible to provide optimal asset formation advice that takes into account the user's emotional state.

[0396] "Asset data" refers to financial information such as the user's income, expenses, savings amount, and target savings amount.

[0397] "Market data" refers to information related to financial markets, such as the latest exchange rates, stock prices, and economic indicators.

[0398] "Means for generating advice" refers to a technology that creates guidelines and suggestions for asset formation that are provided to users based on the collected and analyzed data.

[0399] The "means for providing advice" refers to a technology for transmitting the generated advice to the user's terminal and displaying it in a visually easy-to-understand format.

[0400] "Emotion data" refers to information that indicates the user's psychological state, determined from the user's keystroke speed, mouse click frequency, voice emotion analysis, face recognition, and the like.

[0401] "Means for adjusting advice based on emotional data" refers to technology that reflects the user's emotional state and customizes appropriate asset formation advice in a way that reduces risk, etc.

[0402] "Data of other users of the same age and area" refers to asset data of other users collected based on the user's age and area of ​​residence.

[0403] "Statistical analysis means" refers to techniques that use collected data to statistically analyze, compare, and predict.

[0404] As an embodiment of the present invention, a server, a terminal, and an emotion engine work in conjunction to form an asset formation support system. Specific processing and operations of each component will be described in detail below.

[0405] Server Processing

[0406] The server plays a key role in collecting and analyzing asset data, market data, and user sentiment data sent by users, and generating asset formation advice. The specific processes performed by the server are as follows:

[0407] 1. Market Data Collection:

[0408] The server accesses the financial API every morning at 7:00 to obtain the latest exchange rate information, stock prices, and economic indicators. This data is stored in temporary storage and used for analysis. The specific software used is Google Cloud API.

[0409] 2. Data analysis and model updating:

[0410] The server analyzes the collected market data using statistical analysis and machine learning algorithms to predict market trends. This analysis is performed using machine learning platforms such as TensorFlow. The analysis results are stored in a database.

[0411] 3. Collection and Analysis of Personal Data:

[0412] The server receives asset data (income, expenses, savings amount, savings target amount, etc.) sent by the user via API and stores it in a database.The asset data analysis module then analyzes the user data to determine income and expenditure balance and savings patterns.

[0413] 4. Emotional data collection and analysis:

[0414] The server uses an emotion engine to determine the user's emotional state based on their keystroke speed, mouse click frequency, voice emotion analysis, and facial recognition data. This analysis is performed using OpenCV and TensorFlow.

[0415] 5. Advice Generation:

[0416] Based on the analysis results, the server generates specific asset formation advice to help the user achieve their savings target. Based on the emotion data, the server provides appropriate advice that reflects the user's emotional state.

[0417] 6. Sending the results:

[0418] The server sends the generated advice to the user's device. The advice is packaged in JSON format or similar and provided to the user in real time.

[0419] Terminal handling

[0420] The terminal is responsible for inputting asset data by the user and displaying asset formation advice sent from the server. It also collects emotional data.

[0421] 1. Data input from the user:

[0422] The terminal displays a form for the user to input data such as income, expenses, current savings, target savings, etc. The data entered by the user is sent to the server.

[0423] 2. Collecting Emotional Data:

[0424] The device analyzes the user's typing speed, mouse click frequency, and even emotion using facial recognition. This data is sent to a server and used for emotion analysis.

[0425] 3. Data reception and display:

[0426] The device receives the analysis results and advice sent from the server and displays them to the user in a visually easy-to-understand format such as graphs and charts. A concrete example of this is the application display on a smartphone or smart glasses.

[0427] User Action

[0428] The user uses a terminal to input data into the system and check the advice sent from the server. The specific steps are as follows:

[0429] 1. Data Entry:

[0430] The user enters their income, expenses, current savings amount, and target savings amount into the form on the terminal and clicks the submit button.

[0431] 2. Reflecting emotions:

[0432] The user's interactions (such as keystroke speed and mouse click frequency) are analyzed by the emotion engine, and the user's emotional state is reflected in the system.

[0433] 3. Check the advice:

[0434] The user checks the analysis results and advice displayed on the device and receives specific asset formation guidelines.

[0435] Below are some examples of prompt sentences.

[0436] Market Data Collection:

[0437] Get the latest stock prices, exchange rates, and economic indicators data via Google Cloud API and store it in Firebase

[0438] Sentiment Data Analysis:

[0439] Analyzing keystroke speed and mouse click frequency with TensorFlow to estimate the user's emotional state

[0440] This allows users to find the optimal asset formation policy that takes into account their emotional state.

[0441] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0442] Step 1: Server

[0443] The server accesses the financial API every morning at 7:00 to collect the latest market data, such as exchange rates, stock prices, and economic indicators. The specific software used is Google Cloud API. The collected market data is stored in temporary storage. The input is market data obtained from the financial API, and the output is the market data stored in temporary storage.

[0444] Step 2: Server

[0445] The server analyzes the market data stored in temporary storage using statistical analysis and machine learning algorithms. TensorFlow is used for this analysis. As a result of the analysis, a predictive model is updated and stored in the database. The input is the market data stored in temporary storage, and the output is the updated predictive model.

[0446] Step 3: Users

[0447] The user uses a device to input income, expenses, current savings, and savings goals. The data entered by the user through a smartphone or smart glasses is sent from the device to the server. The input is the asset data entered by the user into the ANDROID / iOS application, and the output is the asset data sent to the server.

[0448] Step 4: Server

[0449] The server receives the asset data sent by the user and stores it in a database.Then, it uses the asset data analysis module to analyze the user's income and expenditure balance and savings pattern.The input is the user's asset data stored on the server, and the output is the analysis result, which is the income and expenditure balance and savings pattern.

[0450] Step 5: Terminal

[0451] The device collects emotional data using the user's keystroke speed, mouse click frequency, and even facial recognition. The emotional data is collected in real time and sent from the device to a server. Specific technologies used include OpenCV and TensorFlow. The input is the user's interaction data, and the output is the emotional data sent to the server.

[0452] Step 6: Server

[0453] The server uses an emotion engine to analyze the transmitted emotion data. As a result of the analysis, the server determines the user's emotional state and stores it in a database. The input is the emotion data transmitted from the device, and the output is the analyzed emotional state.

[0454] Step 7: Server

[0455] The server generates asset formation advice based on the user's asset data and emotional data. It makes investment suggestions with appropriate risk levels, taking into account the user's emotional state. For example, it suggests low-risk products to users with high anxiety. The input is the analyzed asset data and emotional data, and the output is the generated asset formation advice.

[0456] Step 8: Server

[0457] The server sends the generated advice to the user's device. The advice is packaged in JSON format or similar and converted into a format that is easy to understand visually on the device. The input is the generated asset formation advice, and the output is the advice sent to the user's device.

[0458] Step 9: Terminal

[0459] The device receives the advice sent from the server and displays it visually to the user using graphs and charts. Specific examples include displays on smartphones and smart glasses. The input is the advice sent from the server, and the output is advice in a visually easy-to-understand format.

[0460] Through the above processing steps, the user can find the optimal asset formation policy that takes into account his or her emotional state.

[0461] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0462] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0463] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0464] [Second embodiment]

[0465] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0466] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0467] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0468] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0469] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0470] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0471] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0472] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0473] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0474] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0475] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0476] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0477] In one embodiment of the present invention, a system for supporting asset formation is configured by users, servers, and terminals working together. The processing and specific operations of each component will be explained in natural language below.

[0478] Server Processing

[0479] The server is responsible for the central data processing and analysis of the system.

[0480] 1. Market data collection

[0481] The server periodically accesses the financial API to obtain the latest exchange rates, stock prices, and economic indicators. The collected data is temporarily stored in storage and used for subsequent analysis.

[0482] 2. Data analysis and model updating

[0483] The server analyzes the acquired market data and updates the model for predicting market trends using statistical methods and machine learning models. The results of this analysis are stored in a database and used to generate advice for users.

[0484] 3. Import of personal data

[0485] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user and stores it in a database.

[0486] 4. Analysis of personal data

[0487] The server analyzes the user's income and expenditure balance and savings patterns based on the saved asset data, and compares them with the data of other users of the same age and region.

[0488] 5. Advice Generation

[0489] Based on the analysis results, the server generates specific asset formation advice for the user to achieve their savings target. The advice generated is customized to the user's individual situation.

[0490] 6. Submitting the results

[0491] The server transmits the generated advice to the user's terminal.

[0492] Terminal handling

[0493] The terminal provides the interface with the user and is responsible for inputting data and displaying results.

[0494] 1. Data input from the user

[0495] The terminal provides an interface for the user to input data such as income, expenses, current savings, target savings, etc. The input data is sent to the server.

[0496] 2. Data reception and display

[0497] The device receives the analysis results and advice sent from the server and displays them to the user in an easy-to-read format, such as graphs or charts, which are visually easy to understand.

[0498] User Action

[0499] The user uses a terminal to input data into the system and checks the advice sent from the server.

[0500] 1. Data Entry

[0501] The user inputs his / her income, expenses, current savings amount, and target savings amount through the terminal interface, and sends the data to the server by clicking the send button.

[0502] 2. Check the advice

[0503] Users can check the analysis results and advice displayed on their device and use them to plan their asset-building activities, such as how much to save each month and which investment products to purchase.

[0504] 3. Providing Feedback

[0505] Users can input feedback about the advice provided and submit their wishes and changes to the system. For example, by inputting a wish such as "I want to take more risks," new advice will be provided.

[0506] Specific examples

[0507] Every morning, the server retrieves and analyzes market data such as exchange rates and stock indexes from a specified financial API. The user inputs data such as a monthly income of 300,000 yen, a savings goal of 5 million yen, and current savings of 1 million yen into a smartphone app. The server analyzes this data and generates a result by comparing it with the average savings of people in their 30s. The generated result and advice are sent to the user's device, and the user receives specific guidelines such as saving 30,000 yen per month and purchasing low-risk investment products. The user can provide feedback on the advice and have it reflected in the system, resulting in a more accurate asset formation plan.

[0508] In this way, the present invention can provide specific and reliable advice to help users build assets efficiently.

[0509] The processing flow will be explained below.

[0510] Server Processing Steps

[0511] Step 1:

[0512] The server runs a scheduled job every morning at 7:00 am, accessing the API of economic data providers to obtain market data such as exchange rates, stock indexes, and economic indicators, and stores it in temporary storage.

[0513] Step 2:

[0514] The server analyzes the stored market data using a data analysis module, which uses statistical analysis and machine learning algorithms to predict market trends and stores the results in a database.

[0515] Step 3:

[0516] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user via API and stores it in a database.

[0517] Step 4:

[0518] The server retrieves the user data stored in the database and analyzes it using the asset data analysis module. The user's income and expenditure balance and savings patterns are analyzed and compared with the data of other users of the same age and region.

[0519] Step 5:

[0520] Based on the analysis results, the server generates specific asset formation advice to help users achieve their savings goals. The advice is customized based on each user's situation.

[0521] Step 6:

[0522] The server packages the generated advice in JSON format and sends it to the user's device.

[0523] Terminal processing steps

[0524] Step 1:

[0525] The terminal presents the user with a data entry form, where the user enters information such as income, expenses, current savings, and savings goals.

[0526] Step 2:

[0527] The device receives the user's input data and generates an API request to send it to the server. The API request is encrypted and sent.

[0528] Step 3:

[0529] The device receives the analysis results and advice sent from the server, which are also received as API responses.

[0530] Step 4:

[0531] The device analyzes the data it receives and displays it in a format that is easy for the user to understand, such as a graph, chart, or list.

[0532] User processing steps

[0533] Step 1:

[0534] The user enters income, expenses, current savings amount, and target savings amount into the data input form on the terminal and clicks the submit button.

[0535] Step 2:

[0536] The user checks the analysis results and advice displayed on the device, such as how much they should save each month and which investment products they should choose.

[0537] Step 3:

[0538] The user inputs feedback about the advice provided, such as "I want to take more risks" or "I want to know about safer options," and sends this feedback from the device to the server.

[0539] Through these steps, the system can provide users with personalized asset formation advice and support optimal asset formation.

[0540] Example 1

[0541] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0542] Conventional asset formation support systems have struggled to provide specific and reliable advice tailored to each user's individual circumstances. Furthermore, there was a lack of systems that could accurately reflect daily fluctuating market data and allow users to obtain timely information. Furthermore, it was difficult to generate personalized plans based on a user's income, expenses, and savings, and comparisons with a large amount of user data were not conducted.

[0543] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0544] In this invention, the server includes means for collecting asset data from users, means for collecting daily market data, means for analyzing the asset data and market data to generate asset formation advice, means for providing the advice to users, means for updating a machine learning model using the market data and asset data, a terminal interface for inputting data on the user's income, expenses, savings, and target savings, and means for confirming the analysis results and advice displayed on the terminal. This allows users to receive specific and reliable advice tailored to their individual circumstances. Furthermore, by reflecting market data that fluctuates daily in a timely manner, asset formation based on the latest information is possible. Furthermore, by comparing user data with data on other users of the same age and region, more accurate analysis and advice can be provided.

[0545] The "means for collecting asset data from a user" refers to a means for inputting, receiving, and storing asset data such as a user's income, expenses, savings amount, and target savings amount.

[0546] "Means of collecting daily market data" refers to the use of financial APIs to regularly obtain and store market data such as foreign exchange information, stock prices, and economic indicators.

[0547] The "means for analyzing the asset data and market data to generate asset formation advice" refers to a means for analyzing the acquired asset data and market data and using statistical techniques and machine learning models to generate specific asset formation advice for the user.

[0548] The "means for providing the advice to the user" refers to means for transmitting information to the user's terminal through an interface for providing the generated advice to the user.

[0549] "Means for updating machine learning models using market data and asset data" refers to means for updating predictive models using machine learning algorithms based on regularly collected market data and asset data from users.

[0550] A "terminal interface for inputting user's income, expenditure, savings, and savings goal data" is a terminal that provides a graphical interface for a user to input personal data such as income, expenditure, current savings, and savings goal.

[0551] "Means for checking the analysis results and advice displayed on the terminal" refers to a terminal function for receiving the analysis results and advice sent from the server and visually displaying them.

[0552] This invention provides a system that supports asset formation through cooperation between users, servers, and terminals. The specific configuration and operation of this system will be described below.

[0553] Server Roles

[0554] The server is responsible for the central data processing and analysis of this system and uses the following hardware and software:

[0555] Hardware: High-performance servers, SSD storage, network interfaces

[0556] Software: Python, TensorFlow, Scikit-learn, Pandas, Jupyter Notebook, MongoDB, RESTful API

[0557] The server collects daily market data using financial APIs. For example, it periodically accesses APIs from Alpha Vantage and Yahoo Finance to obtain the latest exchange rates, stock prices, and economic indicators. This data is temporarily stored in a database such as MongoDB.

[0558] The server then analyzes the collected market data using Python and Jupyter Notebook, preprocessing the data with the Pandas library, and updating machine learning models using TensorFlow and Scikit-learn. The analyzed data is then used to generate recommendations for users.

[0559] Furthermore, the server receives asset data (income, expenses, savings amount, savings target, etc.) sent by the user and stores it in a database. Based on the stored data, the server analyzes the user's income and expenditure balance and savings pattern and performs statistical comparisons. Based on the results, it generates specific asset formation advice for the user and sends it to the user's device via a RESTful API.

[0560] Device Role

[0561] The terminal provides the interface with the user, allowing data entry and displaying results. The terminal uses the following hardware and software:

[0562] Hardware: Smartphones, tablets, computers

[0563] Software: HTML, CSS, JavaScript, AJAX, Chart.js, D3.js

[0564] The terminal provides an interface for users to input data such as income, expenses, current savings, and target savings. These data are retrieved by JavaScript through an HTML form and sent to the server in JSON format using AJAX.

[0565] The device also receives analysis results and advice sent from the server and visually displays them to the user using Chart.js and D3.js, using graphs and charts to help users intuitively understand the information.

[0566] User Roles

[0567] The user uses a terminal interface to input asset data into the system and review the advice provided by the server.

[0568] Users enter their income, expenses, current savings amount, and target savings amount into an HTML form on their device, and then click the submit button to send the data to the server. The analysis results and advice sent from the server are displayed on the device. This allows users to obtain specific asset formation guidelines and implement an asset formation plan that suits their own situation.

[0569] Furthermore, users can provide feedback on the advice provided. For example, they can enter their wishes or changes, such as "I want to take more risks" or "I want more detailed advice," and click the submit button. The server receives this feedback and reflects it in the next advice generation.

[0570] Specific examples

[0571] Every morning, the server retrieves market data such as exchange rates and stock indexes from a specified financial API (e.g., Alpha Vantage) and analyzes it. The user enters data into the smartphone app, such as monthly income of 300,000 yen, savings goal of 5 million yen, and current savings of 1 million yen. This data is sent to the server, which analyzes and compares it to generate specific advice. For example, this advice might include "save 30,000 yen per month and purchase low-risk investment products."

[0572] Examples of prompt statements

[0573] Below is an example of a prompt sentence to input to the generative AI model.

[0574] I'm in my 30s, earn 300,000 yen a month, have a savings goal of 5 million yen, and currently have 1 million yen saved. Please give me some advice on how to build up assets with low risk.

[0575] In this way, the present invention is a system that provides specific and reliable advice to help users build up their assets efficiently.

[0576] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0577] Step 1: Gather market data

[0578] Every morning, the server periodically accesses a financial API (e.g., Alpha Vantage, Yahoo Finance) to retrieve exchange rate information, stock prices, and economic indicators. The input is the API key and request parameters, and the output is market data in JSON format. The server temporarily stores this JSON data in MongoDB. Specifically, it sends an API request using a Python library, receives the response, and stores it in the database.

[0579] Step 2: Analyze market data and update the model

[0580] The server analyzes market data using Python scripts and Jupyter Notebook. The input is market data stored in MongoDB, and the output is the analysis results and an updated machine learning model. Specifically, the data is read and preprocessed using the Pandas library, and the model is trained and updated using TensorFlow and Scikit-learn. This analysis data is stored in a database.

[0581] Step 3: Import user data

[0582] The user enters asset data such as income, expenses, savings amount, and savings goal through an HTML form on the device and clicks the submit button. The input is the user's asset data, and the output is JSON format data stored on the server. The device uses JavaScript and AJAX to send the data to the server, which then receives the data and stores it in a database.

[0583] Step 4: Analyzing personal data

[0584] The server analyzes income / expense balances and savings patterns based on the saved user asset data. The input is asset data obtained from the user database, and the output is the results of statistical analysis. Specifically, data is obtained using SQL queries, and statistical analysis such as standard deviation and average values ​​is performed using Python scripts. The results are then compared with data from users of the same age and region.

[0585] Step 5: Generating Advice

[0586] The server generates asset formation advice for the user based on the analysis results. The input is the analysis results of personal data and market data, and the output is a customized advice message. Specifically, it uses machine learning models and natural language generation models (e.g., GPT-3) to generate specific guidelines in text that are tailored to the user's situation. The results are stored in a database.

[0587] Step 6: Send and view results

[0588] The server sends the generated advice to the user's device. The input is the generated advice, and the output is the advice message displayed on the user's device. Specifically, the advice is sent in JSON format using a RESTful API, and is received on the device using AJAX. The received advice is displayed visually using Chart.js or D3.js. For example, a text message such as "Save 30,000 yen each month and purchase low-risk investment products" is displayed.

[0589] Through this series of processes, users can receive specific and reliable advice on how to build assets efficiently.

[0590] (Application example 1)

[0591] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0592] Conventional asset formation support systems provide advice based on basic asset data and market data from users, but are unable to reflect feedback on users' daily purchasing behavior or actual spending. As a result, it is difficult to provide real-time advice adapted to individual situations, and users are unable to obtain sufficient information to formulate specific asset formation plans.

[0593] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0594] In this invention, the server includes means for collecting asset data from users, means for collecting daily market data, means for analyzing the asset data and market data to generate asset formation advice, means for providing the advice to users, means for collecting user purchase history and expenditure data, means for analyzing the purchase history, expenditure data, and market data to generate asset formation advice based on purchasing behavior, means for providing the advice to users in real time, and means for updating the advice based on user feedback, thereby making it possible to provide more specific, personalized, real-time advice to users in asset formation.

[0595] "Means for collecting asset data from users" refers to a function that allows users to input asset data such as their income, expenses, savings amount, and target savings amount, and transmit this data to the server.

[0596] "Means of collecting daily market data" refers to the function of regularly collecting market data such as exchange rates, stock prices, and economic indicators from external sources such as financial APIs.

[0597] "Means for analyzing the asset data and market data to generate asset formation advice" refers to a function that performs analysis based on the collected asset data and market data and generates asset formation advice to be provided to the user.

[0598] The "means for providing the advice to the user" refers to a function for transmitting the generated asset formation advice to the user's terminal and displaying it in a visually easy-to-understand format.

[0599] "Means for collecting user purchase history and expenditure data" refers to a function that automatically collects a user's electronic payment transaction history and daily expenditure data and transmits it to a server for analysis.

[0600] "Means for analyzing the purchase history, expenditure data and market data, and generating asset formation advice based on purchasing behavior" refers to a function that comprehensively analyzes a user's purchase history, expenditure data and market data, and generates specific asset formation advice based on individual purchasing behavior.

[0601] The "means for providing the advice to the user in real time" refers to a function that allows advice based on the analysis results to be immediately provided to the user and feedback to be received in real time.

[0602] "Means for updating advice based on user feedback" refers to the function of collecting feedback information from users and appropriately updating and adjusting the advice content generated based on that information.

[0603] This invention configures a system that supports users' asset formation by linking users, servers, and terminals. The processing and specific operations of each component will be described below.

[0604] Server Processing

[0605] The server is responsible for the system's central data processing and analysis. It analyzes asset data and purchase history data obtained from users, along with the latest market data. Market data is obtained from financial APIs, and includes exchange information, stock prices, economic indicators, and more. Statistical methods and machine learning models are used to predict market trends and purchasing behavior. Based on the results of this analysis, the server generates asset formation advice personalized for the user and sends it to the terminal.

[0606] Terminal handling

[0607] The terminal provides an interface for the user and is responsible for inputting data and displaying the results. The user inputs data such as income, expenses, current savings amount, and savings goal, and daily purchase history and expenditure data are also collected. The input data is sent to the server. The analysis results and advice sent from the server are displayed on the terminal in real time. The data is displayed in a visually easy-to-understand format such as graphs and charts.

[0608] User Action

[0609] Users use their devices to input data into the system and check the advice sent from the server. Based on the advice, users plan specific asset formation actions. For example, they are presented with guidelines on how much to save each month and which investment products to purchase. Users also provide feedback on the advice provided and send their wishes and changes to the system. This allows the server to improve the analysis model based on the feedback and provide more accurate advice.

[0610] Specific examples

[0611] Every morning, the server retrieves market data such as exchange rates and stock indexes from a specified financial API. The user enters data into their smartphone, such as monthly income of 300,000 yen, savings goal of 5 million yen, and current savings of 1 million yen. At the same time, the device automatically collects the user's purchase history and expenditure data. The server analyzes this data and generates results that compare the user's savings with the average savings of people in their 30s. The generated results and advice are sent to the user's device in real time as specific guidelines, such as saving 30,000 yen per month or purchasing low-risk investment products. The user can provide feedback on the advice and have it reflected in the system, resulting in an even more accurate asset formation plan.

[0612] Prompt Sentence Examples

[0613] "Input: My monthly income is ¥200,000, my monthly expenses are ¥150,000, my current savings are ¥300,000, and my goal savings is ¥5 million. How can I achieve this in the next five years?

[0614] Output: I recommend you put away 10,000 yen per month in a low-risk mutual fund. This will increase your chances of reaching your goal.

[0615] As a result, the present invention provides a system that helps users to efficiently build assets by automatically tracking their daily expenses and income and providing financial advice in real time.

[0616] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0617] Step 1:

[0618] The server periodically accesses the financial API to obtain market data (foreign exchange information, stock prices, economic indicators, etc.). The obtained market data is temporarily stored in storage. The input is market data from the financial API, and the output is the temporarily stored market data.

[0619] Step 2:

[0620] The server analyzes the acquired market data and updates a model for predicting market trends using statistical methods and machine learning models (e.g., Linear Regression). The analyzed data is stored in a database and used to generate advice for users. The input is temporarily stored market data, and the output is the updated results of the analytical model.

[0621] Step 3:

[0622] The user uses a terminal to input asset data such as their income, expenses, current savings amount, and target savings amount. In addition, the user's purchase history and daily expenditure data are also automatically collected through the terminal. The input is the asset data and purchase history data entered by the user into the terminal, and the output is the data sent to the server.

[0623] Step 4:

[0624] The server receives asset data and purchase history data sent from the user and stores them in a database. The input is the asset data and purchase history data sent from the terminal, and the output is the stored data.

[0625] Step 5:

[0626] The server analyzes the saved user asset data and purchase history data in combination with market data. This analysis generates specific advice for the user regarding asset formation. The inputs are market data, the user's asset data, and purchase history data, and the output is the generated advice.

[0627] Step 6:

[0628] The server sends the generated asset formation advice to the user's terminal. The advice is specific and tailored to the user's purchasing behavior and asset data. The input is the generated advice, and the output is the advice sent to the user's terminal.

[0629] Step 7:

[0630] The user checks the analysis results and advice displayed on the terminal and plans asset formation actions based on them. The user inputs feedback about the advice provided and sends it to the system. The input is feedback about the analysis results and advice, and the output is the feedback sent to the server.

[0631] Step 8:

[0632] The server receives feedback from users and updates the analytical model and advice generation logic based on the feedback. The input is the user feedback, and the output is the updated analytical model and advice generation logic.

[0633] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0634] As an embodiment of the present invention, a user, a server, a terminal, and an emotion engine work in cooperation to form an asset formation support system. Specific processing and operations of each component will be described in detail below.

[0635] Server Processing

[0636] The server is responsible for collecting asset and market data, analyzing it, generating advice, and analyzing user sentiment data.

[0637] 1. Market data collection

[0638] The server accesses the financial API at 7:00 every morning to obtain the latest exchange rate information, stock prices, and economic indicators, and stores them in temporary storage.

[0639] 2. Data analysis and model updating

[0640] The server analyzes the collected market data using statistical analysis and machine learning algorithms to predict market trends, and the results are stored in a database.

[0641] 3. Import of personal data

[0642] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user via API and stores it in a database.

[0643] 4. Analysis of personal data

[0644] The server retrieves user data stored in the database and analyzes it using the asset data analysis module. The server analyzes income and expenditure balances and savings patterns, and compares them with data from other users of the same age and region.

[0645] 5. Advice Generation

[0646] Based on the analysis results, the server generates specific asset formation advice to help users achieve their savings goals. The advice generated is customized to fit each user's situation.

[0647] 6. Emotional Data Collection and Analysis

[0648] The server uses an emotion engine to determine the user's emotional state from input data and interaction data (e.g., the user's keystroke speed, mouse click frequency, etc.) The emotion data is stored in a database as part of the analysis.

[0649] 7. Adjusting advice based on emotions

[0650] The server adjusts the asset formation advice based on the user's emotional state. For example, if the user is feeling stressed, the server generates more appropriate advice, such as suggesting low-risk investment methods.

[0651] 8. Submitting the results

[0652] The server sends the generated advice to the user's device, packaged in JSON format or similar.

[0653] Terminal handling

[0654] The terminal provides the interface with the user and is responsible for inputting data and displaying results.

[0655] 1. Data input from the user

[0656] The terminal displays a form for the user to input data such as income, expenses, current savings, target savings, etc. The data input by the user is sent to the server.

[0657] 2. Collecting Emotional Data

[0658] The device also analyzes the user's keystroke speed, mouse click frequency, and emotion using facial recognition, and sends this data to the server.

[0659] 3. Data reception and display

[0660] The terminal receives the analysis results and advice sent from the server and displays them to the user in a visually easy-to-understand format such as graphs and charts.

[0661] User Action

[0662] The user uses a terminal to input data into the system and checks the advice sent from the server.

[0663] 1. Data Entry

[0664] The user enters their income, expenses, current savings amount, and target savings amount into a form on the terminal and clicks the send button to send the data to the server.

[0665] 2. Reflecting emotions

[0666] The user's interactions (such as keystroke speed and mouse click frequency) are analyzed by the emotion engine, and the user's emotional state is reflected in the system.

[0667] 3. Check the advice

[0668] Users can view the analysis results and advice displayed on their device, including specific guidelines on how much they should save each month and which investment products they should choose.

[0669] 4. Providing Feedback

[0670] The user inputs feedback about the advice provided, for example, a preference such as "I want to take more risks," and sends this feedback to the server from the terminal.

[0671] Specific examples

[0672] Every morning at 7am, the server retrieves and analyzes market data such as exchange rates and stock indexes from a financial API. The user inputs data such as a monthly income of 300,000 yen, a savings goal of 5 million yen, and a current savings of 1 million yen into the smartphone app. The server analyzes this data and generates a result by comparing it with the average savings of people in their 30s. The generated result and advice are sent to the user's device, and the user receives specific guidelines such as saving 30,000 yen per month and purchasing low-risk investment products.

[0673] Furthermore, if the user's input speed is slow and they are feeling anxious, the emotion engine will provide advice based on the user's emotional state, such as suggesting low-risk investment methods. This allows users to find the optimal asset formation policy that takes their emotional state into account.

[0674] The processing flow will be explained below.

[0675] Server Processing Steps

[0676] Step 1:

[0677] The server accesses the financial API at 7am every morning to obtain the latest exchange rates, stock prices, and economic indicators, and stores them in temporary storage.

[0678] Step 2:

[0679] The server analyzes the stored market data using a data analysis module, and uses statistical analysis and machine learning algorithms to predict market trends, and stores the results in a database.

[0680] Step 3:

[0681] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user via API and stores it in a database.

[0682] Step 4:

[0683] The server retrieves user data stored in the database and analyzes it using the asset data analysis module. The analysis includes income and expenditure balances and savings patterns, and compares them with data from other users of the same age and region.

[0684] Step 5:

[0685] Based on the analysis results, the server generates specific asset formation advice to help users achieve their savings goals. The advice is customized to each user's situation.

[0686] Step 6:

[0687] The server uses an emotion engine to determine the user's emotional state from their input data and interaction data (e.g., keystroke speed, mouse click frequency, etc.), and the emotional data is stored in a database.

[0688] Step 7:

[0689] The server adjusts asset formation advice based on the user's emotional state. For example, if the user is feeling stressed, the server will suggest low-risk investment methods.

[0690] Step 8:

[0691] The server packages the generated customized advice in JSON format and sends it to the user's device.

[0692] Terminal processing steps

[0693] Step 1:

[0694] The terminal presents the user with a data entry form, where the user enters information such as income, expenses, current savings, and savings goals.

[0695] Step 2:

[0696] The device receives the user's input data and generates an API request to send it to the server. The API request is encrypted and sent.

[0697] Step 3:

[0698] The device collects user interactions (such as keystroke speed, mouse click frequency, and facial recognition data) and sends them to a server.

[0699] Step 4:

[0700] The device receives the analysis results and advice sent from the server and displays them in a user-friendly format (graphs, charts, lists, etc.).

[0701] User processing steps

[0702] Step 1:

[0703] The user enters their income, expenses, current savings amount, target savings amount, etc. into the data input form on the terminal and clicks the submit button.

[0704] Step 2:

[0705] The user checks the analysis results and advice displayed on the device, receiving specific guidance on how much to save each month, which investment products to choose, and so on.

[0706] Step 3:

[0707] The user inputs feedback about the advice provided. For example, the user sends a request such as "I want to take more risks" to the server via the terminal.

[0708] Specific examples

[0709] Server Processing

[0710] Step 1:

[0711] The server retrieves "exchange rates and stock indexes from the API" every morning at 7:00.

[0712] Step 2:

[0713] The server "analyzes the acquired market data using statistical analysis and machine learning algorithms" and "stores the results in a database."

[0714] Step 3:

[0715] The server receives the data sent by the user, including a monthly income of 300,000 yen, a savings goal of 5 million yen, and a current savings amount of 1 million yen, and stores this data in the database.

[0716] Step 4:

[0717] The server performs the process of "analyzing user data stored in a database and comparing it with the average savings amount of people in their 30s."

[0718] Step 5:

[0719] The server "generates asset formation advice based on each user's situation" and "suggests monthly savings of 30,000 yen and low-risk investment products."

[0720] Step 6:

[0721] The server "uses an emotion engine to determine the user's emotional state" and "saves the emotional data in a database."

[0722] Step 7:

[0723] The server adjusts advice based on the user's emotional state, such as suggesting low-risk investment methods if the user is feeling stressed.

[0724] Step 8:

[0725] The server "packages the generated advice in JSON format" and "sends it to the user's device."

[0726] Terminal handling

[0727] Step 1:

[0728] The device "presents the user with a data entry form for income, expenses, savings, and savings goals."

[0729] Step 2:

[0730] The device "generates an API request to send the input data to the server" and "encrypts and sends it."

[0731] Step 3:

[0732] The device "collects user interaction data (such as keystroke speed and mouse click frequency)" and "sends it to the server."

[0733] Step 4:

[0734] The device "displays the analysis results and advice received from the server in graphs and charts."

[0735] User Action

[0736] Step 1:

[0737] The user "enters their income, expenses, current savings amount, and target savings amount, and clicks the submit button."

[0738] Step 2:

[0739] The user "checks the displayed analysis results and advice (saving 30,000 yen per month, low-risk investment products, etc.)."

[0740] Step 3:

[0741] Users "enter feedback about the advice provided" and "submit preferences such as 'I'd like to take more risks.'"

[0742] Through these steps, the system provides users with personalized asset formation advice, and by taking the user's emotional state into consideration, it achieves more accurate support.

[0743] Example 2

[0744] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0745] Conventional asset formation support systems generally provide uniform advice based on data input by users, making it difficult to provide advice that takes into account individual emotions and unique situations. In addition, it is difficult for users to accurately grasp market trends and their own asset status, and it takes a lot of time and effort to find the optimal asset formation strategy.

[0746] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0747] In this invention, the server includes means for receiving asset data from a user, means for periodically recording market data, means for analyzing the asset data and market data to generate asset formation advice, means for notifying the user of the advice, means for collecting user interaction data and analyzing emotion data, and means for adjusting the advice based on the emotion data, thereby enabling the provision of customized advice that takes into account the individual circumstances and emotional state of the user.

[0748] "Asset data" refers to information about assets owned by a user, and specifically includes income, expenses, current savings, target savings, and the like.

[0749] "Market data" is a general term for information collected from financial markets, and includes data such as exchange rates, stock prices, and economic indicators.

[0750] "Means for generating advice" refers to machine learning algorithms and statistical analysis means for analyzing collected asset data and market data and creating appropriate asset formation advice for users.

[0751] The "means for notifying advice" refers to communication means and display means for transmitting the generated advice to the user's terminal and making it available for the user to view.

[0752] "Interaction data" refers to data related to user operations, such as keystroke speed, mouse click frequency, and facial recognition data, when a user operates a device.

[0753] "Emotional data" refers to information about a user's emotional state obtained by analyzing interaction data and facial recognition data.

[0754] "Means for adjusting advice based on emotional data" refers to algorithms and analytical means for taking into account the user's emotional data and providing optimal asset formation advice.

[0755] As an embodiment of the present invention, a user, a server, a terminal, and an emotion engine work in cooperation to form an asset formation support system. Specific processing and operations of each component will be described in detail below.

[0756] Server Processing

[0757] The server is responsible for collecting asset and market data, analyzing it, generating advice, and analyzing user sentiment data.

[0758] 1. Market data collection

[0759] The server automatically runs a Python script every morning at 7:00, connects to a financial API (e.g., Alpha Vantage) using an API access library (e.g., requests), retrieves the latest exchange rates, stock prices, and economic indicators, and stores them in temporary storage (e.g., Redis, memcached).

[0760] 2. Market data analysis and model updates

[0761] The server preprocesses the collected market data using Python data processing libraries such as Pandas and NumPy, and analyzes it using statistical analysis and machine learning algorithms (e.g., ARIMA model, regression). The analysis results are stored in a database (e.g., MySQL). The machine learning model is also updated regularly.

[0762] 3. Import of personal data

[0763] The server uses a web framework (e.g., Flask, Django) to receive asset data entered by the user via a REST API and store it in a database.

[0764] 4. Analysis of personal data

[0765] The server retrieves the stored user data and performs statistical analysis using Python's analytics module, such as calculating a user's income and expenditure balance and savings patterns using a three-month rolling average and comparing them with data from other users of the same age and region.

[0766] 5. Advice Generation

[0767] Based on the analysis results, the server uses a machine learning model (e.g., random forest) to automatically generate optimal asset formation advice for each user. The advice generated is customized to fit each user's data.

[0768] 6. Emotional Data Collection and Analysis

[0769] The server sends the user's interaction data to an emotion engine (e.g., Microsoft Azure Emotion API) to analyze the user's emotional state. The analysis results are stored in a database.

[0770] 7. Adjusting advice based on emotions

[0771] Based on the results of the emotion analysis, the server readjusts the advice to take into account the user's stress and anxiety.

[0772] 8. Submitting the results

[0773] The server packages the generated advice in JSON format and sends it to the user's device as an HTTP response.

[0774] Terminal handling

[0775] The terminal provides the interface with the user and is responsible for inputting data and displaying results.

[0776] 1. Data input from the user

[0777] The device (e.g. smartphone, PC) uses a front-end framework (e.g. React, Vue.js) to display a form for entering income, expenses, current savings amount, target savings amount, etc. The entered data is sent to the server's API via JavaScript.

[0778] 2. Collecting Emotional Data

[0779] The device uses JavaScript to measure the user's keystroke speed and mouse click frequency, and periodically sends the data to a server in the background. It also uses facial recognition software (e.g., OpenCV) via the camera to perform real-time emotion analysis.

[0780] 3. Data reception and display

[0781] The device receives the advice results sent from the server and displays them to the user in a visually easy-to-understand format (e.g., graphs or charts). A JavaScript library (e.g., Chart.js) is used for display.

[0782] User Action

[0783] The user uses a terminal to input data into the system and checks the advice sent from the server.

[0784] 1. Data Entry

[0785] The user enters their income, expenses, current savings amount, and target savings amount into a form on the terminal, and clicks the submit button to send the data to the server.

[0786] 2. Reflecting emotions

[0787] Data such as the user's keystroke speed and mouse click frequency is analyzed by the emotion engine, allowing the system to understand the user's emotional state.

[0788] 3. Check the advice

[0789] Users can view the analysis results and advice displayed on their device, including specific guidelines on how much they should save each month and which investment products they should choose.

[0790] 4. Providing Feedback

[0791] The user fills in the input form with feedback about the advice provided and clicks the submit button to send it to the server, for example, to indicate a preference such as "I would like to take more risks."

[0792] Specific examples

[0793] Every morning at 7am, the server retrieves market data such as exchange rates and stock indexes from a financial API (e.g., Alpha Vantage) and analyzes the data using NumPy and Pandas. The user enters their monthly income of 300,000 yen, savings goal of 5 million yen, and current savings of 1 million yen into the smartphone app. The front end is implemented in React, and the entered data is sent to the server via JavaScript and REST API. The server saves the received data in a MySQL database and analyzes the asset data using a Python script. Based on the results of this analysis, the user is compared with the average savings of people in their 30s and optimal asset formation advice is generated.

[0794] The emotion engine (e.g., Microsoft Azure Emotion API) analyzes the user's keystroke speed and mouse click frequency, and if it determines that the user is feeling anxious, it suggests low-risk investment methods. The server sends this advice in JSON format to the user's device.

[0795] Example prompt sentence:

[0796] "I'm 30 years old and earn 300,000 yen a month. My current savings goal is 5 million yen, but I've only saved 1 million yen. Please tell me how I can achieve my savings goal in the future."

[0797] To this prompt, the generative AI model responds as follows:

[0798] "We recommend that you review your monthly income and expenditures based on your current income and expenditure data and continue to save at least 30,000 yen per month. Also, if you are feeling anxious, consider choosing low-risk investment products and ways to safely increase your assets."

[0799] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0800] Server Processing

[0801] Step 1: Gather market data

[0802] The server automatically runs a Python script every morning at 7:00, connecting to a financial API (e.g., Alpha Vantage) using an API access library (e.g., requests) to retrieve the latest exchange rates, stock prices, and economic indicators. This data is stored in temporary storage (e.g., Redis, memcached). The input is market data retrieved from the API, and the output is the raw market data stored in temporary storage.

[0803] Step 2: Analyze market data and update the model

[0804] The server retrieves market data from temporary storage and preprocesses it using data processing libraries such as Pandas and NumPy. It then analyzes the market data using statistical analysis and machine learning algorithms (e.g., ARIMA model, regression) to predict market trends. It stores the analysis results in a database (e.g., MySQL). The input is the preprocessed market data, and the output is the analysis results stored in the database.

[0805] Step 3: Importing personal data

[0806] The server receives asset data (income, expenses, current savings, target savings, etc.) entered by the user via REST API and stores it in a database. The input is asset data sent by the user from the device, and the output is user data stored in the database.

[0807] Step 4: Analyzing personal data

[0808] The server retrieves user data stored in the database and performs statistical analysis using a Python analysis module. It calculates income / expense balance and savings patterns and compares them with data from other users of the same age and region. The results of this analysis are then stored back in the database. The input is the user's asset data, and the output is the analysis results.

[0809] Step 5: Advice Generation

[0810] The server generates optimal asset formation advice for the user using a machine learning model (e.g., random forest) based on user data and market data. The generated advice is stored in a database. The input is the analyzed market data and user data, and the output is the generated advice.

[0811] Step 6: Collect and analyze emotion data

[0812] The server sends the user's interaction data (keystroke speed, mouse click frequency, etc.) to the emotion engine (e.g., Microsoft Azure Emotion API) to analyze the user's emotional state. The analysis results are also stored in a database. The input is the user's interaction data, and the output is the analyzed emotional data.

[0813] Step 7: Adjust your advice based on emotions

[0814] The server readjusts the advice based on the results of the sentiment analysis. If the user is feeling stressed, it generates customized advice, such as suggesting low-risk investment methods. The adjusted advice is stored in a database. The input is the sentiment analysis result and existing advice, and the output is the adjusted advice.

[0815] Step 8: Sending the results

[0816] The server packages the generated and adjusted advice in JSON format and sends it to the user's device as an HTTP response. The input is the adjusted advice, and the output is the advice sent to the user's device.

[0817] Terminal handling

[0818] Step 1: Data input from the user

[0819] The device (e.g. smartphone, PC) uses a front-end framework (e.g. React, Vue.js) to display a form for inputting income, expenses, current savings, target savings, etc. When the user enters the data and clicks the submit button, the data is sent to the server's API via JavaScript. The input is the asset data entered by the user, and the output is the data sent to the server.

[0820] Step 2: Collecting emotion data

[0821] The device uses JavaScript to measure keystroke speed and mouse click frequency, and periodically sends the data to the server. It also uses face recognition software (e.g., OpenCV) via the camera to perform real-time emotion analysis, and sends the data to the server. The input is the user's interaction data, and the output is the emotion data sent to the server.

[0822] Step 3: Receiving and displaying data

[0823] The terminal receives the advice results sent from the server and displays them to the user in a visually easy-to-understand format such as graphs or charts using a JavaScript library (e.g., Chart.js). The input is the advice data received from the server, and the output is the advice displayed on the terminal.

[0824] User Action

[0825] Step 1: Data entry

[0826] The user enters their income, expenses, current savings amount, and target savings amount into the form on their device and clicks the submit button. This sends the data to the server. The input is the asset data entered by the user, and the output is the data sent to the server.

[0827] Step 2: Reflecting your emotions

[0828] Data such as the user's keystroke speed and mouse click frequency is sent to the server in real time and analyzed by the emotion engine. The input is the user's interaction data, and the output is emotion data stored on the server.

[0829] Step 3: Review the advice

[0830] The user checks the analysis results and advice displayed on the terminal. For example, specific guidelines are provided, such as how much to save each month or which investment product to choose. The input is advice data from the server, and the output is advice displayed on the terminal.

[0831] Step 4: Provide feedback

[0832] The user fills in the input form with feedback about the advice provided and clicks the submit button to send it to the server. For example, the user may indicate their preference for "taking more risks." The input is the feedback entered by the user, and the output is the feedback sent to the server.

[0833] (Application example 2)

[0834] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0835] Conventional asset formation support systems provide advice based solely on the analysis of asset data and market data entered by users. However, because they do not take into account the user's emotional state, they may suggest high-risk investments even when the user is feeling stressed or anxious, which makes it difficult to provide optimal asset formation for the user.

[0836] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0837] In this invention, the server includes means for collecting asset data from a user, means for collecting daily market data, means for analyzing the asset data and market data to generate asset formation advice, means for providing the advice to the user, means for analyzing user emotion data, and means for adjusting the advice based on the emotion data, thereby making it possible to provide optimal asset formation advice that takes into account the user's emotional state.

[0838] "Asset data" refers to financial information such as the user's income, expenses, savings amount, and target savings amount.

[0839] "Market data" refers to information related to financial markets, such as the latest exchange rates, stock prices, and economic indicators.

[0840] "Means for generating advice" refers to a technology that creates guidelines and suggestions for asset formation that are provided to users based on the collected and analyzed data.

[0841] The "means for providing advice" refers to a technology for transmitting the generated advice to the user's terminal and displaying it in a visually easy-to-understand format.

[0842] "Emotion data" refers to information that indicates the user's psychological state, determined from the user's keystroke speed, mouse click frequency, voice emotion analysis, face recognition, and the like.

[0843] "Means for adjusting advice based on emotional data" refers to technology that reflects the user's emotional state and customizes appropriate asset formation advice in a way that reduces risk, etc.

[0844] "Data of other users of the same age and area" refers to asset data of other users collected based on the user's age and area of ​​residence.

[0845] "Statistical analysis means" refers to techniques that use collected data to statistically analyze, compare, and predict.

[0846] As an embodiment of the present invention, a server, a terminal, and an emotion engine work in conjunction to form an asset formation support system. Specific processing and operations of each component will be described in detail below.

[0847] Server Processing

[0848] The server plays a key role in collecting and analyzing asset data, market data, and user sentiment data sent by users, and generating asset formation advice. The specific processes performed by the server are as follows:

[0849] 1. Market Data Collection:

[0850] The server accesses the financial API every morning at 7:00 to obtain the latest exchange rates, stock prices, and economic indicators. This data is stored in temporary storage and used for analysis. The specific software used is the Google Cloud API.

[0851] 2. Data analysis and model updating:

[0852] The server analyzes the collected market data using statistical analysis and machine learning algorithms to predict market trends. This analysis is performed using machine learning platforms such as TensorFlow. The analysis results are stored in a database.

[0853] 3. Collection and Analysis of Personal Data:

[0854] The server receives asset data (income, expenses, savings amount, savings target amount, etc.) sent by the user via API and stores it in a database.The asset data analysis module then analyzes the user data to determine income and expenditure balance and savings patterns.

[0855] 4. Emotional data collection and analysis:

[0856] The server uses an emotion engine to determine the user's emotional state based on their keystroke speed, mouse click frequency, voice emotion analysis, and facial recognition data. This analysis is performed using OpenCV and TensorFlow.

[0857] 5. Advice Generation:

[0858] Based on the analysis results, the server generates specific asset formation advice to help the user achieve their savings target. Based on the emotion data, the server provides appropriate advice that reflects the user's emotional state.

[0859] 6. Sending the results:

[0860] The server sends the generated advice to the user's device. The advice is packaged in JSON format or similar and provided to the user in real time.

[0861] Terminal handling

[0862] The terminal is responsible for inputting asset data by the user and displaying asset formation advice sent from the server. It also collects emotional data.

[0863] 1. Data input from the user:

[0864] The terminal displays a form for the user to input data such as income, expenses, current savings, target savings, etc. The data entered by the user is sent to the server.

[0865] 2. Collecting Emotional Data:

[0866] The device analyzes the user's typing speed, mouse click frequency, and even emotion using facial recognition. This data is sent to a server and used for emotion analysis.

[0867] 3. Data reception and display:

[0868] The device receives the analysis results and advice sent from the server and displays them to the user in a visually easy-to-understand format such as graphs and charts. A concrete example of this is the application display on a smartphone or smart glasses.

[0869] User Action

[0870] The user uses a terminal to input data into the system and check the advice sent from the server. The specific steps are as follows:

[0871] 1. Data Entry:

[0872] The user enters their income, expenses, current savings amount, and target savings amount into the form on the terminal and clicks the submit button.

[0873] 2. Reflecting emotions:

[0874] The user's interactions (such as keystroke speed and mouse click frequency) are analyzed by the emotion engine, and the user's emotional state is reflected in the system.

[0875] 3. Check the advice:

[0876] The user checks the analysis results and advice displayed on the device and receives specific asset formation guidelines.

[0877] Below are some examples of prompt sentences.

[0878] Market Data Collection:

[0879] Get the latest stock prices, exchange rates, and economic indicators data via Google Cloud API and store it in Firebase

[0880] Sentiment Data Analysis:

[0881] Analyzing keystroke speed and mouse click frequency with TensorFlow to estimate the user's emotional state

[0882] This allows users to find the optimal asset formation policy that takes into account their emotional state.

[0883] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0884] Step 1: Server

[0885] The server accesses the financial API every morning at 7:00 to collect the latest market data, such as exchange rates, stock prices, and economic indicators. The specific software used is Google Cloud API. The collected market data is stored in temporary storage. The input is market data obtained from the financial API, and the output is the market data stored in temporary storage.

[0886] Step 2: Server

[0887] The server analyzes the market data stored in temporary storage using statistical analysis and machine learning algorithms. TensorFlow is used for this analysis. As a result of the analysis, a predictive model is updated and stored in the database. The input is the market data stored in temporary storage, and the output is the updated predictive model.

[0888] Step 3: Users

[0889] The user uses a device to input their income, expenses, current savings amount, and target savings amount. The data entered by the user through a smartphone or smart glasses is sent from the device to the server. The input is the asset data entered by the user into the Android / iOS application, and the output is the asset data sent to the server.

[0890] Step 4: Server

[0891] The server receives the asset data sent by the user and stores it in a database.Then, it uses the asset data analysis module to analyze the user's income and expenditure balance and savings pattern.The input is the user's asset data stored on the server, and the output is the analysis result, which is the income and expenditure balance and savings pattern.

[0892] Step 5: Terminal

[0893] The device collects emotional data using the user's keystroke speed, mouse click frequency, and even facial recognition. The emotional data is collected in real time and sent from the device to a server. Specific technologies used include OpenCV and TensorFlow. The input is the user's interaction data, and the output is the emotional data sent to the server.

[0894] Step 6: Server

[0895] The server uses an emotion engine to analyze the transmitted emotion data. As a result of the analysis, the server determines the user's emotional state and stores it in a database. The input is the emotion data transmitted from the device, and the output is the analyzed emotional state.

[0896] Step 7: Server

[0897] The server generates asset formation advice based on the user's asset data and emotional data. It makes investment suggestions with appropriate risk levels, taking into account the user's emotional state. For example, it suggests low-risk products to users with high anxiety. The input is the analyzed asset data and emotional data, and the output is the generated asset formation advice.

[0898] Step 8: Server

[0899] The server sends the generated advice to the user's device. The advice is packaged in JSON format or similar and converted into a format that is easy to understand visually on the device. The input is the generated asset formation advice, and the output is the advice sent to the user's device.

[0900] Step 9: Terminal

[0901] The device receives the advice sent from the server and displays it visually to the user using graphs and charts. Specific examples include displays on smartphones and smart glasses. The input is the advice sent from the server, and the output is advice in a visually easy-to-understand format.

[0902] Through the above processing steps, the user can find the optimal asset formation policy that takes into account his or her emotional state.

[0903] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0904] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0905] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0906] [Third embodiment]

[0907] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0908] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0909] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0910] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0911] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0912] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0913] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0914] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0915] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0916] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0917] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0918] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0919] In one embodiment of the present invention, a system for supporting asset formation is configured by users, servers, and terminals working together. The processing and specific operations of each component will be explained in natural language below.

[0920] Server Processing

[0921] The server is responsible for the central data processing and analysis of the system.

[0922] 1. Market data collection

[0923] The server periodically accesses the financial API to obtain the latest exchange rates, stock prices, and economic indicators. The collected data is temporarily stored in storage and used for subsequent analysis.

[0924] 2. Data analysis and model updating

[0925] The server analyzes the acquired market data and updates the model for predicting market trends using statistical methods and machine learning models. The results of this analysis are stored in a database and used to generate advice for users.

[0926] 3. Import of personal data

[0927] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user and stores it in a database.

[0928] 4. Analysis of personal data

[0929] The server analyzes the user's income and expenditure balance and savings patterns based on the saved asset data, and compares them with the data of other users of the same age and region.

[0930] 5. Advice Generation

[0931] Based on the analysis results, the server generates specific asset formation advice for the user to achieve their savings target. The advice generated is customized to the user's individual situation.

[0932] 6. Submitting the results

[0933] The server transmits the generated advice to the user's terminal.

[0934] Terminal handling

[0935] The terminal provides the interface with the user and is responsible for inputting data and displaying results.

[0936] 1. Data input from the user

[0937] The terminal provides an interface for the user to input data such as income, expenses, current savings, target savings, etc. The input data is sent to the server.

[0938] 2. Data reception and display

[0939] The device receives the analysis results and advice sent from the server and displays them to the user in an easy-to-read format, such as graphs or charts, which are visually easy to understand.

[0940] User Action

[0941] The user uses a terminal to input data into the system and checks the advice sent from the server.

[0942] 1. Data Entry

[0943] The user inputs his / her income, expenses, current savings amount, and target savings amount through the terminal interface, and sends the data to the server by clicking the send button.

[0944] 2. Check the advice

[0945] Users can check the analysis results and advice displayed on their device and use them to plan their asset-building activities, such as how much to save each month and which investment products to purchase.

[0946] 3. Providing Feedback

[0947] Users can input feedback about the advice provided and submit their wishes and changes to the system. For example, by inputting a wish such as "I want to take more risks," new advice will be provided.

[0948] Specific examples

[0949] Every morning, the server retrieves and analyzes market data such as exchange rates and stock indexes from a specified financial API. The user inputs data such as a monthly income of 300,000 yen, a savings goal of 5 million yen, and current savings of 1 million yen into a smartphone app. The server analyzes this data and generates a result by comparing it with the average savings of people in their 30s. The generated result and advice are sent to the user's device, and the user receives specific guidelines such as saving 30,000 yen per month and purchasing low-risk investment products. The user can provide feedback on the advice and have it reflected in the system, resulting in a more accurate asset formation plan.

[0950] In this way, the present invention can provide specific and reliable advice to help users build assets efficiently.

[0951] The processing flow will be explained below.

[0952] Server Processing Steps

[0953] Step 1:

[0954] The server runs a scheduled job every morning at 7:00 am, accessing the API of economic data providers to obtain market data such as exchange rates, stock indexes, and economic indicators, and stores it in temporary storage.

[0955] Step 2:

[0956] The server analyzes the stored market data using a data analysis module, which uses statistical analysis and machine learning algorithms to predict market trends and stores the results in a database.

[0957] Step 3:

[0958] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user via API and stores it in a database.

[0959] Step 4:

[0960] The server retrieves the user data stored in the database and analyzes it using the asset data analysis module. The user's income and expenditure balance and savings patterns are analyzed and compared with the data of other users of the same age and region.

[0961] Step 5:

[0962] Based on the analysis results, the server generates specific asset formation advice to help users achieve their savings goals. The advice is customized based on each user's situation.

[0963] Step 6:

[0964] The server packages the generated advice in JSON format and sends it to the user's device.

[0965] Terminal processing steps

[0966] Step 1:

[0967] The terminal presents the user with a data entry form, where the user enters information such as income, expenses, current savings, and savings goals.

[0968] Step 2:

[0969] The device receives the user's input data and generates an API request to send it to the server. The API request is encrypted and sent.

[0970] Step 3:

[0971] The device receives the analysis results and advice sent from the server, which are also received as API responses.

[0972] Step 4:

[0973] The device analyzes the data it receives and displays it in a format that is easy for the user to understand, such as a graph, chart, or list.

[0974] User processing steps

[0975] Step 1:

[0976] The user enters income, expenses, current savings amount, and target savings amount into the data input form on the terminal and clicks the submit button.

[0977] Step 2:

[0978] The user checks the analysis results and advice displayed on the device, such as how much they should save each month and which investment products they should choose.

[0979] Step 3:

[0980] The user inputs feedback about the advice provided, such as "I want to take more risks" or "I want to know about safer options," and sends this feedback from the device to the server.

[0981] Through these steps, the system can provide users with personalized asset formation advice and support optimal asset formation.

[0982] Example 1

[0983] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0984] Conventional asset formation support systems have struggled to provide specific and reliable advice tailored to each user's individual circumstances. Furthermore, there was a lack of systems that could accurately reflect daily fluctuating market data and allow users to obtain timely information. Furthermore, it was difficult to generate personalized plans based on a user's income, expenses, and savings, and comparisons with a large amount of user data were not conducted.

[0985] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0986] In this invention, the server includes means for collecting asset data from users, means for collecting daily market data, means for analyzing the asset data and market data to generate asset formation advice, means for providing the advice to users, means for updating a machine learning model using the market data and asset data, a terminal interface for inputting data on the user's income, expenses, savings, and target savings, and means for confirming the analysis results and advice displayed on the terminal. This allows users to receive specific and reliable advice tailored to their individual circumstances. Furthermore, by reflecting market data that fluctuates daily in a timely manner, asset formation based on the latest information is possible. Furthermore, by comparing user data with data on other users of the same age and region, more accurate analysis and advice can be provided.

[0987] The "means for collecting asset data from a user" refers to a means for inputting, receiving, and storing asset data such as a user's income, expenses, savings amount, and target savings amount.

[0988] "Means of collecting daily market data" refers to the use of financial APIs to regularly obtain and store market data such as foreign exchange information, stock prices, and economic indicators.

[0989] The "means for analyzing the asset data and market data to generate asset formation advice" refers to a means for analyzing the acquired asset data and market data and using statistical techniques and machine learning models to generate specific asset formation advice for the user.

[0990] The "means for providing the advice to the user" refers to means for transmitting information to the user's terminal through an interface for providing the generated advice to the user.

[0991] "Means for updating machine learning models using market data and asset data" refers to means for updating predictive models using machine learning algorithms based on regularly collected market data and asset data from users.

[0992] A "terminal interface for inputting user's income, expenditure, savings, and savings goal data" is a terminal that provides a graphical interface for a user to input personal data such as income, expenditure, current savings, and savings goal.

[0993] "Means for checking the analysis results and advice displayed on the terminal" refers to a terminal function for receiving the analysis results and advice sent from the server and visually displaying them.

[0994] This invention provides a system that supports asset formation through cooperation between users, servers, and terminals. The specific configuration and operation of this system will be described below.

[0995] Server Roles

[0996] The server is responsible for the central data processing and analysis of this system and uses the following hardware and software:

[0997] Hardware: High-performance servers, SSD storage, network interfaces

[0998] Software: Python, TensorFlow, Scikit-learn, Pandas, Jupyter Notebook, MongoDB, RESTful API

[0999] The server collects daily market data using financial APIs. For example, it periodically accesses APIs from Alpha Vantage and Yahoo Finance to obtain the latest exchange rates, stock prices, and economic indicators. This data is temporarily stored in a database such as MongoDB.

[1000] The server then analyzes the collected market data using Python and Jupyter Notebook, preprocessing the data with the Pandas library, and updating machine learning models using TensorFlow and Scikit-learn. The analyzed data is then used to generate recommendations for users.

[1001] Furthermore, the server receives asset data (income, expenses, savings amount, savings target, etc.) sent by the user and stores it in a database. Based on the stored data, the server analyzes the user's income and expenditure balance and savings pattern and performs statistical comparisons. Based on the results, it generates specific asset formation advice for the user and sends it to the user's device via a RESTful API.

[1002] Device Role

[1003] The terminal provides the interface with the user, allowing data entry and displaying results. The terminal uses the following hardware and software:

[1004] Hardware: Smartphones, tablets, computers

[1005] Software: HTML, CSS, JavaScript, AJAX, Chart.js, D3.js

[1006] The terminal provides an interface for users to input data such as income, expenses, current savings, and target savings. These data are retrieved by JavaScript through an HTML form and sent to the server in JSON format using AJAX.

[1007] The device also receives analysis results and advice sent from the server and visually displays them to the user using Chart.js and D3.js, using graphs and charts to help users intuitively understand the information.

[1008] User Roles

[1009] The user uses a terminal interface to input asset data into the system and review the advice provided by the server.

[1010] Users enter their income, expenses, current savings amount, and target savings amount into an HTML form on their device, and then click the submit button to send the data to the server. The analysis results and advice sent from the server are displayed on the device. This allows users to obtain specific asset formation guidelines and implement an asset formation plan that suits their own situation.

[1011] Furthermore, users can provide feedback on the advice provided. For example, they can enter their wishes or changes, such as "I want to take more risks" or "I want more detailed advice," and click the submit button. The server receives this feedback and reflects it in the next advice generation.

[1012] Specific examples

[1013] Every morning, the server retrieves market data such as exchange rates and stock indexes from a specified financial API (e.g., Alpha Vantage) and analyzes it. The user enters data into the smartphone app, such as monthly income of 300,000 yen, savings goal of 5 million yen, and current savings of 1 million yen. This data is sent to the server, which analyzes and compares it to generate specific advice. For example, this advice might include "save 30,000 yen per month and purchase low-risk investment products."

[1014] Examples of prompt statements

[1015] Below is an example of a prompt sentence to input to the generative AI model.

[1016] I'm in my 30s, earn 300,000 yen a month, have a savings goal of 5 million yen, and currently have 1 million yen saved. Please give me some advice on how to build up assets with low risk.

[1017] In this way, the present invention is a system that provides specific and reliable advice to help users build up their assets efficiently.

[1018] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1019] Step 1: Gather market data

[1020] Every morning, the server periodically accesses a financial API (e.g., Alpha Vantage, Yahoo Finance) to retrieve exchange rate information, stock prices, and economic indicators. The input is the API key and request parameters, and the output is market data in JSON format. The server temporarily stores this JSON data in MongoDB. Specifically, it sends an API request using a Python library, receives the response, and stores it in the database.

[1021] Step 2: Analyze market data and update the model

[1022] The server analyzes market data using Python scripts and Jupyter Notebook. The input is market data stored in MongoDB, and the output is the analysis results and an updated machine learning model. Specifically, the data is read and preprocessed using the Pandas library, and the model is trained and updated using TensorFlow and Scikit-learn. This analysis data is stored in a database.

[1023] Step 3: Import user data

[1024] The user enters asset data such as income, expenses, savings amount, and savings goal through an HTML form on the device and clicks the submit button. The input is the user's asset data, and the output is JSON format data stored on the server. The device uses JavaScript and AJAX to send the data to the server, which then receives the data and stores it in a database.

[1025] Step 4: Analyzing personal data

[1026] The server analyzes income / expense balances and savings patterns based on the saved user asset data. The input is asset data obtained from the user database, and the output is the results of statistical analysis. Specifically, data is obtained using SQL queries, and statistical analysis such as standard deviation and average values ​​is performed using Python scripts. The results are then compared with data from users of the same age and region.

[1027] Step 5: Generating Advice

[1028] The server generates asset formation advice for the user based on the analysis results. The input is the analysis results of personal data and market data, and the output is a customized advice message. Specifically, it uses machine learning models and natural language generation models (e.g., GPT-3) to generate specific guidelines in text that are tailored to the user's situation. The results are stored in a database.

[1029] Step 6: Send and view results

[1030] The server sends the generated advice to the user's device. The input is the generated advice, and the output is the advice message displayed on the user's device. Specifically, the advice is sent in JSON format using a RESTful API, and is received on the device using AJAX. The received advice is displayed visually using Chart.js or D3.js. For example, a text message such as "Save 30,000 yen each month and purchase low-risk investment products" is displayed.

[1031] Through this series of processes, users can receive specific and reliable advice on how to build assets efficiently.

[1032] (Application example 1)

[1033] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1034] Conventional asset formation support systems provide advice based on basic asset data and market data from users, but are unable to reflect feedback on users' daily purchasing behavior or actual spending. As a result, it is difficult to provide real-time advice adapted to individual situations, and users are unable to obtain sufficient information to formulate specific asset formation plans.

[1035] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1036] In this invention, the server includes means for collecting asset data from users, means for collecting daily market data, means for analyzing the asset data and market data to generate asset formation advice, means for providing the advice to users, means for collecting user purchase history and expenditure data, means for analyzing the purchase history, expenditure data, and market data to generate asset formation advice based on purchasing behavior, means for providing the advice to users in real time, and means for updating the advice based on user feedback, thereby making it possible to provide more specific, personalized, real-time advice to users in asset formation.

[1037] "Means for collecting asset data from users" refers to a function that allows users to input asset data such as their income, expenses, savings amount, and target savings amount, and transmit this data to the server.

[1038] "Means of collecting daily market data" refers to the function of regularly collecting market data such as exchange rates, stock prices, and economic indicators from external sources such as financial APIs.

[1039] "Means for analyzing the asset data and market data to generate asset formation advice" refers to a function that performs analysis based on the collected asset data and market data and generates asset formation advice to be provided to the user.

[1040] The "means for providing the advice to the user" refers to a function for transmitting the generated asset formation advice to the user's terminal and displaying it in a visually easy-to-understand format.

[1041] "Means for collecting user purchase history and expenditure data" refers to a function that automatically collects a user's electronic payment transaction history and daily expenditure data and transmits it to a server for analysis.

[1042] "Means for analyzing the purchase history, expenditure data and market data, and generating asset formation advice based on purchasing behavior" refers to a function that comprehensively analyzes a user's purchase history, expenditure data and market data, and generates specific asset formation advice based on individual purchasing behavior.

[1043] The "means for providing the advice to the user in real time" refers to a function that allows advice based on the analysis results to be immediately provided to the user and feedback to be received in real time.

[1044] "Means for updating advice based on user feedback" refers to the function of collecting feedback information from users and appropriately updating and adjusting the advice content generated based on that information.

[1045] This invention configures a system that supports users' asset formation by linking users, servers, and terminals. The processing and specific operations of each component will be described below.

[1046] Server Processing

[1047] The server is responsible for the system's central data processing and analysis. It analyzes asset data and purchase history data obtained from users, along with the latest market data. Market data is obtained from financial APIs, and includes exchange information, stock prices, economic indicators, and more. Statistical methods and machine learning models are used to predict market trends and purchasing behavior. Based on the results of this analysis, the server generates asset formation advice personalized for the user and sends it to the terminal.

[1048] Terminal handling

[1049] The terminal provides an interface for the user and is responsible for inputting data and displaying the results. The user inputs data such as income, expenses, current savings amount, and savings goal, and daily purchase history and expenditure data are also collected. The input data is sent to the server. The analysis results and advice sent from the server are displayed on the terminal in real time. The data is displayed in a visually easy-to-understand format such as graphs and charts.

[1050] User Action

[1051] Users use their devices to input data into the system and check the advice sent from the server. Based on the advice, users plan specific asset formation actions. For example, they are presented with guidelines on how much to save each month and which investment products to purchase. Users also provide feedback on the advice provided and send their wishes and changes to the system. This allows the server to improve the analysis model based on the feedback and provide more accurate advice.

[1052] Specific examples

[1053] Every morning, the server retrieves market data such as exchange rates and stock indexes from a specified financial API. The user enters data into their smartphone, such as monthly income of 300,000 yen, savings goal of 5 million yen, and current savings of 1 million yen. At the same time, the device automatically collects the user's purchase history and expenditure data. The server analyzes this data and generates results that compare the user's savings with the average savings of people in their 30s. The generated results and advice are sent to the user's device in real time as specific guidelines, such as saving 30,000 yen per month or purchasing low-risk investment products. The user can provide feedback on the advice and have it reflected in the system, resulting in an even more accurate asset formation plan.

[1054] Prompt Sentence Examples

[1055] "Input: My monthly income is ¥200,000, my monthly expenses are ¥150,000, my current savings are ¥300,000, and my goal savings is ¥5 million. How can I achieve this in the next five years?

[1056] Output: I recommend you put away 10,000 yen per month in a low-risk mutual fund. This will increase your chances of reaching your goal.

[1057] As a result, the present invention provides a system that helps users to efficiently build assets by automatically tracking their daily expenses and income and providing financial advice in real time.

[1058] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1059] Step 1:

[1060] The server periodically accesses the financial API to obtain market data (foreign exchange information, stock prices, economic indicators, etc.). The obtained market data is temporarily stored in storage. The input is market data from the financial API, and the output is the temporarily stored market data.

[1061] Step 2:

[1062] The server analyzes the acquired market data and updates a model for predicting market trends using statistical methods and machine learning models (e.g., Linear Regression). The analyzed data is stored in a database and used to generate advice for users. The input is temporarily stored market data, and the output is the updated results of the analytical model.

[1063] Step 3:

[1064] The user uses a terminal to input asset data such as their income, expenses, current savings amount, and target savings amount. In addition, the user's purchase history and daily expenditure data are also automatically collected through the terminal. The input is the asset data and purchase history data entered by the user into the terminal, and the output is the data sent to the server.

[1065] Step 4:

[1066] The server receives asset data and purchase history data sent from the user and stores them in a database. The input is the asset data and purchase history data sent from the terminal, and the output is the stored data.

[1067] Step 5:

[1068] The server analyzes the saved user asset data and purchase history data in combination with market data. This analysis generates specific advice for the user regarding asset formation. The inputs are market data, the user's asset data, and purchase history data, and the output is the generated advice.

[1069] Step 6:

[1070] The server sends the generated asset formation advice to the user's terminal. The advice is specific and tailored to the user's purchasing behavior and asset data. The input is the generated advice, and the output is the advice sent to the user's terminal.

[1071] Step 7:

[1072] The user checks the analysis results and advice displayed on the terminal and plans asset formation actions based on them. The user inputs feedback about the advice provided and sends it to the system. The input is feedback about the analysis results and advice, and the output is the feedback sent to the server.

[1073] Step 8:

[1074] The server receives feedback from users and updates the analytical model and advice generation logic based on the feedback. The input is the user feedback, and the output is the updated analytical model and advice generation logic.

[1075] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1076] As an embodiment of the present invention, a user, a server, a terminal, and an emotion engine work in cooperation to form an asset formation support system. Specific processing and operations of each component will be described in detail below.

[1077] Server Processing

[1078] The server is responsible for collecting asset and market data, analyzing it, generating advice, and analyzing user sentiment data.

[1079] 1. Market data collection

[1080] The server accesses the financial API at 7:00 every morning to obtain the latest exchange rate information, stock prices, and economic indicators, and stores them in temporary storage.

[1081] 2. Data analysis and model updating

[1082] The server analyzes the collected market data using statistical analysis and machine learning algorithms to predict market trends, and the results are stored in a database.

[1083] 3. Import of personal data

[1084] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user via API and stores it in a database.

[1085] 4. Analysis of personal data

[1086] The server retrieves user data stored in the database and analyzes it using the asset data analysis module. The server analyzes income and expenditure balances and savings patterns, and compares them with data from other users of the same age and region.

[1087] 5. Advice Generation

[1088] Based on the analysis results, the server generates specific asset formation advice to help users achieve their savings goals. The advice generated is customized to fit each user's situation.

[1089] 6. Emotional Data Collection and Analysis

[1090] The server uses an emotion engine to determine the user's emotional state from input data and interaction data (e.g., the user's keystroke speed, mouse click frequency, etc.) The emotion data is stored in a database as part of the analysis.

[1091] 7. Adjusting advice based on emotions

[1092] The server adjusts the asset formation advice based on the user's emotional state. For example, if the user is feeling stressed, the server generates more appropriate advice, such as suggesting low-risk investment methods.

[1093] 8. Submitting the results

[1094] The server sends the generated advice to the user's device, packaged in JSON format or similar.

[1095] Terminal handling

[1096] The terminal provides the interface with the user and is responsible for inputting data and displaying results.

[1097] 1. Data input from the user

[1098] The terminal displays a form for the user to input data such as income, expenses, current savings, target savings, etc. The data input by the user is sent to the server.

[1099] 2. Collecting Emotional Data

[1100] The device also analyzes the user's keystroke speed, mouse click frequency, and emotion using facial recognition, and sends this data to the server.

[1101] 3. Data reception and display

[1102] The terminal receives the analysis results and advice sent from the server and displays them to the user in a visually easy-to-understand format such as graphs and charts.

[1103] User Action

[1104] The user uses a terminal to input data into the system and checks the advice sent from the server.

[1105] 1. Data Entry

[1106] The user enters their income, expenses, current savings amount, and target savings amount into a form on the terminal and clicks the send button to send the data to the server.

[1107] 2. Reflecting emotions

[1108] The user's interactions (such as keystroke speed and mouse click frequency) are analyzed by the emotion engine, and the user's emotional state is reflected in the system.

[1109] 3. Check the advice

[1110] Users can view the analysis results and advice displayed on their device, including specific guidelines on how much they should save each month and which investment products they should choose.

[1111] 4. Providing Feedback

[1112] The user inputs feedback about the advice provided, for example, a preference such as "I want to take more risks," and sends this feedback to the server from the terminal.

[1113] Specific examples

[1114] Every morning at 7am, the server retrieves and analyzes market data such as exchange rates and stock indexes from a financial API. The user inputs data such as a monthly income of 300,000 yen, a savings goal of 5 million yen, and a current savings of 1 million yen into the smartphone app. The server analyzes this data and generates a result by comparing it with the average savings of people in their 30s. The generated result and advice are sent to the user's device, and the user receives specific guidelines such as saving 30,000 yen per month and purchasing low-risk investment products.

[1115] Furthermore, if the user's input speed is slow and they are feeling anxious, the emotion engine will provide advice based on the user's emotional state, such as suggesting low-risk investment methods. This allows users to find the optimal asset formation policy that takes their emotional state into account.

[1116] The processing flow will be explained below.

[1117] Server Processing Steps

[1118] Step 1:

[1119] The server accesses the financial API at 7am every morning to obtain the latest exchange rates, stock prices, and economic indicators, and stores them in temporary storage.

[1120] Step 2:

[1121] The server analyzes the stored market data using a data analysis module, and uses statistical analysis and machine learning algorithms to predict market trends, and stores the results in a database.

[1122] Step 3:

[1123] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user via API and stores it in a database.

[1124] Step 4:

[1125] The server retrieves user data stored in the database and analyzes it using the asset data analysis module. The analysis includes income and expenditure balances and savings patterns, and compares them with data from other users of the same age and region.

[1126] Step 5:

[1127] Based on the analysis results, the server generates specific asset formation advice to help users achieve their savings goals. The advice is customized to each user's situation.

[1128] Step 6:

[1129] The server uses an emotion engine to determine the user's emotional state from their input data and interaction data (e.g., keystroke speed, mouse click frequency, etc.), and the emotional data is stored in a database.

[1130] Step 7:

[1131] The server adjusts asset formation advice based on the user's emotional state. For example, if the user is feeling stressed, the server will suggest low-risk investment methods.

[1132] Step 8:

[1133] The server packages the generated customized advice in JSON format and sends it to the user's device.

[1134] Terminal processing steps

[1135] Step 1:

[1136] The terminal presents the user with a data entry form, where the user enters information such as income, expenses, current savings, and savings goals.

[1137] Step 2:

[1138] The device receives the user's input data and generates an API request to send it to the server. The API request is encrypted and sent.

[1139] Step 3:

[1140] The device collects user interactions (such as keystroke speed, mouse click frequency, and facial recognition data) and sends them to a server.

[1141] Step 4:

[1142] The device receives the analysis results and advice sent from the server and displays them in a user-friendly format (graphs, charts, lists, etc.).

[1143] User processing steps

[1144] Step 1:

[1145] The user enters their income, expenses, current savings amount, target savings amount, etc. into the data input form on the terminal and clicks the submit button.

[1146] Step 2:

[1147] The user checks the analysis results and advice displayed on the device, receiving specific guidance on how much to save each month, which investment products to choose, and so on.

[1148] Step 3:

[1149] The user inputs feedback about the advice provided. For example, the user sends a request such as "I want to take more risks" to the server via the terminal.

[1150] Specific examples

[1151] Server Processing

[1152] Step 1:

[1153] The server retrieves "exchange rates and stock indexes from the API" every morning at 7:00.

[1154] Step 2:

[1155] The server "analyzes the acquired market data using statistical analysis and machine learning algorithms" and "stores the results in a database."

[1156] Step 3:

[1157] The server receives the data sent by the user, including a monthly income of 300,000 yen, a savings goal of 5 million yen, and a current savings amount of 1 million yen, and stores this data in the database.

[1158] Step 4:

[1159] The server performs the process of "analyzing user data stored in a database and comparing it with the average savings amount of people in their 30s."

[1160] Step 5:

[1161] The server "generates asset formation advice based on each user's situation" and "suggests monthly savings of 30,000 yen and low-risk investment products."

[1162] Step 6:

[1163] The server "uses an emotion engine to determine the user's emotional state" and "saves the emotional data in a database."

[1164] Step 7:

[1165] The server adjusts advice based on the user's emotional state, such as suggesting low-risk investment methods if the user is feeling stressed.

[1166] Step 8:

[1167] The server "packages the generated advice in JSON format" and "sends it to the user's device."

[1168] Terminal handling

[1169] Step 1:

[1170] The device "presents the user with a data entry form for income, expenses, savings, and savings goals."

[1171] Step 2:

[1172] The device "generates an API request to send the input data to the server" and "encrypts and sends it."

[1173] Step 3:

[1174] The device "collects user interaction data (such as keystroke speed and mouse click frequency)" and "sends it to the server."

[1175] Step 4:

[1176] The device "displays the analysis results and advice received from the server in graphs and charts."

[1177] User Action

[1178] Step 1:

[1179] The user "enters their income, expenses, current savings amount, and target savings amount, and clicks the submit button."

[1180] Step 2:

[1181] The user "checks the displayed analysis results and advice (saving 30,000 yen per month, low-risk investment products, etc.)."

[1182] Step 3:

[1183] Users "enter feedback about the advice provided" and "submit preferences such as 'I'd like to take more risks.'"

[1184] Through these steps, the system provides users with personalized asset formation advice, and by taking the user's emotional state into consideration, it achieves more accurate support.

[1185] Example 2

[1186] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1187] Conventional asset formation support systems generally provide uniform advice based on data input by users, making it difficult to provide advice that takes into account individual emotions and unique situations. In addition, it is difficult for users to accurately grasp market trends and their own asset status, and it takes a lot of time and effort to find the optimal asset formation strategy.

[1188] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1189] In this invention, the server includes means for receiving asset data from a user, means for periodically recording market data, means for analyzing the asset data and market data to generate asset formation advice, means for notifying the user of the advice, means for collecting user interaction data and analyzing emotion data, and means for adjusting the advice based on the emotion data, thereby enabling the provision of customized advice that takes into account the individual circumstances and emotional state of the user.

[1190] "Asset data" refers to information about assets owned by a user, and specifically includes income, expenses, current savings, target savings, and the like.

[1191] "Market data" is a general term for information collected from financial markets, and includes data such as exchange rates, stock prices, and economic indicators.

[1192] "Means for generating advice" refers to machine learning algorithms and statistical analysis means for analyzing collected asset data and market data and creating appropriate asset formation advice for users.

[1193] The "means for notifying advice" refers to communication means and display means for transmitting the generated advice to the user's terminal and making it available for the user to view.

[1194] "Interaction data" refers to data related to user operations, such as keystroke speed, mouse click frequency, and facial recognition data, when a user operates a device.

[1195] "Emotional data" refers to information about a user's emotional state obtained by analyzing interaction data and facial recognition data.

[1196] "Means for adjusting advice based on emotional data" refers to algorithms and analytical means for taking into account the user's emotional data and providing optimal asset formation advice.

[1197] As an embodiment of the present invention, a user, a server, a terminal, and an emotion engine work in cooperation to form an asset formation support system. Specific processing and operations of each component will be described in detail below.

[1198] Server Processing

[1199] The server is responsible for collecting asset and market data, analyzing it, generating advice, and analyzing user sentiment data.

[1200] 1. Market data collection

[1201] The server automatically runs a Python script every morning at 7:00, connects to a financial API (e.g., Alpha Vantage) using an API access library (e.g., requests), retrieves the latest exchange rates, stock prices, and economic indicators, and stores them in temporary storage (e.g., Redis, memcached).

[1202] 2. Market data analysis and model updates

[1203] The server preprocesses the collected market data using Python data processing libraries such as Pandas and NumPy, and analyzes it using statistical analysis and machine learning algorithms (e.g., ARIMA model, regression). The analysis results are stored in a database (e.g., MySQL). The machine learning model is also updated regularly.

[1204] 3. Import of personal data

[1205] The server uses a web framework (e.g., Flask, Django) to receive asset data entered by the user via a REST API and store it in a database.

[1206] 4. Analysis of personal data

[1207] The server retrieves the stored user data and performs statistical analysis using Python's analytics module, such as calculating a user's income and expenditure balance and savings patterns using a three-month rolling average and comparing them with data from other users of the same age and region.

[1208] 5. Advice Generation

[1209] Based on the analysis results, the server uses a machine learning model (e.g., random forest) to automatically generate optimal asset formation advice for each user. The advice generated is customized to fit each user's data.

[1210] 6. Emotional Data Collection and Analysis

[1211] The server sends the user's interaction data to an emotion engine (e.g., Microsoft Azure Emotion API) to analyze the user's emotional state. The analysis results are stored in a database.

[1212] 7. Adjusting advice based on emotions

[1213] Based on the results of the emotion analysis, the server readjusts the advice to take into account the user's stress and anxiety.

[1214] 8. Submitting the results

[1215] The server packages the generated advice in JSON format and sends it to the user's device as an HTTP response.

[1216] Terminal handling

[1217] The terminal provides the interface with the user and is responsible for inputting data and displaying results.

[1218] 1. Data input from the user

[1219] The device (e.g. smartphone, PC) uses a front-end framework (e.g. React, Vue.js) to display a form for entering income, expenses, current savings amount, target savings amount, etc. The entered data is sent to the server's API via JavaScript.

[1220] 2. Collecting Emotional Data

[1221] The device uses JavaScript to measure the user's keystroke speed and mouse click frequency, and periodically sends the data to a server in the background. It also uses facial recognition software (e.g., OpenCV) via the camera to perform real-time emotion analysis.

[1222] 3. Data reception and display

[1223] The device receives the advice results sent from the server and displays them to the user in a visually easy-to-understand format (e.g., graphs or charts). A JavaScript library (e.g., Chart.js) is used for display.

[1224] User Action

[1225] The user uses a terminal to input data into the system and checks the advice sent from the server.

[1226] 1. Data Entry

[1227] The user enters their income, expenses, current savings amount, and target savings amount into a form on the terminal, and clicks the submit button to send the data to the server.

[1228] 2. Reflecting emotions

[1229] Data such as the user's keystroke speed and mouse click frequency is analyzed by the emotion engine, allowing the system to understand the user's emotional state.

[1230] 3. Check the advice

[1231] Users can view the analysis results and advice displayed on their device, including specific guidelines on how much they should save each month and which investment products they should choose.

[1232] 4. Providing Feedback

[1233] The user fills in the input form with feedback about the advice provided and clicks the submit button to send it to the server, for example, to indicate a preference such as "I would like to take more risks."

[1234] Specific examples

[1235] Every morning at 7am, the server retrieves market data such as exchange rates and stock indexes from a financial API (e.g., Alpha Vantage) and analyzes the data using NumPy and Pandas. The user enters their monthly income of 300,000 yen, savings goal of 5 million yen, and current savings of 1 million yen into the smartphone app. The front end is implemented in React, and the entered data is sent to the server via JavaScript and REST API. The server saves the received data in a MySQL database and analyzes the asset data using a Python script. Based on the results of this analysis, the user is compared with the average savings of people in their 30s and optimal asset formation advice is generated.

[1236] The emotion engine (e.g., Microsoft Azure Emotion API) analyzes the user's keystroke speed and mouse click frequency, and if it determines that the user is feeling anxious, it suggests low-risk investment methods. The server sends this advice in JSON format to the user's device.

[1237] Example prompt sentence:

[1238] "I'm 30 years old and earn 300,000 yen a month. My current savings goal is 5 million yen, but I've only saved 1 million yen. Please tell me how I can achieve my savings goal in the future."

[1239] To this prompt, the generative AI model responds as follows:

[1240] "We recommend that you review your monthly income and expenditures based on your current income and expenditure data and continue to save at least 30,000 yen per month. Also, if you are feeling anxious, consider choosing low-risk investment products and ways to safely increase your assets."

[1241] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1242] Server Processing

[1243] Step 1: Gather market data

[1244] The server automatically runs a Python script every morning at 7:00, connecting to a financial API (e.g., Alpha Vantage) using an API access library (e.g., requests) to retrieve the latest exchange rates, stock prices, and economic indicators. This data is stored in temporary storage (e.g., Redis, memcached). The input is market data retrieved from the API, and the output is the raw market data stored in temporary storage.

[1245] Step 2: Analyze market data and update the model

[1246] The server retrieves market data from temporary storage and preprocesses it using data processing libraries such as Pandas and NumPy. It then analyzes the market data using statistical analysis and machine learning algorithms (e.g., ARIMA model, regression) to predict market trends. It stores the analysis results in a database (e.g., MySQL). The input is the preprocessed market data, and the output is the analysis results stored in the database.

[1247] Step 3: Importing personal data

[1248] The server receives asset data (income, expenses, current savings, target savings, etc.) entered by the user via REST API and stores it in a database. The input is asset data sent by the user from the device, and the output is user data stored in the database.

[1249] Step 4: Analyzing personal data

[1250] The server retrieves user data stored in the database and performs statistical analysis using a Python analysis module. It calculates income / expense balance and savings patterns and compares them with data from other users of the same age and region. The results of this analysis are then stored back in the database. The input is the user's asset data, and the output is the analysis results.

[1251] Step 5: Advice Generation

[1252] The server generates optimal asset formation advice for the user using a machine learning model (e.g., random forest) based on user data and market data. The generated advice is stored in a database. The input is the analyzed market data and user data, and the output is the generated advice.

[1253] Step 6: Collect and analyze emotion data

[1254] The server sends the user's interaction data (keystroke speed, mouse click frequency, etc.) to the emotion engine (e.g., Microsoft Azure Emotion API) to analyze the user's emotional state. The analysis results are also stored in a database. The input is the user's interaction data, and the output is the analyzed emotional data.

[1255] Step 7: Adjust your advice based on emotions

[1256] The server readjusts the advice based on the results of the sentiment analysis. If the user is feeling stressed, it generates customized advice, such as suggesting low-risk investment methods. The adjusted advice is stored in a database. The input is the sentiment analysis result and existing advice, and the output is the adjusted advice.

[1257] Step 8: Sending the results

[1258] The server packages the generated and adjusted advice in JSON format and sends it to the user's device as an HTTP response. The input is the adjusted advice, and the output is the advice sent to the user's device.

[1259] Terminal handling

[1260] Step 1: Data input from the user

[1261] The device (e.g. smartphone, PC) uses a front-end framework (e.g. React, Vue.js) to display a form for inputting income, expenses, current savings, target savings, etc. When the user enters the data and clicks the submit button, the data is sent to the server's API via JavaScript. The input is the asset data entered by the user, and the output is the data sent to the server.

[1262] Step 2: Collecting emotion data

[1263] The device uses JavaScript to measure keystroke speed and mouse click frequency, and periodically sends the data to the server. It also uses face recognition software (e.g., OpenCV) via the camera to perform real-time emotion analysis, and sends the data to the server. The input is the user's interaction data, and the output is the emotion data sent to the server.

[1264] Step 3: Receiving and displaying data

[1265] The terminal receives the advice results sent from the server and displays them to the user in a visually easy-to-understand format such as graphs or charts using a JavaScript library (e.g., Chart.js). The input is the advice data received from the server, and the output is the advice displayed on the terminal.

[1266] User Action

[1267] Step 1: Data entry

[1268] The user enters their income, expenses, current savings amount, and target savings amount into the form on their device and clicks the submit button. This sends the data to the server. The input is the asset data entered by the user, and the output is the data sent to the server.

[1269] Step 2: Reflecting your emotions

[1270] Data such as the user's keystroke speed and mouse click frequency is sent to the server in real time and analyzed by the emotion engine. The input is the user's interaction data, and the output is emotion data stored on the server.

[1271] Step 3: Review the advice

[1272] The user checks the analysis results and advice displayed on the terminal. For example, specific guidelines are provided, such as how much to save each month or which investment product to choose. The input is advice data from the server, and the output is advice displayed on the terminal.

[1273] Step 4: Provide feedback

[1274] The user fills in the input form with feedback about the advice provided and clicks the submit button to send it to the server. For example, the user may indicate their preference for "taking more risks." The input is the feedback entered by the user, and the output is the feedback sent to the server.

[1275] (Application example 2)

[1276] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1277] Conventional asset formation support systems provide advice based solely on the analysis of asset data and market data entered by users. However, because they do not take into account the user's emotional state, they may suggest high-risk investments even when the user is feeling stressed or anxious, which makes it difficult to provide optimal asset formation for the user.

[1278] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1279] In this invention, the server includes means for collecting asset data from a user, means for collecting daily market data, means for analyzing the asset data and market data to generate asset formation advice, means for providing the advice to the user, means for analyzing user emotion data, and means for adjusting the advice based on the emotion data, thereby making it possible to provide optimal asset formation advice that takes into account the user's emotional state.

[1280] "Asset data" refers to financial information such as the user's income, expenses, savings amount, and target savings amount.

[1281] "Market data" refers to information related to financial markets, such as the latest exchange rates, stock prices, and economic indicators.

[1282] "Means for generating advice" refers to a technology that creates guidelines and suggestions for asset formation that are provided to users based on the collected and analyzed data.

[1283] The "means for providing advice" refers to a technology for transmitting the generated advice to the user's terminal and displaying it in a visually easy-to-understand format.

[1284] "Emotion data" refers to information that indicates the user's psychological state, determined from the user's keystroke speed, mouse click frequency, voice emotion analysis, face recognition, and the like.

[1285] "Means for adjusting advice based on emotional data" refers to technology that reflects the user's emotional state and customizes appropriate asset formation advice in a way that reduces risk, etc.

[1286] "Data of other users of the same age and area" refers to asset data of other users collected based on the user's age and area of ​​residence.

[1287] "Statistical analysis means" refers to techniques that use collected data to statistically analyze, compare, and predict.

[1288] As an embodiment of the present invention, a server, a terminal, and an emotion engine work in conjunction to form an asset formation support system. Specific processing and operations of each component will be described in detail below.

[1289] Server Processing

[1290] The server plays a key role in collecting and analyzing asset data, market data, and user sentiment data sent by users, and generating asset formation advice. The specific processes performed by the server are as follows:

[1291] 1. Market Data Collection:

[1292] The server accesses the financial API every morning at 7:00 to obtain the latest exchange rates, stock prices, and economic indicators. This data is stored in temporary storage and used for analysis. The specific software used is the Google Cloud API.

[1293] 2. Data analysis and model updating:

[1294] The server analyzes the collected market data using statistical analysis and machine learning algorithms to predict market trends. This analysis is performed using machine learning platforms such as TensorFlow. The analysis results are stored in a database.

[1295] 3. Collection and Analysis of Personal Data:

[1296] The server receives asset data (income, expenses, savings amount, savings target amount, etc.) sent by the user via API and stores it in a database.The asset data analysis module then analyzes the user data to determine income and expenditure balance and savings patterns.

[1297] 4. Emotional data collection and analysis:

[1298] The server uses an emotion engine to determine the user's emotional state based on their keystroke speed, mouse click frequency, voice emotion analysis, and facial recognition data. This analysis is performed using OpenCV and TensorFlow.

[1299] 5. Advice Generation:

[1300] Based on the analysis results, the server generates specific asset formation advice to help the user achieve their savings target. Based on the emotion data, the server provides appropriate advice that reflects the user's emotional state.

[1301] 6. Sending the results:

[1302] The server sends the generated advice to the user's device. The advice is packaged in JSON format or similar and provided to the user in real time.

[1303] Terminal handling

[1304] The terminal is responsible for inputting asset data by the user and displaying asset formation advice sent from the server. It also collects emotional data.

[1305] 1. Data input from the user:

[1306] The terminal displays a form for the user to input data such as income, expenses, current savings, target savings, etc. The data entered by the user is sent to the server.

[1307] 2. Collecting Emotional Data:

[1308] The device analyzes the user's typing speed, mouse click frequency, and even emotion using facial recognition. This data is sent to a server and used for emotion analysis.

[1309] 3. Data reception and display:

[1310] The device receives the analysis results and advice sent from the server and displays them to the user in a visually easy-to-understand format such as graphs and charts. A concrete example of this is the application display on a smartphone or smart glasses.

[1311] User Action

[1312] The user uses a terminal to input data into the system and check the advice sent from the server. The specific steps are as follows:

[1313] 1. Data Entry:

[1314] The user enters their income, expenses, current savings amount, and target savings amount into the form on the terminal and clicks the submit button.

[1315] 2. Reflecting emotions:

[1316] The user's interactions (such as keystroke speed and mouse click frequency) are analyzed by the emotion engine, and the user's emotional state is reflected in the system.

[1317] 3. Check the advice:

[1318] The user checks the analysis results and advice displayed on the device and receives specific asset formation guidelines.

[1319] Below are some examples of prompt sentences.

[1320] Market Data Collection:

[1321] Get the latest stock prices, exchange rates, and economic indicators data via Google Cloud API and store it in Firebase

[1322] Sentiment Data Analysis:

[1323] Analyzing keystroke speed and mouse click frequency with TensorFlow to estimate the user's emotional state

[1324] This allows users to find the optimal asset formation policy that takes into account their emotional state.

[1325] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1326] Step 1: Server

[1327] The server accesses the financial API every morning at 7:00 to collect the latest market data, such as exchange rates, stock prices, and economic indicators. The specific software used is Google Cloud API. The collected market data is stored in temporary storage. The input is market data obtained from the financial API, and the output is the market data stored in temporary storage.

[1328] Step 2: Server

[1329] The server analyzes the market data stored in temporary storage using statistical analysis and machine learning algorithms. TensorFlow is used for this analysis. As a result of the analysis, a predictive model is updated and stored in the database. The input is the market data stored in temporary storage, and the output is the updated predictive model.

[1330] Step 3: Users

[1331] The user uses a device to input their income, expenses, current savings amount, and target savings amount. The data entered by the user through a smartphone or smart glasses is sent from the device to the server. The input is the asset data entered by the user into the Android / iOS application, and the output is the asset data sent to the server.

[1332] Step 4: Server

[1333] The server receives the asset data sent by the user and stores it in a database.Then, it uses the asset data analysis module to analyze the user's income and expenditure balance and savings pattern.The input is the user's asset data stored on the server, and the output is the analysis result, which is the income and expenditure balance and savings pattern.

[1334] Step 5: Terminal

[1335] The device collects emotional data using the user's keystroke speed, mouse click frequency, and even facial recognition. The emotional data is collected in real time and sent from the device to a server. Specific technologies used include OpenCV and TensorFlow. The input is the user's interaction data, and the output is the emotional data sent to the server.

[1336] Step 6: Server

[1337] The server uses an emotion engine to analyze the transmitted emotion data. As a result of the analysis, the server determines the user's emotional state and stores it in a database. The input is the emotion data transmitted from the device, and the output is the analyzed emotional state.

[1338] Step 7: Server

[1339] The server generates asset formation advice based on the user's asset data and emotional data. It makes investment suggestions with appropriate risk levels, taking into account the user's emotional state. For example, it suggests low-risk products to users with high anxiety. The input is the analyzed asset data and emotional data, and the output is the generated asset formation advice.

[1340] Step 8: Server

[1341] The server sends the generated advice to the user's device. The advice is packaged in JSON format or similar and converted into a format that is easy to understand visually on the device. The input is the generated asset formation advice, and the output is the advice sent to the user's device.

[1342] Step 9: Terminal

[1343] The device receives the advice sent from the server and displays it visually to the user using graphs and charts. Specific examples include displays on smartphones and smart glasses. The input is the advice sent from the server, and the output is advice in a visually easy-to-understand format.

[1344] Through the above processing steps, the user can find the optimal asset formation policy that takes into account his or her emotional state.

[1345] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1346] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1347] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1348] [Fourth embodiment]

[1349] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1350] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1351] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1352] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1353] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1354] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1355] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1356] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1357] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1358] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1359] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1360] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1361] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1362] In one embodiment of the present invention, a system for supporting asset formation is configured by users, servers, and terminals working together. The processing and specific operations of each component will be explained in natural language below.

[1363] Server Processing

[1364] The server is responsible for the central data processing and analysis of the system.

[1365] 1. Market data collection

[1366] The server periodically accesses the financial API to obtain the latest exchange rates, stock prices, and economic indicators. The collected data is temporarily stored in storage and used for subsequent analysis.

[1367] 2. Data analysis and model updating

[1368] The server analyzes the acquired market data and updates the model for predicting market trends using statistical methods and machine learning models. The results of this analysis are stored in a database and used to generate advice for users.

[1369] 3. Import of personal data

[1370] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user and stores it in a database.

[1371] 4. Analysis of personal data

[1372] The server analyzes the user's income and expenditure balance and savings patterns based on the saved asset data, and compares them with the data of other users of the same age and region.

[1373] 5. Advice Generation

[1374] Based on the analysis results, the server generates specific asset formation advice for the user to achieve their savings target. The advice generated is customized to the user's individual situation.

[1375] 6. Submitting the results

[1376] The server transmits the generated advice to the user's terminal.

[1377] Terminal handling

[1378] The terminal provides the interface with the user and is responsible for inputting data and displaying results.

[1379] 1. Data input from the user

[1380] The terminal provides an interface for the user to input data such as income, expenses, current savings, target savings, etc. The input data is sent to the server.

[1381] 2. Data reception and display

[1382] The device receives the analysis results and advice sent from the server and displays them to the user in an easy-to-read format, such as graphs or charts, which are visually easy to understand.

[1383] User Action

[1384] The user uses a terminal to input data into the system and checks the advice sent from the server.

[1385] 1. Data Entry

[1386] The user inputs his / her income, expenses, current savings amount, and target savings amount through the terminal interface, and sends the data to the server by clicking the send button.

[1387] 2. Check the advice

[1388] Users can check the analysis results and advice displayed on their device and use them to plan their asset-building activities, such as how much to save each month and which investment products to purchase.

[1389] 3. Providing Feedback

[1390] Users can input feedback about the advice provided and submit their wishes and changes to the system. For example, by inputting a wish such as "I want to take more risks," new advice will be provided.

[1391] Specific examples

[1392] Every morning, the server retrieves and analyzes market data such as exchange rates and stock indexes from a specified financial API. The user inputs data such as a monthly income of 300,000 yen, a savings goal of 5 million yen, and current savings of 1 million yen into a smartphone app. The server analyzes this data and generates a result by comparing it with the average savings of people in their 30s. The generated result and advice are sent to the user's device, and the user receives specific guidelines such as saving 30,000 yen per month and purchasing low-risk investment products. The user can provide feedback on the advice and have it reflected in the system, resulting in a more accurate asset formation plan.

[1393] In this way, the present invention can provide specific and reliable advice to help users build assets efficiently.

[1394] The processing flow will be explained below.

[1395] Server Processing Steps

[1396] Step 1:

[1397] The server runs a scheduled job every morning at 7:00 am, accessing the API of economic data providers to obtain market data such as exchange rates, stock indexes, and economic indicators, and stores it in temporary storage.

[1398] Step 2:

[1399] The server analyzes the stored market data using a data analysis module, which uses statistical analysis and machine learning algorithms to predict market trends and stores the results in a database.

[1400] Step 3:

[1401] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user via API and stores it in a database.

[1402] Step 4:

[1403] The server retrieves the user data stored in the database and analyzes it using the asset data analysis module. The user's income and expenditure balance and savings patterns are analyzed and compared with the data of other users of the same age and region.

[1404] Step 5:

[1405] Based on the analysis results, the server generates specific asset formation advice to help users achieve their savings goals. The advice is customized based on each user's situation.

[1406] Step 6:

[1407] The server packages the generated advice in JSON format and sends it to the user's device.

[1408] Terminal processing steps

[1409] Step 1:

[1410] The terminal presents the user with a data entry form, where the user enters information such as income, expenses, current savings, and savings goals.

[1411] Step 2:

[1412] The device receives the user's input data and generates an API request to send it to the server. The API request is encrypted and sent.

[1413] Step 3:

[1414] The device receives the analysis results and advice sent from the server, which are also received as API responses.

[1415] Step 4:

[1416] The device analyzes the data it receives and displays it in a format that is easy for the user to understand, such as a graph, chart, or list.

[1417] User processing steps

[1418] Step 1:

[1419] The user enters income, expenses, current savings amount, and target savings amount into the data input form on the terminal and clicks the submit button.

[1420] Step 2:

[1421] The user checks the analysis results and advice displayed on the device, such as how much they should save each month and which investment products they should choose.

[1422] Step 3:

[1423] The user inputs feedback about the advice provided, such as "I want to take more risks" or "I want to know about safer options," and sends this feedback from the device to the server.

[1424] Through these steps, the system can provide users with personalized asset formation advice and support optimal asset formation.

[1425] Example 1

[1426] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1427] Conventional asset formation support systems have struggled to provide specific and reliable advice tailored to each user's individual circumstances. Furthermore, there was a lack of systems that could accurately reflect daily fluctuating market data and allow users to obtain timely information. Furthermore, it was difficult to generate personalized plans based on a user's income, expenses, and savings, and comparisons with a large amount of user data were not conducted.

[1428] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1429] In this invention, the server includes means for collecting asset data from users, means for collecting daily market data, means for analyzing the asset data and market data to generate asset formation advice, means for providing the advice to users, means for updating a machine learning model using the market data and asset data, a terminal interface for inputting data on the user's income, expenses, savings, and target savings, and means for confirming the analysis results and advice displayed on the terminal. This allows users to receive specific and reliable advice tailored to their individual circumstances. Furthermore, by reflecting market data that fluctuates daily in a timely manner, asset formation based on the latest information is possible. Furthermore, by comparing user data with data on other users of the same age and region, more accurate analysis and advice can be provided.

[1430] The "means for collecting asset data from a user" refers to a means for inputting, receiving, and storing asset data such as a user's income, expenses, savings amount, and target savings amount.

[1431] "Means of collecting daily market data" refers to the use of financial APIs to regularly obtain and store market data such as foreign exchange information, stock prices, and economic indicators.

[1432] The "means for analyzing the asset data and market data to generate asset formation advice" refers to a means for analyzing the acquired asset data and market data and using statistical techniques and machine learning models to generate specific asset formation advice for the user.

[1433] The "means for providing the advice to the user" refers to means for transmitting information to the user's terminal through an interface for providing the generated advice to the user.

[1434] "Means for updating machine learning models using market data and asset data" refers to means for updating predictive models using machine learning algorithms based on regularly collected market data and asset data from users.

[1435] A "terminal interface for inputting user's income, expenditure, savings, and savings goal data" is a terminal that provides a graphical interface for a user to input personal data such as income, expenditure, current savings, and savings goal.

[1436] "Means for checking the analysis results and advice displayed on the terminal" refers to a terminal function for receiving the analysis results and advice sent from the server and visually displaying them.

[1437] This invention provides a system that supports asset formation through cooperation between users, servers, and terminals. The specific configuration and operation of this system will be described below.

[1438] Server Roles

[1439] The server is responsible for the central data processing and analysis of this system and uses the following hardware and software:

[1440] Hardware: High-performance servers, SSD storage, network interfaces

[1441] Software: Python, TensorFlow, Scikit-learn, Pandas, Jupyter Notebook, MongoDB, RESTful API

[1442] The server collects daily market data using financial APIs. For example, it periodically accesses APIs from Alpha Vantage and Yahoo Finance to obtain the latest exchange rates, stock prices, and economic indicators. This data is temporarily stored in a database such as MongoDB.

[1443] The server then analyzes the collected market data using Python and Jupyter Notebook, preprocessing the data with the Pandas library, and updating machine learning models using TensorFlow and Scikit-learn. The analyzed data is then used to generate recommendations for users.

[1444] Furthermore, the server receives asset data (income, expenses, savings amount, savings target, etc.) sent by the user and stores it in a database. Based on the stored data, the server analyzes the user's income and expenditure balance and savings pattern and performs statistical comparisons. Based on the results, it generates specific asset formation advice for the user and sends it to the user's device via a RESTful API.

[1445] Device Role

[1446] The terminal provides the interface with the user, allowing data entry and displaying results. The terminal uses the following hardware and software:

[1447] Hardware: Smartphones, tablets, computers

[1448] Software: HTML, CSS, JavaScript, AJAX, Chart.js, D3.js

[1449] The terminal provides an interface for users to input data such as income, expenses, current savings, and target savings. These data are retrieved by JavaScript through an HTML form and sent to the server in JSON format using AJAX.

[1450] The device also receives analysis results and advice sent from the server and visually displays them to the user using Chart.js and D3.js, using graphs and charts to help users intuitively understand the information.

[1451] User Roles

[1452] The user uses a terminal interface to input asset data into the system and review the advice provided by the server.

[1453] Users enter their income, expenses, current savings amount, and target savings amount into an HTML form on their device, and then click the submit button to send the data to the server. The analysis results and advice sent from the server are displayed on the device. This allows users to obtain specific asset formation guidelines and implement an asset formation plan that suits their own situation.

[1454] Furthermore, users can provide feedback on the advice provided. For example, they can enter their wishes or changes, such as "I want to take more risks" or "I want more detailed advice," and click the submit button. The server receives this feedback and reflects it in the next advice generation.

[1455] Specific examples

[1456] Every morning, the server retrieves market data such as exchange rates and stock indexes from a specified financial API (e.g., Alpha Vantage) and analyzes it. The user enters data into the smartphone app, such as monthly income of 300,000 yen, savings goal of 5 million yen, and current savings of 1 million yen. This data is sent to the server, which analyzes and compares it to generate specific advice. For example, this advice might include "save 30,000 yen per month and purchase low-risk investment products."

[1457] Examples of prompt statements

[1458] Below is an example of a prompt sentence to input to the generative AI model.

[1459] I'm in my 30s, earn 300,000 yen a month, have a savings goal of 5 million yen, and currently have 1 million yen saved. Please give me some advice on how to build up assets with low risk.

[1460] In this way, the present invention is a system that provides specific and reliable advice to help users build up their assets efficiently.

[1461] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1462] Step 1: Gather market data

[1463] Every morning, the server periodically accesses a financial API (e.g., Alpha Vantage, Yahoo Finance) to retrieve exchange rate information, stock prices, and economic indicators. The input is the API key and request parameters, and the output is market data in JSON format. The server temporarily stores this JSON data in MongoDB. Specifically, it sends an API request using a Python library, receives the response, and stores it in the database.

[1464] Step 2: Analyze market data and update the model

[1465] The server analyzes market data using Python scripts and Jupyter Notebook. The input is market data stored in MongoDB, and the output is the analysis results and an updated machine learning model. Specifically, the data is read and preprocessed using the Pandas library, and the model is trained and updated using TensorFlow and Scikit-learn. This analysis data is stored in a database.

[1466] Step 3: Import user data

[1467] The user enters asset data such as income, expenses, savings amount, and savings goal through an HTML form on the device and clicks the submit button. The input is the user's asset data, and the output is JSON format data stored on the server. The device uses JavaScript and AJAX to send the data to the server, which then receives the data and stores it in a database.

[1468] Step 4: Analyzing personal data

[1469] The server analyzes income / expense balances and savings patterns based on the saved user asset data. The input is asset data obtained from the user database, and the output is the results of statistical analysis. Specifically, data is obtained using SQL queries, and statistical analysis such as standard deviation and average values ​​is performed using Python scripts. The results are then compared with data from users of the same age and region.

[1470] Step 5: Generating Advice

[1471] The server generates asset formation advice for the user based on the analysis results. The input is the analysis results of personal data and market data, and the output is a customized advice message. Specifically, it uses machine learning models and natural language generation models (e.g., GPT-3) to generate specific guidelines in text that are tailored to the user's situation. The results are stored in a database.

[1472] Step 6: Send and view results

[1473] The server sends the generated advice to the user's device. The input is the generated advice, and the output is the advice message displayed on the user's device. Specifically, the advice is sent in JSON format using a RESTful API, and is received on the device using AJAX. The received advice is displayed visually using Chart.js or D3.js. For example, a text message such as "Save 30,000 yen each month and purchase low-risk investment products" is displayed.

[1474] Through this series of processes, users can receive specific and reliable advice on how to build assets efficiently.

[1475] (Application example 1)

[1476] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1477] Conventional asset formation support systems provide advice based on basic asset data and market data from users, but are unable to reflect feedback on users' daily purchasing behavior or actual spending. As a result, it is difficult to provide real-time advice adapted to individual situations, and users are unable to obtain sufficient information to formulate specific asset formation plans.

[1478] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1479] In this invention, the server includes means for collecting asset data from users, means for collecting daily market data, means for analyzing the asset data and market data to generate asset formation advice, means for providing the advice to users, means for collecting user purchase history and expenditure data, means for analyzing the purchase history, expenditure data, and market data to generate asset formation advice based on purchasing behavior, means for providing the advice to users in real time, and means for updating the advice based on user feedback, thereby making it possible to provide more specific, personalized, real-time advice to users in asset formation.

[1480] "Means for collecting asset data from users" refers to a function that allows users to input asset data such as their income, expenses, savings amount, and target savings amount, and transmit this data to the server.

[1481] "Means of collecting daily market data" refers to the function of regularly collecting market data such as exchange rates, stock prices, and economic indicators from external sources such as financial APIs.

[1482] "Means for analyzing the asset data and market data to generate asset formation advice" refers to a function that performs analysis based on the collected asset data and market data and generates asset formation advice to be provided to the user.

[1483] The "means for providing the advice to the user" refers to a function for transmitting the generated asset formation advice to the user's terminal and displaying it in a visually easy-to-understand format.

[1484] "Means for collecting user purchase history and expenditure data" refers to a function that automatically collects a user's electronic payment transaction history and daily expenditure data and transmits it to a server for analysis.

[1485] "Means for analyzing the purchase history, expenditure data and market data, and generating asset formation advice based on purchasing behavior" refers to a function that comprehensively analyzes a user's purchase history, expenditure data and market data, and generates specific asset formation advice based on individual purchasing behavior.

[1486] The "means for providing the advice to the user in real time" refers to a function that allows advice based on the analysis results to be immediately provided to the user and feedback to be received in real time.

[1487] "Means for updating advice based on user feedback" refers to the function of collecting feedback information from users and appropriately updating and adjusting the advice content generated based on that information.

[1488] This invention configures a system that supports users' asset formation by linking users, servers, and terminals. The processing and specific operations of each component will be described below.

[1489] Server Processing

[1490] The server is responsible for the system's central data processing and analysis. It analyzes asset data and purchase history data obtained from users, along with the latest market data. Market data is obtained from financial APIs, and includes exchange information, stock prices, economic indicators, and more. Statistical methods and machine learning models are used to predict market trends and purchasing behavior. Based on the results of this analysis, the server generates asset formation advice personalized for the user and sends it to the terminal.

[1491] Terminal handling

[1492] The terminal provides an interface for the user and is responsible for inputting data and displaying the results. The user inputs data such as income, expenses, current savings amount, and savings goal, and daily purchase history and expenditure data are also collected. The input data is sent to the server. The analysis results and advice sent from the server are displayed on the terminal in real time. The data is displayed in a visually easy-to-understand format such as graphs and charts.

[1493] User Action

[1494] Users use their devices to input data into the system and check the advice sent from the server. Based on the advice, users plan specific asset formation actions. For example, they are presented with guidelines on how much to save each month and which investment products to purchase. Users also provide feedback on the advice provided and send their wishes and changes to the system. This allows the server to improve the analysis model based on the feedback and provide more accurate advice.

[1495] Specific examples

[1496] Every morning, the server retrieves market data such as exchange rates and stock indexes from a specified financial API. The user enters data into their smartphone, such as monthly income of 300,000 yen, savings goal of 5 million yen, and current savings of 1 million yen. At the same time, the device automatically collects the user's purchase history and expenditure data. The server analyzes this data and generates results that compare the user's savings with the average savings of people in their 30s. The generated results and advice are sent to the user's device in real time as specific guidelines, such as saving 30,000 yen per month or purchasing low-risk investment products. The user can provide feedback on the advice and have it reflected in the system, resulting in an even more accurate asset formation plan.

[1497] Prompt Sentence Examples

[1498] "Input: My monthly income is ¥200,000, my monthly expenses are ¥150,000, my current savings are ¥300,000, and my goal savings is ¥5 million. How can I achieve this in the next five years?

[1499] Output: I recommend you put away 10,000 yen per month in a low-risk mutual fund. This will increase your chances of reaching your goal.

[1500] As a result, the present invention provides a system that helps users to efficiently build assets by automatically tracking their daily expenses and income and providing financial advice in real time.

[1501] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1502] Step 1:

[1503] The server periodically accesses the financial API to obtain market data (foreign exchange information, stock prices, economic indicators, etc.). The obtained market data is temporarily stored in storage. The input is market data from the financial API, and the output is the temporarily stored market data.

[1504] Step 2:

[1505] The server analyzes the acquired market data and updates a model for predicting market trends using statistical methods and machine learning models (e.g., Linear Regression). The analyzed data is stored in a database and used to generate advice for users. The input is temporarily stored market data, and the output is the updated results of the analytical model.

[1506] Step 3:

[1507] The user uses a terminal to input asset data such as their income, expenses, current savings amount, and target savings amount. In addition, the user's purchase history and daily expenditure data are also automatically collected through the terminal. The input is the asset data and purchase history data entered by the user into the terminal, and the output is the data sent to the server.

[1508] Step 4:

[1509] The server receives asset data and purchase history data sent from the user and stores them in a database. The input is the asset data and purchase history data sent from the terminal, and the output is the stored data.

[1510] Step 5:

[1511] The server analyzes the saved user asset data and purchase history data in combination with market data. This analysis generates specific advice for the user regarding asset formation. The inputs are market data, the user's asset data, and purchase history data, and the output is the generated advice.

[1512] Step 6:

[1513] The server sends the generated asset formation advice to the user's terminal. The advice is specific and tailored to the user's purchasing behavior and asset data. The input is the generated advice, and the output is the advice sent to the user's terminal.

[1514] Step 7:

[1515] The user checks the analysis results and advice displayed on the terminal and plans asset formation actions based on them. The user inputs feedback about the advice provided and sends it to the system. The input is feedback about the analysis results and advice, and the output is the feedback sent to the server.

[1516] Step 8:

[1517] The server receives feedback from users and updates the analytical model and advice generation logic based on the feedback. The input is the user feedback, and the output is the updated analytical model and advice generation logic.

[1518] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1519] As an embodiment of the present invention, a user, a server, a terminal, and an emotion engine work in cooperation to form an asset formation support system. Specific processing and operations of each component will be described in detail below.

[1520] Server Processing

[1521] The server is responsible for collecting asset and market data, analyzing it, generating advice, and analyzing user sentiment data.

[1522] 1. Market data collection

[1523] The server accesses the financial API at 7:00 every morning to obtain the latest exchange rate information, stock prices, and economic indicators, and stores them in temporary storage.

[1524] 2. Data analysis and model updating

[1525] The server analyzes the collected market data using statistical analysis and machine learning algorithms to predict market trends, and the results are stored in a database.

[1526] 3. Import of personal data

[1527] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user via API and stores it in a database.

[1528] 4. Analysis of personal data

[1529] The server retrieves user data stored in the database and analyzes it using the asset data analysis module. The server analyzes income and expenditure balances and savings patterns, and compares them with data from other users of the same age and region.

[1530] 5. Advice Generation

[1531] Based on the analysis results, the server generates specific asset formation advice to help users achieve their savings goals. The advice generated is customized to fit each user's situation.

[1532] 6. Emotional Data Collection and Analysis

[1533] The server uses an emotion engine to determine the user's emotional state from input data and interaction data (e.g., the user's keystroke speed, mouse click frequency, etc.) The emotion data is stored in a database as part of the analysis.

[1534] 7. Adjusting advice based on emotions

[1535] The server adjusts the asset formation advice based on the user's emotional state. For example, if the user is feeling stressed, the server generates more appropriate advice, such as suggesting low-risk investment methods.

[1536] 8. Submitting the results

[1537] The server sends the generated advice to the user's device, packaged in JSON format or similar.

[1538] Terminal handling

[1539] The terminal provides the interface with the user and is responsible for inputting data and displaying results.

[1540] 1. Data input from the user

[1541] The terminal displays a form for the user to input data such as income, expenses, current savings, target savings, etc. The data input by the user is sent to the server.

[1542] 2. Collecting Emotional Data

[1543] The device also analyzes the user's keystroke speed, mouse click frequency, and emotion using facial recognition, and sends this data to the server.

[1544] 3. Data reception and display

[1545] The terminal receives the analysis results and advice sent from the server and displays them to the user in a visually easy-to-understand format such as graphs and charts.

[1546] User Action

[1547] The user uses a terminal to input data into the system and checks the advice sent from the server.

[1548] 1. Data Entry

[1549] The user enters their income, expenses, current savings amount, and target savings amount into a form on the terminal and clicks the send button to send the data to the server.

[1550] 2. Reflecting emotions

[1551] The user's interactions (such as keystroke speed and mouse click frequency) are analyzed by the emotion engine, and the user's emotional state is reflected in the system.

[1552] 3. Check the advice

[1553] Users can view the analysis results and advice displayed on their device, including specific guidelines on how much they should save each month and which investment products they should choose.

[1554] 4. Providing Feedback

[1555] The user inputs feedback about the advice provided, for example, a preference such as "I want to take more risks," and sends this feedback to the server from the terminal.

[1556] Specific examples

[1557] Every morning at 7am, the server retrieves and analyzes market data such as exchange rates and stock indexes from a financial API. The user inputs data such as a monthly income of 300,000 yen, a savings goal of 5 million yen, and a current savings of 1 million yen into the smartphone app. The server analyzes this data and generates a result by comparing it with the average savings of people in their 30s. The generated result and advice are sent to the user's device, and the user receives specific guidelines such as saving 30,000 yen per month and purchasing low-risk investment products.

[1558] Furthermore, if the user's input speed is slow and they are feeling anxious, the emotion engine will provide advice based on the user's emotional state, such as suggesting low-risk investment methods. This allows users to find the optimal asset formation policy that takes their emotional state into account.

[1559] The processing flow will be explained below.

[1560] Server Processing Steps

[1561] Step 1:

[1562] The server accesses the financial API at 7am every morning to obtain the latest exchange rates, stock prices, and economic indicators, and stores them in temporary storage.

[1563] Step 2:

[1564] The server analyzes the stored market data using a data analysis module, and uses statistical analysis and machine learning algorithms to predict market trends, and stores the results in a database.

[1565] Step 3:

[1566] The server receives asset data (income, expenses, savings amount, target savings amount, etc.) sent by the user via API and stores it in a database.

[1567] Step 4:

[1568] The server retrieves user data stored in the database and analyzes it using the asset data analysis module. The analysis includes income and expenditure balances and savings patterns, and compares them with data from other users of the same age and region.

[1569] Step 5:

[1570] Based on the analysis results, the server generates specific asset formation advice to help users achieve their savings goals. The advice is customized to each user's situation.

[1571] Step 6:

[1572] The server uses an emotion engine to determine the user's emotional state from their input data and interaction data (e.g., keystroke speed, mouse click frequency, etc.), and the emotional data is stored in a database.

[1573] Step 7:

[1574] The server adjusts asset formation advice based on the user's emotional state. For example, if the user is feeling stressed, the server will suggest low-risk investment methods.

[1575] Step 8:

[1576] The server packages the generated customized advice in JSON format and sends it to the user's device.

[1577] Terminal processing steps

[1578] Step 1:

[1579] The terminal presents the user with a data entry form, where the user enters information such as income, expenses, current savings, and savings goals.

[1580] Step 2:

[1581] The device receives the user's input data and generates an API request to send it to the server. The API request is encrypted and sent.

[1582] Step 3:

[1583] The device collects user interactions (such as keystroke speed, mouse click frequency, and facial recognition data) and sends them to a server.

[1584] Step 4:

[1585] The device receives the analysis results and advice sent from the server and displays them in a user-friendly format (graphs, charts, lists, etc.).

[1586] User processing steps

[1587] Step 1:

[1588] The user enters their income, expenses, current savings amount, target savings amount, etc. into the data input form on the terminal and clicks the submit button.

[1589] Step 2:

[1590] The user checks the analysis results and advice displayed on the device, receiving specific guidance on how much to save each month, which investment products to choose, and so on.

[1591] Step 3:

[1592] The user inputs feedback about the advice provided. For example, the user sends a request such as "I want to take more risks" to the server via the terminal.

[1593] Specific examples

[1594] Server Processing

[1595] Step 1:

[1596] The server retrieves "exchange rates and stock indexes from the API" every morning at 7:00.

[1597] Step 2:

[1598] The server "analyzes the acquired market data using statistical analysis and machine learning algorithms" and "stores the results in a database."

[1599] Step 3:

[1600] The server receives the data sent by the user, including a monthly income of 300,000 yen, a savings goal of 5 million yen, and a current savings amount of 1 million yen, and stores this data in the database.

[1601] Step 4:

[1602] The server performs the process of "analyzing user data stored in a database and comparing it with the average savings amount of people in their 30s."

[1603] Step 5:

[1604] The server "generates asset formation advice based on each user's situation" and "suggests monthly savings of 30,000 yen and low-risk investment products."

[1605] Step 6:

[1606] The server "uses an emotion engine to determine the user's emotional state" and "saves the emotional data in a database."

[1607] Step 7:

[1608] The server adjusts advice based on the user's emotional state, such as suggesting low-risk investment methods if the user is feeling stressed.

[1609] Step 8:

[1610] The server "packages the generated advice in JSON format" and "sends it to the user's device."

[1611] Terminal handling

[1612] Step 1:

[1613] The device "presents the user with a data entry form for income, expenses, savings, and savings goals."

[1614] Step 2:

[1615] The device "generates an API request to send the input data to the server" and "encrypts and sends it."

[1616] Step 3:

[1617] The device "collects user interaction data (such as keystroke speed and mouse click frequency)" and "sends it to the server."

[1618] Step 4:

[1619] The device "displays the analysis results and advice received from the server in graphs and charts."

[1620] User Action

[1621] Step 1:

[1622] The user "enters their income, expenses, current savings amount, and target savings amount, and clicks the submit button."

[1623] Step 2:

[1624] The user "checks the displayed analysis results and advice (saving 30,000 yen per month, low-risk investment products, etc.)."

[1625] Step 3:

[1626] Users "enter feedback about the advice provided" and "submit preferences such as 'I'd like to take more risks.'"

[1627] Through these steps, the system provides users with personalized asset formation advice, and by taking the user's emotional state into consideration, it achieves more accurate support.

[1628] Example 2

[1629] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1630] Conventional asset formation support systems generally provide uniform advice based on data input by users, making it difficult to provide advice that takes into account individual emotions and unique situations. In addition, it is difficult for users to accurately grasp market trends and their own asset status, and it takes a lot of time and effort to find the optimal asset formation strategy.

[1631] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1632] In this invention, the server includes means for receiving asset data from a user, means for periodically recording market data, means for analyzing the asset data and market data to generate asset formation advice, means for notifying the user of the advice, means for collecting user interaction data and analyzing emotion data, and means for adjusting the advice based on the emotion data, thereby enabling the provision of customized advice that takes into account the individual circumstances and emotional state of the user.

[1633] "Asset data" refers to information about assets owned by a user, and specifically includes income, expenses, current savings, target savings, and the like.

[1634] "Market data" is a general term for information collected from financial markets, and includes data such as exchange rates, stock prices, and economic indicators.

[1635] "Means for generating advice" refers to machine learning algorithms and statistical analysis means for analyzing collected asset data and market data and creating appropriate asset formation advice for users.

[1636] The "means for notifying advice" refers to communication means and display means for transmitting the generated advice to the user's terminal and making it available for the user to view.

[1637] "Interaction data" refers to data related to user operations, such as keystroke speed, mouse click frequency, and facial recognition data, when a user operates a device.

[1638] "Emotional data" refers to information about a user's emotional state obtained by analyzing interaction data and facial recognition data.

[1639] "Means for adjusting advice based on emotional data" refers to algorithms and analytical means for taking into account the user's emotional data and providing optimal asset formation advice.

[1640] As an embodiment of the present invention, a user, a server, a terminal, and an emotion engine work in cooperation to form an asset formation support system. Specific processing and operations of each component will be described in detail below.

[1641] Server Processing

[1642] The server is responsible for collecting asset and market data, analyzing it, generating advice, and analyzing user sentiment data.

[1643] 1. Market data collection

[1644] The server automatically runs a Python script every morning at 7:00, connects to a financial API (e.g., Alpha Vantage) using an API access library (e.g., requests), retrieves the latest exchange rates, stock prices, and economic indicators, and stores them in temporary storage (e.g., Redis, memcached).

[1645] 2. Market data analysis and model updates

[1646] The server preprocesses the collected market data using Python data processing libraries such as Pandas and NumPy, and analyzes it using statistical analysis and machine learning algorithms (e.g., ARIMA model, regression). The analysis results are stored in a database (e.g., MySQL). The machine learning model is also updated regularly.

[1647] 3. Import of personal data

[1648] The server uses a web framework (e.g., Flask, Django) to receive asset data entered by the user via a REST API and store it in a database.

[1649] 4. Analysis of personal data

[1650] The server retrieves the stored user data and performs statistical analysis using Python's analytics module, such as calculating a user's income and expenditure balance and savings patterns using a three-month rolling average and comparing them with data from other users of the same age and region.

[1651] 5. Advice Generation

[1652] Based on the analysis results, the server uses a machine learning model (e.g., random forest) to automatically generate optimal asset formation advice for each user. The advice generated is customized to fit each user's data.

[1653] 6. Emotional Data Collection and Analysis

[1654] The server sends the user's interaction data to an emotion engine (e.g., Microsoft Azure Emotion API) to analyze the user's emotional state. The analysis results are stored in a database.

[1655] 7. Adjusting advice based on emotions

[1656] Based on the results of the emotion analysis, the server readjusts the advice to take into account the user's stress and anxiety.

[1657] 8. Submitting the results

[1658] The server packages the generated advice in JSON format and sends it to the user's device as an HTTP response.

[1659] Terminal handling

[1660] The terminal provides the interface with the user and is responsible for inputting data and displaying results.

[1661] 1. Data input from the user

[1662] The device (e.g. smartphone, PC) uses a front-end framework (e.g. React, Vue.js) to display a form for entering income, expenses, current savings amount, target savings amount, etc. The entered data is sent to the server's API via JavaScript.

[1663] 2. Collecting Emotional Data

[1664] The device uses JavaScript to measure the user's keystroke speed and mouse click frequency, and periodically sends the data to a server in the background. It also uses facial recognition software (e.g., OpenCV) via the camera to perform real-time emotion analysis.

[1665] 3. Data reception and display

[1666] The device receives the advice results sent from the server and displays them to the user in a visually easy-to-understand format (e.g., graphs or charts). A JavaScript library (e.g., Chart.js) is used for display.

[1667] User Action

[1668] The user uses a terminal to input data into the system and checks the advice sent from the server.

[1669] 1. Data Entry

[1670] The user enters their income, expenses, current savings amount, and target savings amount into a form on the terminal, and clicks the submit button to send the data to the server.

[1671] 2. Reflecting emotions

[1672] Data such as the user's keystroke speed and mouse click frequency is analyzed by the emotion engine, allowing the system to understand the user's emotional state.

[1673] 3. Check the advice

[1674] Users can view the analysis results and advice displayed on their device, including specific guidelines on how much they should save each month and which investment products they should choose.

[1675] 4. Providing Feedback

[1676] The user fills in the input form with feedback about the advice provided and clicks the submit button to send it to the server, for example, to indicate a preference such as "I would like to take more risks."

[1677] Specific examples

[1678] Every morning at 7am, the server retrieves market data such as exchange rates and stock indexes from a financial API (e.g., Alpha Vantage) and analyzes the data using NumPy and Pandas. The user enters their monthly income of 300,000 yen, savings goal of 5 million yen, and current savings of 1 million yen into the smartphone app. The front end is implemented in React, and the entered data is sent to the server via JavaScript and REST API. The server saves the received data in a MySQL database and analyzes the asset data using a Python script. Based on the results of this analysis, the user is compared with the average savings of people in their 30s and optimal asset formation advice is generated.

[1679] The emotion engine (e.g., Microsoft Azure Emotion API) analyzes the user's keystroke speed and mouse click frequency, and if it determines that the user is feeling anxious, it suggests low-risk investment methods. The server sends this advice in JSON format to the user's device.

[1680] Example prompt sentence:

[1681] "I'm 30 years old and earn 300,000 yen a month. My current savings goal is 5 million yen, but I've only saved 1 million yen. Please tell me how I can achieve my savings goal in the future."

[1682] To this prompt, the generative AI model responds as follows:

[1683] "We recommend that you review your monthly income and expenditures based on your current income and expenditure data and continue to save at least 30,000 yen per month. Also, if you are feeling anxious, consider choosing low-risk investment products and ways to safely increase your assets."

[1684] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1685] Server Processing

[1686] Step 1: Gather market data

[1687] The server automatically runs a Python script every morning at 7:00, connecting to a financial API (e.g., Alpha Vantage) using an API access library (e.g., requests) to retrieve the latest exchange rates, stock prices, and economic indicators. This data is stored in temporary storage (e.g., Redis, memcached). The input is market data retrieved from the API, and the output is the raw market data stored in temporary storage.

[1688] Step 2: Analyze market data and update the model

[1689] The server retrieves market data from temporary storage and preprocesses it using data processing libraries such as Pandas and NumPy. It then analyzes the market data using statistical analysis and machine learning algorithms (e.g., ARIMA model, regression) to predict market trends. It stores the analysis results in a database (e.g., MySQL). The input is the preprocessed market data, and the output is the analysis results stored in the database.

[1690] Step 3: Importing personal data

[1691] The server receives asset data (income, expenses, current savings, target savings, etc.) entered by the user via REST API and stores it in a database. The input is asset data sent by the user from the device, and the output is user data stored in the database.

[1692] Step 4: Analyzing personal data

[1693] The server retrieves user data stored in the database and performs statistical analysis using a Python analysis module. It calculates income / expense balance and savings patterns and compares them with data from other users of the same age and region. The results of this analysis are then stored back in the database. The input is the user's asset data, and the output is the analysis results.

[1694] Step 5: Advice Generation

[1695] The server generates optimal asset formation advice for the user using a machine learning model (e.g., random forest) based on user data and market data. The generated advice is stored in a database. The input is the analyzed market data and user data, and the output is the generated advice.

[1696] Step 6: Collect and analyze emotion data

[1697] The server sends the user's interaction data (keystroke speed, mouse click frequency, etc.) to the emotion engine (e.g., Microsoft Azure Emotion API) to analyze the user's emotional state. The analysis results are also stored in a database. The input is the user's interaction data, and the output is the analyzed emotional data.

[1698] Step 7: Adjust your advice based on emotions

[1699] The server readjusts the advice based on the results of the sentiment analysis. If the user is feeling stressed, it generates customized advice, such as suggesting low-risk investment methods. The adjusted advice is stored in a database. The input is the sentiment analysis result and existing advice, and the output is the adjusted advice.

[1700] Step 8: Sending the results

[1701] The server packages the generated and adjusted advice in JSON format and sends it to the user's device as an HTTP response. The input is the adjusted advice, and the output is the advice sent to the user's device.

[1702] Terminal handling

[1703] Step 1: Data input from the user

[1704] The device (e.g. smartphone, PC) uses a front-end framework (e.g. React, Vue.js) to display a form for inputting income, expenses, current savings, target savings, etc. When the user enters the data and clicks the submit button, the data is sent to the server's API via JavaScript. The input is the asset data entered by the user, and the output is the data sent to the server.

[1705] Step 2: Collecting emotion data

[1706] The device uses JavaScript to measure keystroke speed and mouse click frequency, and periodically sends the data to the server. It also uses face recognition software (e.g., OpenCV) via the camera to perform real-time emotion analysis, and sends the data to the server. The input is the user's interaction data, and the output is the emotion data sent to the server.

[1707] Step 3: Receiving and displaying data

[1708] The terminal receives the advice results sent from the server and displays them to the user in a visually easy-to-understand format such as graphs or charts using a JavaScript library (e.g., Chart.js). The input is the advice data received from the server, and the output is the advice displayed on the terminal.

[1709] User Action

[1710] Step 1: Data entry

[1711] The user enters their income, expenses, current savings amount, and target savings amount into the form on their device and clicks the submit button. This sends the data to the server. The input is the asset data entered by the user, and the output is the data sent to the server.

[1712] Step 2: Reflecting your emotions

[1713] Data such as the user's keystroke speed and mouse click frequency is sent to the server in real time and analyzed by the emotion engine. The input is the user's interaction data, and the output is emotion data stored on the server.

[1714] Step 3: Review the advice

[1715] The user checks the analysis results and advice displayed on the terminal. For example, specific guidelines are provided, such as how much to save each month or which investment product to choose. The input is advice data from the server, and the output is advice displayed on the terminal.

[1716] Step 4: Provide feedback

[1717] The user fills in the input form with feedback about the advice provided and clicks the submit button to send it to the server. For example, the user may indicate their preference for "taking more risks." The input is the feedback entered by the user, and the output is the feedback sent to the server.

[1718] (Application example 2)

[1719] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1720] Conventional asset formation support systems provide advice based solely on the analysis of asset data and market data entered by users. However, because they do not take into account the user's emotional state, they may suggest high-risk investments even when the user is feeling stressed or anxious, which makes it difficult to provide optimal asset formation for the user.

[1721] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1722] In this invention, the server includes means for collecting asset data from a user, means for collecting daily market data, means for analyzing the asset data and market data to generate asset formation advice, means for providing the advice to the user, means for analyzing user emotion data, and means for adjusting the advice based on the emotion data, thereby making it possible to provide optimal asset formation advice that takes into account the user's emotional state.

[1723] "Asset data" refers to financial information such as the user's income, expenses, savings amount, and target savings amount.

[1724] "Market data" refers to information related to financial markets, such as the latest exchange rates, stock prices, and economic indicators.

[1725] "Means for generating advice" refers to a technology that creates guidelines and suggestions for asset formation that are provided to users based on the collected and analyzed data.

[1726] The "means for providing advice" refers to a technology for transmitting the generated advice to the user's terminal and displaying it in a visually easy-to-understand format.

[1727] "Emotion data" refers to information that indicates the user's psychological state, determined from the user's keystroke speed, mouse click frequency, voice emotion analysis, face recognition, and the like.

[1728] "Means for adjusting advice based on emotional data" refers to technology that reflects the user's emotional state and customizes appropriate asset formation advice in a way that reduces risk, etc.

[1729] "Data of other users of the same age and area" refers to asset data of other users collected based on the user's age and area of ​​residence.

[1730] "Statistical analysis means" refers to techniques that use collected data to statistically analyze, compare, and predict.

[1731] As an embodiment of the present invention, a server, a terminal, and an emotion engine work in conjunction to form an asset formation support system. Specific processing and operations of each component will be described in detail below.

[1732] Server Processing

[1733] The server plays a key role in collecting and analyzing asset data, market data, and user sentiment data sent by users, and generating asset formation advice. The specific processes performed by the server are as follows:

[1734] 1. Market Data Collection:

[1735] The server accesses the financial API every morning at 7:00 to obtain the latest exchange rates, stock prices, and economic indicators. This data is stored in temporary storage and used for analysis. The specific software used is the Google Cloud API.

[1736] 2. Data analysis and model updating:

[1737] The server analyzes the collected market data using statistical analysis and machine learning algorithms to predict market trends. This analysis is performed using machine learning platforms such as TensorFlow. The analysis results are stored in a database.

[1738] 3. Collection and Analysis of Personal Data:

[1739] The server receives asset data (income, expenses, savings amount, savings target amount, etc.) sent by the user via API and stores it in a database.The asset data analysis module then analyzes the user data to determine income and expenditure balance and savings patterns.

[1740] 4. Emotional data collection and analysis:

[1741] The server uses an emotion engine to determine the user's emotional state based on their keystroke speed, mouse click frequency, voice emotion analysis, and facial recognition data. This analysis is performed using OpenCV and TensorFlow.

[1742] 5. Advice Generation:

[1743] Based on the analysis results, the server generates specific asset formation advice to help the user achieve their savings target. Based on the emotion data, the server provides appropriate advice that reflects the user's emotional state.

[1744] 6. Sending the results:

[1745] The server sends the generated advice to the user's device. The advice is packaged in JSON format or similar and provided to the user in real time.

[1746] Terminal handling

[1747] The terminal is responsible for inputting asset data by the user and displaying asset formation advice sent from the server. It also collects emotional data.

[1748] 1. Data input from the user:

[1749] The terminal displays a form for the user to input data such as income, expenses, current savings, target savings, etc. The data entered by the user is sent to the server.

[1750] 2. Collecting Emotional Data:

[1751] The device analyzes the user's typing speed, mouse click frequency, and even emotion using facial recognition. This data is sent to a server and used for emotion analysis.

[1752] 3. Data reception and display:

[1753] The device receives the analysis results and advice sent from the server and displays them to the user in a visually easy-to-understand format such as graphs and charts. A concrete example of this is the application display on a smartphone or smart glasses.

[1754] User Action

[1755] The user uses a terminal to input data into the system and check the advice sent from the server. The specific steps are as follows:

[1756] 1. Data Entry:

[1757] The user enters their income, expenses, current savings amount, and target savings amount into the form on the terminal and clicks the submit button.

[1758] 2. Reflecting emotions:

[1759] The user's interactions (such as keystroke speed and mouse click frequency) are analyzed by the emotion engine, and the user's emotional state is reflected in the system.

[1760] 3. Check the advice:

[1761] The user checks the analysis results and advice displayed on the device and receives specific asset formation guidelines.

[1762] Below are some examples of prompt sentences.

[1763] Market Data Collection:

[1764] Get the latest stock prices, exchange rates, and economic indicators data via Google Cloud API and store it in Firebase

[1765] Sentiment Data Analysis:

[1766] Analyzing keystroke speed and mouse click frequency with TensorFlow to estimate the user's emotional state

[1767] This allows users to find the optimal asset formation policy that takes into account their emotional state.

[1768] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1769] Step 1: Server

[1770] The server accesses the financial API every morning at 7:00 to collect the latest market data, such as exchange rates, stock prices, and economic indicators. The specific software used is Google Cloud API. The collected market data is stored in temporary storage. The input is market data obtained from the financial API, and the output is the market data stored in temporary storage.

[1771] Step 2: Server

[1772] The server analyzes the market data stored in temporary storage using statistical analysis and machine learning algorithms. TensorFlow is used for this analysis. As a result of the analysis, a predictive model is updated and stored in the database. The input is the market data stored in temporary storage, and the output is the updated predictive model.

[1773] Step 3: Users

[1774] The user uses a device to input their income, expenses, current savings amount, and target savings amount. The data entered by the user through a smartphone or smart glasses is sent from the device to the server. The input is the asset data entered by the user into the Android / iOS application, and the output is the asset data sent to the server.

[1775] Step 4: Server

[1776] The server receives the asset data sent by the user and stores it in a database.Then, it uses the asset data analysis module to analyze the user's income and expenditure balance and savings pattern.The input is the user's asset data stored on the server, and the output is the analysis result, which is the income and expenditure balance and savings pattern.

[1777] Step 5: Terminal

[1778] The device collects emotional data using the user's keystroke speed, mouse click frequency, and even facial recognition. The emotional data is collected in real time and sent from the device to a server. Specific technologies used include OpenCV and TensorFlow. The input is the user's interaction data, and the output is the emotional data sent to the server.

[1779] Step 6: Server

[1780] The server uses an emotion engine to analyze the transmitted emotion data. As a result of the analysis, the server determines the user's emotional state and stores it in a database. The input is the emotion data transmitted from the device, and the output is the analyzed emotional state.

[1781] Step 7: Server

[1782] The server generates asset formation advice based on the user's asset data and emotional data. It makes investment suggestions with appropriate risk levels, taking into account the user's emotional state. For example, it suggests low-risk products to users with high anxiety. The input is the analyzed asset data and emotional data, and the output is the generated asset formation advice.

[1783] Step 8: Server

[1784] The server sends the generated advice to the user's device. The advice is packaged in JSON format or similar and converted into a format that is easy to understand visually on the device. The input is the generated asset formation advice, and the output is the advice sent to the user's device.

[1785] Step 9: Terminal

[1786] The device receives the advice sent from the server and displays it visually to the user using graphs and charts. Specific examples include displays on smartphones and smart glasses. The input is the advice sent from the server, and the output is advice in a visually easy-to-understand format.

[1787] Through the above processing steps, the user can find the optimal asset formation policy that takes into account his or her emotional state.

[1788] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1789] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1790] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1791] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1792] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1793] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1794] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1795] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1796] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1797] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1798] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1799] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers includ...

Claims

1. means for collecting asset data from users; A means of collecting daily market data; means for analyzing the asset data and market data to generate asset formation advice; means for providing said advice to a user; A system including:

2. 10. The system of claim 1, further comprising means for generating a personalized wealth creation plan based on user input.

3. The system of claim 1, further comprising statistical analysis means for comparing the data of the user with that of other users of the same age and region.

Images