system

Abstract

We provide the system. [Solution] Means for collecting income and expenditure data, A means for analyzing the collected data and identifying the user's economic activity patterns, Based on the aforementioned analysis results, a means for generating savings plans and investment proposals for users, A means of monitoring financial market data in real time and notifying users of significant fluctuations, A means for generating responses to user queries in natural language, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, it has become a common problem for many people that it is difficult for individuals to efficiently manage income and expenses and make future financial plans. Therefore, unnecessary expenses may accumulate, and the state of insufficient savings may continue. Furthermore, due to a lack of specialized knowledge about the financial market, it is often impossible to make appropriate investment decisions. In addition, since it is costly and time-consuming to obtain financial advice from experts, there is also a problem that it is difficult for general consumers to use. As a result, the financial status of individuals becomes unstable, and a situation occurs where future economic independence is hindered.

Means for Solving the Problems

[0005] This invention is a system for improving personal financial management, equipped with means for automatically collecting income and expenditure data. It then analyzes this data using generative AI to identify user patterns. Based on this, it provides means for generating individual savings plans and investment proposals. In addition, it includes a function to monitor financial market data in real time and notify users of significant fluctuations. Furthermore, it utilizes natural language processing to generate responses to user inquiries, thereby helping to deepen user understanding. This enables individuals to make better financial decisions and helps them achieve their future financial goals.

[0006] "Income and expenditure data" refers to information about an individual's financial income and the financial expenses they incur in their daily life.

[0007] "Analysis" refers to the process of thoroughly analyzing collected data and extracting meaningful patterns and trends from it.

[0008] A "savings plan" refers to a strategy for regularly saving an appropriate amount of money towards future financial goals.

[0009] An "investment proposal" refers to a recommendation that outlines specific investment directions or products based on the user's financial situation and risk tolerance.

[0010] "Financial market data" refers to market-related information such as prices and trading volumes of stocks, bonds, foreign exchange, and other financial products.

[0011] "Notifications" refer to messages or alerts that a system sends to a user to inform them of important information or an urgent situation.

[0012] "Natural language processing" refers to the technology that enables computers to understand natural language used by humans and generate appropriate responses. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] In one embodiment of this invention, a system for supporting personal financial management is implemented in a form that includes three main components: a user, a terminal, and a server.

[0035] First, users input their income and expense data using devices such as smartphones or computers. This includes entering daily shopping and payroll information. It's also possible to automatically collect transaction data by linking bank accounts and credit card accounts to the device.

[0036] Next, the collected data is sent to the server via the terminal. The data is encrypted and securely transferred using advanced security protocols. The server has a generative AI model implemented, which is used to analyze the data.

[0037] The server analyzes the received data to identify the user's income and expenditure patterns and spending habits. Based on these results, it generates optimal savings plans and investment suggestions for the user. For example, it provides specific plans tailored to individual financial goals, such as monthly savings targets or participation in automated investment programs.

[0038] Furthermore, the server has the ability to monitor financial market trends in real time and send notifications to the terminal when there are significant market fluctuations that could affect the user. This allows users to make necessary financial decisions quickly.

[0039] Furthermore, users can input various questions into the system using natural language. The server uses generative AI to generate appropriate responses in real time based on these inputs and provides them to the user. For example, a question such as "Tell me about my spending patterns this month" can be answered with a detailed analysis result.

[0040] In this way, the invention can be implemented as a system that provides user-friendly and highly personalized financial management and advisory functions.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] Users use their devices to input income and expense information into the application. Users link their bank accounts and credit cards to their devices and set up automatic collection of transaction data.

[0044] Step 2:

[0045] The terminal encrypts the transaction data it collects and sends it to the server via a secure communication protocol. The terminal verifies the reliability of the data and performs error checking.

[0046] Step 3:

[0047] The server saves the received data to the database. A process is implemented to filter out duplicate data and ensure data consistency and integrity.

[0048] Step 4:

[0049] The server analyzes stored data using an AI model. It understands the user's income and expenditure patterns and identifies unusual spending and savings trends.

[0050] Step 5:

[0051] The server generates personalized savings plans and investment suggestions for the user based on the analysis results. This process includes risk tolerance analysis and portfolio recommendations.

[0052] Step 6:

[0053] The server monitors financial market data in real time and detects significant fluctuations. If an anomaly or market trend affects the user, an alert is sent to the device.

[0054] Step 7:

[0055] The user inputs a question using natural language through their device. For example, they might ask a specific question like, "What are this month's savings points?"

[0056] Step 8:

[0057] The server uses the natural language processing capabilities of its AI to generate responses to user questions. Based on the analysis results and suggestions, it provides information to the user in an easy-to-understand manner.

[0058] Step 9:

[0059] The terminal displays the response from the server to the user, who then reviews the proposed plan. If necessary, the user can modify the plan or add new settings.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] Modern personal financial management is complex and dynamic, requiring the collection, analysis, and forecasting of appropriate information. However, traditional systems often suffer from insufficient information gathering, or their analysis and recommendations are generic rather than individually optimized. Furthermore, they are inadequate in responding to real-time market fluctuations. As a result, individuals face challenges in making accurate financial decisions.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for collecting economic information, means for analyzing the collected information and identifying the user's economic activity patterns, and means for making future predictions using a generative AI model based on the received data. This makes it possible to provide users with highly personalized savings policies and investment proposals.

[0065] "Economic information" refers to data related to a user's income and expenses, including transaction history, sources of income, and expense details.

[0066] "Analysis" refers to the process of identifying user behavior patterns and trends from collected economic information, and may involve the use of statistical processing and algorithms.

[0067] A "savings policy" refers to a plan that provides specific guidelines for users to appropriately save money for the future.

[0068] "Investment proposals" refer to information that recommends specific and appropriate methods of asset management based on the user's financial situation and market trends.

[0069] "Goods market information" refers to data related to market trends in stocks, foreign exchange, commodities, etc., and includes prices, trading volume, trends, etc.

[0070] A "generative AI model" refers to a technology that uses machine learning algorithms to learn patterns from data and perform future predictions and real-time analysis.

[0071] "Natural language generation technology" refers to the technologies and methods used by computers to generate human language and communicate information in an easily understandable way.

[0072] This invention is a system that supports personal financial management and consists mainly of three elements: user, terminal, and server. First, the user uses a terminal such as a smartphone or computer to collect income and expenditure data. There are two methods of collection: manual input and automatic collection, the latter of which is achieved by linking the terminal with bank accounts or credit card accounts.

[0073] The terminal encrypts the collected economic information and sends it to the server using a security protocol. After receiving the data, the server performs preprocessing such as format conversion and imputation of missing data, and then analyzes it using a generative AI model. This allows the server to identify the user's consumption patterns and characteristics and make future predictions. For example, it can analyze a user's spending over the past three months, detect if a specific category, such as "food expenses," is exceeding the budget, and suggest ways to improve it.

[0074] Based on the analysis results, the server generates savings policies and investment suggestions, and presents them to the user in an easy-to-understand format using natural language generation technology. Specific suggestions include advice such as, "Let's make sure to save money thoroughly until the next payday and then check the results."

[0075] Furthermore, the server monitors market data in real time and sends notifications to the terminal when significant fluctuations occur. This feature gives users the opportunity to review their financial strategies in a timely manner. For example, when the stock market plummets, they may receive a notification saying, "The market is volatile. Please consider reviewing your portfolio."

[0076] Furthermore, users can obtain various information by entering questions in natural language. The server can use generative AI to generate responses to these questions and display them quickly on the terminal. An example of a prompt would be, "Tell me about my spending trends this week."

[0077] This configuration allows the system to provide highly personalized financial management and advisory functions that are easily accessible to users.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] Users input income and expense data using devices such as smartphones and computers. The data entered is economic information based on specific amounts and dates, such as purchases and pay stubs. This data is organized by category and stored in a database within the device. In the case of automated collection, the device uses APIs from bank accounts and credit cards to retrieve and collect the latest transaction data.

[0081] Step 2:

[0082] The terminal protects the collected data using encryption technology (e.g., AES encryption) and sends it to the server using a security protocol (e.g., HTTPS). Input data undergoes format conversion before transmission. Specifically, date formats and currency units are standardized, making analysis on the server easier.

[0083] Step 3:

[0084] The server receives the transmitted data and first performs data cleaning, such as imputing missing data and correcting outliers. This step includes operations such as converting incorrectly entered, excessively large numbers to an appropriate range. Once the data cleaning is complete, a generative AI model is prepared, and the data is ready for subsequent analysis.

[0085] Step 4:

[0086] The server uses a generative AI model to analyze clean data. This involves identifying behavioral patterns from past spending history and analyzing seasonal spending trends. Statistical methods and machine learning algorithms are used for data processing. The analysis output includes reports on user consumption habits and suggestions for improvement.

[0087] Step 5:

[0088] Based on the analysis results, the server generates beneficial savings policies and investment proposals for the user, and documents the proposals in an easy-to-understand format using natural language generation technology. The output text includes specific action plans and recommendations. This document is sent to the terminal for the user to view.

[0089] Step 6:

[0090] The server continuously monitors goods market data in real time and generates and sends notifications to terminals when it detects significant changes. For example, if there are important market trends, it will provide information such as "The market is changing" via push notification.

[0091] Step 7:

[0092] Users can ask the system questions in natural language via their terminal. The server inputs the prompt into an AI model that generates appropriate responses. For example, if a user asks, "Tell me my expenses for this week," the server will create a weekly expense summary from the analyzed data, convert it to text, and display it on the terminal.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] In financial management, there are challenges in accurately tracking daily expenses and efficiently managing long-term savings and investment plans for individual users. Furthermore, while systems capable of responding immediately to fluctuating market information are needed, users currently face the time and effort required to check this information themselves. Additionally, many users desire smooth responses to inquiries in natural language, and meeting these needs is essential.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes means for collecting financial information data, means for analyzing the collected information and identifying the user's economic activity trends, and means for monitoring market information in real time and notifying the user of important changes. This enables the user to automatically grasp their daily spending and efficiently manage their long-term finances. Furthermore, by responding immediately to fluctuating market information, quick and effective financial decisions become possible. In addition, rapid responses to inquiries in natural language can be obtained, enhancing user convenience.

[0098] "Financial information data" refers to information related to a user's income, expenses, and transactions, which allows for a comprehensive understanding of an individual's economic activities.

[0099] "Analysis" is the process of analyzing collected data and identifying patterns and trends to gain insights into users' economic activities.

[0100] "Economic activity trends" refer to patterns and tendencies in users' income, expenditure, and asset management behaviors, and represent individual financial behavioral habits.

[0101] "Market information" refers to various data related to financial markets, including information on market trends and fluctuations.

[0102] "Natural language" refers to the language that humans use on a daily basis, enabling users to give instructions and make inquiries to the system using ordinary language.

[0103] A "user" refers to an individual who uses this system and seeks to manage or improve their own financial situation.

[0104] "Means" refers to methods or devices used to achieve a specific purpose, and in this system, they enable functions such as the collection, analysis, and notification of various types of data.

[0105] Users input data about their income and expenses using devices such as smartphones and computers. Furthermore, by linking with bank accounts and digital payment services, transaction data can be automatically collected.

[0106] The terminal has the ability to encrypt collected financial information data and securely transmit it to the server using security protocols. The server has a generative AI model implemented, which is used to perform detailed analysis of the data. The server identifies the user's income and expenditure trends and generates savings policies and investment proposals based on them.

[0107] Furthermore, the server monitors financial market information in real time and immediately sends notifications to the user's terminal when significant market changes occur. This notification function allows users to make necessary financial decisions quickly.

[0108] Furthermore, users can query the system using natural language, and the server uses generative AI to return appropriate responses in real time. These responses are based on the user's specific financial situation and include detailed explanations and predictive information.

[0109] As a concrete example, if a user inputs "Tell me about my spending this month" into the terminal, the server uses a generative AI model to analyze the spending data and returns advice to the terminal such as, "Your spending on food and beverages has increased by 10% this month. We recommend reviewing your budget for next month." In this way, this invention provides users with high convenience and effective financial management.

[0110] Examples of prompts for generative AI models

[0111] Based on the user's spending data, analyze their spending trends for the current month and generate specific advice for saving money. For example, include specific comments on increases or decreases in dining out expenses.

[0112] Therefore, this system can streamline financial management and provide users with optimal financial advice.

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] Users input income and expense data using their smartphones or computers. This data includes daily living expenses and earnings information. Furthermore, users can automatically retrieve transaction data by linking their bank accounts and digital payment services. This data input allows the device to accumulate the basic information necessary for financial management.

[0116] Step 2:

[0117] The terminal encrypts the collected financial information data and sends it to the server using a security protocol. This process uses encryption technologies such as SSL / TLS to ensure the secure transfer of data. The input is encrypted financial information data, and the output is data securely delivered to the server via a secure communication path.

[0118] Step 3:

[0119] The server decrypts the received encrypted data and performs data analysis using a generative AI model. This analysis uses data mining techniques to identify the user's income and expenditure trends and spending habits. The input to the analysis is the decrypted financial information data, and the output is a detailed report of the user's economic activity trends and spending patterns.

[0120] Step 4:

[0121] The server generates appropriate savings policies and investment proposals for the user based on the analysis results. This generation process applies machine learning algorithms to create personalized suggestions optimized for each user. The input is trend data on economic activity, and the output is specific savings and investment proposals.

[0122] Step 5:

[0123] The server monitors financial market information in real time and, if significant market changes occur, immediately sends notifications to the user's terminal as needed. This monitoring uses an API to ingest market data and detect anomalies or significant fluctuations. The input is market information data, and the output is a fluctuation information alert.

[0124] Step 6:

[0125] Users can input questions into the terminal using natural language. The server receives these questions, generates appropriate responses using a generative AI model, and sends them back to the user in real time. This process utilizes natural language processing technology to accurately understand the user's intent and provide answers. The input is the user's question text, and the output is the generated response message.

[0126] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0127] As an embodiment of this invention, a personal financial management system incorporating an emotion engine consists of three main components: a user, a terminal, and a server.

[0128] First, users input information about their income and expenses using devices such as smartphones or computers. These devices can be linked to bank accounts and credit cards to automatically collect transaction data. Furthermore, users can interact with the system using voice or text input.

[0129] Next, the collected data is sent to the server via the terminal. The server contains a generative AI model and an emotion engine. The generative AI model analyzes income and expenditure data to identify the user's economic activity patterns. This allows for personalized savings plans and investment suggestions.

[0130] Meanwhile, the emotion engine analyzes voice and text data obtained from the user to recognize the user's emotional state. Based on this recognition, the server generates optimal financial advice that reflects the user's emotional state. For example, if it detects that the user is stressed, it may recommend low-risk investment options or suggest mitigation measures to save money.

[0131] The server sends suggestions generated based on analysis results and sentiment analysis to the terminal. The terminal notifies the user in real time, enabling the user to take action quickly.

[0132] Furthermore, users can ask questions about asset management and spending in natural language and receive responses. For example, in response to a specific question such as "Please give me saving suggestions based on my current emotional state," the system will provide advice tailored to the user's emotions.

[0133] In this way, a system incorporating an emotion engine can comprehensively consider the user's economic and emotional state and support individually optimized financial management.

[0134] The following describes the processing flow.

[0135] Step 1:

[0136] Users enter information about their income and expenses into the application using their device. Users also set up automatic collection of transaction data by linking their bank accounts and credit cards to their device.

[0137] Step 2:

[0138] Users input information about their daily emotional state via voice or text into their device. This data is used for processing by the emotion engine.

[0139] Step 3:

[0140] The device encrypts the income, expenditure, and sentiment input data it collects and sends it to the server using a secure communication protocol. The device performs a basic integrity check on the data before transmission.

[0141] Step 4:

[0142] The server stores the received transaction data in the database. Duplicate data removal and data integrity checks are performed.

[0143] Step 5:

[0144] The server applies a generative AI model to transaction data to analyze the user's income and expenditure patterns. From the resulting analysis, it identifies the user's usual spending and savings trends.

[0145] Step 6:

[0146] The server's emotion engine analyzes the user's voice and text data to identify the user's current emotional state. For example, if the user indicates stress, the result is recorded.

[0147] Step 7:

[0148] The server integrates the results of income and expenditure data analysis with sentiment analysis to generate savings plans and investment suggestions that take the user's emotional state into account. Specific examples include saving methods that consider relaxation and low-risk investment suggestions.

[0149] Step 8:

[0150] The server sends the generated financial advice and plan to the terminal. The terminal displays this information on the user's screen, making it accessible to the user.

[0151] Step 9:

[0152] When a user inputs a natural language question through their device, the server generates a sentiment-sensitive response to the question and sends it to the user via the device. For example, it might answer a question like, "I'm feeling anxious right now, how should I protect my assets?"

[0153] Through this series of steps, the system can comprehensively manage the user's financial and emotional state and provide individually optimized advice.

[0154] (Example 2)

[0155] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0156] In personal financial management, it has been difficult to provide advice that not only analyzes income and expenditure patterns but also takes into account a person's emotional state. Furthermore, there was a lack of real-time information to quickly respond to market fluctuations and make optimal financial choices. Additionally, there was a problem with the lack of individualization when developing savings and investment plans tailored to individual user goals, as the influence of emotions was not considered.

[0157] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0158] In this invention, the server includes means for using a generative model to analyze income and expenditure data and identify the user's economic activity patterns; means for analyzing voice and text data to recognize the user's emotional state; and means for generating individual savings plans and investment proposals for the user based on the analysis results and emotional state. This makes it possible to provide individually optimized financial management that comprehensively considers the user's economic activities and emotional state.

[0159] "Income and expenditure information" refers to all the benefits a user receives and all the expenses they incur, and is data that indicates an individual's financial status.

[0160] A "generative model" refers to an algorithm that analyzes specific patterns based on collected data and generates new analytical results.

[0161] "Voice and text data" refers to data in the form of spoken or written language entered by users, and is fundamental information that represents the user's intentions and emotions.

[0162] "Emotional state" refers to the psychological or emotional condition a user is in, including feelings such as anxiety and joy.

[0163] "Savings plans and investment proposals" refer to asset management and investment plans recommended to help users achieve their future financial goals.

[0164] "Market data" refers to information about fluctuations in financial markets such as stock prices, exchange rates, and interest rates, which can influence financial decisions.

[0165] "Natural language queries" refer to questions and requests that users make to a system using everyday language.

[0166] In an embodiment of this invention, the personal financial management system consists of three main components: a user, a terminal, and a server. The user inputs information about their income and expenses using a terminal such as a smartphone or computer. The terminal is equipped with software that links with bank accounts and financial institutions to automatically collect transaction data. The user can input information interactively into the system using voice and text.

[0167] Financial information collected by the terminal is sent to a server. This server houses a generative AI model that analyzes the user's income and expenditure data to identify economic activity patterns. The analysis utilizes models employing time series analysis and machine learning techniques.

[0168] Furthermore, the server is equipped with an emotion engine that analyzes voice and text data to recognize the user's emotional state. This engine uses natural language processing and voice emotion analysis algorithms to understand the user's psychological state and generate advice based on that state.

[0169] The server combines analyzed economic data with the user's emotional state to generate personalized savings plans and investment suggestions. These suggestions reflect the user's current emotional state and include recommendations that consider appropriate risk levels. For example, if a user asks, "How much should I save this month?", the server can provide a specific amount based on the user's individual circumstances.

[0170] As a concrete example, a prompt might be written as, "If the system determines that the user is experiencing stress, what investment strategy would be recommended?" By inputting this prompt into the AI ​​model on the server, the system will suggest the optimal investment strategy tailored to the user's situation.

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] Users input income and expense information using devices such as smartphones and computers. These devices connect with bank accounts and financial institutions, automatically collecting and inputting transaction data. The input data includes salary, food expenses, rent, etc., and this data is automatically categorized and organized on the device.

[0174] Step 2:

[0175] Data collected by the device is sent to the server. The server receives this information as input and uses a generative AI model to analyze the user's income and expenditure data. Specifically, it performs data calculations to identify the user's past income and expenditure patterns through time series analysis and predict future financial conditions. As output, the user's economic activity patterns are identified.

[0176] Step 3:

[0177] The server receives voice and text data sent by the user and activates the emotion engine to analyze the emotional state. This process analyzes the tone of voice and emotional expressions contained in the text, and processes the data to recognize emotional states such as anxiety and joy. As a result of the analysis, the user's emotional state is output.

[0178] Step 4:

[0179] The server integrates analysis results from the generation AI model and the emotion engine to generate personalized financial advice for the user. Specifically, it creates appropriate savings plans and investment suggestions based on the user's current financial situation and emotional state. For example, it may recommend low-risk investments or suggest specific ways to save money. The output is a personalized savings and investment plan for the user.

[0180] Step 5:

[0181] The server sends the generated suggestions to the terminal, which then notifies the user in real time. Notifications are sent via push notifications or email, allowing the user to immediately review and take action. Furthermore, the user can obtain additional information and advice by sending prompts such as "How much have I saved this month?" or "Tell me your investment strategy."

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] Modern individuals need to manage their finances amidst complex economic conditions and emotional fluctuations. However, current financial management systems lack an approach based on individual emotions, making it difficult to provide advice tailored to individual circumstances. Therefore, there is a need for individually optimized financial management that takes into account the user's emotional state.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes means for collecting income and expenditure information, means for identifying an individual's economic activity patterns, and means for generating individual savings plans and investment proposals. This enables comprehensive financial management that takes into account an individual's emotional state.

[0187] "Income and expenditure information" refers to data on income and expenditures related to an individual's financial activities, and is fundamental information for understanding an individual's economic situation.

[0188] An "economic activity pattern" comprehensively represents an individual's income and expenditure trends and habits, serving as the basis for individual financial planning and proposals.

[0189] "Savings plans and investment proposals" refer to specific suggestions to help optimize savings allocation and asset growth based on an individual's financial situation and emotional state.

[0190] "Economic market information" refers to the latest data related to financial and stock markets, and is important information that should be considered when making individual investment decisions.

[0191] "Natural language queries" refer to questions and requests that individuals make to a system using everyday language, which facilitates smooth interaction with the system.

[0192] "Emotional state" refers to an individual's feelings and psychological condition, and is a factor that enables appropriate financial advice to be provided based on this state.

[0193] An "information processing system" refers to a technical framework that includes a series of hardware and software components for analyzing collected data and generating proposals.

[0194] To implement this invention, an information processing system is constructed to support personal financial management. The system collects income and expenditure information from the user's smartphone, computer, or other terminal and transmits it to a server. This information is automatically acquired through cooperation with financial institutions and credit agencies.

[0195] The server is equipped with a generative AI model that analyzes collected information using Google® Cloud Natural Language API and TENSORFLOW®. The generative AI model analyzes economic activity patterns and provides personalized savings plans and investment suggestions. Furthermore, an emotion analysis engine evaluates the user's voice or text data to identify their emotional state. Based on this emotional state, the server provides personalized financial advice.

[0196] The terminal notifies the user of suggestions from the server in real time, allowing the user to receive feedback quickly. Users can also ask questions about finances and emotions using natural language and receive responses from a generative AI model.

[0197] For example, if the system detects stress in the user, it will recommend low-risk investment options. By prompting the user with questions like, "What big purchase would I feel comfortable making right now?", the system can provide personalized information. This approach enables comprehensive financial management that takes the user's emotional state into account.

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The user's device collects income and expenditure information from the user. This information is automatically obtained through collaboration with financial institutions and credit agencies. The input is the user's transaction information, and the output is the preparation of data for transmission to the server. Specifically, the device accesses the financial institution's API via the internet and securely downloads the transaction information.

[0201] Step 2:

[0202] The server receives income and expenditure information sent from the terminal. The input is financial data sent from the terminal, and the output is ready for analysis. At this point, the server verifies the integrity of the data and saves it to the database for analysis. During this process, duplicate data is removed and the format is normalized.

[0203] Step 3:

[0204] The server analyzes the collected information using a generative AI model to identify the user's economic activity patterns. The input is normalized financial data, and the output is the result of the economic activity analysis. Specifically, the AI ​​model uses machine learning algorithms to identify past spending patterns and trends, and generates numerical data and graphs of the analysis results.

[0205] Step 4:

[0206] The server uses an emotion analysis engine to analyze the user's emotional state. The input is voice or text data from the user, and the output is the emotion analysis result. In this process, speech recognition and natural language processing technologies are used to analyze the tone of the user's voice and the context in which it is used, and the emotional state is numerically evaluated.

[0207] Step 5:

[0208] The server generates personalized savings plans and investment proposals based on a generated AI model and sentiment analysis results. Inputs are the results of economic activity analysis and sentiment analysis, while output is customized financial advice. The server calculates investment options based on risk profiles and short-term and long-term goals, and sends the results to the terminal.

[0209] Step 6:

[0210] The user's device receives suggestions sent from the server and notifies the user. The input is financial advice from the server, and the output is a notification to the user. Specifically, the device displays notifications to the user in real time through the app's UI and collects user feedback as needed.

[0211] Step 7:

[0212] The user asks additional questions or inquiries using natural language, and the server generates a response using a generative AI model based on the prompt text. The input is the prompt text from the user, and the output is the response from the generative AI model. Specifically, the server analyzes the user's question, prepares an intelligent response that takes into account past data and the current situation, and immediately sends it to the user.

[0213] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0214] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0215] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0219] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0220] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0221] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0222] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0223] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0224] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0225] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0226] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0227] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0228] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0229] In one embodiment of this invention, a system for supporting personal financial management is implemented in a form that includes three main components: a user, a terminal, and a server.

[0230] First, users input their income and expense data using devices such as smartphones or computers. This includes entering daily shopping and payroll information. It's also possible to automatically collect transaction data by linking bank accounts and credit card accounts to the device.

[0231] Next, the collected data is sent to the server via the terminal. The data is encrypted and securely transferred using advanced security protocols. The server has a generative AI model implemented, which is used to analyze the data.

[0232] The server analyzes the received data to identify the user's income and expenditure patterns and spending habits. Based on these results, it generates optimal savings plans and investment suggestions for the user. For example, it provides specific plans tailored to individual financial goals, such as monthly savings targets or participation in automated investment programs.

[0233] Furthermore, the server has the ability to monitor financial market trends in real time and send notifications to the terminal when there are significant market fluctuations that could affect the user. This allows users to make necessary financial decisions quickly.

[0234] Furthermore, users can input various questions into the system using natural language. The server uses generative AI to generate appropriate responses in real time based on these inputs and provides them to the user. For example, a question such as "Tell me about my spending patterns this month" can be answered with a detailed analysis result.

[0235] In this way, the invention can be implemented as a system that provides user-friendly and highly personalized financial management and advisory functions.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] Users use their devices to input income and expense information into the application. Users link their bank accounts and credit cards to their devices and set up automatic collection of transaction data.

[0239] Step 2:

[0240] The terminal encrypts the transaction data it collects and sends it to the server via a secure communication protocol. The terminal verifies the reliability of the data and performs error checking.

[0241] Step 3:

[0242] The server saves the received data to the database. A process is implemented to filter out duplicate data and ensure data consistency and integrity.

[0243] Step 4:

[0244] The server analyzes stored data using an AI model. It understands the user's income and expenditure patterns and identifies unusual spending and savings trends.

[0245] Step 5:

[0246] The server generates personalized savings plans and investment suggestions for the user based on the analysis results. This process includes risk tolerance analysis and portfolio recommendations.

[0247] Step 6:

[0248] The server monitors financial market data in real time and detects significant fluctuations. If an anomaly or market trend affects the user, an alert is sent to the device.

[0249] Step 7:

[0250] The user inputs a question using natural language through their device. For example, they might ask a specific question like, "What are this month's savings points?"

[0251] Step 8:

[0252] The server uses the natural language processing capabilities of its AI to generate responses to user questions. Based on the analysis results and suggestions, it provides information to the user in an easy-to-understand manner.

[0253] Step 9:

[0254] The terminal displays the response from the server to the user, who then reviews the proposed plan. If necessary, the user can modify the plan or add new settings.

[0255] (Example 1)

[0256] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0257] Modern personal financial management is complex and dynamic, requiring the collection, analysis, and forecasting of appropriate information. However, traditional systems often suffer from insufficient information gathering, or their analysis and recommendations are generic rather than individually optimized. Furthermore, they are inadequate in responding to real-time market fluctuations. As a result, individuals face challenges in making accurate financial decisions.

[0258] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0259] In this invention, the server includes means for collecting economic information, means for analyzing the collected information and identifying the user's economic activity patterns, and means for making future predictions using a generative AI model based on the received data. This makes it possible to provide users with highly personalized savings policies and investment proposals.

[0260] "Economic information" refers to data related to a user's income and expenses, including transaction history, sources of income, and expense details.

[0261] "Analysis" refers to the process of identifying user behavior patterns and trends from collected economic information, and may involve the use of statistical processing and algorithms.

[0262] A "savings policy" refers to a plan that provides specific guidelines for users to appropriately save money for the future.

[0263] "Investment proposals" refer to information that recommends specific and appropriate methods of asset management based on the user's financial situation and market trends.

[0264] "Goods market information" refers to data related to market trends in stocks, foreign exchange, commodities, etc., and includes prices, trading volume, trends, etc.

[0265] A "generative AI model" refers to a technology that uses machine learning algorithms to learn patterns from data and perform future predictions and real-time analysis.

[0266] "Natural language generation technology" refers to the technologies and methods used by computers to generate human language and communicate information in an easily understandable way.

[0267] This invention is a system that supports personal financial management and consists mainly of three elements: user, terminal, and server. First, the user uses a terminal such as a smartphone or computer to collect income and expenditure data. There are two methods of collection: manual input and automatic collection, the latter of which is achieved by linking the terminal with bank accounts or credit card accounts.

[0268] The terminal encrypts the collected economic information and sends it to the server using a security protocol. After receiving the data, the server performs preprocessing such as format conversion and imputation of missing data, and then analyzes it using a generative AI model. This allows the server to identify the user's consumption patterns and characteristics and make future predictions. For example, it can analyze a user's spending over the past three months, detect if a specific category, such as "food expenses," is exceeding the budget, and suggest ways to improve it.

[0269] Based on the analysis results, the server generates savings policies and investment suggestions, and presents them to the user in an easy-to-understand format using natural language generation technology. Specific suggestions include advice such as, "Let's make sure to save money thoroughly until the next payday and then check the results."

[0270] Furthermore, the server monitors market data in real time and sends notifications to the terminal when significant fluctuations occur. This feature gives users the opportunity to review their financial strategies in a timely manner. For example, when the stock market plummets, they may receive a notification saying, "The market is volatile. Please consider reviewing your portfolio."

[0271] Furthermore, users can obtain various information by entering questions in natural language. The server can use generative AI to generate responses to these questions and display them quickly on the terminal. An example of a prompt would be, "Tell me about my spending trends this week."

[0272] This configuration allows the system to provide highly personalized financial management and advisory functions that are easily accessible to users.

[0273] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0274] Step 1:

[0275] Users input income and expense data using devices such as smartphones and computers. The data entered is economic information based on specific amounts and dates, such as purchases and pay stubs. This data is organized by category and stored in a database within the device. In the case of automated collection, the device uses APIs from bank accounts and credit cards to retrieve and collect the latest transaction data.

[0276] Step 2:

[0277] The terminal protects the collected data using encryption technology (e.g., AES encryption) and sends it to the server using a security protocol (e.g., HTTPS). The input data is subject to format conversion before transmission. Specifically, standardization of date formats and currency units is performed, which facilitates analysis on the server.

[0278] Step 3:

[0279] The server receives the transmitted data and first performs data cleaning such as complementing missing data and correcting outliers. This step includes operations such as converting an erroneously entered overly large numerical value to an appropriate range. Once the data cleaning is complete, a generative AI model is prepared and the data is readied for subsequent analysis.

[0280] Step 4:

[0281] The server uses the generative AI model to analyze the clean data. Here, identifying behavioral patterns from past spending histories and spending trends by season are analyzed. Statistical methods and machine learning algorithms are used for data calculations. As the output of the analysis, a report on the user's consumption habits and areas for improvement are extracted.

[0282] Step 5:

[0283] Based on the analysis results, the server generates savings policies and investment proposals beneficial to the user and documents the proposal content in an easy-to-understand form for the user using natural language generation technology. The output text includes specific action plans and recommendations. This document is sent to the terminal so that the user can view it.

[0284] Step 6:

[0285] The server continuously monitors financial market data in real time. When it detects significant fluctuations, it generates notifications and sends them to the terminal. For example, when there are significant market trends, it provides information such as "The market is changing" via push notifications.

[0286] Step 7:

[0287] Users can ask questions in natural language to the system via the terminal. The server inputs the prompt text into the AI model for generating appropriate responses. For example, if the user asks "Tell me about this week's expenses", the server creates a weekly expense summary from the analyzed data, converts it into text, and displays it on the terminal.

[0288] (Application Example 1)

[0289] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0290] In financial management, there is an issue that it is difficult for individual users to accurately grasp their daily expenses and efficiently manage long-term savings and investment plans. Also, regarding fluctuating market information, a system that can respond immediately is required, but it takes time and effort for users to check the information each time. Furthermore, many users hope to smoothly obtain responses to inquiries in natural language, and there is a need to meet such needs.

[0291] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0292] In this invention, the server includes means for collecting financial information data, means for analyzing the collected information and identifying the user's economic activity trends, and means for monitoring market information in real time and notifying the user of important changes. This enables the user to automatically grasp their daily spending and efficiently manage their long-term finances. Furthermore, by responding immediately to fluctuating market information, quick and effective financial decisions become possible. In addition, rapid responses to inquiries in natural language can be obtained, enhancing user convenience.

[0293] "Financial information data" refers to information related to a user's income, expenses, and transactions, which allows for a comprehensive understanding of an individual's economic activities.

[0294] "Analysis" is the process of analyzing collected data and identifying patterns and trends to gain insights into users' economic activities.

[0295] "Economic activity trends" refer to patterns and tendencies in users' income, expenditure, and asset management behaviors, and represent individual financial behavioral habits.

[0296] "Market information" refers to various data related to financial markets, including information on market trends and fluctuations.

[0297] "Natural language" refers to the language that humans use on a daily basis, enabling users to give instructions and make inquiries to the system using ordinary language.

[0298] A "user" refers to an individual who uses this system and seeks to manage or improve their own financial situation.

[0299] "Means" refers to methods or devices used to achieve a specific purpose, and in this system, they enable functions such as the collection, analysis, and notification of various types of data.

[0300] Users input data about their income and expenses using devices such as smartphones and computers. Furthermore, by linking with bank accounts and digital payment services, transaction data can be automatically collected.

[0301] The terminal has the ability to encrypt collected financial information data and securely transmit it to the server using security protocols. The server has a generative AI model implemented, which is used to perform detailed analysis of the data. The server identifies the user's income and expenditure trends and generates savings policies and investment proposals based on them.

[0302] Furthermore, the server monitors financial market information in real time and immediately sends notifications to the user's terminal when significant market changes occur. This notification function allows users to make necessary financial decisions quickly.

[0303] Furthermore, users can query the system using natural language, and the server uses generative AI to return appropriate responses in real time. These responses are based on the user's specific financial situation and include detailed explanations and predictive information.

[0304] As a concrete example, if a user inputs "Tell me about my spending this month" into the terminal, the server uses a generative AI model to analyze the spending data and returns advice to the terminal such as, "Your spending on food and beverages has increased by 10% this month. We recommend reviewing your budget for next month." In this way, this invention provides users with high convenience and effective financial management.

[0305] Examples of prompts for generative AI models

[0306] Based on the user's spending data, analyze their spending trends for the current month and generate specific advice for saving money. For example, include specific comments on increases or decreases in dining out expenses.

[0307] As described above, this system can streamline financial management and provide optimal financial advice to users.

[0308] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0309] Step 1:

[0310] The user uses a smartphone or computer to input data related to income and expenses. The input data includes daily living expenses and income information. Furthermore, the user can also automatically obtain transaction data by linking with a bank account or digital payment service. By inputting this data, the basic information necessary for financial management is aggregated on the terminal.

[0311] Step 2:

[0312] The terminal encrypts the collected financial information data and transmits it to the server using a security protocol. In this process, encryption technologies such as SSL / TLS are used to ensure secure data transfer. The input is the encrypted financial information data, and the output is the data that is securely delivered to the server through a secure communication channel.

[0313] Step 3:

[0314] The server decrypts the received encrypted data and performs data analysis using a generated AI model. In this analysis, data mining techniques are used to identify the user's income and expenditure trends and spending habits. The input of the analysis is the decrypted financial information data, and the output is a detailed report on the user's economic activity trends and spending patterns.

[0315] Step 4:

[0316] The server generates appropriate savings policies and investment proposals for the user based on the analysis results. This generation process applies machine learning algorithms to create personalized suggestions optimized for each user. The input is trend data on economic activity, and the output is specific savings and investment proposals.

[0317] Step 5:

[0318] The server monitors financial market information in real time and, if significant market changes occur, immediately sends notifications to the user's terminal as needed. This monitoring uses an API to ingest market data and detect anomalies or significant fluctuations. The input is market information data, and the output is a fluctuation information alert.

[0319] Step 6:

[0320] Users can input questions into the terminal using natural language. The server receives these questions, generates appropriate responses using a generative AI model, and sends them back to the user in real time. This process utilizes natural language processing technology to accurately understand the user's intent and provide answers. The input is the user's question text, and the output is the generated response message.

[0321] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0322] As an embodiment of this invention, a personal financial management system incorporating an emotion engine consists of three main components: a user, a terminal, and a server.

[0323] First, users input information about their income and expenses using devices such as smartphones or computers. These devices can be linked to bank accounts and credit cards to automatically collect transaction data. Furthermore, users can interact with the system using voice or text input.

[0324] Next, the collected data is sent to the server via the terminal. The server contains a generative AI model and an emotion engine. The generative AI model analyzes income and expenditure data to identify the user's economic activity patterns. This allows for personalized savings plans and investment suggestions.

[0325] Meanwhile, the emotion engine analyzes voice and text data obtained from the user to recognize the user's emotional state. Based on this recognition, the server generates optimal financial advice that reflects the user's emotional state. For example, if it detects that the user is stressed, it may recommend low-risk investment options or suggest mitigation measures to save money.

[0326] The server sends suggestions generated based on analysis results and sentiment analysis to the terminal. The terminal notifies the user in real time, enabling the user to take action quickly.

[0327] Furthermore, users can ask questions about asset management and spending in natural language and receive responses. For example, in response to a specific question such as "Please give me saving suggestions based on my current emotional state," the system will provide advice tailored to the user's emotions.

[0328] In this way, a system incorporating an emotion engine can comprehensively consider the user's economic and emotional state and support individually optimized financial management.

[0329] The following describes the processing flow.

[0330] Step 1:

[0331] Users enter information about their income and expenses into the application using their device. Users also set up automatic collection of transaction data by linking their bank accounts and credit cards to their device.

[0332] Step 2:

[0333] Users input information about their daily emotional state via voice or text into their device. This data is used for processing by the emotion engine.

[0334] Step 3:

[0335] The device encrypts the income, expenditure, and sentiment input data it collects and sends it to the server using a secure communication protocol. The device performs a basic integrity check on the data before transmission.

[0336] Step 4:

[0337] The server stores the received transaction data in the database. Duplicate data removal and data integrity checks are performed.

[0338] Step 5:

[0339] The server applies a generative AI model to transaction data to analyze the user's income and expenditure patterns. From the resulting analysis, it identifies the user's usual spending and savings trends.

[0340] Step 6:

[0341] The server's emotion engine analyzes the user's voice and text data to identify the user's current emotional state. For example, if the user indicates stress, the result is recorded.

[0342] Step 7:

[0343] The server integrates the results of income and expenditure data analysis with sentiment analysis to generate savings plans and investment suggestions that take the user's emotional state into account. Specific examples include saving methods that consider relaxation and low-risk investment suggestions.

[0344] Step 8:

[0345] The server sends the generated financial advice and plan to the terminal. The terminal displays this information on the user's screen, making it accessible to the user.

[0346] Step 9:

[0347] When a user inputs a natural language question through their device, the server generates a sentiment-sensitive response to the question and sends it to the user via the device. For example, it might answer a question like, "I'm feeling anxious right now, how should I protect my assets?"

[0348] Through this series of steps, the system can comprehensively manage the user's financial and emotional state and provide individually optimized advice.

[0349] (Example 2)

[0350] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0351] In personal financial management, it has been difficult to provide advice that not only analyzes income and expenditure patterns but also takes into account a person's emotional state. Furthermore, there was a lack of real-time information to quickly respond to market fluctuations and make optimal financial choices. Additionally, there was a problem with the lack of individualization when developing savings and investment plans tailored to individual user goals, as the influence of emotions was not considered.

[0352] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0353] In this invention, the server includes means for using a generative model to analyze income and expenditure data and identify the user's economic activity patterns; means for analyzing voice and text data to recognize the user's emotional state; and means for generating individual savings plans and investment proposals for the user based on the analysis results and emotional state. This makes it possible to provide individually optimized financial management that comprehensively considers the user's economic activities and emotional state.

[0354] "Income and expenditure information" refers to all the benefits a user receives and all the expenses they incur, and is data that indicates an individual's financial status.

[0355] A "generative model" refers to an algorithm that analyzes specific patterns based on collected data and generates new analytical results.

[0356] "Voice and text data" refers to data in the form of spoken or written language entered by users, and is fundamental information that represents the user's intentions and emotions.

[0357] "Emotional state" refers to the psychological or emotional condition a user is in, including feelings such as anxiety and joy.

[0358] "Savings plans and investment proposals" refer to asset management and investment plans recommended to help users achieve their future financial goals.

[0359] "Market data" refers to information about fluctuations in financial markets such as stock prices, exchange rates, and interest rates, which can influence financial decisions.

[0360] "Natural language queries" refer to questions and requests that users make to a system using everyday language.

[0361] In an embodiment of this invention, the personal financial management system consists of three main components: a user, a terminal, and a server. The user inputs information about their income and expenses using a terminal such as a smartphone or computer. The terminal is equipped with software that links with bank accounts and financial institutions to automatically collect transaction data. The user can input information interactively into the system using voice and text.

[0362] Financial information collected by the terminal is sent to a server. This server houses a generative AI model that analyzes the user's income and expenditure data to identify economic activity patterns. The analysis utilizes models employing time series analysis and machine learning techniques.

[0363] Furthermore, the server is equipped with an emotion engine that analyzes voice and text data to recognize the user's emotional state. This engine uses natural language processing and voice emotion analysis algorithms to understand the user's psychological state and generate advice based on that state.

[0364] The server combines analyzed economic data with the user's emotional state to generate personalized savings plans and investment suggestions. These suggestions reflect the user's current emotional state and include recommendations that consider appropriate risk levels. For example, if a user asks, "How much should I save this month?", the server can provide a specific amount based on the user's individual circumstances.

[0365] As a concrete example, a prompt might be written as, "If the system determines that the user is experiencing stress, what investment strategy would be recommended?" By inputting this prompt into the AI ​​model on the server, the system will suggest the optimal investment strategy tailored to the user's situation.

[0366] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0367] Step 1:

[0368] Users input income and expense information using devices such as smartphones and computers. These devices connect with bank accounts and financial institutions, automatically collecting and inputting transaction data. The input data includes salary, food expenses, rent, etc., and this data is automatically categorized and organized on the device.

[0369] Step 2:

[0370] Data collected by the device is sent to the server. The server receives this information as input and uses a generative AI model to analyze the user's income and expenditure data. Specifically, it performs data calculations to identify the user's past income and expenditure patterns through time series analysis and predict future financial conditions. As output, the user's economic activity patterns are identified.

[0371] Step 3:

[0372] The server receives voice and text data sent by the user and activates the emotion engine to analyze the emotional state. This process analyzes the tone of voice and emotional expressions contained in the text, and processes the data to recognize emotional states such as anxiety and joy. As a result of the analysis, the user's emotional state is output.

[0373] Step 4:

[0374] The server integrates analysis results from the generation AI model and the emotion engine to generate personalized financial advice for the user. Specifically, it creates appropriate savings plans and investment suggestions based on the user's current financial situation and emotional state. For example, it may recommend low-risk investments or suggest specific ways to save money. The output is a personalized savings and investment plan for the user.

[0375] Step 5:

[0376] The server sends the generated suggestions to the terminal, which then notifies the user in real time. Notifications are sent via push notifications or email, allowing the user to immediately review and take action. Furthermore, the user can obtain additional information and advice by sending prompts such as "How much have I saved this month?" or "Tell me your investment strategy."

[0377] (Application Example 2)

[0378] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0379] Modern individuals need to manage their finances amidst complex economic conditions and emotional fluctuations. However, current financial management systems lack an approach based on individual emotions, making it difficult to provide advice tailored to individual circumstances. Therefore, there is a need for individually optimized financial management that takes into account the user's emotional state.

[0380] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0381] In this invention, the server includes means for collecting income and expenditure information, means for identifying an individual's economic activity patterns, and means for generating individual savings plans and investment proposals. This enables comprehensive financial management that takes into account an individual's emotional state.

[0382] "Income and expenditure information" refers to data on income and expenditures related to an individual's financial activities, and is fundamental information for understanding an individual's economic situation.

[0383] An "economic activity pattern" comprehensively represents an individual's income and expenditure trends and habits, serving as the basis for individual financial planning and proposals.

[0384] "Savings plans and investment proposals" refer to specific suggestions to help optimize savings allocation and asset growth based on an individual's financial situation and emotional state.

[0385] "Economic market information" refers to the latest data related to financial and stock markets, and is important information that should be considered when making individual investment decisions.

[0386] "Natural language queries" refer to questions and requests that individuals make to a system using everyday language, which facilitates smooth interaction with the system.

[0387] "Emotional state" refers to an individual's feelings and psychological condition, and is a factor that enables appropriate financial advice to be provided based on this state.

[0388] An "information processing system" refers to a technical framework that includes a series of hardware and software components for analyzing collected data and generating proposals.

[0389] To implement this invention, an information processing system is constructed to support personal financial management. The system collects income and expenditure information from the user's smartphone, computer, or other terminal and transmits it to a server. This information is automatically acquired through cooperation with financial institutions and credit agencies.

[0390] The server is equipped with a generative AI model that uses Google Cloud Natural Language API and TensorFlow to analyze the collected information. This generative AI model analyzes economic activity patterns and provides personalized savings plans and investment suggestions. Furthermore, an emotion analysis engine evaluates the user's voice or text data to identify their emotional state. Based on this emotional state, the server provides personalized financial advice.

[0391] The terminal notifies the user of suggestions from the server in real time, allowing the user to receive feedback quickly. Users can also ask questions about finances and emotions using natural language and receive responses from a generative AI model.

[0392] For example, if the system detects stress in the user, it will recommend low-risk investment options. By prompting the user with questions like, "What big purchase would I feel comfortable making right now?", the system can provide personalized information. This approach enables comprehensive financial management that takes the user's emotional state into account.

[0393] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0394] Step 1:

[0395] The user's device collects income and expenditure information from the user. This information is automatically obtained through collaboration with financial institutions and credit agencies. The input is the user's transaction information, and the output is the preparation of data for transmission to the server. Specifically, the device accesses the financial institution's API via the internet and securely downloads the transaction information.

[0396] Step 2:

[0397] The server receives income and expenditure information sent from the terminal. The input is financial data sent from the terminal, and the output is ready for analysis. At this point, the server verifies the integrity of the data and saves it to the database for analysis. During this process, duplicate data is removed and the format is normalized.

[0398] Step 3:

[0399] The server analyzes the collected information using a generative AI model to identify the user's economic activity patterns. The input is normalized financial data, and the output is the result of the economic activity analysis. Specifically, the AI ​​model uses machine learning algorithms to identify past spending patterns and trends, and generates numerical data and graphs of the analysis results.

[0400] Step 4:

[0401] The server uses an emotion analysis engine to analyze the user's emotional state. The input is voice or text data from the user, and the output is the emotion analysis result. In this process, speech recognition and natural language processing technologies are used to analyze the tone of the user's voice and the context in which it is used, and the emotional state is numerically evaluated.

[0402] Step 5:

[0403] The server generates personalized savings plans and investment proposals based on a generated AI model and sentiment analysis results. Inputs are the results of economic activity analysis and sentiment analysis, while output is customized financial advice. The server calculates investment options based on risk profiles and short-term and long-term goals, and sends the results to the terminal.

[0404] Step 6:

[0405] The user's device receives suggestions sent from the server and notifies the user. The input is financial advice from the server, and the output is a notification to the user. Specifically, the device displays notifications to the user in real time through the app's UI and collects user feedback as needed.

[0406] Step 7:

[0407] The user asks additional questions or inquiries using natural language, and the server generates a response using a generative AI model based on the prompt text. The input is the prompt text from the user, and the output is the response from the generative AI model. Specifically, the server analyzes the user's question, prepares an intelligent response that takes into account past data and the current situation, and immediately sends it to the user.

[0408] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0409] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0410] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0411] [Third Embodiment]

[0412] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0413] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0414] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0415] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0416] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0417] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0418] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0419] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0420] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0421] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0422] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0423] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0424] In one embodiment of this invention, a system for supporting personal financial management is implemented in a form that includes three main components: a user, a terminal, and a server.

[0425] First, users input their income and expense data using devices such as smartphones or computers. This includes entering daily shopping and payroll information. It's also possible to automatically collect transaction data by linking bank accounts and credit card accounts to the device.

[0426] Next, the collected data is sent to the server via the terminal. The data is encrypted and securely transferred using advanced security protocols. The server has a generative AI model implemented, which is used to analyze the data.

[0427] The server analyzes the received data to identify the user's income and expenditure patterns and spending habits. Based on these results, it generates optimal savings plans and investment suggestions for the user. For example, it provides specific plans tailored to individual financial goals, such as monthly savings targets or participation in automated investment programs.

[0428] Furthermore, the server has the ability to monitor financial market trends in real time and send notifications to the terminal when there are significant market fluctuations that could affect the user. This allows users to make necessary financial decisions quickly.

[0429] Furthermore, users can input various questions into the system using natural language. The server uses generative AI to generate appropriate responses in real time based on these inputs and provides them to the user. For example, a question such as "Tell me about my spending patterns this month" can be answered with a detailed analysis result.

[0430] In this way, the invention can be implemented as a system that provides user-friendly and highly personalized financial management and advisory functions.

[0431] The following describes the processing flow.

[0432] Step 1:

[0433] Users use their devices to input income and expense information into the application. Users link their bank accounts and credit cards to their devices and set up automatic collection of transaction data.

[0434] Step 2:

[0435] The terminal encrypts the transaction data it collects and sends it to the server via a secure communication protocol. The terminal verifies the reliability of the data and performs error checking.

[0436] Step 3:

[0437] The server saves the received data to the database. A process is implemented to filter out duplicate data and ensure data consistency and integrity.

[0438] Step 4:

[0439] The server analyzes stored data using an AI model. It understands the user's income and expenditure patterns and identifies unusual spending and savings trends.

[0440] Step 5:

[0441] The server generates personalized savings plans and investment suggestions for the user based on the analysis results. This process includes risk tolerance analysis and portfolio recommendations.

[0442] Step 6:

[0443] The server monitors financial market data in real time and detects significant fluctuations. If an anomaly or market trend affects the user, an alert is sent to the device.

[0444] Step 7:

[0445] The user inputs a question using natural language through their device. For example, they might ask a specific question like, "What are this month's savings points?"

[0446] Step 8:

[0447] The server uses the natural language processing capabilities of its AI to generate responses to user questions. Based on the analysis results and suggestions, it provides information to the user in an easy-to-understand manner.

[0448] Step 9:

[0449] The terminal displays the response from the server to the user, who then reviews the proposed plan. If necessary, the user can modify the plan or add new settings.

[0450] (Example 1)

[0451] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0452] Modern personal financial management is complex and dynamic, requiring the collection, analysis, and forecasting of appropriate information. However, traditional systems often suffer from insufficient information gathering, or their analysis and recommendations are generic rather than individually optimized. Furthermore, they are inadequate in responding to real-time market fluctuations. As a result, individuals face challenges in making accurate financial decisions.

[0453] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0454] In this invention, the server includes means for collecting economic information, means for analyzing the collected information and identifying the user's economic activity patterns, and means for making future predictions using a generative AI model based on the received data. This makes it possible to provide users with highly personalized savings policies and investment proposals.

[0455] "Economic information" refers to data related to a user's income and expenses, including transaction history, sources of income, and expense details.

[0456] "Analysis" refers to the process of identifying user behavior patterns and trends from collected economic information, and may involve the use of statistical processing and algorithms.

[0457] A "savings policy" refers to a plan that provides specific guidelines for users to appropriately save money for the future.

[0458] "Investment proposals" refer to information that recommends specific and appropriate methods of asset management based on the user's financial situation and market trends.

[0459] "Goods market information" refers to data related to market trends in stocks, foreign exchange, commodities, etc., and includes prices, trading volume, trends, etc.

[0460] A "generative AI model" refers to a technology that uses machine learning algorithms to learn patterns from data and perform future predictions and real-time analysis.

[0461] "Natural language generation technology" refers to the technologies and methods used by computers to generate human language and communicate information in an easily understandable way.

[0462] This invention is a system that supports personal financial management and consists mainly of three elements: user, terminal, and server. First, the user uses a terminal such as a smartphone or computer to collect income and expenditure data. There are two methods of collection: manual input and automatic collection, the latter of which is achieved by linking the terminal with bank accounts or credit card accounts.

[0463] The terminal encrypts the collected economic information and sends it to the server using a security protocol. After receiving the data, the server performs preprocessing such as format conversion and imputation of missing data, and then analyzes it using a generative AI model. This allows the server to identify the user's consumption patterns and characteristics and make future predictions. For example, it can analyze a user's spending over the past three months, detect if a specific category, such as "food expenses," is exceeding the budget, and suggest ways to improve it.

[0464] Based on the analysis results, the server generates savings policies and investment suggestions, and presents them to the user in an easy-to-understand format using natural language generation technology. Specific suggestions include advice such as, "Let's make sure to save money thoroughly until the next payday and then check the results."

[0465] Furthermore, the server monitors market data in real time and sends notifications to the terminal when significant fluctuations occur. This feature gives users the opportunity to review their financial strategies in a timely manner. For example, when the stock market plummets, they may receive a notification saying, "The market is volatile. Please consider reviewing your portfolio."

[0466] Furthermore, users can obtain various information by entering questions in natural language. The server can use generative AI to generate responses to these questions and display them quickly on the terminal. An example of a prompt would be, "Tell me about my spending trends this week."

[0467] This configuration allows the system to provide highly personalized financial management and advisory functions that are easily accessible to users.

[0468] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0469] Step 1:

[0470] Users input income and expense data using devices such as smartphones and computers. The data entered is economic information based on specific amounts and dates, such as purchases and pay stubs. This data is organized by category and stored in a database within the device. In the case of automated collection, the device uses APIs from bank accounts and credit cards to retrieve and collect the latest transaction data.

[0471] Step 2:

[0472] The terminal protects the collected data using encryption technology (e.g., AES encryption) and sends it to the server using a security protocol (e.g., HTTPS). Input data undergoes format conversion before transmission. Specifically, date formats and currency units are standardized, making analysis on the server easier.

[0473] Step 3:

[0474] The server receives the transmitted data and first performs data cleaning, such as imputing missing data and correcting outliers. This step includes operations such as converting incorrectly entered, excessively large numbers to an appropriate range. Once the data cleaning is complete, a generative AI model is prepared, and the data is ready for subsequent analysis.

[0475] Step 4:

[0476] The server uses a generative AI model to analyze clean data. This involves identifying behavioral patterns from past spending history and analyzing seasonal spending trends. Statistical methods and machine learning algorithms are used for data processing. The analysis output includes reports on user consumption habits and suggestions for improvement.

[0477] Step 5:

[0478] Based on the analysis results, the server generates beneficial savings policies and investment proposals for the user, and documents the proposals in an easy-to-understand format using natural language generation technology. The output text includes specific action plans and recommendations. This document is sent to the terminal for the user to view.

[0479] Step 6:

[0480] The server continuously monitors goods market data in real time and generates and sends notifications to terminals when it detects significant changes. For example, if there are important market trends, it will provide information such as "The market is changing" via push notification.

[0481] Step 7:

[0482] Users can ask the system questions in natural language via their terminal. The server inputs the prompt into an AI model that generates appropriate responses. For example, if a user asks, "Tell me my expenses for this week," the server will create a weekly expense summary from the analyzed data, convert it to text, and display it on the terminal.

[0483] (Application Example 1)

[0484] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0485] In financial management, there are challenges in accurately tracking daily expenses and efficiently managing long-term savings and investment plans for individual users. Furthermore, while systems capable of responding immediately to fluctuating market information are needed, users currently face the time and effort required to check this information themselves. Additionally, many users desire smooth responses to inquiries in natural language, and meeting these needs is essential.

[0486] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0487] In this invention, the server includes means for collecting financial information data, means for analyzing the collected information and identifying the user's economic activity trends, and means for monitoring market information in real time and notifying the user of important changes. This enables the user to automatically grasp their daily spending and efficiently manage their long-term finances. Furthermore, by responding immediately to fluctuating market information, quick and effective financial decisions become possible. In addition, rapid responses to inquiries in natural language can be obtained, enhancing user convenience.

[0488] "Financial information data" refers to information related to a user's income, expenses, and transactions, which allows for a comprehensive understanding of an individual's economic activities.

[0489] "Analysis" is the process of analyzing collected data and identifying patterns and trends to gain insights into users' economic activities.

[0490] "Economic activity trends" refer to patterns and tendencies in users' income, expenditure, and asset management behaviors, and represent individual financial behavioral habits.

[0491] "Market information" refers to various data related to financial markets, including information on market trends and fluctuations.

[0492] "Natural language" refers to the language that humans use on a daily basis, enabling users to give instructions and make inquiries to the system using ordinary language.

[0493] A "user" refers to an individual who uses this system and seeks to manage or improve their own financial situation.

[0494] "Means" refers to methods or devices used to achieve a specific purpose, and in this system, they enable functions such as the collection, analysis, and notification of various types of data.

[0495] Users input data about their income and expenses using devices such as smartphones and computers. Furthermore, by linking with bank accounts and digital payment services, transaction data can be automatically collected.

[0496] The terminal has the ability to encrypt collected financial information data and securely transmit it to the server using security protocols. The server has a generative AI model implemented, which is used to perform detailed analysis of the data. The server identifies the user's income and expenditure trends and generates savings policies and investment proposals based on them.

[0497] Furthermore, the server monitors financial market information in real time and immediately sends notifications to the user's terminal when significant market changes occur. This notification function allows users to make necessary financial decisions quickly.

[0498] Furthermore, users can query the system using natural language, and the server uses generative AI to return appropriate responses in real time. These responses are based on the user's specific financial situation and include detailed explanations and predictive information.

[0499] As a concrete example, if a user inputs "Tell me about my spending this month" into the terminal, the server uses a generative AI model to analyze the spending data and returns advice to the terminal such as, "Your spending on food and beverages has increased by 10% this month. We recommend reviewing your budget for next month." In this way, this invention provides users with high convenience and effective financial management.

[0500] Examples of prompts for generative AI models

[0501] Based on the user's spending data, analyze their spending trends for the current month and generate specific advice for saving money. For example, include specific comments on increases or decreases in dining out expenses.

[0502] Therefore, this system can streamline financial management and provide users with optimal financial advice.

[0503] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0504] Step 1:

[0505] Users input income and expense data using their smartphones or computers. This data includes daily living expenses and earnings information. Furthermore, users can automatically retrieve transaction data by linking their bank accounts and digital payment services. This data input allows the device to accumulate the basic information necessary for financial management.

[0506] Step 2:

[0507] The terminal encrypts the collected financial information data and sends it to the server using a security protocol. This process uses encryption technologies such as SSL / TLS to ensure the secure transfer of data. The input is encrypted financial information data, and the output is data securely delivered to the server via a secure communication path.

[0508] Step 3:

[0509] The server decrypts the received encrypted data and performs data analysis using a generative AI model. This analysis uses data mining techniques to identify the user's income and expenditure trends and spending habits. The input to the analysis is the decrypted financial information data, and the output is a detailed report of the user's economic activity trends and spending patterns.

[0510] Step 4:

[0511] The server generates appropriate savings policies and investment proposals for the user based on the analysis results. This generation process applies machine learning algorithms to create personalized suggestions optimized for each user. The input is trend data on economic activity, and the output is specific savings and investment proposals.

[0512] Step 5:

[0513] The server monitors financial market information in real time and, if significant market changes occur, immediately sends notifications to the user's terminal as needed. This monitoring uses an API to ingest market data and detect anomalies or significant fluctuations. The input is market information data, and the output is a fluctuation information alert.

[0514] Step 6:

[0515] Users can input questions into the terminal using natural language. The server receives these questions, generates appropriate responses using a generative AI model, and sends them back to the user in real time. This process utilizes natural language processing technology to accurately understand the user's intent and provide answers. The input is the user's question text, and the output is the generated response message.

[0516] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0517] As an embodiment of this invention, a personal financial management system incorporating an emotion engine consists of three main components: a user, a terminal, and a server.

[0518] First, users input information about their income and expenses using devices such as smartphones or computers. These devices can be linked to bank accounts and credit cards to automatically collect transaction data. Furthermore, users can interact with the system using voice or text input.

[0519] Next, the collected data is sent to the server via the terminal. The server contains a generative AI model and an emotion engine. The generative AI model analyzes income and expenditure data to identify the user's economic activity patterns. This allows for personalized savings plans and investment suggestions.

[0520] Meanwhile, the emotion engine analyzes voice and text data obtained from the user to recognize the user's emotional state. Based on this recognition, the server generates optimal financial advice that reflects the user's emotional state. For example, if it detects that the user is stressed, it may recommend low-risk investment options or suggest mitigation measures to save money.

[0521] The server sends suggestions generated based on analysis results and sentiment analysis to the terminal. The terminal notifies the user in real time, enabling the user to take action quickly.

[0522] Furthermore, users can ask questions about asset management and spending in natural language and receive responses. For example, in response to a specific question such as "Please give me saving suggestions based on my current emotional state," the system will provide advice tailored to the user's emotions.

[0523] In this way, a system incorporating an emotion engine can comprehensively consider the user's economic and emotional state and support individually optimized financial management.

[0524] The following describes the processing flow.

[0525] Step 1:

[0526] Users enter information about their income and expenses into the application using their device. Users also set up automatic collection of transaction data by linking their bank accounts and credit cards to their device.

[0527] Step 2:

[0528] Users input information about their daily emotional state via voice or text into their device. This data is used for processing by the emotion engine.

[0529] Step 3:

[0530] The device encrypts the income, expenditure, and sentiment input data it collects and sends it to the server using a secure communication protocol. The device performs a basic integrity check on the data before transmission.

[0531] Step 4:

[0532] The server stores the received transaction data in the database. Duplicate data removal and data integrity checks are performed.

[0533] Step 5:

[0534] The server applies a generative AI model to transaction data to analyze the user's income and expenditure patterns. From the resulting analysis, it identifies the user's usual spending and savings trends.

[0535] Step 6:

[0536] The server's emotion engine analyzes the user's voice and text data to identify the user's current emotional state. For example, if the user indicates stress, the result is recorded.

[0537] Step 7:

[0538] The server integrates the results of income and expenditure data analysis with sentiment analysis to generate savings plans and investment suggestions that take the user's emotional state into account. Specific examples include saving methods that consider relaxation and low-risk investment suggestions.

[0539] Step 8:

[0540] The server sends the generated financial advice and plan to the terminal. The terminal displays this information on the user's screen, making it accessible to the user.

[0541] Step 9:

[0542] When a user inputs a natural language question through their device, the server generates a sentiment-sensitive response to the question and sends it to the user via the device. For example, it might answer a question like, "I'm feeling anxious right now, how should I protect my assets?"

[0543] Through this series of steps, the system can comprehensively manage the user's financial and emotional state and provide individually optimized advice.

[0544] (Example 2)

[0545] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0546] In personal financial management, it has been difficult to provide advice that not only analyzes income and expenditure patterns but also takes into account a person's emotional state. Furthermore, there was a lack of real-time information to quickly respond to market fluctuations and make optimal financial choices. Additionally, there was a problem with the lack of individualization when developing savings and investment plans tailored to individual user goals, as the influence of emotions was not considered.

[0547] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0548] In this invention, the server includes means for using a generative model to analyze income and expenditure data and identify the user's economic activity patterns; means for analyzing voice and text data to recognize the user's emotional state; and means for generating individual savings plans and investment proposals for the user based on the analysis results and emotional state. This makes it possible to provide individually optimized financial management that comprehensively considers the user's economic activities and emotional state.

[0549] "Income and expenditure information" refers to all the benefits a user receives and all the expenses they incur, and is data that indicates an individual's financial status.

[0550] A "generative model" refers to an algorithm that analyzes specific patterns based on collected data and generates new analytical results.

[0551] "Voice and text data" refers to data in the form of spoken or written language entered by users, and is fundamental information that represents the user's intentions and emotions.

[0552] "Emotional state" refers to the psychological or emotional condition a user is in, including feelings such as anxiety and joy.

[0553] "Savings plans and investment proposals" refer to asset management and investment plans recommended to help users achieve their future financial goals.

[0554] "Market data" refers to information about fluctuations in financial markets such as stock prices, exchange rates, and interest rates, which can influence financial decisions.

[0555] "Natural language queries" refer to questions and requests that users make to a system using everyday language.

[0556] In an embodiment of this invention, the personal financial management system consists of three main components: a user, a terminal, and a server. The user inputs information about their income and expenses using a terminal such as a smartphone or computer. The terminal is equipped with software that links with bank accounts and financial institutions to automatically collect transaction data. The user can input information interactively into the system using voice and text.

[0557] Financial information collected by the terminal is sent to a server. This server houses a generative AI model that analyzes the user's income and expenditure data to identify economic activity patterns. The analysis utilizes models employing time series analysis and machine learning techniques.

[0558] Furthermore, the server is equipped with an emotion engine that analyzes voice and text data to recognize the user's emotional state. This engine uses natural language processing and voice emotion analysis algorithms to understand the user's psychological state and generate advice based on that state.

[0559] The server combines analyzed economic data with the user's emotional state to generate personalized savings plans and investment suggestions. These suggestions reflect the user's current emotional state and include recommendations that consider appropriate risk levels. For example, if a user asks, "How much should I save this month?", the server can provide a specific amount based on the user's individual circumstances.

[0560] As a concrete example, a prompt might be written as, "If the system determines that the user is experiencing stress, what investment strategy would be recommended?" By inputting this prompt into the AI ​​model on the server, the system will suggest the optimal investment strategy tailored to the user's situation.

[0561] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0562] Step 1:

[0563] Users input income and expense information using devices such as smartphones and computers. These devices connect with bank accounts and financial institutions, automatically collecting and inputting transaction data. The input data includes salary, food expenses, rent, etc., and this data is automatically categorized and organized on the device.

[0564] Step 2:

[0565] Data collected by the device is sent to the server. The server receives this information as input and uses a generative AI model to analyze the user's income and expenditure data. Specifically, it performs data calculations to identify the user's past income and expenditure patterns through time series analysis and predict future financial conditions. As output, the user's economic activity patterns are identified.

[0566] Step 3:

[0567] The server receives voice and text data sent by the user and activates the emotion engine to analyze the emotional state. This process analyzes the tone of voice and emotional expressions contained in the text, and processes the data to recognize emotional states such as anxiety and joy. As a result of the analysis, the user's emotional state is output.

[0568] Step 4:

[0569] The server integrates analysis results from the generation AI model and the emotion engine to generate personalized financial advice for the user. Specifically, it creates appropriate savings plans and investment suggestions based on the user's current financial situation and emotional state. For example, it may recommend low-risk investments or suggest specific ways to save money. The output is a personalized savings and investment plan for the user.

[0570] Step 5:

[0571] The server sends the generated suggestions to the terminal, which then notifies the user in real time. Notifications are sent via push notifications or email, allowing the user to immediately review and take action. Furthermore, the user can obtain additional information and advice by sending prompts such as "How much have I saved this month?" or "Tell me your investment strategy."

[0572] (Application Example 2)

[0573] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0574] Modern individuals need to manage their finances amidst complex economic conditions and emotional fluctuations. However, current financial management systems lack an approach based on individual emotions, making it difficult to provide advice tailored to individual circumstances. Therefore, there is a need for individually optimized financial management that takes into account the user's emotional state.

[0575] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0576] In this invention, the server includes means for collecting income and expenditure information, means for identifying an individual's economic activity patterns, and means for generating individual savings plans and investment proposals. This enables comprehensive financial management that takes into account an individual's emotional state.

[0577] "Income and expenditure information" refers to data on income and expenditures related to an individual's financial activities, and is fundamental information for understanding an individual's economic situation.

[0578] An "economic activity pattern" comprehensively represents an individual's income and expenditure trends and habits, serving as the basis for individual financial planning and proposals.

[0579] "Savings plans and investment proposals" refer to specific suggestions to help optimize savings allocation and asset growth based on an individual's financial situation and emotional state.

[0580] "Economic market information" refers to the latest data related to financial and stock markets, and is important information that should be considered when making individual investment decisions.

[0581] "Natural language queries" refer to questions and requests that individuals make to a system using everyday language, which facilitates smooth interaction with the system.

[0582] "Emotional state" refers to an individual's feelings and psychological condition, and is a factor that enables appropriate financial advice to be provided based on this state.

[0583] An "information processing system" refers to a technical framework that includes a series of hardware and software components for analyzing collected data and generating proposals.

[0584] To implement this invention, an information processing system is constructed to support personal financial management. The system collects income and expenditure information from the user's smartphone, computer, or other terminal and transmits it to a server. This information is automatically acquired through cooperation with financial institutions and credit agencies.

[0585] The server is equipped with a generative AI model that uses Google Cloud Natural Language API and TensorFlow to analyze the collected information. This generative AI model analyzes economic activity patterns and provides personalized savings plans and investment suggestions. Furthermore, an emotion analysis engine evaluates the user's voice or text data to identify their emotional state. Based on this emotional state, the server provides personalized financial advice.

[0586] The terminal notifies the user of suggestions from the server in real time, allowing the user to receive feedback quickly. Users can also ask questions about finances and emotions using natural language and receive responses from a generative AI model.

[0587] For example, if the system detects stress in the user, it will recommend low-risk investment options. By prompting the user with questions like, "What big purchase would I feel comfortable making right now?", the system can provide personalized information. This approach enables comprehensive financial management that takes the user's emotional state into account.

[0588] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0589] Step 1:

[0590] The user's device collects income and expenditure information from the user. This information is automatically obtained through collaboration with financial institutions and credit agencies. The input is the user's transaction information, and the output is the preparation of data for transmission to the server. Specifically, the device accesses the financial institution's API via the internet and securely downloads the transaction information.

[0591] Step 2:

[0592] The server receives income and expenditure information sent from the terminal. The input is financial data sent from the terminal, and the output is ready for analysis. At this point, the server verifies the integrity of the data and saves it to the database for analysis. During this process, duplicate data is removed and the format is normalized.

[0593] Step 3:

[0594] The server analyzes the collected information using a generative AI model to identify the user's economic activity patterns. The input is normalized financial data, and the output is the result of the economic activity analysis. Specifically, the AI ​​model uses machine learning algorithms to identify past spending patterns and trends, and generates numerical data and graphs of the analysis results.

[0595] Step 4:

[0596] The server uses an emotion analysis engine to analyze the user's emotional state. The input is voice or text data from the user, and the output is the emotion analysis result. In this process, speech recognition and natural language processing technologies are used to analyze the tone of the user's voice and the context in which it is used, and the emotional state is numerically evaluated.

[0597] Step 5:

[0598] The server generates personalized savings plans and investment proposals based on a generated AI model and sentiment analysis results. Inputs are the results of economic activity analysis and sentiment analysis, while output is customized financial advice. The server calculates investment options based on risk profiles and short-term and long-term goals, and sends the results to the terminal.

[0599] Step 6:

[0600] The user's device receives suggestions sent from the server and notifies the user. The input is financial advice from the server, and the output is a notification to the user. Specifically, the device displays notifications to the user in real time through the app's UI and collects user feedback as needed.

[0601] Step 7:

[0602] The user asks additional questions or inquiries using natural language, and the server generates a response using a generative AI model based on the prompt text. The input is the prompt text from the user, and the output is the response from the generative AI model. Specifically, the server analyzes the user's question, prepares an intelligent response that takes into account past data and the current situation, and immediately sends it to the user.

[0603] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0604] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0605] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0606] [Fourth Embodiment]

[0607] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0608] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0609] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0610] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0611] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0612] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0613] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0614] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0615] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0616] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0617] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0618] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0619] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0620] In one embodiment of this invention, a system for supporting personal financial management is implemented in a form that includes three main components: a user, a terminal, and a server.

[0621] First, users input their income and expense data using devices such as smartphones or computers. This includes entering daily shopping and payroll information. It's also possible to automatically collect transaction data by linking bank accounts and credit card accounts to the device.

[0622] Next, the collected data is sent to the server via the terminal. The data is encrypted and securely transferred using advanced security protocols. The server has a generative AI model implemented, which is used to analyze the data.

[0623] The server analyzes the received data to identify the user's income and expenditure patterns and spending habits. Based on these results, it generates optimal savings plans and investment suggestions for the user. For example, it provides specific plans tailored to individual financial goals, such as monthly savings targets or participation in automated investment programs.

[0624] Furthermore, the server has the ability to monitor financial market trends in real time and send notifications to the terminal when there are significant market fluctuations that could affect the user. This allows users to make necessary financial decisions quickly.

[0625] Furthermore, users can input various questions into the system using natural language. The server uses generative AI to generate appropriate responses in real time based on these inputs and provides them to the user. For example, a question such as "Tell me about my spending patterns this month" can be answered with a detailed analysis result.

[0626] In this way, the invention can be implemented as a system that provides user-friendly and highly personalized financial management and advisory functions.

[0627] The following describes the processing flow.

[0628] Step 1:

[0629] Users use their devices to input income and expense information into the application. Users link their bank accounts and credit cards to their devices and set up automatic collection of transaction data.

[0630] Step 2:

[0631] The terminal encrypts the transaction data it collects and sends it to the server via a secure communication protocol. The terminal verifies the reliability of the data and performs error checking.

[0632] Step 3:

[0633] The server saves the received data to the database. A process is implemented to filter out duplicate data and ensure data consistency and integrity.

[0634] Step 4:

[0635] The server analyzes stored data using an AI model. It understands the user's income and expenditure patterns and identifies unusual spending and savings trends.

[0636] Step 5:

[0637] The server generates personalized savings plans and investment suggestions for the user based on the analysis results. This process includes risk tolerance analysis and portfolio recommendations.

[0638] Step 6:

[0639] The server monitors financial market data in real time and detects significant fluctuations. If an anomaly or market trend affects the user, an alert is sent to the device.

[0640] Step 7:

[0641] The user inputs a question using natural language through their device. For example, they might ask a specific question like, "What are this month's savings points?"

[0642] Step 8:

[0643] The server uses the natural language processing capabilities of its AI to generate responses to user questions. Based on the analysis results and suggestions, it provides information to the user in an easy-to-understand manner.

[0644] Step 9:

[0645] The terminal displays the response from the server to the user, who then reviews the proposed plan. If necessary, the user can modify the plan or add new settings.

[0646] (Example 1)

[0647] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0648] Modern personal financial management is complex and dynamic, requiring the collection, analysis, and forecasting of appropriate information. However, traditional systems often suffer from insufficient information gathering, or their analysis and recommendations are generic rather than individually optimized. Furthermore, they are inadequate in responding to real-time market fluctuations. As a result, individuals face challenges in making accurate financial decisions.

[0649] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0650] In this invention, the server includes means for collecting economic information, means for analyzing the collected information and identifying the user's economic activity patterns, and means for making future predictions using a generative AI model based on the received data. This makes it possible to provide users with highly personalized savings policies and investment proposals.

[0651] "Economic information" refers to data related to a user's income and expenses, including transaction history, sources of income, and expense details.

[0652] "Analysis" refers to the process of identifying user behavior patterns and trends from collected economic information, and may involve the use of statistical processing and algorithms.

[0653] A "savings policy" refers to a plan that provides specific guidelines for users to appropriately save money for the future.

[0654] "Investment proposals" refer to information that recommends specific and appropriate methods of asset management based on the user's financial situation and market trends.

[0655] "Goods market information" refers to data related to market trends in stocks, foreign exchange, commodities, etc., and includes prices, trading volume, trends, etc.

[0656] A "generative AI model" refers to a technology that uses machine learning algorithms to learn patterns from data and perform future predictions and real-time analysis.

[0657] "Natural language generation technology" refers to the technologies and methods used by computers to generate human language and communicate information in an easily understandable way.

[0658] This invention is a system that supports personal financial management and consists mainly of three elements: user, terminal, and server. First, the user uses a terminal such as a smartphone or computer to collect income and expenditure data. There are two methods of collection: manual input and automatic collection, the latter of which is achieved by linking the terminal with bank accounts or credit card accounts.

[0659] The terminal encrypts the collected economic information and sends it to the server using a security protocol. After receiving the data, the server performs preprocessing such as format conversion and imputation of missing data, and then analyzes it using a generative AI model. This allows the server to identify the user's consumption patterns and characteristics and make future predictions. For example, it can analyze a user's spending over the past three months, detect if a specific category, such as "food expenses," is exceeding the budget, and suggest ways to improve it.

[0660] Based on the analysis results, the server generates savings policies and investment suggestions, and presents them to the user in an easy-to-understand format using natural language generation technology. Specific suggestions include advice such as, "Let's make sure to save money thoroughly until the next payday and then check the results."

[0661] Furthermore, the server monitors market data in real time and sends notifications to the terminal when significant fluctuations occur. This feature gives users the opportunity to review their financial strategies in a timely manner. For example, when the stock market plummets, they may receive a notification saying, "The market is volatile. Please consider reviewing your portfolio."

[0662] Furthermore, users can obtain various information by entering questions in natural language. The server can use generative AI to generate responses to these questions and display them quickly on the terminal. An example of a prompt would be, "Tell me about my spending trends this week."

[0663] This configuration allows the system to provide highly personalized financial management and advisory functions that are easily accessible to users.

[0664] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0665] Step 1:

[0666] Users input income and expense data using devices such as smartphones and computers. The data entered is economic information based on specific amounts and dates, such as purchases and pay stubs. This data is organized by category and stored in a database within the device. In the case of automated collection, the device uses APIs from bank accounts and credit cards to retrieve and collect the latest transaction data.

[0667] Step 2:

[0668] The terminal protects the collected data using encryption technology (e.g., AES encryption) and sends it to the server using a security protocol (e.g., HTTPS). Input data undergoes format conversion before transmission. Specifically, date formats and currency units are standardized, making analysis on the server easier.

[0669] Step 3:

[0670] The server receives the transmitted data and first performs data cleaning, such as imputing missing data and correcting outliers. This step includes operations such as converting incorrectly entered, excessively large numbers to an appropriate range. Once the data cleaning is complete, a generative AI model is prepared, and the data is ready for subsequent analysis.

[0671] Step 4:

[0672] The server uses a generative AI model to analyze clean data. This involves identifying behavioral patterns from past spending history and analyzing seasonal spending trends. Statistical methods and machine learning algorithms are used for data processing. The analysis output includes reports on user consumption habits and suggestions for improvement.

[0673] Step 5:

[0674] Based on the analysis results, the server generates beneficial savings policies and investment proposals for the user, and documents the proposals in an easy-to-understand format using natural language generation technology. The output text includes specific action plans and recommendations. This document is sent to the terminal for the user to view.

[0675] Step 6:

[0676] The server continuously monitors goods market data in real time and generates and sends notifications to terminals when it detects significant changes. For example, if there are important market trends, it will provide information such as "The market is changing" via push notification.

[0677] Step 7:

[0678] Users can ask the system questions in natural language via their terminal. The server inputs the prompt into an AI model that generates appropriate responses. For example, if a user asks, "Tell me my expenses for this week," the server will create a weekly expense summary from the analyzed data, convert it to text, and display it on the terminal.

[0679] (Application Example 1)

[0680] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0681] In financial management, there are challenges in accurately tracking daily expenses and efficiently managing long-term savings and investment plans for individual users. Furthermore, while systems capable of responding immediately to fluctuating market information are needed, users currently face the time and effort required to check this information themselves. Additionally, many users desire smooth responses to inquiries in natural language, and meeting these needs is essential.

[0682] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0683] In this invention, the server includes means for collecting financial information data, means for analyzing the collected information and identifying the user's economic activity trends, and means for monitoring market information in real time and notifying the user of important changes. This enables the user to automatically grasp their daily spending and efficiently manage their long-term finances. Furthermore, by responding immediately to fluctuating market information, quick and effective financial decisions become possible. In addition, rapid responses to inquiries in natural language can be obtained, enhancing user convenience.

[0684] "Financial information data" refers to information related to a user's income, expenses, and transactions, which allows for a comprehensive understanding of an individual's economic activities.

[0685] "Analysis" is the process of analyzing collected data and identifying patterns and trends to gain insights into users' economic activities.

[0686] "Economic activity trends" refer to patterns and tendencies in users' income, expenditure, and asset management behaviors, and represent individual financial behavioral habits.

[0687] "Market information" refers to various data related to financial markets, including information on market trends and fluctuations.

[0688] "Natural language" refers to the language that humans use on a daily basis, enabling users to give instructions and make inquiries to the system using ordinary language.

[0689] A "user" refers to an individual who uses this system and seeks to manage or improve their own financial situation.

[0690] "Means" refers to methods or devices used to achieve a specific purpose, and in this system, they enable functions such as the collection, analysis, and notification of various types of data.

[0691] Users input data about their income and expenses using devices such as smartphones and computers. Furthermore, by linking with bank accounts and digital payment services, transaction data can be automatically collected.

[0692] The terminal has the ability to encrypt collected financial information data and securely transmit it to the server using security protocols. The server has a generative AI model implemented, which is used to perform detailed analysis of the data. The server identifies the user's income and expenditure trends and generates savings policies and investment proposals based on them.

[0693] Furthermore, the server monitors financial market information in real time and immediately sends notifications to the user's terminal when significant market changes occur. This notification function allows users to make necessary financial decisions quickly.

[0694] Furthermore, users can query the system using natural language, and the server uses generative AI to return appropriate responses in real time. These responses are based on the user's specific financial situation and include detailed explanations and predictive information.

[0695] As a concrete example, if a user inputs "Tell me about my spending this month" into the terminal, the server uses a generative AI model to analyze the spending data and returns advice to the terminal such as, "Your spending on food and beverages has increased by 10% this month. We recommend reviewing your budget for next month." In this way, this invention provides users with high convenience and effective financial management.

[0696] Examples of prompts for generative AI models

[0697] Based on the user's spending data, analyze their spending trends for the current month and generate specific advice for saving money. For example, include specific comments on increases or decreases in dining out expenses.

[0698] Therefore, this system can streamline financial management and provide users with optimal financial advice.

[0699] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0700] Step 1:

[0701] Users input income and expense data using their smartphones or computers. This data includes daily living expenses and earnings information. Furthermore, users can automatically retrieve transaction data by linking their bank accounts and digital payment services. This data input allows the device to accumulate the basic information necessary for financial management.

[0702] Step 2:

[0703] The terminal encrypts the collected financial information data and sends it to the server using a security protocol. This process uses encryption technologies such as SSL / TLS to ensure the secure transfer of data. The input is encrypted financial information data, and the output is data securely delivered to the server via a secure communication path.

[0704] Step 3:

[0705] The server decrypts the received encrypted data and performs data analysis using a generative AI model. This analysis uses data mining techniques to identify the user's income and expenditure trends and spending habits. The input to the analysis is the decrypted financial information data, and the output is a detailed report of the user's economic activity trends and spending patterns.

[0706] Step 4:

[0707] The server generates appropriate savings policies and investment proposals for the user based on the analysis results. This generation process applies machine learning algorithms to create personalized suggestions optimized for each user. The input is trend data on economic activity, and the output is specific savings and investment proposals.

[0708] Step 5:

[0709] The server monitors financial market information in real time and, if significant market changes occur, immediately sends notifications to the user's terminal as needed. This monitoring uses an API to ingest market data and detect anomalies or significant fluctuations. The input is market information data, and the output is a fluctuation information alert.

[0710] Step 6:

[0711] Users can input questions into the terminal using natural language. The server receives these questions, generates appropriate responses using a generative AI model, and sends them back to the user in real time. This process utilizes natural language processing technology to accurately understand the user's intent and provide answers. The input is the user's question text, and the output is the generated response message.

[0712] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0713] As an embodiment of this invention, a personal financial management system incorporating an emotion engine consists of three main components: a user, a terminal, and a server.

[0714] First, users input information about their income and expenses using devices such as smartphones or computers. These devices can be linked to bank accounts and credit cards to automatically collect transaction data. Furthermore, users can interact with the system using voice or text input.

[0715] Next, the collected data is sent to the server via the terminal. The server contains a generative AI model and an emotion engine. The generative AI model analyzes income and expenditure data to identify the user's economic activity patterns. This allows for personalized savings plans and investment suggestions.

[0716] Meanwhile, the emotion engine analyzes voice and text data obtained from the user to recognize the user's emotional state. Based on this recognition, the server generates optimal financial advice that reflects the user's emotional state. For example, if it detects that the user is stressed, it may recommend low-risk investment options or suggest mitigation measures to save money.

[0717] The server sends suggestions generated based on analysis results and sentiment analysis to the terminal. The terminal notifies the user in real time, enabling the user to take action quickly.

[0718] Furthermore, users can ask questions about asset management and spending in natural language and receive responses. For example, in response to a specific question such as "Please give me saving suggestions based on my current emotional state," the system will provide advice tailored to the user's emotions.

[0719] In this way, a system incorporating an emotion engine can comprehensively consider the user's economic and emotional state and support individually optimized financial management.

[0720] The following describes the processing flow.

[0721] Step 1:

[0722] Users enter information about their income and expenses into the application using their device. Users also set up automatic collection of transaction data by linking their bank accounts and credit cards to their device.

[0723] Step 2:

[0724] Users input information about their daily emotional state via voice or text into their device. This data is used for processing by the emotion engine.

[0725] Step 3:

[0726] The device encrypts the income, expenditure, and sentiment input data it collects and sends it to the server using a secure communication protocol. The device performs a basic integrity check on the data before transmission.

[0727] Step 4:

[0728] The server stores the received transaction data in the database. Duplicate data removal and data integrity checks are performed.

[0729] Step 5:

[0730] The server applies a generative AI model to transaction data to analyze the user's income and expenditure patterns. From the resulting analysis, it identifies the user's usual spending and savings trends.

[0731] Step 6:

[0732] The server's emotion engine analyzes the user's voice and text data to identify the user's current emotional state. For example, if the user indicates stress, the result is recorded.

[0733] Step 7:

[0734] The server integrates the results of income and expenditure data analysis with sentiment analysis to generate savings plans and investment suggestions that take the user's emotional state into account. Specific examples include saving methods that consider relaxation and low-risk investment suggestions.

[0735] Step 8:

[0736] The server sends the generated financial advice and plan to the terminal. The terminal displays this information on the user's screen, making it accessible to the user.

[0737] Step 9:

[0738] When a user inputs a natural language question through their device, the server generates a sentiment-sensitive response to the question and sends it to the user via the device. For example, it might answer a question like, "I'm feeling anxious right now, how should I protect my assets?"

[0739] Through this series of steps, the system can comprehensively manage the user's financial and emotional state and provide individually optimized advice.

[0740] (Example 2)

[0741] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0742] In personal financial management, it has been difficult to provide advice that not only analyzes income and expenditure patterns but also takes into account a person's emotional state. Furthermore, there was a lack of real-time information to quickly respond to market fluctuations and make optimal financial choices. Additionally, there was a problem with the lack of individualization when developing savings and investment plans tailored to individual user goals, as the influence of emotions was not considered.

[0743] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0744] In this invention, the server includes means for using a generative model to analyze income and expenditure data and identify the user's economic activity patterns; means for analyzing voice and text data to recognize the user's emotional state; and means for generating individual savings plans and investment proposals for the user based on the analysis results and emotional state. This makes it possible to provide individually optimized financial management that comprehensively considers the user's economic activities and emotional state.

[0745] "Income and expenditure information" refers to all the benefits a user receives and all the expenses they incur, and is data that indicates an individual's financial status.

[0746] A "generative model" refers to an algorithm that analyzes specific patterns based on collected data and generates new analytical results.

[0747] "Voice and text data" refers to data in the form of spoken or written language entered by users, and is fundamental information that represents the user's intentions and emotions.

[0748] "Emotional state" refers to the psychological or emotional condition a user is in, including feelings such as anxiety and joy.

[0749] "Savings plans and investment proposals" refer to asset management and investment plans recommended to help users achieve their future financial goals.

[0750] "Market data" refers to information about fluctuations in financial markets such as stock prices, exchange rates, and interest rates, which can influence financial decisions.

[0751] "Natural language queries" refer to questions and requests that users make to a system using everyday language.

[0752] In an embodiment of this invention, the personal financial management system consists of three main components: a user, a terminal, and a server. The user inputs information about their income and expenses using a terminal such as a smartphone or computer. The terminal is equipped with software that links with bank accounts and financial institutions to automatically collect transaction data. The user can input information interactively into the system using voice and text.

[0753] Financial information collected by the terminal is sent to a server. This server houses a generative AI model that analyzes the user's income and expenditure data to identify economic activity patterns. The analysis utilizes models employing time series analysis and machine learning techniques.

[0754] Furthermore, the server is equipped with an emotion engine that analyzes voice and text data to recognize the user's emotional state. This engine uses natural language processing and voice emotion analysis algorithms to understand the user's psychological state and generate advice based on that state.

[0755] The server combines analyzed economic data with the user's emotional state to generate personalized savings plans and investment suggestions. These suggestions reflect the user's current emotional state and include recommendations that consider appropriate risk levels. For example, if a user asks, "How much should I save this month?", the server can provide a specific amount based on the user's individual circumstances.

[0756] As a concrete example, a prompt might be written as, "If the system determines that the user is experiencing stress, what investment strategy would be recommended?" By inputting this prompt into the AI ​​model on the server, the system will suggest the optimal investment strategy tailored to the user's situation.

[0757] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0758] Step 1:

[0759] Users input income and expense information using devices such as smartphones and computers. These devices connect with bank accounts and financial institutions, automatically collecting and inputting transaction data. The input data includes salary, food expenses, rent, etc., and this data is automatically categorized and organized on the device.

[0760] Step 2:

[0761] Data collected by the device is sent to the server. The server receives this information as input and uses a generative AI model to analyze the user's income and expenditure data. Specifically, it performs data calculations to identify the user's past income and expenditure patterns through time series analysis and predict future financial conditions. As output, the user's economic activity patterns are identified.

[0762] Step 3:

[0763] The server receives voice and text data sent by the user and activates the emotion engine to analyze the emotional state. This process analyzes the tone of voice and emotional expressions contained in the text, and processes the data to recognize emotional states such as anxiety and joy. As a result of the analysis, the user's emotional state is output.

[0764] Step 4:

[0765] The server integrates analysis results from the generation AI model and the emotion engine to generate personalized financial advice for the user. Specifically, it creates appropriate savings plans and investment suggestions based on the user's current financial situation and emotional state. For example, it may recommend low-risk investments or suggest specific ways to save money. The output is a personalized savings and investment plan for the user.

[0766] Step 5:

[0767] The server sends the generated suggestions to the terminal, which then notifies the user in real time. Notifications are sent via push notifications or email, allowing the user to immediately review and take action. Furthermore, the user can obtain additional information and advice by sending prompts such as "How much have I saved this month?" or "Tell me your investment strategy."

[0768] (Application Example 2)

[0769] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0770] Modern individuals need to manage their finances amidst complex economic conditions and emotional fluctuations. However, current financial management systems lack an approach based on individual emotions, making it difficult to provide advice tailored to individual circumstances. Therefore, there is a need for individually optimized financial management that takes into account the user's emotional state.

[0771] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0772] In this invention, the server includes means for collecting income and expenditure information, means for identifying an individual's economic activity patterns, and means for generating individual savings plans and investment proposals. This enables comprehensive financial management that takes into account an individual's emotional state.

[0773] "Income and expenditure information" refers to data on income and expenditures related to an individual's financial activities, and is fundamental information for understanding an individual's economic situation.

[0774] An "economic activity pattern" comprehensively represents an individual's income and expenditure trends and habits, serving as the basis for individual financial planning and proposals.

[0775] "Savings plans and investment proposals" refer to specific suggestions to help optimize savings allocation and asset growth based on an individual's financial situation and emotional state.

[0776] "Economic market information" refers to the latest data related to financial and stock markets, and is important information that should be considered when making individual investment decisions.

[0777] "Natural language queries" refer to questions and requests that individuals make to a system using everyday language, which facilitates smooth interaction with the system.

[0778] "Emotional state" refers to an individual's feelings and psychological condition, and is a factor that enables appropriate financial advice to be provided based on this state.

[0779] An "information processing system" refers to a technical framework that includes a series of hardware and software components for analyzing collected data and generating proposals.

[0780] To implement this invention, an information processing system is constructed to support personal financial management. The system collects income and expenditure information from the user's smartphone, computer, or other terminal and transmits it to a server. This information is automatically acquired through cooperation with financial institutions and credit agencies.

[0781] The server is equipped with a generative AI model that uses Google Cloud Natural Language API and TensorFlow to analyze the collected information. This generative AI model analyzes economic activity patterns and provides personalized savings plans and investment suggestions. Furthermore, an emotion analysis engine evaluates the user's voice or text data to identify their emotional state. Based on this emotional state, the server provides personalized financial advice.

[0782] The terminal notifies the user of suggestions from the server in real time, allowing the user to receive feedback quickly. Users can also ask questions about finances and emotions using natural language and receive responses from a generative AI model.

[0783] For example, if the system detects stress in the user, it will recommend low-risk investment options. By prompting the user with questions like, "What big purchase would I feel comfortable making right now?", the system can provide personalized information. This approach enables comprehensive financial management that takes the user's emotional state into account.

[0784] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0785] Step 1:

[0786] The user's device collects income and expenditure information from the user. This information is automatically obtained through collaboration with financial institutions and credit agencies. The input is the user's transaction information, and the output is the preparation of data for transmission to the server. Specifically, the device accesses the financial institution's API via the internet and securely downloads the transaction information.

[0787] Step 2:

[0788] The server receives income and expenditure information sent from the terminal. The input is financial data sent from the terminal, and the output is ready for analysis. At this point, the server verifies the integrity of the data and saves it to the database for analysis. During this process, duplicate data is removed and the format is normalized.

[0789] Step 3:

[0790] The server analyzes the collected information using a generative AI model to identify the user's economic activity patterns. The input is normalized financial data, and the output is the result of the economic activity analysis. Specifically, the AI ​​model uses machine learning algorithms to identify past spending patterns and trends, and generates numerical data and graphs of the analysis results.

[0791] Step 4:

[0792] The server uses an emotion analysis engine to analyze the user's emotional state. The input is voice or text data from the user, and the output is the emotion analysis result. In this process, speech recognition and natural language processing technologies are used to analyze the tone of the user's voice and the context in which it is used, and the emotional state is numerically evaluated.

[0793] Step 5:

[0794] The server generates personalized savings plans and investment proposals based on a generated AI model and sentiment analysis results. Inputs are the results of economic activity analysis and sentiment analysis, while output is customized financial advice. The server calculates investment options based on risk profiles and short-term and long-term goals, and sends the results to the terminal.

[0795] Step 6:

[0796] The user's device receives suggestions sent from the server and notifies the user. The input is financial advice from the server, and the output is a notification to the user. Specifically, the device displays notifications to the user in real time through the app's UI and collects user feedback as needed.

[0797] Step 7:

[0798] The user asks additional questions or inquiries using natural language, and the server generates a response using a generative AI model based on the prompt text. The input is the prompt text from the user, and the output is the response from the generative AI model. Specifically, the server analyzes the user's question, prepares an intelligent response that takes into account past data and the current situation, and immediately sends it to the user.

[0799] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0800] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0801] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0802] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0803] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0804] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0805] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0806] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0807] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0808] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0809] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0810] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0811] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0812] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0813] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0814] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0815] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0816] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0817] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0818] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0819] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0820] The following is further disclosed regarding the embodiments described above.

[0821] (Claim 1)

[0822] Means for collecting income and expenditure data,

[0823] A means for analyzing the collected data and identifying the user's economic activity patterns,

[0824] Based on the aforementioned analysis results, a means for generating savings plans and investment proposals for users,

[0825] A means of monitoring financial market data in real time and notifying users of significant fluctuations,

[0826] A means for generating responses to user queries in natural language,

[0827] A system that includes this.

[0828] (Claim 2)

[0829] The system according to claim 1, which automatically collects user transaction data through bank account and credit card information.

[0830] (Claim 3)

[0831] The system according to claim 1, which recommends a savings amount based on the user's financial situation.

[0832] "Example 1"

[0833] (Claim 1)

[0834] Means of collecting economic information,

[0835] The collected information is analyzed and used to identify the user's economic activity patterns.

[0836] Based on the aforementioned analysis results, a means for generating savings policies and investment proposals for users,

[0837] A means of monitoring goods market information in real time and notifying users of significant changes,

[0838] A means for generating responses to user queries in natural language,

[0839] A means of making future predictions using a generative AI model based on received data,

[0840] Based on the analysis and predictions described above, a means to clarify the content of the proposal to the user using natural language generation technology,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, which automatically collects user transaction information through financial institution accounts and payment card information.

[0844] (Claim 3)

[0845] The system according to claim 1, which recommends a savings amount based on the user's financial status.

[0846] "Application Example 1"

[0847] (Claim 1)

[0848] Means of collecting financial information data,

[0849] A means for analyzing the collected information and identifying the economic activity trends of users,

[0850] Based on the aforementioned analysis results, a means for generating savings policies and investment plans for users,

[0851] A means of monitoring market information in real time and informing users of important changes,

[0852] A means for generating responses to user questions in natural language,

[0853] A means of automatically recording user spending information and presenting budget management and spending trends,

[0854] ...

[0855] A system that includes this.

[0856] (Claim 2)

[0857] The system according to claim 1, which automatically collects user transaction information through financial accounts and digital payment information.

[0858] (Claim 3)

[0859] The system according to claim 1, which recommends a savings amount based on the user's financial situation.

[0860] "Example 2 of combining an emotion engine"

[0861] (Claim 1)

[0862] A means of inputting information on income and expenses,

[0863] A means for analyzing the aforementioned income and expenditure data and using a generative model to identify the user's economic activity patterns,

[0864] A means of recognizing the user's emotional state by analyzing voice and text data,

[0865] A means for generating individual savings plans and investment proposals for users based on the aforementioned analysis results and emotional state,

[0866] A means of monitoring market data in real time and notifying users of significant fluctuations,

[0867] A means for generating responses to user queries in natural language,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, which automatically collects user transaction information through financial institution information.

[0871] (Claim 3)

[0872] The system according to claim 1, which recommends savings amounts based on the user's financial and emotional state.

[0873] "Application example 2 when combining with an emotional engine"

[0874] (Claim 1)

[0875] Means for collecting income and expenditure information,

[0876] A means for analyzing the collected information and identifying individual economic activity patterns,

[0877] A means for generating individual savings plans and investment proposals based on the aforementioned analysis results,

[0878] A means of monitoring economic market information in real time and notifying individuals of significant fluctuations,

[0879] A means for generating responses in response to natural language queries,

[0880] A means of analyzing an individual's emotional state and generating emotionally-based financial advice,

[0881] An information processing system that includes this.

[0882] (Claim 2)

[0883] The information processing system according to claim 1, which automatically collects personal transaction information through financial institution information.

[0884] (Claim 3)

[0885] The information processing system according to claim 1, which recommends savings amounts based on an individual's financial situation and emotional state. [Explanation of symbols]

[0886] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting income and expenditure data, A means for analyzing the collected data and identifying the user's economic activity patterns, Based on the aforementioned analysis results, a means for generating savings plans and investment proposals for users, A means of monitoring financial market data in real time and notifying users of significant fluctuations, A means for generating responses to user queries in natural language, A system that includes this.

2. The system according to claim 1, which automatically collects user transaction data through bank account and credit card information.

3. The system according to claim 1, which recommends a savings amount based on the user's financial situation.

Images