system

Abstract

We provide the system. [Solution] An artificial intelligence tool that acquires market data and predicts future financial market trends, A calculation means that receives individual economic situation data and calculates a suitable savings amount for the user, Information generation means that generates the results of the artificial intelligence means and the calculation means and provides recommended information to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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 asset formation faced by modern individuals, there are often problems that they do not have the knowledge and experience to accurately predict the trends of the financial market, and it is difficult to make a reasonable investment plan according to their own economic situation. Therefore, there is a need to solve the problem that there is a lack of an environment in which young people who are about to start investing and those with little investment experience can safely conduct asset formation.

Means for Solving the Problems

[0005] To address this challenge, the present invention provides a system that uses artificial intelligence to collect market data and predicts future financial market trends based on that data. Furthermore, this system includes a calculation means that calculates an appropriate savings amount for each user based on individual economic situation data. This makes it possible to provide users with an optimal recommended investment portfolio and a long-term savings plan that takes into account their financial burden.

[0006] "Market data" refers to information about fluctuations in financial markets, such as stock prices, exchange rates, interest rates, commodity prices, and economic indicators.

[0007] "Future financial market trends" refers to the changes and trends in future financial markets predicted using artificial intelligence technology.

[0008] "Artificial intelligence tools" refer to software or systems that use machine learning and data analysis algorithms to make useful predictions and decisions from input data.

[0009] "Individual economic data" refers to information that shows the specific financial situation of each user, such as income, expenses, assets, and liabilities.

[0010] "An appropriate investment amount for the user" refers to an amount of investment funds that can be set aside without burden, based on the user's own income, expenses, and risk tolerance.

[0011] "Calculation means" refers to a device, part of a device, or software that performs a process or method for deriving a predetermined numerical value from input data.

[0012] "Information generation means" refers to devices or systems that create information in a specific format based on analysis and calculation results and present it to the user.

[0013] "Recommended information" refers to investment advice or guidance generated by the system and provided to assist users in making decisions. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

[0017] In the following embodiments, a labeled 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.

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

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

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a support system designed to facilitate asset building for users. This system automates financial market forecasting and individual savings plans through the use of a server, terminal, and user components.

[0036] Server Functions

[0037] The server has the ability to acquire various financial market data and predict market trends using AI models based on that data. The server also receives users' financial situation data and calculates the optimal investment amount for each user based on that data. Furthermore, the server integrates market forecasts and investment plans to generate recommendations for users. These recommendations include suggested investment portfolios and explanations of the reasoning behind them.

[0038] Device functions

[0039] The terminal is equipped with communication means to send information entered by the user to the server, and receives the returned data from the server and displays it to the user. The terminal appropriately transfers information such as income, expenses, and investment style entered by the user to the server, and receives and displays the analysis results from the server.

[0040] User actions

[0041] Users input their income, expenses, and desired investment style (e.g., safety-first, moderately risk-tolerant) into the terminal. Once the user enters the information, it is encrypted and sent to the server. Based on the server's generated recommendations for stocks and investment amounts, users can then decide whether or not to start investing.

[0042] This system compensates for a lack of investment knowledge, supports manageable asset building tailored to individual financial situations, and provides an environment for confident investing. Therefore, it is particularly useful for young people looking to start investing and for users who have previously given up on investing.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The user activates the device and enters their monthly income, expenses, and desired investment style. This collects basic financial information.

[0046] Step 2:

[0047] The device encrypts the collected user information and transmits it to the server using a secure communication protocol.

[0048] Step 3:

[0049] The server receives the individual economic situation data that is sent and securely stores it in the database. Next, the server retrieves the latest market data through financial APIs.

[0050] Step 4:

[0051] Artificial intelligence installed on the server analyzes market data and predicts future financial market trends. This process analyzes financial information such as stock price fluctuations and exchange rates.

[0052] Step 5:

[0053] The server calculates the investment amount based on the AI's predictions and the user's financial situation data. Furthermore, it selects the most suitable investment products for the user and generates recommendation information.

[0054] Step 6:

[0055] The server sends the generated recommendations and savings plan to the device. This data is also encrypted, so your privacy is protected.

[0056] Step 7:

[0057] The terminal decrypts the data received from the server and presents it to the user through a graphical user interface. At this stage, the recommended portfolio and investment amount are displayed.

[0058] Step 8:

[0059] The user reviews the provided information and decides whether or not to actually invest. If they choose to invest, the investment process begins when they send instructions from their device.

[0060] Step 9:

[0061] The server, upon user approval, executes the order with the partner financial institution. All transactions are recorded and can be referenced later.

[0062] (Example 1)

[0063] 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."

[0064] The present invention aims to efficiently and optimally support asset building tailored to the individual financial situation of each user. Specifically, it aims to create a system that allows even novice investors or those with little experience to confidently begin investing by appropriately predicting trends in financial markets and providing savings plans suitable for each user.

[0065] 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.

[0066] In this invention, the server includes artificial intelligence means for acquiring market information and predicting future economic market trends; calculation means for receiving individual economic situation information and calculating an appropriate savings amount for the user; and information generation means for integrating the results of the artificial intelligence means and the calculation means and providing recommended information to the user. This makes it possible to provide each user with an accurate investment plan.

[0067] "Market information" refers to data related to financial markets, such as stock prices, exchange rates, and commodity prices.

[0068] "Artificial intelligence tools" refer to computer programs that include machine learning algorithms for analyzing market information and predicting future economic market trends.

[0069] "Individual economic information" refers to information regarding each user's income, expenses, asset status, and investment policies.

[0070] "Calculation means" refers to algorithms and calculation mechanisms used to derive appropriate savings amounts and investment plans for users based on individual economic situation information.

[0071] "Information generation means" refers to a computer program that integrates the results of artificial intelligence means and computation means and has the function of providing users with recommended investment plans and reasons.

[0072] "Communication methods" refer to network communication technologies used to securely encrypt and transmit information from users to the server.

[0073] "Display means" refers to a user interface that presents recommended information received from the server to the user in a visually easy-to-understand format.

[0074] This invention is a system that enables users to build assets with peace of mind, and it proceeds through the interaction of servers, terminals, and users.

[0075] The server continuously acquires market information from external data providers. Python is used as the software for this, and machine learning models are built using its libraries, TENSORFLOW® and PyTorch. This allows the server to predict future economic markets based on historical market data. For example, it analyzes short- and long-term time series data to perform stock price trend analysis and predict economic indicators. Furthermore, the server receives individual economic information from users and creates investment plans based on this information.

[0076] The terminal is equipped with a means of securely transmitting user-entered financial information to a server. A secure communication protocol is used to prevent data leakage. The terminal also receives recommended information from the server and displays it in a way that is intuitively understandable to the user. Specifically, the user interface shows an overview of the risks and returns of each investment, as well as recommended monthly contribution amounts, using visual charts and text.

[0077] Users input their monthly income and expenses, as well as their desired investment style (e.g., safety-oriented) through their device. Based on this, they can then decide whether or not to actually invest, using the server-generated recommended portfolio and investment plan as a reference. For example, a user might input information based on a prompt such as, "Please suggest the optimal investment plan for a monthly income of 500,000 yen, monthly expenses of 300,000 yen, and a safety-oriented style."

[0078] In this way, the present invention utilizes a generative AI model to provide asset management options tailored to the individual needs of users, thereby fulfilling its role as a system that compensates for a lack of understanding of investment.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] Users input their financial information using their device. Specifically, they enter information such as their monthly income, essential monthly expenses, and investment risk tolerance (e.g., safety-oriented) into the interface. This input information is encrypted on the device and prepared for transmission to the server. Encryption of the entered data protects the data during transmission.

[0082] Step 2:

[0083] The terminal sends the entered economic status information to the server. During this process, encrypted data is sent to the server using a secure communication protocol. The server receives this data and decrypts it afterward. The output of this process is the decrypted user's economic information.

[0084] Step 3:

[0085] The server retrieves current market information from an external data provider. This information includes the latest stock prices, interest rates, and exchange rates. Using the retrieved market information, the server runs a generating AI model to analyze future market trends. The analysis results in the output of predicted market trend data.

[0086] Step 4:

[0087] The server integrates decoded user economic information and market forecast data to calculate individually optimized monthly investment amounts. This calculation takes into account predicted market risk and return. After the calculation, data containing the optimal investment plan and recommended monthly investment amounts for the user is generated and output.

[0088] Step 5:

[0089] The server sends the calculated recommendation information to the terminal. The output from the server is a dataset containing the recommendation information, which also includes the recommended portfolio and the reasons for it. After receiving this information, the terminal prepares to decrypt it from its encrypted state and convert it into a user-friendly format.

[0090] Step 6:

[0091] The terminal displays recommended information provided by the server through its user interface. Specifically, it shows the risk and return of each investment and the recommended monthly investment amount in graphs and text, and also displays data explaining the reasons for the investment. The output here is a recommended plan presented in a visual form.

[0092] Step 7:

[0093] Users make their investment decisions based on the recommendations provided by their device. If they understand and agree with the displayed data, they can choose to operate the device and begin making an actual investment.

[0094] (Application Example 1)

[0095] 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."

[0096] In today's financial markets, users are faced with a vast amount of information, making it difficult to make informed decisions about how to build wealth. Therefore, users with little experience in wealth building require considerable effort and knowledge to make appropriate investments. Furthermore, managing daily expenses and building wealth simultaneously is challenging and a significant burden for users lacking time and expertise. Thus, there is a need for a system that automatically adjusts wealth building based on the user's spending patterns.

[0097] 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.

[0098] In this invention, the server includes an analysis means for acquiring market data and predicting future financial market trends, a calculation means for receiving individual economic situation data and calculating an appropriate savings amount for the user, and an adjustment means for automatically adjusting the investment plan based on the user's spending patterns. This enables optimal investment advice tailored to the user's spending situation, compensating for any lack of specialized knowledge and allowing the user to build assets with peace of mind.

[0099] "Market data" refers to a collection of information that shows the state and trends of financial markets, and includes stock prices, exchange rates, interest rates, and economic indicators.

[0100] "Analytical tools" refer to methods and techniques for analyzing market data and predicting future financial market trends.

[0101] "Economic status data" refers to a collection of information that shows the financial status of users, such as their income, expenses, assets, and liabilities.

[0102] "Calculation methods" refer to methods and techniques for calculating an appropriate savings amount based on the user's financial situation data.

[0103] "Adjustment mechanisms" refer to systems or functions that automatically optimize investment plans according to the user's spending patterns and economic situation.

[0104] "Information generation means" refers to methods and technologies for providing users with appropriate investment plans and recommended information based on the results of analysis and calculation means.

[0105] This invention is a support system for users to easily build assets. This system consists of a server, a terminal, and a user.

[0106] The server collects market data from financial markets. Through analytical methods, the server uses this data to predict future trends in financial markets. Specifically, the server utilizes generative AI models to analyze historical market data and current market information to derive future market trends. This process utilizes a cloud computing environment capable of processing large amounts of data.

[0107] The server also receives user financial data from the terminal. Using calculation tools, the server calculates the optimal savings amount for each user based on their income, expenses, and other economic indicators. Furthermore, adjustment tools work based on this information to automatically optimize the investment plan according to the user's spending patterns.

[0108] The terminal functions as the user's input interface. The user inputs information about their income, expenses, and investment style on the terminal, and this data is sent and received between the terminal and the server. The terminal receives recommendation information generated by the server and displays it visually to the user. Based on this recommendation information, the user can easily begin building their assets.

[0109] As a concrete example, if a user inputs a monthly income of 50,000 yen and expenses of 20,000 yen, the server can analyze that disposable income and recommend investing 3,000 yen per month. This recommendation can be applied to various investment opportunities, such as mutual funds or stock purchases. As market trends change, the AI ​​dynamically adjusts the investment amount and plan, so the user always receives optimized advice. An example of a prompt message would be, "Your income is 50,000 yen and your expenses are 20,000 yen. Please create a stable portfolio."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server collects real-time market data from financial markets. The input is market information, and the output is a dataset for analysis. The server performs large-scale data processing and prepares it for input into generative AI models.

[0113] Step 2:

[0114] The server uses a generative AI model to analyze market data. The input is a dataset for analysis, and the output is forecast information for future financial markets. The AI ​​model learns from past market trends and performs forecast calculations using a new dataset.

[0115] Step 3:

[0116] The terminal receives data from the user regarding income, expenses, and investment style. The input is the user's financial status data, and the output is transformed data sent to the server. The terminal collects data through the user interface and sends it to the server in an appropriate format.

[0117] Step 4:

[0118] The server calculates the appropriate savings amount for each user based on their financial situation data. The input is transformed data, and the output is the calculated savings amount. A calculation method is used to determine the optimal savings amount based on the user's income and expenses.

[0119] Step 5:

[0120] The server automatically optimizes an investment plan that takes into account the user's spending patterns, using an adjustment mechanism. The input is the calculated savings amount and market forecast information, and the output is the optimized investment plan. The adjustment mechanism analyzes the user's spending history and dynamically adjusts the investment plan.

[0121] Step 6:

[0122] The server provides the generated optimized investment plan to the user as recommended information through an information generation mechanism. The input is the optimized investment plan, and the output is the recommended information displayed to the user. The information generation mechanism generates a prompt statement and clearly explains the reasons for the recommendation.

[0123] Step 7:

[0124] The user reviews the recommendations received from the server via their device and makes a decision to start investing based on the information presented. The input is the recommendations from the server, and the output is the user's decision. The user understands the contents of the presented portfolio and makes investments as needed.

[0125] 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.

[0126] This invention provides an asset building support system that takes into account the user's emotions in addition to forecasting financial market trends and creating individual savings plans. This system is realized through the collaboration of various elements, including a server, terminal, user, and emotion engine.

[0127] Server Functions

[0128] The server first securely stores the user's financial situation data received from the terminal. Simultaneously, the server collects market data and uses AI models to predict future financial market trends. The results of this prediction are then used, along with information generation tools, to create a recommended investment portfolio tailored to the user.

[0129] Functions of the Emotion Engine

[0130] The emotion engine analyzes the user's biometric and interaction data acquired through the device to identify their current emotional state. Based on this emotional state, the emotion engine evaluates stress levels and risk preferences and sends the results to the server.

[0131] Device functions

[0132] The device transmits financial and biometric data collected from the user to the server and emotion engine. It also has the function of displaying recommendations and investment advice returned by the server to the user.

[0133] User actions

[0134] Users can input their income and expenditure data into the device and participate in acquiring biometric data (such as voice tone and facial expression images) as prompted by the device. This allows the system to provide an optimized investment plan that also takes into account the user's emotional state for the day. Users then decide whether to execute the investment based on the results adjusted by the emotion engine.

[0135] This system allows users to make more rational investment decisions that are often influenced by emotions, enabling them to build wealth with less stress and greater peace of mind. This approach represents an evolution from traditional wealth-building methods and is an innovative approach that takes into account the importance of an individual's emotional state in wealth creation.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] Users use their devices to input information about their monthly income, expenses, and current financial situation. This information is used as basic data for wealth building.

[0139] Step 2:

[0140] The device collects emotion-related data provided by the user. This includes biometric data such as voice tone, facial expressions, and heart rate.

[0141] Step 3:

[0142] The device encrypts the collected financial and emotional data before sending it to the server. Strong security protocols are used to protect data privacy.

[0143] Step 4:

[0144] The server retrieves the latest market data from financial market data providers and analyzes that data using artificial intelligence. This analysis is performed to predict future market trends.

[0145] Step 5:

[0146] The server calculates the optimal savings amount based on the individual financial situation data it receives. This includes adjustments to reduce the burden based on the user's income, expenses, and emotional state.

[0147] Step 6:

[0148] The emotion engine analyzes emotional data sent from the server to assess the user's stress levels and risk preferences. This information is then used to refine the recommended portfolio.

[0149] Step 7:

[0150] The server integrates the prediction results from artificial intelligence and the evaluation results from the emotion engine to generate a recommended investment portfolio tailored to the user. This includes specific investment products and investment proportions.

[0151] Step 8:

[0152] The server sends the generated recommendation information to the terminal. The terminal receives this information and displays it in an easy-to-understand format for the user.

[0153] Step 9:

[0154] Based on the information presented, users make investment decisions that align with their emotional state. The selection is completed on the device, and the investment can then be executed by following subsequent instructions.

[0155] (Example 2)

[0156] 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".

[0157] In modern asset management, a problem exists where users find it difficult to make rational investment decisions due to stress stemming from short-term emotional fluctuations and market uncertainty. Furthermore, traditional systems offer uniform investment recommendations without considering the emotional state of the user, making it difficult to create asset formation optimized for each individual.

[0158] 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.

[0159] In this invention, the server includes artificial intelligence means for acquiring market information and predicting future economic market trends; calculation means for receiving individual economic situation information and biometric data and calculating an appropriate savings amount for the user; and information generation means for generating the results of the artificial intelligence means and the calculation means and providing recommendation information that takes into account the results of sentiment analysis. This makes it possible to provide an optimized investment portfolio that takes into account the user's emotional state, thereby supporting rational investment decisions while reducing stress and enabling secure asset building.

[0160] "Market information" refers to price trends and trading information for stocks, bonds, currencies, and other financial instruments in the financial markets, as well as economic indicator data.

[0161] "Artificial intelligence methods" refer to technologies that use machine learning to analyze large amounts of data and predict future trends and patterns.

[0162] "Individual economic information" refers to data on an individual user's income, expenses, assets, and liabilities.

[0163] "Biometric data" refers to physiological data related to emotional states, such as voice tone and facial expression images, obtained from users.

[0164] "Calculation means" refers to devices or software that perform the process of calculating specific numerical values ​​using mathematical formulas or algorithms based on received data.

[0165] "Information generation means" refers to devices and software that are responsible for the process of constructing useful information based on calculation results and prediction results and providing it to users.

[0166] "Emotional analysis results" refer to information about stress levels and risk preferences obtained by analyzing the user's biometric data.

[0167] An "investment portfolio" refers to a combination of financial instruments in which assets are allocated to achieve a specific investment objective.

[0168] This invention is an asset formation support system that takes into account the emotional state of the user, and is implemented by utilizing a server, terminal, user, and emotion analysis function.

[0169] Server Functions

[0170] The server first receives data representing the user's financial situation and biometric data transmitted from the terminal and securely stores it. The server collects market information in real time from financial data provision services and uses this to predict future economic market trends using an AI model. This AI model utilizes machine learning frameworks such as TensorFlow and PyTorch. The data obtained from the prediction results is processed by information generation means to create an optimal investment portfolio for the user.

[0171] Emotion analysis function

[0172] The emotion analysis function analyzes user biometric data acquired through the device. Specifically, it uses open-source emotion recognition models (e.g., OpenFace) to evaluate stress levels and risk preferences from the user's facial expressions and voice tone. This result is sent to a server and incorporated into investment advice.

[0173] Device functions

[0174] The terminal collects economic and biometric data from users and transmits it to the server and sentiment analysis functions. The terminal also visually displays recommended investment portfolios received from the server to the user. In this process, the terminal's display software can be used to represent the information in graphs and charts.

[0175] User actions

[0176] Users input their daily income and expenditure data into the device and, following the device's instructions, also collect biometric data, such as recording their voice tone and taking photos of their facial expressions. Based on this information, the system provides an optimized investment plan that takes their emotional state into account. Specifically, it supports asset building by having users record their expenses using their smartphones in their daily lives and making conservative investment choices on stressful days.

[0177] Examples of specific cases and prompt statements

[0178] For example, if a user enters an annual income of $100,000 and monthly expenses of $7,000, the server will use this data to make market predictions. Simultaneously, the sentiment analysis function will capture the user's smile in front of the camera and evaluate their "relaxed emotional state." Based on this data, the server will suggest an appropriate allocation of stocks and bonds. An example of a prompt message would be: "Please generate an optimal investment portfolio considering the user's financial situation data and emotional state."

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] Users input their financial data, such as income and expenses, into the device. They also provide biometric data by recording their voice tone and taking facial images with the camera, following the device's instructions. This input data reflects the user's financial situation and emotional state.

[0182] Step 2:

[0183] The terminal sends the collected economic and biometric data to the server. In this process, the input data is encrypted via a dedicated protocol and securely transferred to the server over the network.

[0184] Step 3:

[0185] The server stores the user's economic data received from the terminal in a database. It also transfers biometric data to the sentiment analysis function. The data processing performed here involves formatting the data itself and standardizing the data format.

[0186] Step 4:

[0187] The emotion analysis function recognizes the user's emotional state by analyzing biometric data. This process involves an AI model analyzing facial expressions and vocal intonation, performing data calculations to identify stress levels and risk preferences. The emotion analysis results are then sent to a server as output.

[0188] Step 5:

[0189] The server acquires market information and uses the AI ​​model again to predict future market trends. Using market data as input, it extracts trends and patterns using machine learning algorithms and outputs prediction results.

[0190] Step 6:

[0191] The server designs an optimal investment portfolio using information generation methods based on the user's economic data and sentiment analysis results. This data processing uses AI model predictions and sentiment analysis results to calculate asset allocation that considers risk appropriateness. The generated recommendations are then sent to the terminal.

[0192] Step 7:

[0193] The terminal displays a recommended investment portfolio sent from the server to the user. This process presents information visually and clearly through a visual interface. Based on the recommended portfolio, the user can make their own investment decisions.

[0194] (Application Example 2)

[0195] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0196] Traditional asset building systems make investment decisions without considering the user's emotional state, leading to problems such as irrational investment decisions due to emotional fluctuations and the accumulation of stress. In particular, they lacked proposals for investment portfolios tailored to stress levels and risk preferences, making it difficult to provide flexible investment strategies that meet the diverse needs of users.

[0197] 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.

[0198] In this invention, the server includes analytical means for acquiring market information and predicting future financial market trends; computation means for receiving individual economic situation data and calculating a suitable amount for the user; sentiment analysis means for analyzing the user's biometric data and evaluating their emotional state; and adjustment means for evaluating and adjusting stress levels and risk preferences based on the emotional state. This enables the provision of investment advice adapted to the user's emotional state and rational investment decisions.

[0199] "Market information" is a general term for data that shows trends such as price fluctuations and trading conditions in financial markets.

[0200] "Analytical tools" are elements that have the function of predicting future financial market trends based on market information.

[0201] "Economic situation data" refers to data that includes economic information such as the user's income, expenses, assets, and liabilities.

[0202] A "calculation tool" is an element that has the function of calculating an appropriate amount of storage for the user based on the received economic situation data.

[0203] An "information generation means" is an element that has the function of creating recommended information to present to users using data obtained from analysis.

[0204] "Biometric data" refers to data that measures a user's physical characteristics, including, for example, voice and facial expressions.

[0205] An "emotion analysis tool" is an element that has the function of identifying the user's current emotional state based on biometric data.

[0206] "Adjustment mechanisms" are functions used to assess stress levels and risk preferences, taking into account emotional states, in order to provide appropriate investment advice.

[0207] An "investment portfolio" is a combination of financial assets and a plan designed to propose the optimal allocation according to the user's investment goals.

[0208] "Stress level" is an indicator that shows the degree of stress in a user's emotional state.

[0209] "Risk preference" is an indicator that shows how much risk a user is willing to tolerate in their investments.

[0210] This invention realizes an asset formation support system that takes into account the user's emotions. This system consists of a server, terminals, users, and an emotion analysis engine.

[0211] The server acquires market information and uses AI models to predict future financial market trends. This allows it to provide an optimal storage plan based on the user's economic situation data. The server also uses advanced computer hardware and software for data processing through analytical and computational means. Specifically, it stores market data in conjunction with a database system and provides an advanced computing environment for operating AI models.

[0212] The device has the function of transmitting financial information and biometric data collected from the user to a server and sentiment analysis engine. Users can use the device to input their own financial data and provide biometric data such as voice and facial expressions. This allows for real-time analysis of the user's emotional state, influencing their investment decisions for the day.

[0213] The emotion analysis engine analyzes emotional states based on acquired biometric data. It evaluates stress levels and risk preferences, and adjusts investment portfolios accordingly. This engine utilizes machine learning models to accurately assess subtle emotional changes in users.

[0214] For example, if a smartphone user is experiencing stress due to their mood that day, the system will recommend low-risk investment options and adjust the system to allow them to manage their assets with peace of mind. The generative AI model is used to support investment decisions, generating flexible advice that responds to emotions using prompt sentences.

[0215] Examples of specific prompt messages are as follows:

[0216] "Consider a situation where a user is experiencing stress, and describe how you would provide risk-averse investment advice to that user."

[0217] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0218] Step 1:

[0219] The device receives economic and biometric data from the user as input. The device formats this input data and prepares it for transmission to the server and sentiment analysis engine.

[0220] Step 2:

[0221] The server collects market data and uses an AI model to predict future financial market trends. The input is the acquired market data, and the output is the predicted market trend data. Through this process, the server processes large amounts of data and generates optimized prediction results.

[0222] Step 3:

[0223] The emotion analysis engine analyzes biometric data received from the device to evaluate the user's current emotional state. The input is biometric data, and the output is indicator information showing the user's emotional state. This analysis quantifies the user's stress level and risk preference.

[0224] Step 4:

[0225] The server integrates the market trend data obtained in step 2 and the sentiment indicator obtained in step 3 to generate a recommended portfolio. The input is market trend data and sentiment indicator, and the output is adjusted investment portfolio data. This allows the server to create a rational investment strategy tailored to the user's sentiment and market conditions.

[0226] Step 5:

[0227] The terminal displays recommended portfolios received from the server to the user. The input is recommended portfolio data from the server, and the output is information presented visually to the user. The terminal uses visualization technology to provide information in a way that is easy for the user to understand.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] [Second Embodiment]

[0232] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0233] 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.

[0234] 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).

[0235] 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.

[0236] 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.

[0237] 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).

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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".

[0244] This invention is a support system designed to facilitate asset building for users. This system automates financial market forecasting and individual savings plans through the use of a server, terminal, and user components.

[0245] Server Functions

[0246] The server has the ability to acquire various financial market data and predict market trends using AI models based on that data. The server also receives users' financial situation data and calculates the optimal investment amount for each user based on that data. Furthermore, the server integrates market forecasts and investment plans to generate recommendations for users. These recommendations include suggested investment portfolios and explanations of the reasoning behind them.

[0247] Device functions

[0248] The terminal is equipped with communication means to send information entered by the user to the server, and receives the returned data from the server and displays it to the user. The terminal appropriately transfers information such as income, expenses, and investment style entered by the user to the server, and receives and displays the analysis results from the server.

[0249] User actions

[0250] Users input their income, expenses, and desired investment style (e.g., safety-first, moderately risk-tolerant) into the terminal. Once the user enters the information, it is encrypted and sent to the server. Based on the server's generated recommendations for stocks and investment amounts, users can then decide whether or not to start investing.

[0251] This system compensates for a lack of investment knowledge, supports manageable asset building tailored to individual financial situations, and provides an environment for confident investing. Therefore, it is particularly useful for young people looking to start investing and for users who have previously given up on investing.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The user activates the device and enters their monthly income, expenses, and desired investment style. This collects basic financial information.

[0255] Step 2:

[0256] The device encrypts the collected user information and transmits it to the server using a secure communication protocol.

[0257] Step 3:

[0258] The server receives the individual economic situation data that is sent and securely stores it in the database. Next, the server retrieves the latest market data through financial APIs.

[0259] Step 4:

[0260] Artificial intelligence installed on the server analyzes market data and predicts future financial market trends. This process analyzes financial information such as stock price fluctuations and exchange rates.

[0261] Step 5:

[0262] The server calculates the investment amount based on the AI's predictions and the user's financial situation data. Furthermore, it selects the most suitable investment products for the user and generates recommendation information.

[0263] Step 6:

[0264] The server sends the generated recommendations and savings plan to the device. This data is also encrypted, so your privacy is protected.

[0265] Step 7:

[0266] The terminal decrypts the data received from the server and presents it to the user through a graphical user interface. At this stage, the recommended portfolio and investment amount are displayed.

[0267] Step 8:

[0268] The user reviews the provided information and decides whether or not to actually invest. If they choose to invest, the investment process begins when they send instructions from their device.

[0269] Step 9:

[0270] The server, upon user approval, executes the order with the partner financial institution. All transactions are recorded and can be referenced later.

[0271] (Example 1)

[0272] 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."

[0273] The present invention aims to efficiently and optimally support asset building tailored to the individual financial situation of each user. Specifically, it aims to create a system that allows even novice investors or those with little experience to confidently begin investing by appropriately predicting trends in financial markets and providing savings plans suitable for each user.

[0274] 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.

[0275] In this invention, the server includes artificial intelligence means for acquiring market information and predicting future economic market trends; calculation means for receiving individual economic situation information and calculating an appropriate savings amount for the user; and information generation means for integrating the results of the artificial intelligence means and the calculation means and providing recommended information to the user. This makes it possible to provide each user with an accurate investment plan.

[0276] "Market information" refers to data related to financial markets, such as stock prices, exchange rates, and commodity prices.

[0277] The "artificial intelligence means" refers to a computer program including machine learning algorithms for analyzing market information and predicting the trends of future economic markets.

[0278] The "individual economic situation information" refers to information regarding the income, expenditure, asset situation, and investment policies of each user.

[0279] The "calculation means" refers to an algorithm and computing mechanism for deriving a savings amount and investment plan suitable for the user based on the individual economic situation information.

[0280] The "information generation means" refers to a computer program having a function of integrating the results of the artificial intelligence means and the calculation means and providing an investment plan and reasons recommended to the user.

[0281] The "communication means" refers to network communication technology for securely encrypting information from the user and transmitting it to the server.

[0282] The "display means" refers to a user interface for visually presenting the recommended information received from the server to the user in an easy-to-see form.

[0283] The present invention is a system for enabling a user to safely perform asset formation, and it proceeds through the interaction of the server, the terminal, and the user.

[0284] The server continuously obtains market information from an external data provider. At this time, as the software used, Python is used, and a machine learning model is constructed using its libraries such as TensorFlow and PyTorch. Thereby, the server has a function of predicting the future economic market based on past market data. For example, long-term and short-term time series data is analyzed to perform trend analysis of stock prices and prediction of economic indicators. Furthermore, the server receives the individual economic situation information of the user and creates a savings plan based on it.

[0285] The terminal has communication means for securely transmitting the economic information input by the user to the server. For communication, a secure communication protocol is used to prevent data leakage. The terminal also receives the recommended information transmitted from the server and displays it in a way that can be intuitively understood by the user. Specifically, the user interface shows the risk and return overview of each investment destination and the recommended savings amount in visual charts and text.

[0286] The user inputs monthly income, expenses, and the desired investment style (e.g., safety - first type) through the terminal. Based on the recommended portfolio and savings plan generated by the server, the user makes a decision on whether to actually invest. For example, the user can input based on a prompt such as "My monthly income is 500,000 yen, my monthly expenses are 300,000 yen, and I prefer a safety - first investment style. Please propose the optimal investment plan."

[0287] In this way, the present invention utilizes a generative AI model and provides asset management options according to the individual needs of users, thus playing a role as a system to compensate for the lack of understanding of investment.

[0288] The flow of the specific process in Example 1 will be described using FIG. 11.

[0289] Step 1:

[0290] The user uses the terminal to input their economic situation. Specifically, information such as monthly income, monthly essential expenses, and investment risk tolerance (e.g., safety - first type) is input into the interface. This input information is encrypted within the terminal and prepared for transmission to the server. By encrypting the input data, the data during communication is protected.

[0291] Step 2:

[0292] The terminal sends the entered economic status information to the server. During this process, encrypted data is sent to the server using a secure communication protocol. The server receives this data and decrypts it afterward. The output of this process is the decrypted user's economic information.

[0293] Step 3:

[0294] The server retrieves current market information from an external data provider. This information includes the latest stock prices, interest rates, and exchange rates. Using the retrieved market information, the server runs a generating AI model to analyze future market trends. The analysis results in the output of predicted market trend data.

[0295] Step 4:

[0296] The server integrates decoded user economic information and market forecast data to calculate individually optimized monthly investment amounts. This calculation takes into account predicted market risk and return. After the calculation, data containing the optimal investment plan and recommended monthly investment amounts for the user is generated and output.

[0297] Step 5:

[0298] The server sends the calculated recommendation information to the terminal. The output from the server is a dataset containing the recommendation information, which also includes the recommended portfolio and the reasons for it. After receiving this information, the terminal prepares to decrypt it from its encrypted state and convert it into a user-friendly format.

[0299] Step 6:

[0300] The terminal displays recommended information provided by the server through its user interface. Specifically, it shows the risk and return of each investment and the recommended monthly investment amount in graphs and text, and also displays data explaining the reasons for the investment. The output here is a recommended plan presented in a visual form.

[0301] Step 7:

[0302] Based on the recommended information provided by the terminal, the user makes their own investment decisions. If the user understands and agrees with the displayed data, they can choose to operate the terminal and start actual investments.

[0303] (Application Example 1)

[0304] 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".

[0305] In the modern financial market, users are faced with a vast amount of information and it is difficult to make judgments for appropriate asset formation. Therefore, for users with little experience in asset formation to make appropriate investments, a lot of effort and knowledge are required. Also, it is difficult to manage daily expenses and conduct asset formation simultaneously, which is a major burden for users lacking time and specialized knowledge. Thus, a mechanism that takes into account the user's spending patterns and automatically adjusts asset formation is required.

[0306] 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.

[0307] In this invention, the server includes an analysis means for acquiring market data and predicting future financial market trends, a calculation means for receiving individual economic situation data and calculating an appropriate savings amount for the user, and an adjustment means for automatically adjusting the investment plan based on the user's spending pattern. Thereby, optimal investment advice according to the user's spending situation becomes possible, and while compensating for the lack of specialized knowledge, the user can safely conduct asset formation.

[0308] "Market data" is a collection of information indicating the situation and trends of the financial market, which includes stock prices, exchange rates, interest rates, economic indicators, etc.

[0309] "Analytical tools" refer to methods and techniques for analyzing market data and predicting future financial market trends.

[0310] "Economic status data" refers to a collection of information that shows the financial status of users, such as their income, expenses, assets, and liabilities.

[0311] "Calculation methods" refer to methods and techniques for calculating an appropriate savings amount based on the user's financial situation data.

[0312] "Adjustment mechanisms" refer to systems or functions that automatically optimize investment plans according to the user's spending patterns and economic situation.

[0313] "Information generation means" refers to methods and technologies for providing users with appropriate investment plans and recommended information based on the results of analysis and calculation means.

[0314] This invention is a support system for users to easily build assets. This system consists of a server, a terminal, and a user.

[0315] The server collects market data from financial markets. Through analytical methods, the server uses this data to predict future trends in financial markets. Specifically, the server utilizes generative AI models to analyze historical market data and current market information to derive future market trends. This process utilizes a cloud computing environment capable of processing large amounts of data.

[0316] The server also receives user financial data from the terminal. Using calculation tools, the server calculates the optimal savings amount for each user based on their income, expenses, and other economic indicators. Furthermore, adjustment tools work based on this information to automatically optimize the investment plan according to the user's spending patterns.

[0317] The terminal functions as the user's input interface. The user inputs information about their income, expenses, and investment style on the terminal, and this data is sent and received between the terminal and the server. The terminal receives recommendation information generated by the server and displays it visually to the user. Based on this recommendation information, the user can easily begin building their assets.

[0318] As a concrete example, if a user inputs a monthly income of 50,000 yen and expenses of 20,000 yen, the server can analyze that disposable income and recommend investing 3,000 yen per month. This recommendation can be applied to various investment opportunities, such as mutual funds or stock purchases. As market trends change, the AI ​​dynamically adjusts the investment amount and plan, so the user always receives optimized advice. An example of a prompt message would be, "Your income is 50,000 yen and your expenses are 20,000 yen. Please create a stable portfolio."

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] The server collects real-time market data from financial markets. The input is market information, and the output is a dataset for analysis. The server performs large-scale data processing and prepares it for input into generative AI models.

[0322] Step 2:

[0323] The server uses a generative AI model to analyze market data. The input is a dataset for analysis, and the output is forecast information for future financial markets. The AI ​​model learns from past market trends and performs forecast calculations using a new dataset.

[0324] Step 3:

[0325] The terminal receives data from the user regarding income, expenses, and investment style. The input is the user's financial status data, and the output is transformed data sent to the server. The terminal collects data through the user interface and sends it to the server in an appropriate format.

[0326] Step 4:

[0327] The server calculates the appropriate savings amount for each user based on their financial situation data. The input is transformed data, and the output is the calculated savings amount. A calculation method is used to determine the optimal savings amount based on the user's income and expenses.

[0328] Step 5:

[0329] The server automatically optimizes an investment plan that takes into account the user's spending patterns, using an adjustment mechanism. The input is the calculated savings amount and market forecast information, and the output is the optimized investment plan. The adjustment mechanism analyzes the user's spending history and dynamically adjusts the investment plan.

[0330] Step 6:

[0331] The server provides the generated optimized investment plan to the user as recommended information through an information generation mechanism. The input is the optimized investment plan, and the output is the recommended information displayed to the user. The information generation mechanism generates a prompt statement and clearly explains the reasons for the recommendation.

[0332] Step 7:

[0333] The user reviews the recommendations received from the server via their device and makes a decision to start investing based on the information presented. The input is the recommendations from the server, and the output is the user's decision. The user understands the contents of the presented portfolio and makes investments as needed.

[0334] 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.

[0335] This invention provides an asset building support system that takes into account the user's emotions in addition to forecasting financial market trends and creating individual savings plans. This system is realized through the collaboration of various elements, including a server, terminal, user, and emotion engine.

[0336] Server Functions

[0337] The server first securely stores the user's financial situation data received from the terminal. Simultaneously, the server collects market data and uses AI models to predict future financial market trends. The results of this prediction are then used, along with information generation tools, to create a recommended investment portfolio tailored to the user.

[0338] Functions of the Emotion Engine

[0339] The emotion engine analyzes the user's biometric and interaction data acquired through the device to identify their current emotional state. Based on this emotional state, the emotion engine evaluates stress levels and risk preferences and sends the results to the server.

[0340] Device functions

[0341] The device transmits financial and biometric data collected from the user to the server and emotion engine. It also has the function of displaying recommendations and investment advice returned by the server to the user.

[0342] User actions

[0343] Users can input their income and expenditure data into the device and participate in acquiring biometric data (such as voice tone and facial expression images) as prompted by the device. This allows the system to provide an optimized investment plan that also takes into account the user's emotional state for the day. Users then decide whether to execute the investment based on the results adjusted by the emotion engine.

[0344] This system allows users to make more rational investment decisions that are often influenced by emotions, enabling them to build wealth with less stress and greater peace of mind. This approach represents an evolution from traditional wealth-building methods and is an innovative approach that takes into account the importance of an individual's emotional state in wealth creation.

[0345] The following describes the processing flow.

[0346] Step 1:

[0347] Users use their devices to input information about their monthly income, expenses, and current financial situation. This information is used as basic data for wealth building.

[0348] Step 2:

[0349] The device collects emotion-related data provided by the user. This includes biometric data such as voice tone, facial expressions, and heart rate.

[0350] Step 3:

[0351] The device encrypts the collected financial and emotional data before sending it to the server. Strong security protocols are used to protect data privacy.

[0352] Step 4:

[0353] The server retrieves the latest market data from financial market data providers and analyzes that data using artificial intelligence. This analysis is performed to predict future market trends.

[0354] Step 5:

[0355] The server calculates the optimal savings amount based on the individual financial situation data it receives. This includes adjustments to reduce the burden based on the user's income, expenses, and emotional state.

[0356] Step 6:

[0357] The emotion engine analyzes emotional data sent from the server to assess the user's stress levels and risk preferences. This information is then used to refine the recommended portfolio.

[0358] Step 7:

[0359] The server integrates the prediction results from artificial intelligence and the evaluation results from the emotion engine to generate a recommended investment portfolio tailored to the user. This includes specific investment products and investment proportions.

[0360] Step 8:

[0361] The server sends the generated recommendation information to the terminal. The terminal receives this information and displays it in an easy-to-understand format for the user.

[0362] Step 9:

[0363] Based on the information presented, users make investment decisions that align with their emotional state. The selection is completed on the device, and the investment can then be executed by following subsequent instructions.

[0364] (Example 2)

[0365] 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".

[0366] In modern asset management, a problem exists where users find it difficult to make rational investment decisions due to stress stemming from short-term emotional fluctuations and market uncertainty. Furthermore, traditional systems offer uniform investment recommendations without considering the emotional state of the user, making it difficult to create asset formation optimized for each individual.

[0367] 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.

[0368] In this invention, the server includes artificial intelligence means for acquiring market information and predicting future economic market trends; calculation means for receiving individual economic situation information and biometric data and calculating an appropriate savings amount for the user; and information generation means for generating the results of the artificial intelligence means and the calculation means and providing recommendation information that takes into account the results of sentiment analysis. This makes it possible to provide an optimized investment portfolio that takes into account the user's emotional state, thereby supporting rational investment decisions while reducing stress and enabling secure asset building.

[0369] "Market information" refers to price trends and trading information for stocks, bonds, currencies, and other financial instruments in the financial markets, as well as economic indicator data.

[0370] "Artificial intelligence methods" refer to technologies that use machine learning to analyze large amounts of data and predict future trends and patterns.

[0371] "Individual economic information" refers to data on an individual user's income, expenses, assets, and liabilities.

[0372] "Biometric data" refers to physiological data related to emotional states, such as voice tone and facial expression images, obtained from users.

[0373] "Calculation means" refers to devices or software that perform the process of calculating specific numerical values ​​using mathematical formulas or algorithms based on received data.

[0374] "Information generation means" refers to devices and software that are responsible for the process of constructing useful information based on calculation results and prediction results and providing it to users.

[0375] "Emotional analysis results" refer to information about stress levels and risk preferences obtained by analyzing the user's biometric data.

[0376] An "investment portfolio" refers to a combination of financial instruments in which assets are allocated to achieve a specific investment objective.

[0377] This invention is an asset formation support system that takes into account the emotional state of the user, and is implemented by utilizing a server, terminal, user, and emotion analysis function.

[0378] Server Functions

[0379] The server first receives data representing the user's financial situation and biometric data transmitted from the terminal and securely stores it. The server collects market information in real time from financial data provision services and uses this to predict future economic market trends using an AI model. This AI model utilizes machine learning frameworks such as TensorFlow and PyTorch. The data obtained from the prediction results is processed by information generation means to create an optimal investment portfolio for the user.

[0380] Emotion analysis function

[0381] The emotion analysis function analyzes user biometric data acquired through the device. Specifically, it uses open-source emotion recognition models (e.g., OpenFace) to evaluate stress levels and risk preferences from the user's facial expressions and voice tone. This result is sent to a server and incorporated into investment advice.

[0382] Device functions

[0383] The terminal collects economic and biometric data from users and transmits it to the server and sentiment analysis functions. The terminal also visually displays recommended investment portfolios received from the server to the user. In this process, the terminal's display software can be used to represent the information in graphs and charts.

[0384] User actions

[0385] Users input their daily income and expenditure data into the device and, following the device's instructions, also collect biometric data, such as recording their voice tone and taking photos of their facial expressions. Based on this information, the system provides an optimized investment plan that takes their emotional state into account. Specifically, it supports asset building by having users record their expenses using their smartphones in their daily lives and making conservative investment choices on stressful days.

[0386] Examples of specific cases and prompt statements

[0387] For example, if a user enters an annual income of $100,000 and monthly expenses of $7,000, the server will use this data to make market predictions. Simultaneously, the sentiment analysis function will capture the user's smile in front of the camera and evaluate their "relaxed emotional state." Based on this data, the server will suggest an appropriate allocation of stocks and bonds. An example of a prompt message would be: "Please generate an optimal investment portfolio considering the user's financial situation data and emotional state."

[0388] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0389] Step 1:

[0390] Users input their financial data, such as income and expenses, into the device. They also provide biometric data by recording their voice tone and taking facial images with the camera, following the device's instructions. This input data reflects the user's financial situation and emotional state.

[0391] Step 2:

[0392] The terminal sends the collected economic and biometric data to the server. In this process, the input data is encrypted via a dedicated protocol and securely transferred to the server over the network.

[0393] Step 3:

[0394] The server stores the user's economic data received from the terminal in a database. It also transfers biometric data to the sentiment analysis function. The data processing performed here involves formatting the data itself and standardizing the data format.

[0395] Step 4:

[0396] The emotion analysis function recognizes the user's emotional state by analyzing biometric data. This process involves an AI model analyzing facial expressions and vocal intonation, performing data calculations to identify stress levels and risk preferences. The emotion analysis results are then sent to a server as output.

[0397] Step 5:

[0398] The server acquires market information and uses the AI ​​model again to predict future market trends. Using market data as input, it extracts trends and patterns using machine learning algorithms and outputs prediction results.

[0399] Step 6:

[0400] The server designs an optimal investment portfolio using information generation methods based on the user's economic data and sentiment analysis results. This data processing uses AI model predictions and sentiment analysis results to calculate asset allocation that considers risk appropriateness. The generated recommendations are then sent to the terminal.

[0401] Step 7:

[0402] The terminal displays a recommended investment portfolio sent from the server to the user. This process presents information visually and clearly through a visual interface. Based on the recommended portfolio, the user can make their own investment decisions.

[0403] (Application Example 2)

[0404] 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 as the "terminal".

[0405] Traditional asset building systems make investment decisions without considering the user's emotional state, leading to problems such as irrational investment decisions due to emotional fluctuations and the accumulation of stress. In particular, they lacked proposals for investment portfolios tailored to stress levels and risk preferences, making it difficult to provide flexible investment strategies that meet the diverse needs of users.

[0406] 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.

[0407] In this invention, the server includes analytical means for acquiring market information and predicting future financial market trends; computation means for receiving individual economic situation data and calculating a suitable amount for the user; sentiment analysis means for analyzing the user's biometric data and evaluating their emotional state; and adjustment means for evaluating and adjusting stress levels and risk preferences based on the emotional state. This enables the provision of investment advice adapted to the user's emotional state and rational investment decisions.

[0408] "Market information" is a general term for data that shows trends such as price fluctuations and trading conditions in financial markets.

[0409] "Analytical tools" are elements that have the function of predicting future financial market trends based on market information.

[0410] "Economic situation data" refers to data that includes economic information such as the user's income, expenses, assets, and liabilities.

[0411] A "calculation tool" is an element that has the function of calculating an appropriate amount of storage for the user based on the received economic situation data.

[0412] An "information generation means" is an element that has the function of creating recommended information to present to users using data obtained from analysis.

[0413] "Biometric data" refers to data that measures a user's physical characteristics, including, for example, voice and facial expressions.

[0414] An "emotion analysis tool" is an element that has the function of identifying the user's current emotional state based on biometric data.

[0415] "Adjustment mechanisms" are functions used to assess stress levels and risk preferences, taking into account emotional states, in order to provide appropriate investment advice.

[0416] An "investment portfolio" is a combination of financial assets and a plan designed to propose the optimal allocation according to the user's investment goals.

[0417] "Stress level" is an indicator that shows the degree of stress in a user's emotional state.

[0418] "Risk preference" is an indicator that shows how much risk a user is willing to tolerate in their investments.

[0419] This invention realizes an asset formation support system that takes into account the user's emotions. This system consists of a server, terminals, users, and an emotion analysis engine.

[0420] The server acquires market information and uses AI models to predict future financial market trends. This allows it to provide an optimal storage plan based on the user's economic situation data. The server also uses advanced computer hardware and software for data processing through analytical and computational means. Specifically, it stores market data in conjunction with a database system and provides an advanced computing environment for operating AI models.

[0421] The device has the function of transmitting financial information and biometric data collected from the user to a server and sentiment analysis engine. Users can use the device to input their own financial data and provide biometric data such as voice and facial expressions. This allows for real-time analysis of the user's emotional state, influencing their investment decisions for the day.

[0422] The emotion analysis engine analyzes emotional states based on acquired biometric data. It evaluates stress levels and risk preferences, and adjusts investment portfolios accordingly. This engine utilizes machine learning models to accurately assess subtle emotional changes in users.

[0423] For example, if a smartphone user is experiencing stress due to their mood that day, the system will recommend low-risk investment options and adjust the system to allow them to manage their assets with peace of mind. The generative AI model is used to support investment decisions, generating flexible advice that responds to emotions using prompt sentences.

[0424] Examples of specific prompt messages are as follows:

[0425] "Consider a situation where a user is experiencing stress, and describe how you would provide risk-averse investment advice to that user."

[0426] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0427] Step 1:

[0428] The device receives economic and biometric data from the user as input. The device formats this input data and prepares it for transmission to the server and sentiment analysis engine.

[0429] Step 2:

[0430] The server collects market data and uses an AI model to predict future financial market trends. The input is the acquired market data, and the output is the predicted market trend data. Through this process, the server processes large amounts of data and generates optimized prediction results.

[0431] Step 3:

[0432] The emotion analysis engine analyzes biometric data received from the device to evaluate the user's current emotional state. The input is biometric data, and the output is indicator information showing the user's emotional state. This analysis quantifies the user's stress level and risk preference.

[0433] Step 4:

[0434] The server integrates the market trend data obtained in step 2 and the sentiment indicator obtained in step 3 to generate a recommended portfolio. The input is market trend data and sentiment indicator, and the output is adjusted investment portfolio data. This allows the server to create a rational investment strategy tailored to the user's sentiment and market conditions.

[0435] Step 5:

[0436] The terminal displays recommended portfolios received from the server to the user. The input is recommended portfolio data from the server, and the output is information presented visually to the user. The terminal uses visualization technology to provide information in a way that is easy for the user to understand.

[0437] 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.

[0438] 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.

[0439] 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.

[0440] [Third Embodiment]

[0441] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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".

[0453] This invention is a support system designed to facilitate asset building for users. This system automates financial market forecasting and individual savings plans through the use of a server, terminal, and user components.

[0454] Server Functions

[0455] The server has the ability to acquire various financial market data and predict market trends using AI models based on that data. The server also receives users' financial situation data and calculates the optimal investment amount for each user based on that data. Furthermore, the server integrates market forecasts and investment plans to generate recommendations for users. These recommendations include suggested investment portfolios and explanations of the reasoning behind them.

[0456] Device functions

[0457] The terminal is equipped with communication means to send information entered by the user to the server, and receives the returned data from the server and displays it to the user. The terminal appropriately transfers information such as income, expenses, and investment style entered by the user to the server, and receives and displays the analysis results from the server.

[0458] User actions

[0459] Users input their income, expenses, and desired investment style (e.g., safety-first, moderately risk-tolerant) into the terminal. Once the user enters the information, it is encrypted and sent to the server. Based on the server's generated recommendations for stocks and investment amounts, users can then decide whether or not to start investing.

[0460] This system compensates for a lack of investment knowledge, supports manageable asset building tailored to individual financial situations, and provides an environment for confident investing. Therefore, it is particularly useful for young people looking to start investing and for users who have previously given up on investing.

[0461] The following describes the processing flow.

[0462] Step 1:

[0463] The user activates the device and enters their monthly income, expenses, and desired investment style. This collects basic financial information.

[0464] Step 2:

[0465] The device encrypts the collected user information and transmits it to the server using a secure communication protocol.

[0466] Step 3:

[0467] The server receives the individual economic situation data that is sent and securely stores it in the database. Next, the server retrieves the latest market data through financial APIs.

[0468] Step 4:

[0469] Artificial intelligence installed on the server analyzes market data and predicts future financial market trends. This process analyzes financial information such as stock price fluctuations and exchange rates.

[0470] Step 5:

[0471] The server calculates the investment amount based on the AI's predictions and the user's financial situation data. Furthermore, it selects the most suitable investment products for the user and generates recommendation information.

[0472] Step 6:

[0473] The server sends the generated recommendations and savings plan to the device. This data is also encrypted, so your privacy is protected.

[0474] Step 7:

[0475] The terminal decrypts the data received from the server and presents it to the user through a graphical user interface. At this stage, the recommended portfolio and investment amount are displayed.

[0476] Step 8:

[0477] The user reviews the provided information and decides whether or not to actually invest. If they choose to invest, the investment process begins when they send instructions from their device.

[0478] Step 9:

[0479] The server, upon user approval, executes the order with the partner financial institution. All transactions are recorded and can be referenced later.

[0480] (Example 1)

[0481] 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."

[0482] The present invention aims to efficiently and optimally support asset building tailored to the individual financial situation of each user. Specifically, it aims to create a system that allows even novice investors or those with little experience to confidently begin investing by appropriately predicting trends in financial markets and providing savings plans suitable for each user.

[0483] 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.

[0484] In this invention, the server includes artificial intelligence means for acquiring market information and predicting future economic market trends; calculation means for receiving individual economic situation information and calculating an appropriate savings amount for the user; and information generation means for integrating the results of the artificial intelligence means and the calculation means and providing recommended information to the user. This makes it possible to provide each user with an accurate investment plan.

[0485] "Market information" refers to data related to financial markets, such as stock prices, exchange rates, and commodity prices.

[0486] "Artificial intelligence tools" refer to computer programs that include machine learning algorithms for analyzing market information and predicting future economic market trends.

[0487] "Individual economic information" refers to information regarding each user's income, expenses, asset status, and investment policies.

[0488] "Calculation means" refers to algorithms and calculation mechanisms used to derive appropriate savings amounts and investment plans for users based on individual economic situation information.

[0489] "Information generation means" refers to a computer program that integrates the results of artificial intelligence means and computation means and has the function of providing users with recommended investment plans and reasons.

[0490] "Communication methods" refer to network communication technologies used to securely encrypt and transmit information from users to the server.

[0491] "Display means" refers to a user interface that presents recommended information received from the server to the user in a visually easy-to-understand format.

[0492] This invention is a system that enables users to build assets with peace of mind, and it proceeds through the interaction of servers, terminals, and users.

[0493] The server continuously acquires market information from external data providers. Python is used as the software for this, and machine learning models are built using its libraries, TensorFlow and PyTorch. This allows the server to predict future economic markets based on historical market data. For example, it analyzes short- and long-term time series data to perform stock price trend analysis and predict economic indicators. Furthermore, the server receives individual economic information from users and creates investment plans based on this information.

[0494] The terminal is equipped with a means of securely transmitting user-entered financial information to a server. A secure communication protocol is used to prevent data leakage. The terminal also receives recommended information from the server and displays it in a way that is intuitively understandable to the user. Specifically, the user interface shows an overview of the risks and returns of each investment, as well as recommended monthly contribution amounts, using visual charts and text.

[0495] Users input their monthly income and expenses, as well as their desired investment style (e.g., safety-oriented) through their device. Based on this, they can then decide whether or not to actually invest, using the server-generated recommended portfolio and investment plan as a reference. For example, a user might input information based on a prompt such as, "Please suggest the optimal investment plan for a monthly income of 500,000 yen, monthly expenses of 300,000 yen, and a safety-oriented style."

[0496] In this way, the present invention utilizes a generative AI model to provide asset management options tailored to the individual needs of users, thereby fulfilling its role as a system that compensates for a lack of understanding of investment.

[0497] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0498] Step 1:

[0499] Users input their financial information using their device. Specifically, they enter information such as their monthly income, essential monthly expenses, and investment risk tolerance (e.g., safety-oriented) into the interface. This input information is encrypted on the device and prepared for transmission to the server. Encryption of the entered data protects the data during transmission.

[0500] Step 2:

[0501] The terminal sends the entered economic status information to the server. During this process, encrypted data is sent to the server using a secure communication protocol. The server receives this data and decrypts it afterward. The output of this process is the decrypted user's economic information.

[0502] Step 3:

[0503] The server retrieves current market information from an external data provider. This information includes the latest stock prices, interest rates, and exchange rates. Using the retrieved market information, the server runs a generating AI model to analyze future market trends. The analysis results in the output of predicted market trend data.

[0504] Step 4:

[0505] The server integrates decoded user economic information and market forecast data to calculate individually optimized monthly investment amounts. This calculation takes into account predicted market risk and return. After the calculation, data containing the optimal investment plan and recommended monthly investment amounts for the user is generated and output.

[0506] Step 5:

[0507] The server sends the calculated recommendation information to the terminal. The output from the server is a dataset containing the recommendation information, which also includes the recommended portfolio and the reasons for it. After receiving this information, the terminal prepares to decrypt it from its encrypted state and convert it into a user-friendly format.

[0508] Step 6:

[0509] The terminal displays recommended information provided by the server through its user interface. Specifically, it shows the risk and return of each investment and the recommended monthly investment amount in graphs and text, and also displays data explaining the reasons for the investment. The output here is a recommended plan presented in a visual form.

[0510] Step 7:

[0511] Users make their investment decisions based on the recommendations provided by their device. If they understand and agree with the displayed data, they can choose to operate the device and begin making an actual investment.

[0512] (Application Example 1)

[0513] 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."

[0514] In today's financial markets, users are faced with a vast amount of information, making it difficult to make informed decisions about how to build wealth. Therefore, users with little experience in wealth building require considerable effort and knowledge to make appropriate investments. Furthermore, managing daily expenses and building wealth simultaneously is challenging and a significant burden for users lacking time and expertise. Thus, there is a need for a system that automatically adjusts wealth building based on the user's spending patterns.

[0515] 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.

[0516] In this invention, the server includes an analysis means for acquiring market data and predicting future financial market trends, a calculation means for receiving individual economic situation data and calculating an appropriate savings amount for the user, and an adjustment means for automatically adjusting the investment plan based on the user's spending patterns. This enables optimal investment advice tailored to the user's spending situation, compensating for any lack of specialized knowledge and allowing the user to build assets with peace of mind.

[0517] "Market data" refers to a collection of information that shows the state and trends of financial markets, and includes stock prices, exchange rates, interest rates, and economic indicators.

[0518] "Analytical tools" refer to methods and techniques for analyzing market data and predicting future financial market trends.

[0519] "Economic status data" refers to a collection of information that shows the financial status of users, such as their income, expenses, assets, and liabilities.

[0520] "Calculation methods" refer to methods and techniques for calculating an appropriate savings amount based on the user's financial situation data.

[0521] "Adjustment mechanisms" refer to systems or functions that automatically optimize investment plans according to the user's spending patterns and economic situation.

[0522] "Information generation means" refers to methods and technologies for providing users with appropriate investment plans and recommended information based on the results of analysis and calculation means.

[0523] This invention is a support system for users to easily build assets. This system consists of a server, a terminal, and a user.

[0524] The server collects market data from financial markets. Through analytical methods, the server uses this data to predict future trends in financial markets. Specifically, the server utilizes generative AI models to analyze historical market data and current market information to derive future market trends. This process utilizes a cloud computing environment capable of processing large amounts of data.

[0525] The server also receives user financial data from the terminal. Using calculation tools, the server calculates the optimal savings amount for each user based on their income, expenses, and other economic indicators. Furthermore, adjustment tools work based on this information to automatically optimize the investment plan according to the user's spending patterns.

[0526] The terminal functions as the user's input interface. The user inputs information about their income, expenses, and investment style on the terminal, and this data is sent and received between the terminal and the server. The terminal receives recommendation information generated by the server and displays it visually to the user. Based on this recommendation information, the user can easily begin building their assets.

[0527] As a concrete example, if a user inputs a monthly income of 50,000 yen and expenses of 20,000 yen, the server can analyze that disposable income and recommend investing 3,000 yen per month. This recommendation can be applied to various investment opportunities, such as mutual funds or stock purchases. As market trends change, the AI ​​dynamically adjusts the investment amount and plan, so the user always receives optimized advice. An example of a prompt message would be, "Your income is 50,000 yen and your expenses are 20,000 yen. Please create a stable portfolio."

[0528] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0529] Step 1:

[0530] The server collects real-time market data from financial markets. The input is market information, and the output is a dataset for analysis. The server performs large-scale data processing and prepares it for input into generative AI models.

[0531] Step 2:

[0532] The server uses a generative AI model to analyze market data. The input is a dataset for analysis, and the output is forecast information for future financial markets. The AI ​​model learns from past market trends and performs forecast calculations using a new dataset.

[0533] Step 3:

[0534] The terminal receives data from the user regarding income, expenses, and investment style. The input is the user's financial status data, and the output is transformed data sent to the server. The terminal collects data through the user interface and sends it to the server in an appropriate format.

[0535] Step 4:

[0536] The server calculates the appropriate savings amount for each user based on their financial situation data. The input is transformed data, and the output is the calculated savings amount. A calculation method is used to determine the optimal savings amount based on the user's income and expenses.

[0537] Step 5:

[0538] The server automatically optimizes an investment plan that takes into account the user's spending patterns, using an adjustment mechanism. The input is the calculated savings amount and market forecast information, and the output is the optimized investment plan. The adjustment mechanism analyzes the user's spending history and dynamically adjusts the investment plan.

[0539] Step 6:

[0540] The server provides the generated optimized investment plan to the user as recommended information through an information generation mechanism. The input is the optimized investment plan, and the output is the recommended information displayed to the user. The information generation mechanism generates a prompt statement and clearly explains the reasons for the recommendation.

[0541] Step 7:

[0542] The user reviews the recommendations received from the server via their device and makes a decision to start investing based on the information presented. The input is the recommendations from the server, and the output is the user's decision. The user understands the contents of the presented portfolio and makes investments as needed.

[0543] 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.

[0544] This invention provides an asset building support system that takes into account the user's emotions in addition to forecasting financial market trends and creating individual savings plans. This system is realized through the collaboration of various elements, including a server, terminal, user, and emotion engine.

[0545] Server Functions

[0546] The server first securely stores the user's financial situation data received from the terminal. Simultaneously, the server collects market data and uses AI models to predict future financial market trends. The results of this prediction are then used, along with information generation tools, to create a recommended investment portfolio tailored to the user.

[0547] Functions of the Emotion Engine

[0548] The emotion engine analyzes the user's biometric and interaction data acquired through the device to identify their current emotional state. Based on this emotional state, the emotion engine evaluates stress levels and risk preferences and sends the results to the server.

[0549] Device functions

[0550] The device transmits financial and biometric data collected from the user to the server and emotion engine. It also has the function of displaying recommendations and investment advice returned by the server to the user.

[0551] User actions

[0552] Users can input their income and expenditure data into the device and participate in acquiring biometric data (such as voice tone and facial expression images) as prompted by the device. This allows the system to provide an optimized investment plan that also takes into account the user's emotional state for the day. Users then decide whether to execute the investment based on the results adjusted by the emotion engine.

[0553] This system allows users to make more rational investment decisions that are often influenced by emotions, enabling them to build wealth with less stress and greater peace of mind. This approach represents an evolution from traditional wealth-building methods and is an innovative approach that takes into account the importance of an individual's emotional state in wealth creation.

[0554] The following describes the processing flow.

[0555] Step 1:

[0556] Users use their devices to input information about their monthly income, expenses, and current financial situation. This information is used as basic data for wealth building.

[0557] Step 2:

[0558] The device collects emotion-related data provided by the user. This includes biometric data such as voice tone, facial expressions, and heart rate.

[0559] Step 3:

[0560] The device encrypts the collected financial and emotional data before sending it to the server. Strong security protocols are used to protect data privacy.

[0561] Step 4:

[0562] The server retrieves the latest market data from financial market data providers and analyzes that data using artificial intelligence. This analysis is performed to predict future market trends.

[0563] Step 5:

[0564] The server calculates the optimal savings amount based on the individual financial situation data it receives. This includes adjustments to reduce the burden based on the user's income, expenses, and emotional state.

[0565] Step 6:

[0566] The emotion engine analyzes emotional data sent from the server to assess the user's stress levels and risk preferences. This information is then used to refine the recommended portfolio.

[0567] Step 7:

[0568] The server integrates the prediction results from artificial intelligence and the evaluation results from the emotion engine to generate a recommended investment portfolio tailored to the user. This includes specific investment products and investment proportions.

[0569] Step 8:

[0570] The server sends the generated recommendation information to the terminal. The terminal receives this information and displays it in an easy-to-understand format for the user.

[0571] Step 9:

[0572] Based on the information presented, users make investment decisions that align with their emotional state. The selection is completed on the device, and the investment can then be executed by following subsequent instructions.

[0573] (Example 2)

[0574] 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."

[0575] In modern asset management, a problem exists where users find it difficult to make rational investment decisions due to stress stemming from short-term emotional fluctuations and market uncertainty. Furthermore, traditional systems offer uniform investment recommendations without considering the emotional state of the user, making it difficult to create asset formation optimized for each individual.

[0576] 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.

[0577] In this invention, the server includes artificial intelligence means for acquiring market information and predicting future economic market trends; calculation means for receiving individual economic situation information and biometric data and calculating an appropriate savings amount for the user; and information generation means for generating the results of the artificial intelligence means and the calculation means and providing recommendation information that takes into account the results of sentiment analysis. This makes it possible to provide an optimized investment portfolio that takes into account the user's emotional state, thereby supporting rational investment decisions while reducing stress and enabling secure asset building.

[0578] "Market information" refers to price trends and trading information for stocks, bonds, currencies, and other financial instruments in the financial markets, as well as economic indicator data.

[0579] "Artificial intelligence methods" refer to technologies that use machine learning to analyze large amounts of data and predict future trends and patterns.

[0580] "Individual economic information" refers to data on an individual user's income, expenses, assets, and liabilities.

[0581] "Biometric data" refers to physiological data related to emotional states, such as voice tone and facial expression images, obtained from users.

[0582] "Calculation means" refers to devices or software that perform the process of calculating specific numerical values ​​using mathematical formulas or algorithms based on received data.

[0583] "Information generation means" refers to devices and software that are responsible for the process of constructing useful information based on calculation results and prediction results and providing it to users.

[0584] "Emotional analysis results" refer to information about stress levels and risk preferences obtained by analyzing the user's biometric data.

[0585] An "investment portfolio" refers to a combination of financial instruments in which assets are allocated to achieve a specific investment objective.

[0586] This invention is an asset formation support system that takes into account the emotional state of the user, and is implemented by utilizing a server, terminal, user, and emotion analysis function.

[0587] Server Functions

[0588] The server first receives data representing the user's financial situation and biometric data transmitted from the terminal and securely stores it. The server collects market information in real time from financial data provision services and uses this to predict future economic market trends using an AI model. This AI model utilizes machine learning frameworks such as TensorFlow and PyTorch. The data obtained from the prediction results is processed by information generation means to create an optimal investment portfolio for the user.

[0589] Emotion analysis function

[0590] The emotion analysis function analyzes user biometric data acquired through the device. Specifically, it uses open-source emotion recognition models (e.g., OpenFace) to evaluate stress levels and risk preferences from the user's facial expressions and voice tone. This result is sent to a server and incorporated into investment advice.

[0591] Device functions

[0592] The terminal collects economic and biometric data from users and transmits it to the server and sentiment analysis functions. The terminal also visually displays recommended investment portfolios received from the server to the user. In this process, the terminal's display software can be used to represent the information in graphs and charts.

[0593] User actions

[0594] Users input their daily income and expenditure data into the device and, following the device's instructions, also collect biometric data, such as recording their voice tone and taking photos of their facial expressions. Based on this information, the system provides an optimized investment plan that takes their emotional state into account. Specifically, it supports asset building by having users record their expenses using their smartphones in their daily lives and making conservative investment choices on stressful days.

[0595] Examples of specific cases and prompt statements

[0596] For example, if a user enters an annual income of $100,000 and monthly expenses of $7,000, the server will use this data to make market predictions. Simultaneously, the sentiment analysis function will capture the user's smile in front of the camera and evaluate their "relaxed emotional state." Based on this data, the server will suggest an appropriate allocation of stocks and bonds. An example of a prompt message would be: "Please generate an optimal investment portfolio considering the user's financial situation data and emotional state."

[0597] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0598] Step 1:

[0599] Users input their financial data, such as income and expenses, into the device. They also provide biometric data by recording their voice tone and taking facial images with the camera, following the device's instructions. This input data reflects the user's financial situation and emotional state.

[0600] Step 2:

[0601] The terminal sends the collected economic and biometric data to the server. In this process, the input data is encrypted via a dedicated protocol and securely transferred to the server over the network.

[0602] Step 3:

[0603] The server stores the user's economic data received from the terminal in a database. It also transfers biometric data to the sentiment analysis function. The data processing performed here involves formatting the data itself and standardizing the data format.

[0604] Step 4:

[0605] The emotion analysis function recognizes the user's emotional state by analyzing biometric data. This process involves an AI model analyzing facial expressions and vocal intonation, performing data calculations to identify stress levels and risk preferences. The emotion analysis results are then sent to a server as output.

[0606] Step 5:

[0607] The server acquires market information and uses the AI ​​model again to predict future market trends. Using market data as input, it extracts trends and patterns using machine learning algorithms and outputs prediction results.

[0608] Step 6:

[0609] The server designs an optimal investment portfolio using information generation methods based on the user's economic data and sentiment analysis results. This data processing uses AI model predictions and sentiment analysis results to calculate asset allocation that considers risk appropriateness. The generated recommendations are then sent to the terminal.

[0610] Step 7:

[0611] The terminal displays a recommended investment portfolio sent from the server to the user. This process presents information visually and clearly through a visual interface. Based on the recommended portfolio, the user can make their own investment decisions.

[0612] (Application Example 2)

[0613] 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."

[0614] Traditional asset building systems make investment decisions without considering the user's emotional state, leading to problems such as irrational investment decisions due to emotional fluctuations and the accumulation of stress. In particular, they lacked proposals for investment portfolios tailored to stress levels and risk preferences, making it difficult to provide flexible investment strategies that meet the diverse needs of users.

[0615] 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.

[0616] In this invention, the server includes analytical means for acquiring market information and predicting future financial market trends; computation means for receiving individual economic situation data and calculating a suitable amount for the user; sentiment analysis means for analyzing the user's biometric data and evaluating their emotional state; and adjustment means for evaluating and adjusting stress levels and risk preferences based on the emotional state. This enables the provision of investment advice adapted to the user's emotional state and rational investment decisions.

[0617] "Market information" is a general term for data that shows trends such as price fluctuations and trading conditions in financial markets.

[0618] "Analytical tools" are elements that have the function of predicting future financial market trends based on market information.

[0619] "Economic situation data" refers to data that includes economic information such as the user's income, expenses, assets, and liabilities.

[0620] A "calculation tool" is an element that has the function of calculating an appropriate amount of storage for the user based on the received economic situation data.

[0621] An "information generation means" is an element that has the function of creating recommended information to present to users using data obtained from analysis.

[0622] "Biometric data" refers to data that measures a user's physical characteristics, including, for example, voice and facial expressions.

[0623] An "emotion analysis tool" is an element that has the function of identifying the user's current emotional state based on biometric data.

[0624] "Adjustment mechanisms" are functions used to assess stress levels and risk preferences, taking into account emotional states, in order to provide appropriate investment advice.

[0625] An "investment portfolio" is a combination of financial assets and a plan designed to propose the optimal allocation according to the user's investment goals.

[0626] "Stress level" is an indicator that shows the degree of stress in a user's emotional state.

[0627] "Risk preference" is an indicator that shows how much risk a user is willing to tolerate in their investments.

[0628] This invention realizes an asset formation support system that takes into account the user's emotions. This system consists of a server, terminals, users, and an emotion analysis engine.

[0629] The server acquires market information and uses AI models to predict future financial market trends. This allows it to provide an optimal storage plan based on the user's economic situation data. The server also uses advanced computer hardware and software for data processing through analytical and computational means. Specifically, it stores market data in conjunction with a database system and provides an advanced computing environment for operating AI models.

[0630] The device has the function of transmitting financial information and biometric data collected from the user to a server and sentiment analysis engine. Users can use the device to input their own financial data and provide biometric data such as voice and facial expressions. This allows for real-time analysis of the user's emotional state, influencing their investment decisions for the day.

[0631] The emotion analysis engine analyzes emotional states based on acquired biometric data. It evaluates stress levels and risk preferences, and adjusts investment portfolios accordingly. This engine utilizes machine learning models to accurately assess subtle emotional changes in users.

[0632] For example, if a smartphone user is experiencing stress due to their mood that day, the system will recommend low-risk investment options and adjust the system to allow them to manage their assets with peace of mind. The generative AI model is used to support investment decisions, generating flexible advice that responds to emotions using prompt sentences.

[0633] Examples of specific prompt messages are as follows:

[0634] "Consider a situation where a user is experiencing stress, and describe how you would provide risk-averse investment advice to that user."

[0635] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0636] Step 1:

[0637] The device receives economic and biometric data from the user as input. The device formats this input data and prepares it for transmission to the server and sentiment analysis engine.

[0638] Step 2:

[0639] The server collects market data and uses an AI model to predict future financial market trends. The input is the acquired market data, and the output is the predicted market trend data. Through this process, the server processes large amounts of data and generates optimized prediction results.

[0640] Step 3:

[0641] The emotion analysis engine analyzes biometric data received from the device to evaluate the user's current emotional state. The input is biometric data, and the output is indicator information showing the user's emotional state. This analysis quantifies the user's stress level and risk preference.

[0642] Step 4:

[0643] The server integrates the market trend data obtained in step 2 and the sentiment indicator obtained in step 3 to generate a recommended portfolio. The input is market trend data and sentiment indicator, and the output is adjusted investment portfolio data. This allows the server to create a rational investment strategy tailored to the user's sentiment and market conditions.

[0644] Step 5:

[0645] The terminal displays recommended portfolios received from the server to the user. The input is recommended portfolio data from the server, and the output is information presented visually to the user. The terminal uses visualization technology to provide information in a way that is easy for the user to understand.

[0646] 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.

[0647] 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.

[0648] 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.

[0649] [Fourth Embodiment]

[0650] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0651] 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.

[0652] 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).

[0653] 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.

[0654] 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.

[0655] 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).

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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.

[0661] 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.

[0662] 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".

[0663] This invention is a support system designed to facilitate asset building for users. This system automates financial market forecasting and individual savings plans through the use of a server, terminal, and user components.

[0664] Server Functions

[0665] The server has the ability to acquire various financial market data and predict market trends using AI models based on that data. The server also receives users' financial situation data and calculates the optimal investment amount for each user based on that data. Furthermore, the server integrates market forecasts and investment plans to generate recommendations for users. These recommendations include suggested investment portfolios and explanations of the reasoning behind them.

[0666] Device functions

[0667] The terminal is equipped with communication means to send information entered by the user to the server, and receives the returned data from the server and displays it to the user. The terminal appropriately transfers information such as income, expenses, and investment style entered by the user to the server, and receives and displays the analysis results from the server.

[0668] User actions

[0669] Users input their income, expenses, and desired investment style (e.g., safety-first, moderately risk-tolerant) into the terminal. Once the user enters the information, it is encrypted and sent to the server. Based on the server's generated recommendations for stocks and investment amounts, users can then decide whether or not to start investing.

[0670] This system compensates for a lack of investment knowledge, supports manageable asset building tailored to individual financial situations, and provides an environment for confident investing. Therefore, it is particularly useful for young people looking to start investing and for users who have previously given up on investing.

[0671] The following describes the processing flow.

[0672] Step 1:

[0673] The user activates the device and enters their monthly income, expenses, and desired investment style. This collects basic financial information.

[0674] Step 2:

[0675] The device encrypts the collected user information and transmits it to the server using a secure communication protocol.

[0676] Step 3:

[0677] The server receives the individual economic situation data that is sent and securely stores it in the database. Next, the server retrieves the latest market data through financial APIs.

[0678] Step 4:

[0679] Artificial intelligence installed on the server analyzes market data and predicts future financial market trends. This process analyzes financial information such as stock price fluctuations and exchange rates.

[0680] Step 5:

[0681] The server calculates the investment amount based on the AI's predictions and the user's financial situation data. Furthermore, it selects the most suitable investment products for the user and generates recommendation information.

[0682] Step 6:

[0683] The server sends the generated recommendations and savings plan to the device. This data is also encrypted, so your privacy is protected.

[0684] Step 7:

[0685] The terminal decrypts the data received from the server and presents it to the user through a graphical user interface. At this stage, the recommended portfolio and investment amount are displayed.

[0686] Step 8:

[0687] The user reviews the provided information and decides whether or not to actually invest. If they choose to invest, the investment process begins when they send instructions from their device.

[0688] Step 9:

[0689] The server, upon user approval, executes the order with the partner financial institution. All transactions are recorded and can be referenced later.

[0690] (Example 1)

[0691] 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".

[0692] The present invention aims to efficiently and optimally support asset building tailored to the individual financial situation of each user. Specifically, it aims to create a system that allows even novice investors or those with little experience to confidently begin investing by appropriately predicting trends in financial markets and providing savings plans suitable for each user.

[0693] 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.

[0694] In this invention, the server includes artificial intelligence means for acquiring market information and predicting future economic market trends; calculation means for receiving individual economic situation information and calculating an appropriate savings amount for the user; and information generation means for integrating the results of the artificial intelligence means and the calculation means and providing recommended information to the user. This makes it possible to provide each user with an accurate investment plan.

[0695] "Market information" refers to data related to financial markets, such as stock prices, exchange rates, and commodity prices.

[0696] "Artificial intelligence tools" refer to computer programs that include machine learning algorithms for analyzing market information and predicting future economic market trends.

[0697] "Individual economic information" refers to information regarding each user's income, expenses, asset status, and investment policies.

[0698] "Calculation means" refers to algorithms and calculation mechanisms used to derive appropriate savings amounts and investment plans for users based on individual economic situation information.

[0699] "Information generation means" refers to a computer program that integrates the results of artificial intelligence means and computation means and has the function of providing users with recommended investment plans and reasons.

[0700] "Communication methods" refer to network communication technologies used to securely encrypt and transmit information from users to the server.

[0701] "Display means" refers to a user interface that presents recommended information received from the server to the user in a visually easy-to-understand format.

[0702] This invention is a system that enables users to build assets with peace of mind, and it proceeds through the interaction of servers, terminals, and users.

[0703] The server continuously acquires market information from external data providers. Python is used as the software for this, and machine learning models are built using its libraries, TensorFlow and PyTorch. This allows the server to predict future economic markets based on historical market data. For example, it analyzes short- and long-term time series data to perform stock price trend analysis and predict economic indicators. Furthermore, the server receives individual economic information from users and creates investment plans based on this information.

[0704] The terminal is equipped with a means of securely transmitting user-entered financial information to a server. A secure communication protocol is used to prevent data leakage. The terminal also receives recommended information from the server and displays it in a way that is intuitively understandable to the user. Specifically, the user interface shows an overview of the risks and returns of each investment, as well as recommended monthly contribution amounts, using visual charts and text.

[0705] Users input their monthly income and expenses, as well as their desired investment style (e.g., safety-oriented) through their device. Based on this, they can then decide whether or not to actually invest, using the server-generated recommended portfolio and investment plan as a reference. For example, a user might input information based on a prompt such as, "Please suggest the optimal investment plan for a monthly income of 500,000 yen, monthly expenses of 300,000 yen, and a safety-oriented style."

[0706] In this way, the present invention utilizes a generative AI model to provide asset management options tailored to the individual needs of users, thereby fulfilling its role as a system that compensates for a lack of understanding of investment.

[0707] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0708] Step 1:

[0709] Users input their financial information using their device. Specifically, they enter information such as their monthly income, essential monthly expenses, and investment risk tolerance (e.g., safety-oriented) into the interface. This input information is encrypted on the device and prepared for transmission to the server. Encryption of the entered data protects the data during transmission.

[0710] Step 2:

[0711] The terminal sends the entered economic status information to the server. During this process, encrypted data is sent to the server using a secure communication protocol. The server receives this data and decrypts it afterward. The output of this process is the decrypted user's economic information.

[0712] Step 3:

[0713] The server retrieves current market information from an external data provider. This information includes the latest stock prices, interest rates, and exchange rates. Using the retrieved market information, the server runs a generating AI model to analyze future market trends. The analysis results in the output of predicted market trend data.

[0714] Step 4:

[0715] The server integrates decoded user economic information and market forecast data to calculate individually optimized monthly investment amounts. This calculation takes into account predicted market risk and return. After the calculation, data containing the optimal investment plan and recommended monthly investment amounts for the user is generated and output.

[0716] Step 5:

[0717] The server sends the calculated recommendation information to the terminal. The output from the server is a dataset containing the recommendation information, which also includes the recommended portfolio and the reasons for it. After receiving this information, the terminal prepares to decrypt it from its encrypted state and convert it into a user-friendly format.

[0718] Step 6:

[0719] The terminal displays recommended information provided by the server through its user interface. Specifically, it shows the risk and return of each investment and the recommended monthly investment amount in graphs and text, and also displays data explaining the reasons for the investment. The output here is a recommended plan presented in a visual form.

[0720] Step 7:

[0721] Users make their investment decisions based on the recommendations provided by their device. If they understand and agree with the displayed data, they can choose to operate the device and begin making an actual investment.

[0722] (Application Example 1)

[0723] 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".

[0724] In today's financial markets, users are faced with a vast amount of information, making it difficult to make informed decisions about how to build wealth. Therefore, users with little experience in wealth building require considerable effort and knowledge to make appropriate investments. Furthermore, managing daily expenses and building wealth simultaneously is challenging and a significant burden for users lacking time and expertise. Thus, there is a need for a system that automatically adjusts wealth building based on the user's spending patterns.

[0725] 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.

[0726] In this invention, the server includes an analysis means for acquiring market data and predicting future financial market trends, a calculation means for receiving individual economic situation data and calculating an appropriate savings amount for the user, and an adjustment means for automatically adjusting the investment plan based on the user's spending patterns. This enables optimal investment advice tailored to the user's spending situation, compensating for any lack of specialized knowledge and allowing the user to build assets with peace of mind.

[0727] "Market data" refers to a collection of information that shows the state and trends of financial markets, and includes stock prices, exchange rates, interest rates, and economic indicators.

[0728] "Analytical tools" refer to methods and techniques for analyzing market data and predicting future financial market trends.

[0729] "Economic status data" refers to a collection of information that shows the financial status of users, such as their income, expenses, assets, and liabilities.

[0730] "Calculation methods" refer to methods and techniques for calculating an appropriate savings amount based on the user's financial situation data.

[0731] "Adjustment mechanisms" refer to systems or functions that automatically optimize investment plans according to the user's spending patterns and economic situation.

[0732] "Information generation means" refers to methods and technologies for providing users with appropriate investment plans and recommended information based on the results of analysis and calculation means.

[0733] This invention is a support system for users to easily build assets. This system consists of a server, a terminal, and a user.

[0734] The server collects market data from financial markets. Through analytical methods, the server uses this data to predict future trends in financial markets. Specifically, the server utilizes generative AI models to analyze historical market data and current market information to derive future market trends. This process utilizes a cloud computing environment capable of processing large amounts of data.

[0735] The server also receives user financial data from the terminal. Using calculation tools, the server calculates the optimal savings amount for each user based on their income, expenses, and other economic indicators. Furthermore, adjustment tools work based on this information to automatically optimize the investment plan according to the user's spending patterns.

[0736] The terminal functions as the user's input interface. The user inputs information about their income, expenses, and investment style on the terminal, and this data is sent and received between the terminal and the server. The terminal receives recommendation information generated by the server and displays it visually to the user. Based on this recommendation information, the user can easily begin building their assets.

[0737] As a concrete example, if a user inputs a monthly income of 50,000 yen and expenses of 20,000 yen, the server can analyze that disposable income and recommend investing 3,000 yen per month. This recommendation can be applied to various investment opportunities, such as mutual funds or stock purchases. As market trends change, the AI ​​dynamically adjusts the investment amount and plan, so the user always receives optimized advice. An example of a prompt message would be, "Your income is 50,000 yen and your expenses are 20,000 yen. Please create a stable portfolio."

[0738] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0739] Step 1:

[0740] The server collects real-time market data from financial markets. The input is market information, and the output is a dataset for analysis. The server performs large-scale data processing and prepares it for input into generative AI models.

[0741] Step 2:

[0742] The server uses a generative AI model to analyze market data. The input is a dataset for analysis, and the output is forecast information for future financial markets. The AI ​​model learns from past market trends and performs forecast calculations using a new dataset.

[0743] Step 3:

[0744] The terminal receives data from the user regarding income, expenses, and investment style. The input is the user's financial status data, and the output is transformed data sent to the server. The terminal collects data through the user interface and sends it to the server in an appropriate format.

[0745] Step 4:

[0746] The server calculates the appropriate savings amount for each user based on their financial situation data. The input is transformed data, and the output is the calculated savings amount. A calculation method is used to determine the optimal savings amount based on the user's income and expenses.

[0747] Step 5:

[0748] The server automatically optimizes an investment plan that takes into account the user's spending patterns, using an adjustment mechanism. The input is the calculated savings amount and market forecast information, and the output is the optimized investment plan. The adjustment mechanism analyzes the user's spending history and dynamically adjusts the investment plan.

[0749] Step 6:

[0750] The server provides the generated optimized investment plan to the user as recommended information through an information generation mechanism. The input is the optimized investment plan, and the output is the recommended information displayed to the user. The information generation mechanism generates a prompt statement and clearly explains the reasons for the recommendation.

[0751] Step 7:

[0752] The user reviews the recommendations received from the server via their device and makes a decision to start investing based on the information presented. The input is the recommendations from the server, and the output is the user's decision. The user understands the contents of the presented portfolio and makes investments as needed.

[0753] 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.

[0754] This invention provides an asset building support system that takes into account the user's emotions in addition to forecasting financial market trends and creating individual savings plans. This system is realized through the collaboration of various elements, including a server, terminal, user, and emotion engine.

[0755] Server Functions

[0756] The server first securely stores the user's financial situation data received from the terminal. Simultaneously, the server collects market data and uses AI models to predict future financial market trends. The results of this prediction are then used, along with information generation tools, to create a recommended investment portfolio tailored to the user.

[0757] Functions of the Emotion Engine

[0758] The emotion engine analyzes the user's biometric and interaction data acquired through the device to identify their current emotional state. Based on this emotional state, the emotion engine evaluates stress levels and risk preferences and sends the results to the server.

[0759] Device functions

[0760] The device transmits financial and biometric data collected from the user to the server and emotion engine. It also has the function of displaying recommendations and investment advice returned by the server to the user.

[0761] User actions

[0762] Users can input their income and expenditure data into the device and participate in acquiring biometric data (such as voice tone and facial expression images) as prompted by the device. This allows the system to provide an optimized investment plan that also takes into account the user's emotional state for the day. Users then decide whether to execute the investment based on the results adjusted by the emotion engine.

[0763] This system allows users to make more rational investment decisions that are often influenced by emotions, enabling them to build wealth with less stress and greater peace of mind. This approach represents an evolution from traditional wealth-building methods and is an innovative approach that takes into account the importance of an individual's emotional state in wealth creation.

[0764] The following describes the processing flow.

[0765] Step 1:

[0766] Users use their devices to input information about their monthly income, expenses, and current financial situation. This information is used as basic data for wealth building.

[0767] Step 2:

[0768] The device collects emotion-related data provided by the user. This includes biometric data such as voice tone, facial expressions, and heart rate.

[0769] Step 3:

[0770] The device encrypts the collected financial and emotional data before sending it to the server. Strong security protocols are used to protect data privacy.

[0771] Step 4:

[0772] The server retrieves the latest market data from financial market data providers and analyzes that data using artificial intelligence. This analysis is performed to predict future market trends.

[0773] Step 5:

[0774] The server calculates the optimal savings amount based on the individual financial situation data it receives. This includes adjustments to reduce the burden based on the user's income, expenses, and emotional state.

[0775] Step 6:

[0776] The emotion engine analyzes emotional data sent from the server to assess the user's stress levels and risk preferences. This information is then used to refine the recommended portfolio.

[0777] Step 7:

[0778] The server integrates the prediction results from artificial intelligence and the evaluation results from the emotion engine to generate a recommended investment portfolio tailored to the user. This includes specific investment products and investment proportions.

[0779] Step 8:

[0780] The server sends the generated recommendation information to the terminal. The terminal receives this information and displays it in an easy-to-understand format for the user.

[0781] Step 9:

[0782] Based on the information presented, users make investment decisions that align with their emotional state. The selection is completed on the device, and the investment can then be executed by following subsequent instructions.

[0783] (Example 2)

[0784] 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".

[0785] In modern asset management, a problem exists where users find it difficult to make rational investment decisions due to stress stemming from short-term emotional fluctuations and market uncertainty. Furthermore, traditional systems offer uniform investment recommendations without considering the emotional state of the user, making it difficult to create asset formation optimized for each individual.

[0786] 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.

[0787] In this invention, the server includes artificial intelligence means for acquiring market information and predicting future economic market trends; calculation means for receiving individual economic situation information and biometric data and calculating an appropriate savings amount for the user; and information generation means for generating the results of the artificial intelligence means and the calculation means and providing recommendation information that takes into account the results of sentiment analysis. This makes it possible to provide an optimized investment portfolio that takes into account the user's emotional state, thereby supporting rational investment decisions while reducing stress and enabling secure asset building.

[0788] "Market information" refers to price trends and trading information for stocks, bonds, currencies, and other financial instruments in the financial markets, as well as economic indicator data.

[0789] "Artificial intelligence methods" refer to technologies that use machine learning to analyze large amounts of data and predict future trends and patterns.

[0790] "Individual economic information" refers to data on an individual user's income, expenses, assets, and liabilities.

[0791] "Biometric data" refers to physiological data related to emotional states, such as voice tone and facial expression images, obtained from users.

[0792] "Calculation means" refers to devices or software that perform the process of calculating specific numerical values ​​using mathematical formulas or algorithms based on received data.

[0793] "Information generation means" refers to devices and software that are responsible for the process of constructing useful information based on calculation results and prediction results and providing it to users.

[0794] "Emotional analysis results" refer to information about stress levels and risk preferences obtained by analyzing the user's biometric data.

[0795] An "investment portfolio" refers to a combination of financial instruments in which assets are allocated to achieve a specific investment objective.

[0796] This invention is an asset formation support system that takes into account the emotional state of the user, and is implemented by utilizing a server, terminal, user, and emotion analysis function.

[0797] Server Functions

[0798] The server first receives data representing the user's financial situation and biometric data transmitted from the terminal and securely stores it. The server collects market information in real time from financial data provision services and uses this to predict future economic market trends using an AI model. This AI model utilizes machine learning frameworks such as TensorFlow and PyTorch. The data obtained from the prediction results is processed by information generation means to create an optimal investment portfolio for the user.

[0799] Emotion analysis function

[0800] The emotion analysis function analyzes user biometric data acquired through the device. Specifically, it uses open-source emotion recognition models (e.g., OpenFace) to evaluate stress levels and risk preferences from the user's facial expressions and voice tone. This result is sent to a server and incorporated into investment advice.

[0801] Device functions

[0802] The terminal collects economic and biometric data from users and transmits it to the server and sentiment analysis functions. The terminal also visually displays recommended investment portfolios received from the server to the user. In this process, the terminal's display software can be used to represent the information in graphs and charts.

[0803] User actions

[0804] Users input their daily income and expenditure data into the device and, following the device's instructions, also collect biometric data, such as recording their voice tone and taking photos of their facial expressions. Based on this information, the system provides an optimized investment plan that takes their emotional state into account. Specifically, it supports asset building by having users record their expenses using their smartphones in their daily lives and making conservative investment choices on stressful days.

[0805] Examples of specific cases and prompt statements

[0806] For example, if a user enters an annual income of $100,000 and monthly expenses of $7,000, the server will use this data to make market predictions. Simultaneously, the sentiment analysis function will capture the user's smile in front of the camera and evaluate their "relaxed emotional state." Based on this data, the server will suggest an appropriate allocation of stocks and bonds. An example of a prompt message would be: "Please generate an optimal investment portfolio considering the user's financial situation data and emotional state."

[0807] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0808] Step 1:

[0809] Users input their financial data, such as income and expenses, into the device. They also provide biometric data by recording their voice tone and taking facial images with the camera, following the device's instructions. This input data reflects the user's financial situation and emotional state.

[0810] Step 2:

[0811] The terminal sends the collected economic and biometric data to the server. In this process, the input data is encrypted via a dedicated protocol and securely transferred to the server over the network.

[0812] Step 3:

[0813] The server stores the user's economic data received from the terminal in a database. It also transfers biometric data to the sentiment analysis function. The data processing performed here involves formatting the data itself and standardizing the data format.

[0814] Step 4:

[0815] The emotion analysis function recognizes the user's emotional state by analyzing biometric data. This process involves an AI model analyzing facial expressions and vocal intonation, performing data calculations to identify stress levels and risk preferences. The emotion analysis results are then sent to a server as output.

[0816] Step 5:

[0817] The server acquires market information and uses the AI ​​model again to predict future market trends. Using market data as input, it extracts trends and patterns using machine learning algorithms and outputs prediction results.

[0818] Step 6:

[0819] The server designs an optimal investment portfolio using information generation methods based on the user's economic data and sentiment analysis results. This data processing uses AI model predictions and sentiment analysis results to calculate asset allocation that considers risk appropriateness. The generated recommendations are then sent to the terminal.

[0820] Step 7:

[0821] The terminal displays a recommended investment portfolio sent from the server to the user. This process presents information visually and clearly through a visual interface. Based on the recommended portfolio, the user can make their own investment decisions.

[0822] (Application Example 2)

[0823] 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".

[0824] Traditional asset building systems make investment decisions without considering the user's emotional state, leading to problems such as irrational investment decisions due to emotional fluctuations and the accumulation of stress. In particular, they lacked proposals for investment portfolios tailored to stress levels and risk preferences, making it difficult to provide flexible investment strategies that meet the diverse needs of users.

[0825] 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.

[0826] In this invention, the server includes analytical means for acquiring market information and predicting future financial market trends; computation means for receiving individual economic situation data and calculating a suitable amount for the user; sentiment analysis means for analyzing the user's biometric data and evaluating their emotional state; and adjustment means for evaluating and adjusting stress levels and risk preferences based on the emotional state. This enables the provision of investment advice adapted to the user's emotional state and rational investment decisions.

[0827] "Market information" is a general term for data that shows trends such as price fluctuations and trading conditions in financial markets.

[0828] "Analytical tools" are elements that have the function of predicting future financial market trends based on market information.

[0829] "Economic situation data" refers to data that includes economic information such as the user's income, expenses, assets, and liabilities.

[0830] A "calculation tool" is an element that has the function of calculating an appropriate amount of storage for the user based on the received economic situation data.

[0831] An "information generation means" is an element that has the function of creating recommended information to present to users using data obtained from analysis.

[0832] "Biometric data" refers to data that measures a user's physical characteristics, including, for example, voice and facial expressions.

[0833] An "emotion analysis tool" is an element that has the function of identifying the user's current emotional state based on biometric data.

[0834] "Adjustment mechanisms" are functions used to assess stress levels and risk preferences, taking into account emotional states, in order to provide appropriate investment advice.

[0835] An "investment portfolio" is a combination of financial assets and a plan designed to propose the optimal allocation according to the user's investment goals.

[0836] "Stress level" is an indicator that shows the degree of stress in a user's emotional state.

[0837] "Risk preference" is an indicator that shows how much risk a user is willing to tolerate in their investments.

[0838] This invention realizes an asset formation support system that takes into account the user's emotions. This system consists of a server, terminals, users, and an emotion analysis engine.

[0839] The server acquires market information and uses AI models to predict future financial market trends. This allows it to provide an optimal storage plan based on the user's economic situation data. The server also uses advanced computer hardware and software for data processing through analytical and computational means. Specifically, it stores market data in conjunction with a database system and provides an advanced computing environment for operating AI models.

[0840] The device has the function of transmitting financial information and biometric data collected from the user to a server and sentiment analysis engine. Users can use the device to input their own financial data and provide biometric data such as voice and facial expressions. This allows for real-time analysis of the user's emotional state, influencing their investment decisions for the day.

[0841] The emotion analysis engine analyzes emotional states based on acquired biometric data. It evaluates stress levels and risk preferences, and adjusts investment portfolios accordingly. This engine utilizes machine learning models to accurately assess subtle emotional changes in users.

[0842] For example, if a smartphone user is experiencing stress due to their mood that day, the system will recommend low-risk investment options and adjust the system to allow them to manage their assets with peace of mind. The generative AI model is used to support investment decisions, generating flexible advice that responds to emotions using prompt sentences.

[0843] Examples of specific prompt messages are as follows:

[0844] "Consider a situation where a user is experiencing stress, and describe how you would provide risk-averse investment advice to that user."

[0845] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0846] Step 1:

[0847] The device receives economic and biometric data from the user as input. The device formats this input data and prepares it for transmission to the server and sentiment analysis engine.

[0848] Step 2:

[0849] The server collects market data and uses an AI model to predict future financial market trends. The input is the acquired market data, and the output is the predicted market trend data. Through this process, the server processes large amounts of data and generates optimized prediction results.

[0850] Step 3:

[0851] The emotion analysis engine analyzes biometric data received from the device to evaluate the user's current emotional state. The input is biometric data, and the output is indicator information showing the user's emotional state. This analysis quantifies the user's stress level and risk preference.

[0852] Step 4:

[0853] The server integrates the market trend data obtained in step 2 and the sentiment indicator obtained in step 3 to generate a recommended portfolio. The input is market trend data and sentiment indicator, and the output is adjusted investment portfolio data. This allows the server to create a rational investment strategy tailored to the user's sentiment and market conditions.

[0854] Step 5:

[0855] The terminal displays recommended portfolios received from the server to the user. The input is recommended portfolio data from the server, and the output is information presented visually to the user. The terminal uses visualization technology to provide information in a way that is easy for the user to understand.

[0856] 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.

[0857] 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.

[0858] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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."

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0877] The following is further disclosed regarding the embodiments described above.

[0878] (Claim 1)

[0879] An artificial intelligence tool that acquires market data and predicts future financial market trends,

[0880] A calculation means that receives individual economic situation data and calculates a suitable savings amount for the user,

[0881] Information generation means that generates the results of the artificial intelligence means and the calculation means and provides recommended information to the user,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, characterized in that the information generation means presents a recommended investment portfolio.

[0885] (Claim 3)

[0886] The system according to claim 1, characterized in that the calculation means creates a long-term savings plan that takes into account the user's financial burden.

[0887] "Example 1"

[0888] (Claim 1)

[0889] An artificial intelligence tool that acquires market information and predicts future economic market trends,

[0890] A calculation means that receives individual economic situation information and calculates a suitable savings amount for the user,

[0891] Information generation means that integrates the results of the artificial intelligence means and the calculation means and provides recommended information to the user,

[0892] A communication method that encrypts and transmits information from users,

[0893] A display means for displaying the aforementioned recommended information,

[0894] A system that includes this.

[0895] (Claim 2)

[0896] The system according to claim 1, wherein the information generation means presents a recommended investment portfolio and explains the reasons for the investment.

[0897] (Claim 3)

[0898] The system according to claim 1, wherein the calculation means formulates a long-term savings plan that takes into account the user's financial capacity.

[0899] "Application Example 1"

[0900] (Claim 1)

[0901] An analytical tool for acquiring market data and predicting future financial market trends,

[0902] A calculation means that receives individual economic situation data and calculates a suitable savings amount for the user,

[0903] An adjustment mechanism that automatically adjusts the investment plan based on the user's spending patterns,

[0904] Information generation means that generates the results of the analysis means, the calculation means and the adjustment means and provides recommended information to the user,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, characterized in that the information generation means presents a recommended investment portfolio and provides optimized investment advice based on expenditure data.

[0908] (Claim 3)

[0909] The system according to claim 1, characterized in that the calculation means creates a long-term savings plan that takes into account the user's financial burden and adjusts the investment amount using the settlement history.

[0910] "Example 2 of combining an emotion engine"

[0911] (Claim 1)

[0912] An artificial intelligence tool that acquires market information and predicts future economic market trends,

[0913] A calculation means that receives individual economic information and biometric data and calculates a suitable savings amount for the user,

[0914] Information generation means that generates the results of the artificial intelligence means and the calculation means and provides recommendation information that takes into account the sentiment analysis results,

[0915] A system that includes this.

[0916] (Claim 2)

[0917] The system according to claim 1, characterized in that the information generation means presents a recommended investment portfolio adjusted based on the user's current emotional state.

[0918] (Claim 3)

[0919] The system according to claim 1, characterized in that the calculation means creates a long-term savings plan that takes into account the user's financial burden and emotional state.

[0920] "Application example 2 of combining emotional engines"

[0921] (Claim 1)

[0922] An analytical tool for acquiring market information and predicting future financial market trends,

[0923] A computing means that receives individual economic situation data and calculates an appropriate amount of storage for the user,

[0924] Information generation means that generates the results of the analysis means and the calculation means and provides recommended information to the user,

[0925] A means of sentiment analysis that analyzes the user's biometric data and evaluates their emotional state,

[0926] A means of adjustment that evaluates and adjusts stress levels and risk preferences based on emotional state,

[0927] A system that includes this.

[0928] (Claim 2)

[0929] The system according to claim 1, characterized by presenting a recommended investment portfolio and providing investment advice tailored to stress levels and risk preferences.

[0930] (Claim 3)

[0931] The system according to claim 1, characterized in that it takes into account the emotional state of the user and creates a long-term savings plan that reduces the financial burden. [Explanation of Symbols]

[0932] 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. An artificial intelligence tool that acquires market data and predicts future financial market trends, A calculation means that receives individual economic situation data and calculates a suitable savings amount for the user, Information generation means that generates the results of the artificial intelligence means and the calculation means and provides recommended information to the user, A system that includes this.

2. The system according to claim 1, characterized in that the information generation means presents a recommended investment portfolio.

3. The system according to claim 1, characterized in that the calculation means creates a long-term savings plan that takes into account the user's financial burden.

Images