system

Abstract

Provide a system. 【Solution means】 Means for obtaining an investment goal and a risk tolerance based on an input from a user, Means for collecting market information and new information from an external data source, Means for analyzing the market information and new information to generate an investment strategy, Means for automatically executing trading activities according to the generated investment strategy, Means for changing the investment strategy as necessary and notifying the user of the content, Means for visually displaying the investment strategy and the results of asset management to the user, Means for automatically executing the allocation adjustment of funds based on the user's investment strategy, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] To solve the problem that individual investors are facing the complexity of the market, excessive information, and the difficulty of risk management, and require a great deal of effort and time for formulating and implementing investment strategies. Also, to solve the problem that there is a lack of support for meeting investment needs that emphasize efficient asset management and social value and realizing these.

Means for Solving the Problems

[0005] The system obtains investment goals and risk tolerance from users, analyzes market and new information collected from external data sources, and generates an AI model to formulate individual investment strategies. It automatically executes trading activities according to the formulated investment strategy, modifies the strategy as needed, and notifies the user. Furthermore, it considers ESG scores in the investment strategy and visually displays the investment strategy and asset management results to the user. It also addresses these challenges by providing a means to receive user feedback and adjust the investment strategy accordingly.

[0006] A "user" refers to an individual investor who uses the system to set their own investment goals and risk tolerance.

[0007] "Input" refers to information that users provide to the system, such as investment goals and risk tolerance.

[0008] "Investment goals" refer to specific asset management outcomes or objectives that a user wants to achieve.

[0009] "Risk tolerance" refers to the range or level of investment risk that a user can accept.

[0010] "External data sources" refer to sources of data provided by securities companies' APIs or market information providers.

[0011] "Market information" refers to financial data necessary for formulating investment strategies, such as stock prices, trading volume, and corporate financial information.

[0012] "New information" refers to the latest information that may influence investment decisions, such as market news and social trends.

[0013] "Analysis" refers to data processing and analysis used to design investment strategies using market information and new information.

[0014] "Generative AI models" refer to machine learning models and algorithms used in formulating investment strategies.

[0015] "Investment strategy" refers to a plan or guideline for asset management designed based on the user's investment goals and risk tolerance.

[0016] "Trading activities" refer to the trading transactions of financial products executed based on the established investment strategy.

[0017] "ESG score" refers to an indicator evaluated from the perspectives of environment (Environmental), society (Social), and governance (Governance).

[0018] "Visually display" means providing a graphical interface to clearly show the investment strategy and operation results to the user.

[0019] "Feedback" refers to the opinions and evaluations obtained from the user, and the information based on which the system adjusts the strategy.

Brief Explanation of Drawings

[0020] [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. [[ID=3�]] [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.

Modes for Carrying Out the Invention

[0021] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0022] First, the language used in the following description will be explained.

[0023] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of 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.

[0024] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0025] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0026] 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).

[0027] 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."

[0028] [First Embodiment]

[0029] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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".

[0041] This invention relates to a system for providing advanced asset management support to individual investors. The system utilizes a generative AI model to automatically formulate and manage investment strategies that take into account the user's investment goals and risk tolerance. The program processing of this system is described below in natural language.

[0042] Server operation

[0043] The server provides core data processing capabilities. Initially, it collects market and new information from external data sources via APIs from securities firms and market information providers. The acquired data is preprocessed and then analyzed by a generative AI model. The AI ​​model predicts investment market trends and designs optimal investment strategies tailored to the user's goals and risk tolerance. After the strategy is formulated, the server automatically executes trading activities in the market. Furthermore, the server monitors portfolio performance and performs rebalancing as needed.

[0044] As a concrete example, when formulating an investment strategy for growth stocks, the AI ​​model analyzes recent financial reports and news articles of companies to identify sectors that it deems to have high growth potential. Based on this, the server sends buy / sell instructions to the brokerage firm to invest in those specific stocks.

[0045] Terminal operation

[0046] The terminal handles user interaction. Users set investment goals and risk tolerance from the terminal, and this information is sent to the server. The latest investment strategy and portfolio information received from the server is visualized and displayed to the user in an easy-to-understand format. The terminal provides the user with information on the progress of asset management and adjustments to the strategy using graphs and dashboards.

[0047] User actions

[0048] Users set investment goals and input their risk tolerance into the system via their terminal. They then check the performance of their displayed portfolio and provide feedback as needed. This feedback is used to adjust strategies on the server. For example, if a user determines they can tolerate higher risk, a new strategy is redesigned and implemented to align with their preferences.

[0049] This enables users to efficiently and individually manage their assets according to their own goals, and to make socially meaningful investments that take ESG scores into consideration.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The server collects market information and new information from external data sources. It retrieves data from stock exchanges and financial news providers via APIs and organizes it chronologically.

[0053] Step 2:

[0054] The server preprocesses the acquired data. It fills in missing data and handles outliers to format the data into a format suitable for analysis.

[0055] Step 3:

[0056] The server analyzes pre-processed data using a generative AI model. It predicts market trends, assesses risks, and generates the optimal investment strategy for the user.

[0057] Step 4:

[0058] The server automatically sends buy and sell orders to brokerage firms based on the generated investment strategy. Buy and sell orders are issued via API.

[0059] Step 5:

[0060] The server monitors portfolio performance in real time. If a pre-configured risk threshold is exceeded, the portfolio is rebalanced.

[0061] Step 6:

[0062] The terminal provides an interface to the user. It displays a screen to the user where they can input their investment goals and risk tolerance.

[0063] Step 7:

[0064] The terminal receives investment strategy and performance information sent from the server. This information is then visually displayed to the user in the form of diagrams and dashboards.

[0065] Step 8:

[0066] Users input their goals and risk tolerance levels via their device. Once input is complete, the information is sent to the server and incorporated into the strategy design.

[0067] Step 9:

[0068] Users can review investment status and strategy details and provide feedback through their devices. The server receives this feedback and uses it to adjust future strategies.

[0069] (Example 1)

[0070] 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."

[0071] Modern individual investors are required to manage their assets efficiently and customized based on market and trend information gathered from a wide range of sources. However, there is currently a lack of systems that provide sophisticated investment strategies that can be easily used by users who do not require specialized investment knowledge. In this situation, there is a need to provide a system that automatically generates optimal investment strategies based on the user's investment goals and risk tolerance, and manages assets efficiently and individually.

[0072] 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.

[0073] In this invention, the server includes means for obtaining investment targets and risk tolerance based on user input; means for collecting market information and trend information from external information sources; means for analyzing the market information and trend information and generating an investment strategy using prompt statements in a generating AI model; means for automatically executing trading activities based on the generated investment strategy; means for modifying the investment strategy as necessary and notifying the user of the changes; means for visually displaying the investment strategy and asset management results to the user; means for receiving user feedback and adjusting the investment strategy based on that feedback; and means for monitoring the portfolio with an information processing device and adjusting asset allocation as necessary. This makes it possible for users to manage their assets efficiently and on an individual basis without requiring specialized knowledge.

[0074] A "user" refers to an individual or legal entity that uses this system to conduct investment activities through automated asset management.

[0075] "External information sources" refer to external data sources that provide market information and trend information, such as securities companies and market information providers.

[0076] "Market information" refers to information related to investment activities, such as stock prices, corporate financial information, and economic indicators.

[0077] "Trend information" refers to information that may affect the market, such as economic fluctuations, corporate news, and political events.

[0078] A "generative AI model" refers to an artificial intelligence model that analyzes the aforementioned market information and trend information to generate investment strategies.

[0079] A "prompt statement" refers to an instruction statement used to generate a specific investment strategy for a generative AI model.

[0080] An "investment strategy" refers to a plan for asset management generated based on the user's investment goals and risk tolerance.

[0081] The term "automatic execution" refers to a process in which a system carries out buying and selling activities in the market without human intervention.

[0082] "Visual display" refers to presenting investment strategies and asset management results to users in an easy-to-understand format using graphs and dashboards.

[0083] "Feedback" refers to the opinions and requests provided by users, and the input information used by the system to adjust its investment strategy based on this feedback.

[0084] "Information processing equipment" refers to devices, including digital computers, used for acquiring, analyzing, storing, and displaying information.

[0085] A "portfolio" refers to a combination of multiple financial products held by a user, and the asset allocation of that portfolio is managed.

[0086] This invention relates to a system that provides automated asset management for individual investors. Specific embodiments are described below.

[0087] Server operation

[0088] The server functions as the core of the entire system and is responsible for several key processes. First, the server retrieves market and trend information from external sources. Specifically, it uses APIs from securities companies and market information providers to automatically retrieve stock price information, financial reports, economic indicators, and market news, and stores this data in a database.

[0089] Next, the server preprocesses the collected data. Preprocessing includes removing outliers, standardizing data formats, and supplementing missing data. The processed data is then input into a generative AI model, which performs analysis based on prompt messages. The server uses the generative AI model to design an optimal investment strategy tailored to the user's investment goals and risk tolerance. An example of a prompt message used in this process is, "Design an optimal tech stock investment strategy for a user with high risk tolerance."

[0090] The server generates buy and sell orders based on the designed investment strategy and places them on the market via the brokerage firm's API. The server also monitors the portfolio performance in real time and adjusts asset allocation as needed.

[0091] Terminal operation

[0092] The terminal functions as an interface with the user. The user uses the terminal to set investment goals and risk tolerance and send them to the server. The terminal visually displays the latest investment strategies and portfolio updates returned from the server. The terminal includes graphs and dashboards, allowing the user to intuitively understand the progress of their asset management.

[0093] User actions

[0094] Users can provide investment feedback through their devices. For example, users can reset their risk tolerance, and this information is used to readjust strategies on the server. This allows users to manage their assets in a way that reflects their own intentions.

[0095] In this way, the server, terminals, and users cooperate with each other to achieve efficient and personalized asset management. This system allows users to manage their assets with peace of mind without requiring advanced expertise.

[0096] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0097] Step 1:

[0098] The server collects market and trend information from external sources. Specifically, it retrieves stock prices, corporate financial data, economic indicators, and news articles through APIs from securities companies and market information providers. The input is API access information, and the output is market and trend information stored in the database.

[0099] Step 2:

[0100] The server preprocesses the acquired market and trend information. It cleans the data, removes outliers, and standardizes the data format. It also supplements missing data with historical information and estimates. The input is raw data, and the output is well-formed data that has been cleaned and processed.

[0101] Step 3:

[0102] The server inputs well-formed data into a generating AI model for analysis. During this process, it uses prompt statements to generate an investment strategy. In this process, the input consists of well-formed data and prompt statements, while the output is an optimal investment strategy that takes into account the user's investment goals and risk tolerance.

[0103] Step 4:

[0104] The server executes automated trades based on the generated investment strategy. Specifically, it generates buy and sell instructions and sends them to the market via the brokerage firm's API. This results in the execution of trades in financial instruments in accordance with the specified investment strategy. The input is the investment strategy, and the output is a record of the executed trades.

[0105] Step 5:

[0106] The server monitors portfolio performance in real time. Necessary adjustments are made in response to market fluctuations, and rebalancing is performed to optimize asset allocation. Inputs are market information and the portfolio's current asset allocation, while output is the adjusted asset allocation.

[0107] Step 6:

[0108] The terminal visually displays the latest information on investment strategies and portfolios to the user. Specifically, it provides information through graphs and dashboards, making it easier for users to understand the progress of their investments. The input is portfolio data from the server, and the output is visualized information.

[0109] Step 7:

[0110] Users provide feedback through their devices and adjust their investment goals and risk tolerance as needed. This feedback is sent to the server and incorporated into the next investment strategy. The input is the user's feedback information, and the output is the adjusted investment strategy.

[0111] (Application Example 1)

[0112] 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."

[0113] For individual investors, developing and managing optimal investment strategies based on their own investment goals and risk tolerance, and then automatically executing specific fund allocation adjustments, is difficult for the average user who lacks investment expertise and time. Furthermore, in dynamic market environments, rapid changes in investment strategies and reallocation of funds are necessary, but doing this manually is inefficient.

[0114] 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.

[0115] In this invention, the server includes means for acquiring investment targets and risk tolerance based on user input; means for collecting market information and new information from external data sources; means for generating an investment strategy by analyzing the market information and new information; means for automatically executing trading activities according to the generated investment strategy; means for modifying the investment strategy as necessary and notifying the user of the changes; means for visually displaying the investment strategy and asset management results to the user; and means for automatically adjusting the allocation of funds based on the user's investment strategy. This enables the user to efficiently and quickly manage assets in response to market fluctuations.

[0116] "User input" refers to information that users provide to the system regarding their investment goals and risk tolerance.

[0117] An "external data source" refers to an external information source that is accessed to provide market information or new information.

[0118] "Gathering market information and new information" refers to the process of acquiring necessary data from external data sources and making it available within the system.

[0119] "Investment strategy generation" refers to constructing an investment policy that is suitable for the user's goals and risk level, based on the collected information.

[0120] "Automated execution of trading activities" refers to the automatic execution of stock and asset transactions in the market according to a generated investment strategy.

[0121] A "notification of changes to investment strategy" refers to modifying an investment strategy based on market changes or user feedback and communicating those changes to the user.

[0122] "Visual presentation" refers to providing users with an easy-to-understand presentation of investment strategies and asset management results using graphs, dashboards, and other visual aids.

[0123] "Automatic execution of fund allocation adjustments" refers to the process of optimizing fund allocation based on the user's investment strategy and automatically moving funds.

[0124] The system for realizing this invention is built on interaction between three parties: a server, a terminal, and a user.

[0125] The server connects to external data sources to collect market and new information. This includes obtaining real-time data from brokerage firms and market data providers via APIs. The collected data is preprocessed using Python and major libraries (NumPy, Pandas) and analyzed using a generative AI model. Based on the analysis results, an investment strategy optimized for the user's investment goals and risk tolerance is generated, and trading activities in the market are automatically executed. Furthermore, the strategy is updated as needed in response to changes in the investment strategy or new information, and the user is notified accordingly. For example, when growth in the agricultural sector is predicted, an investment strategy for related stocks is formulated.

[0126] The terminal serves as the direct interface with the user. Here, the user can input their investment goals and risk tolerance, and this information is immediately transmitted to the server. Furthermore, the terminal visually displays the received investment strategies and asset management results, presenting them in an easy-to-understand manner for the user. This includes visual displays using graphs and dashboards.

[0127] Users can reflect their intentions in the system by providing feedback on their investment goals and risk tolerance entered through their terminal. This feedback is analyzed on the server and incorporated into the investment strategy as needed. For example, if a user changes their intention towards accepting higher risk, the new investment strategy will be adjusted based on that feedback.

[0128] An example of a specific prompt for the generated AI model is, "Considering current market trends in the agricultural sector, please design the optimal investment strategy for my portfolio." By using such prompts, users can manage their assets in line with market trends while receiving advice from the system.

[0129] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0130] Step 1:

[0131] The server accesses external data sources and collects market and new information via APIs. The collected data is imported into the server as raw data. The input data is real-time data from the API, and the output data is pre-processed. The server uses Python and NumPy to impute missing values ​​and standardize the raw data.

[0132] Step 2:

[0133] The server inputs pre-processed data into the generated AI model and begins the analysis. The AI ​​model performs complex analyses to predict investment market trends and generates an initial investment strategy. The input is pre-processed market data, and the output is an investment strategy tailored to the user's investment goals and risk tolerance. Here, the AI ​​applies an algorithm to predict market trends and calculate investment priorities.

[0134] Step 3:

[0135] The server executes buy and sell orders in the market via an automated trading function based on the generated investment strategy. The target assets are optimized according to the investment strategy. The input is the investment strategy output by the generating AI model, and the output is the actual trade order. The trade is linked to the brokerage firm's API, and funds are transferred to the specified portfolio.

[0136] Step 4:

[0137] The terminal retrieves the user's investment goals and risk tolerance and sends this information to the server. The input is the investment goals and risk tolerance set by the user on the terminal, and the output is feedback data to the server. The terminal allows users to intuitively configure these settings via a user interface.

[0138] Step 5:

[0139] The server re-analyzes the investment strategy as needed based on user feedback and generates a new strategy. The input is user feedback information, and the output is the adjusted investment strategy. At this stage, the server performs a re-evaluation process of the generated AI model and formulates a strategy that reflects the user's new intentions.

[0140] Step 6:

[0141] The terminal visually displays and provides the user with the latest investment strategies and portfolio performance received from the server. The input is investment strategy information sent from the server, and the output is the user-viewed interface for the investment status. The terminal uses graphs and charts to visualize the information in an intuitive and easy-to-understand manner.

[0142] 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.

[0143] This invention enhances the user experience and further personalizes investment decisions by incorporating an emotion engine that recognizes user emotions into an investment support system for individual investors. This system detects the user's emotional state in real time and uses that data to adjust investment strategies and re-evaluate risk tolerance.

[0144] Server operation

[0145] The server processes and analyzes investment-related data. Its basic functions include collecting market and new information from external data sources and designing investment strategies using generative AI models. In addition, the server receives data from the emotion engine and analyzes the user's emotional state. This emotional data is used to adjust investment strategies and set risk tolerance levels. For example, if the emotion engine detects user stress, it can suggest a conservative investment strategy with reduced risk.

[0146] How the emotion engine works

[0147] The emotion engine is installed on the device and recognizes emotions by analyzing the user's facial expressions and voice. The engine updates the user's emotional state in real time and sends that data to the server. For example, it may analyze the tone and tempo of the user's voice input to identify positive or negative emotions.

[0148] Terminal operation

[0149] The device provides users with feedback on their emotional state. It not only presents users with an interface for setting investment goals and risk tolerance, but also visually displays the results of emotional analysis by an emotion engine. The device also provides a screen for users to review and agree to changes in their emotionally-based investment strategy.

[0150] User actions

[0151] Users input investment information via their devices and receive real-time sentiment analysis results. For example, if the sentiment engine analysis indicates that the user is "highly stressed by a sharp market decline," the user can adopt the suggested risk-averse strategy. This system allows users to make flexible investment decisions that align with their own emotional state.

[0152] The following describes the processing flow.

[0153] Step 1:

[0154] The server regularly collects market information and new data through APIs from securities firms and market information providers. This allows it to obtain the latest financial data and prepare for subsequent analysis.

[0155] Step 2:

[0156] The server preprocesses the collected data and designs investment strategies using a generative AI model. Data integrity is ensured during preprocessing, after which the predictive model begins its analysis.

[0157] Step 3:

[0158] The server receives emotion engine data transmitted in real time from the terminal and analyzes the user's emotional state. This information is essential for adjusting investment strategies.

[0159] Step 4:

[0160] The emotion engine analyzes the user's facial expressions and voice to recognize their emotions. This data is transmitted to the server via the device. For example, the emotion engine can use the camera to determine the user's facial expressions.

[0161] Step 5:

[0162] The server re-evaluates the current investment strategy based on emotional data and makes adjustments as needed. For example, it might suggest a strategy to invest in lower-risk assets to users with unstable emotions.

[0163] Step 6:

[0164] The terminal displays updated investment strategies and sentiment analysis results from the server to the user. Visual dashboards and alerts are used to make it easy for the user to understand.

[0165] Step 7:

[0166] Users review the presented information and provide feedback via their device if necessary. For example, they can agree to or reject proposed changes to the strategy.

[0167] Step 8:

[0168] User feedback is sent to the server and used to design future strategies. This enables flexible portfolio management that reflects user opinions.

[0169] (Example 2)

[0170] 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".

[0171] Traditional investment support systems failed to reflect users' emotional factors in investment strategies, making it difficult to respond flexibly to individual stress levels and risk tolerances. This sometimes resulted in users being unable to make optimal investment decisions. In particular, there was a need to consider users' psychological reactions to market fluctuations and rapid changes in information.

[0172] 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.

[0173] In this invention, the server includes means for detecting the user's emotional state in real time and transmitting emotional data to the server, means for generating an investment strategy using a generative AI model, and means for adjusting the investment strategy and re-evaluating risk tolerance using the emotional data. This makes it possible to provide a flexible investment strategy based on the user's real-time emotional state.

[0174] "User emotional state" refers to information that represents the user's psychological and emotional responses in real time, and is data obtained from facial expressions, tone of voice, speaking speed, etc.

[0175] A "generative AI model" is a collection of algorithms that analyze data and generate results tailored to a specific purpose, and is based on machine learning and artificial intelligence technologies.

[0176] "Market information" refers to information about factors that may influence the market, such as price trends, trading volume, and economic news in financial markets.

[0177] "Risk tolerance" is a measure that indicates the range of risk a user is willing to accept when making an investment, and it is one of the important criteria in selecting an investment strategy.

[0178] An "investment strategy" is a plan or method set out to achieve investment objectives, and includes the selection of financial products and the construction of a portfolio.

[0179] An "emotion engine" is a system or program that analyzes a user's emotions and acquires and utilizes that data in real time.

[0180] In embodiments of the present invention, a user, a terminal, and a server collaborate to provide an advanced investment support system that takes the user's emotional state into account. The terminal first interacts with the user and extracts emotional data in real time from the user's facial expressions and voice through an emotion engine. This process utilizes a camera and microphone to collect the user's facial expressions and voice. The emotion engine analyzes the data in real time and identifies positive or negative emotional states. For example, if the user is feeling anxious about market trends, this emotional data is immediately transmitted to the server.

[0181] The server collects market information and news from external data sources. The collected data is analyzed using a generative AI model. The generative AI model uses natural language processing and machine learning to generate an optimal investment strategy based on the user's emotional state. Using the previous example, if the server detects that the user is in a high-stress state, it generates a "risk-reduced, conservative investment strategy" and sends it to the terminal.

[0182] The device visually displays the received investment strategy to the user. The interface is designed to allow the user to intuitively understand the proposed investment strategy, with key elements of the strategy color-coded. Furthermore, the user can review the proposed strategy and make adjustments as needed.

[0183] As a concrete example, when using a prompt, information is provided to the generating AI model in the form of, "Please suggest an investment strategy. The user is currently stressed by the market situation. A conservative approach using emotion engine data is needed." In this way, the system supports investment decisions that reflect the user's psychological tendencies.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] The server collects market information and news from external data sources. Input consists of financial data and the latest news obtained via an API. Data processing involves storing the data in an analytical database and formatting it for use in subsequent analysis steps. Specifically, a program runs at regular intervals to call the API and retrieve the necessary information.

[0187] Step 2:

[0188] The device captures the user's facial expressions and voice in real time. Input consists of the user's facial expressions and voice data acquired from the camera and microphone. An emotion engine analyzes this data to extract the user's emotional state (e.g., positive, negative). Output is the user's emotional state data. The specific operation involves an emotion estimation process using image processing algorithms and voice analysis algorithms.

[0189] Step 3:

[0190] The server uses a generative AI model to integrate market information collected in Step 1 with emotional state data obtained in Step 2. The inputs are market information and emotional data. As a data calculation, the AI ​​model uses this information to generate an investment strategy suitable for the user. The output is the proposed investment strategy. Specific operations include a process that outputs a risk-reducing strategy when the emotional state is "high stress."

[0191] Step 4:

[0192] The terminal presents the user with investment strategies received from the server. The input is the data for the proposed investment strategies. Color coding and icons are used to visually represent the strategies to the user in an easily understandable way. The output is a screen display that the user can easily understand and use. Specifically, an interface is in operation that highlights different aspects of the strategy.

[0193] Step 5:

[0194] The user reviews the presented investment strategy and agrees to or adjusts it. The input is the investment strategy information displayed on the screen. The user adjusts the proposed strategy as needed and makes a final decision. The output is the investment policy adjusted by the user. Specific actions include using an input interface for adjustments and sending the changes to the server.

[0195] (Application Example 2)

[0196] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0197] In modern investment activities, decisions based on individual emotions can significantly influence the outcome. However, traditional systems have struggled to personalize investment decisions while considering the user's emotional state. Therefore, there is a need to provide risk management and investment strategies tailored to each user.

[0198] 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.

[0199] In this invention, the server includes means for recognizing the user's emotional state and adjusting the plan based on that emotional state, means for collecting market data and new information from external sources, and means for analyzing the market data and new information to generate a plan. This makes it possible to propose appropriate risk management and investment strategies that are in line with the user's emotions.

[0200] A "user" refers to an individual or organization that engages in investment activities within the system.

[0201] "Input" refers to the information or instructions that a user provides to the system.

[0202] "Purpose" refers to the individual investment goals or intentions that the user hopes to achieve.

[0203] "Risk tolerance" is an indicator that shows the degree of risk an individual user can tolerate in their investments.

[0204] "External information sources" refer to information providers or media from which market data and related new information are collected.

[0205] "Market data" refers to detailed information about prices, trends, indices, and other factors in financial markets.

[0206] "New information" refers to the latest information based on market fluctuations and socioeconomic factors.

[0207] A "plan" refers to the strategies and policies generated to guide the user's investment activities.

[0208] "Trading activity" refers to the buying and selling of financial products conducted according to a plan.

[0209] "Emotional state" refers to a temporary psychological state recognized through analysis of the user's facial expressions and voice.

[0210] A "server" refers to a computer device that collects, processes, and analyzes data, and manages the entire system.

[0211] This invention incorporates an emotion engine into an investment support system for individual investors, enabling real-time detection of the user's emotional state and personalized investment decisions. The system consists of a server, a terminal, and user operation.

[0212] The server is a computing device that collects market data and new information from external sources, analyzes this data, and generates investment plans. This plan generation utilizes a generative AI model. The server receives data from an emotion engine that recognizes the user's emotional state and adjusts the plan accordingly. For example, if the emotion engine detects the user's stress level, the server can generate a conservative investment plan with reduced risk.

[0213] The terminal is a device for users to interact with the system and plays a role in understanding the user's emotional state in real time. The terminal is equipped with a camera and microphone, which are used to analyze the user's facial expressions and voice tone. Facial expressions are analyzed using facial recognition technology with OpenCV, and emotional states are detected through voice analysis using Google® Cloud Speech-to-Text API. The results are visually fed back to the user, and a screen is displayed to confirm and consent to changes in the investment plan based on their emotions.

[0214] Users input investment instructions through their devices and select risk management and investment strategies based on sentiment analysis feedback. For example, if a user receives a sentiment analysis result indicating they are "highly stressed by a market crash," they can adopt the suggested risk avoidance plan. This allows users to make flexible investment decisions that align with their own emotional state.

[0215] As a concrete example, if a user becomes confused due to sudden market fluctuations after making an investment decision, an emotion engine could be used to detect that stress, and the server could automatically generate and present a conservative plan based on that.

[0216] Example prompt: "Design an AI application that analyzes the user's facial expressions and voice tone, and advises on how to assist them in their daily life based on the emotion estimation results."

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

[0218] Step 1:

[0219] The terminal receives investment-related input from the user and retrieves registered investment goals and risk tolerance levels. Based on the entered information, it queries the database for the user's risk profile and retrieves that data.

[0220] Step 2:

[0221] The device collects facial image and audio data from the user using its camera and microphone. This raw data is then used as input to initiate face recognition and speech analysis. OpenCV is used to extract facial features, and the Google Cloud Speech-to-Text API is used to analyze tone and tempo from the audio. The resulting emotion data is then generated and sent to the server.

[0222] Step 3:

[0223] The server analyzes emotional data received from the terminal to identify the user's emotional state. Using the emotional state as input, a generative AI model is used to create an appropriate investment plan tailored to the current market conditions. New market data and information are acquired from external sources and incorporated into the plan.

[0224] Step 4:

[0225] The server adjusts the newly generated investment plan and its risk level to match the user's emotional state. After adjusting the plan, it sends it to the terminal and notifies the user. As a result, the plan's risk settings take into account the user's stress level.

[0226] Step 5:

[0227] The device visually displays the details of the adjusted investment plan to the user and provides a screen requesting confirmation and acceptance of the plan. Once the user reviews the plan and presses the accept button, the plan becomes actionable.

[0228] Step 6:

[0229] If the user accepts the plan, the server will execute automated trading based on that plan. The terminal will provide real-time feedback on the results of the executed trades and display the trading results to the user.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] [Second Embodiment]

[0234] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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).

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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".

[0246] This invention relates to a system for providing advanced asset management support to individual investors. The system utilizes a generative AI model to automatically formulate and manage investment strategies that take into account the user's investment goals and risk tolerance. The program processing of this system is described below in natural language.

[0247] Server operation

[0248] The server provides core data processing capabilities. Initially, it collects market and new information from external data sources via APIs from securities firms and market information providers. The acquired data is preprocessed and then analyzed by a generative AI model. The AI ​​model predicts investment market trends and designs optimal investment strategies tailored to the user's goals and risk tolerance. After the strategy is formulated, the server automatically executes trading activities in the market. Furthermore, the server monitors portfolio performance and performs rebalancing as needed.

[0249] As a concrete example, when formulating an investment strategy for growth stocks, the AI ​​model analyzes recent financial reports and news articles of companies to identify sectors that it deems to have high growth potential. Based on this, the server sends buy / sell instructions to the brokerage firm to invest in those specific stocks.

[0250] Terminal operation

[0251] The terminal handles user interaction. Users set investment goals and risk tolerance from the terminal, and this information is sent to the server. The latest investment strategy and portfolio information received from the server is visualized and displayed to the user in an easy-to-understand format. The terminal provides the user with information on the progress of asset management and adjustments to the strategy using graphs and dashboards.

[0252] User actions

[0253] Users set investment goals and input their risk tolerance into the system via their terminal. They then check the performance of their displayed portfolio and provide feedback as needed. This feedback is used to adjust strategies on the server. For example, if a user determines they can tolerate higher risk, a new strategy is redesigned and implemented to align with their preferences.

[0254] This enables users to efficiently and individually manage their assets according to their own goals, and to make socially meaningful investments that take ESG scores into consideration.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The server collects market information and new information from external data sources. It retrieves data from stock exchanges and financial news providers via APIs and organizes it chronologically.

[0258] Step 2:

[0259] The server preprocesses the acquired data. It fills in missing data and handles outliers to format the data into a format suitable for analysis.

[0260] Step 3:

[0261] The server analyzes pre-processed data using a generative AI model. It predicts market trends, assesses risks, and generates the optimal investment strategy for the user.

[0262] Step 4:

[0263] The server automatically sends buy and sell orders to brokerage firms based on the generated investment strategy. Buy and sell orders are issued via API.

[0264] Step 5:

[0265] The server monitors portfolio performance in real time. If a pre-configured risk threshold is exceeded, the portfolio is rebalanced.

[0266] Step 6:

[0267] The terminal provides an interface to the user. It displays a screen to the user where they can input their investment goals and risk tolerance.

[0268] Step 7:

[0269] The terminal receives investment strategy and performance information sent from the server. This information is then visually displayed to the user in the form of diagrams and dashboards.

[0270] Step 8:

[0271] Users input their goals and risk tolerance levels via their device. Once input is complete, the information is sent to the server and incorporated into the strategy design.

[0272] Step 9:

[0273] Users can review investment status and strategy details and provide feedback through their devices. The server receives this feedback and uses it to adjust future strategies.

[0274] (Example 1)

[0275] 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".

[0276] Modern individual investors are required to manage their assets efficiently and customized based on market and trend information gathered from a wide range of sources. However, there is currently a lack of systems that provide sophisticated investment strategies that can be easily used by users who do not require specialized investment knowledge. In this situation, there is a need to provide a system that automatically generates optimal investment strategies based on the user's investment goals and risk tolerance, and manages assets efficiently and individually.

[0277] 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.

[0278] In this invention, the server includes means for obtaining an investment goal and a risk tolerance based on an input from a user, means for collecting market information and trend information from an external information source, means for analyzing the market information and trend information and generating an investment strategy using a prompt sentence for a generation AI model, means for automatically executing trading activities based on the generated investment strategy, means for changing the investment strategy as necessary and notifying the user of the content thereof, means for visually displaying the investment strategy and the results of asset management to the user, means for receiving the user's feedback and adjusting the investment strategy based thereon, and means for monitoring a portfolio by an information processing device and adjusting asset allocation as necessary. Thereby, it becomes possible for a user to perform asset management efficiently and individually without requiring specialized knowledge.

[0279] The "user" refers to an individual or a corporation that conducts investment activities through automated asset management by using this system.

[0280] The "external information source" refers to an external data source that provides market information and trend information, such as a securities company or a market information provider.

[0281] The "market information" refers to information related to investment activities, such as stock prices, corporate financial information, and economic indicators.

[0282] The "trend information" refers to information that may affect the market, such as economic fluctuations, corporate news, and political events.

[0283] The "generation AI model" refers to an artificial intelligence model that analyzes the market information and trend information and generates an investment strategy.

[0284] The "prompt sentence" refers to an instruction sentence used to generate a specific investment strategy for a generation AI model.

[0285] "Investment strategy" refers to a plan for asset management generated based on the user's investment goals and risk tolerance.

[0286] "Automatically execute" means a process in which the system conducts trading activities in the market without human intervention.

[0287] "Visually display" means to show the investment strategy and the results of asset management to the user in an easy-to-understand form using graphs and dashboards.

[0288] "Feedback" refers to the opinions and requests provided by the user, which serve as input information for the system to adjust the investment strategy based on them.

[0289] "Information processing device" refers to a device for acquiring, analyzing, storing, and displaying information, including digital computers.

[0290] "Portfolio" refers to a combination of multiple financial products held by the user and is the object whose asset allocation is managed.

[0291] This invention relates to a system that provides automated asset management for individual investors. Specific embodiments will be described below.

[0292] Server operation

[0293] The server functions as the core of the entire system and is responsible for multiple major processes. First, the server acquires market information and trend information from external information sources. Specifically, it automatically acquires stock price information, financial reports, economic indicators, and market news using the APIs of securities companies and market information providers, and accumulates these data in the database.

[0294] Next, the server preprocesses the collected data. Preprocessing includes removing outliers, standardizing data formats, and supplementing missing data. The processed data is then input into a generative AI model, which performs analysis based on prompt messages. The server uses the generative AI model to design an optimal investment strategy tailored to the user's investment goals and risk tolerance. An example of a prompt message used in this process is, "Design an optimal tech stock investment strategy for a user with high risk tolerance."

[0295] The server generates buy and sell orders based on the designed investment strategy and places them on the market via the brokerage firm's API. The server also monitors the portfolio performance in real time and adjusts asset allocation as needed.

[0296] Terminal operation

[0297] The terminal functions as an interface with the user. The user uses the terminal to set investment goals and risk tolerance and send them to the server. The terminal visually displays the latest investment strategies and portfolio updates returned from the server. The terminal includes graphs and dashboards, allowing the user to intuitively understand the progress of their asset management.

[0298] User actions

[0299] Users can provide investment feedback through their devices. For example, users can reset their risk tolerance, and this information is used to readjust strategies on the server. This allows users to manage their assets in a way that reflects their own intentions.

[0300] In this way, the server, terminals, and users cooperate with each other to achieve efficient and personalized asset management. This system allows users to manage their assets with peace of mind without requiring advanced expertise.

[0301] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0302] Step 1:

[0303] The server collects market information and trend information from external information sources. Specifically, it obtains stock prices, corporate financial data, economic indicators, and news articles through the APIs of securities companies and market information providers. The input is the API access information, and the output is the market and trend information stored in the database.

[0304] Step 2:

[0305] The server performs preprocessing on the acquired market information and trend information. It conducts data cleaning, removes outliers, and unifies the data format. Also, it complements missing data with past information or estimated values. The input is the raw data, and the output is the formatted data that has been cleaned and processed.

[0306] Step 3:

[0307] The server inputs the formatted data into the generative AI model for analysis. At this time, it generates an investment strategy using a prompt sentence. In this process, the inputs are the formatted data and the prompt sentence, and the output is the optimal investment strategy considering the user's investment goals and risk tolerance.

[0308] Step 4:

[0309] The server executes automatic trading based on the generated investment strategy. Specifically, it generates trading instructions and transmits them to the market through the API of the securities company. As a result, transactions of financial products are conducted in accordance with the specified investment strategy. The input is the investment strategy, and the output is the executed transaction record.

[0310] Step 5:

[0311] The server monitors portfolio performance in real time. Necessary adjustments are made in response to market fluctuations, and rebalancing is performed to optimize asset allocation. Inputs are market information and the portfolio's current asset allocation, while output is the adjusted asset allocation.

[0312] Step 6:

[0313] The terminal visually displays the latest information on investment strategies and portfolios to the user. Specifically, it provides information through graphs and dashboards, making it easier for users to understand the progress of their investments. The input is portfolio data from the server, and the output is visualized information.

[0314] Step 7:

[0315] Users provide feedback through their devices and adjust their investment goals and risk tolerance as needed. This feedback is sent to the server and incorporated into the next investment strategy. The input is the user's feedback information, and the output is the adjusted investment strategy.

[0316] (Application Example 1)

[0317] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0318] For individual investors, developing and managing optimal investment strategies based on their own investment goals and risk tolerance, and then automatically executing specific fund allocation adjustments, is difficult for the average user who lacks investment expertise and time. Furthermore, in dynamic market environments, rapid changes in investment strategies and reallocation of funds are necessary, but doing this manually is inefficient.

[0319] 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.

[0320] In this invention, the server includes means for acquiring investment targets and risk tolerance based on user input; means for collecting market information and new information from external data sources; means for generating an investment strategy by analyzing the market information and new information; means for automatically executing trading activities according to the generated investment strategy; means for modifying the investment strategy as necessary and notifying the user of the changes; means for visually displaying the investment strategy and asset management results to the user; and means for automatically adjusting the allocation of funds based on the user's investment strategy. This enables the user to efficiently and quickly manage assets in response to market fluctuations.

[0321] "User input" refers to information that users provide to the system regarding their investment goals and risk tolerance.

[0322] An "external data source" refers to an external information source that is accessed to provide market information or new information.

[0323] "Gathering market information and new information" refers to the process of acquiring necessary data from external data sources and making it available within the system.

[0324] "Investment strategy generation" refers to constructing an investment policy that is suitable for the user's goals and risk level, based on the collected information.

[0325] "Automated execution of trading activities" refers to the automatic execution of stock and asset transactions in the market according to a generated investment strategy.

[0326] A "notification of changes to investment strategy" refers to modifying an investment strategy based on market changes or user feedback and communicating those changes to the user.

[0327] "Visual presentation" refers to providing users with an easy-to-understand presentation of investment strategies and asset management results using graphs, dashboards, and other visual aids.

[0328] "Automatic execution of fund allocation adjustments" refers to the process of optimizing fund allocation based on the user's investment strategy and automatically moving funds.

[0329] The system for realizing this invention is built on interaction between three parties: a server, a terminal, and a user.

[0330] The server connects to external data sources to collect market and new information. This includes obtaining real-time data from brokerage firms and market data providers via APIs. The collected data is preprocessed using Python and major libraries (NumPy, Pandas) and analyzed using a generative AI model. Based on the analysis results, an investment strategy optimized for the user's investment goals and risk tolerance is generated, and trading activities in the market are automatically executed. Furthermore, the strategy is updated as needed in response to changes in the investment strategy or new information, and the user is notified accordingly. For example, when growth in the agricultural sector is predicted, an investment strategy for related stocks is formulated.

[0331] The terminal serves as the direct interface with the user. Here, the user can input their investment goals and risk tolerance, and this information is immediately transmitted to the server. Furthermore, the terminal visually displays the received investment strategies and asset management results, presenting them in an easy-to-understand manner for the user. This includes visual displays using graphs and dashboards.

[0332] Users can reflect their intentions in the system by providing feedback on their investment goals and risk tolerance entered through their terminal. This feedback is analyzed on the server and incorporated into the investment strategy as needed. For example, if a user changes their intention towards accepting higher risk, the new investment strategy will be adjusted based on that feedback.

[0333] An example of a specific prompt for the generated AI model is, "Considering current market trends in the agricultural sector, please design the optimal investment strategy for my portfolio." By using such prompts, users can manage their assets in line with market trends while receiving advice from the system.

[0334] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0335] Step 1:

[0336] The server accesses external data sources and collects market and new information via APIs. The collected data is imported into the server as raw data. The input data is real-time data from the API, and the output data is pre-processed. The server uses Python and NumPy to impute missing values ​​and standardize the raw data.

[0337] Step 2:

[0338] The server inputs pre-processed data into the generated AI model and begins the analysis. The AI ​​model performs complex analyses to predict investment market trends and generates an initial investment strategy. The input is pre-processed market data, and the output is an investment strategy tailored to the user's investment goals and risk tolerance. Here, the AI ​​applies an algorithm to predict market trends and calculate investment priorities.

[0339] Step 3:

[0340] The server executes buy and sell orders in the market via an automated trading function based on the generated investment strategy. The target assets are optimized according to the investment strategy. The input is the investment strategy output by the generating AI model, and the output is the actual trade order. The trade is linked to the brokerage firm's API, and funds are transferred to the specified portfolio.

[0341] Step 4:

[0342] The terminal retrieves the user's investment goals and risk tolerance and sends this information to the server. The input is the investment goals and risk tolerance set by the user on the terminal, and the output is feedback data to the server. The terminal allows users to intuitively configure these settings via a user interface.

[0343] Step 5:

[0344] The server re-analyzes the investment strategy as needed based on user feedback and generates a new strategy. The input is user feedback information, and the output is the adjusted investment strategy. At this stage, the server performs a re-evaluation process of the generated AI model and formulates a strategy that reflects the user's new intentions.

[0345] Step 6:

[0346] The terminal visually displays and provides the user with the latest investment strategies and portfolio performance received from the server. The input is investment strategy information sent from the server, and the output is the user-viewed interface for the investment status. The terminal uses graphs and charts to visualize the information in an intuitive and easy-to-understand manner.

[0347] 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.

[0348] This invention enhances the user experience and further personalizes investment decisions by incorporating an emotion engine that recognizes user emotions into an investment support system for individual investors. This system detects the user's emotional state in real time and uses that data to adjust investment strategies and re-evaluate risk tolerance.

[0349] Server operation

[0350] The server processes and analyzes investment-related data. Its basic functions include collecting market and new information from external data sources and designing investment strategies using generative AI models. In addition, the server receives data from the emotion engine and analyzes the user's emotional state. This emotional data is used to adjust investment strategies and set risk tolerance levels. For example, if the emotion engine detects user stress, it can suggest a conservative investment strategy with reduced risk.

[0351] How the emotion engine works

[0352] The emotion engine is installed on the device and recognizes emotions by analyzing the user's facial expressions and voice. The engine updates the user's emotional state in real time and sends that data to the server. For example, it may analyze the tone and tempo of the user's voice input to identify positive or negative emotions.

[0353] Terminal operation

[0354] The device provides users with feedback on their emotional state. It not only presents users with an interface for setting investment goals and risk tolerance, but also visually displays the results of emotional analysis by an emotion engine. The device also provides a screen for users to review and agree to changes in their emotionally-based investment strategy.

[0355] User actions

[0356] Users input investment information via their devices and receive real-time sentiment analysis results. For example, if the sentiment engine analysis indicates that the user is "highly stressed by a sharp market decline," the user can adopt the suggested risk-averse strategy. This system allows users to make flexible investment decisions that align with their own emotional state.

[0357] The following describes the processing flow.

[0358] Step 1:

[0359] The server regularly collects market information and new data through APIs from securities firms and market information providers. This allows it to obtain the latest financial data and prepare for subsequent analysis.

[0360] Step 2:

[0361] The server preprocesses the collected data and designs investment strategies using a generative AI model. Data integrity is ensured during preprocessing, after which the predictive model begins its analysis.

[0362] Step 3:

[0363] The server receives emotion engine data transmitted in real time from the terminal and analyzes the user's emotional state. This information is essential for adjusting investment strategies.

[0364] Step 4:

[0365] The emotion engine analyzes the user's facial expressions and voice to recognize their emotions. This data is transmitted to the server via the device. For example, the emotion engine can use the camera to determine the user's facial expressions.

[0366] Step 5:

[0367] The server re-evaluates the current investment strategy based on emotional data and makes adjustments as needed. For example, it might suggest a strategy to invest in lower-risk assets to users with unstable emotions.

[0368] Step 6:

[0369] The terminal displays updated investment strategies and sentiment analysis results from the server to the user. Visual dashboards and alerts are used to make it easy for the user to understand.

[0370] Step 7:

[0371] Users review the presented information and provide feedback via their device if necessary. For example, they can agree to or reject proposed changes to the strategy.

[0372] Step 8:

[0373] User feedback is sent to the server and used to design future strategies. This enables flexible portfolio management that reflects user opinions.

[0374] (Example 2)

[0375] 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".

[0376] Traditional investment support systems failed to reflect users' emotional factors in investment strategies, making it difficult to respond flexibly to individual stress levels and risk tolerances. This sometimes resulted in users being unable to make optimal investment decisions. In particular, there was a need to consider users' psychological reactions to market fluctuations and rapid changes in information.

[0377] 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.

[0378] In this invention, the server includes means for detecting the user's emotional state in real time and transmitting emotional data to the server, means for generating an investment strategy using a generative AI model, and means for adjusting the investment strategy and re-evaluating risk tolerance using the emotional data. This makes it possible to provide a flexible investment strategy based on the user's real-time emotional state.

[0379] "User emotional state" refers to information that represents the user's psychological and emotional responses in real time, and is data obtained from facial expressions, tone of voice, speaking speed, etc.

[0380] A "generative AI model" is a collection of algorithms that analyze data and generate results tailored to a specific purpose, and is based on machine learning and artificial intelligence technologies.

[0381] "Market information" refers to information about factors that may influence the market, such as price trends, trading volume, and economic news in financial markets.

[0382] "Risk tolerance" is a measure that indicates the range of risk a user is willing to accept when making an investment, and it is one of the important criteria in selecting an investment strategy.

[0383] An "investment strategy" is a plan or method set out to achieve investment objectives, and includes the selection of financial products and the construction of a portfolio.

[0384] An "emotion engine" is a system or program that analyzes a user's emotions and acquires and utilizes that data in real time.

[0385] In embodiments of the present invention, a user, a terminal, and a server collaborate to provide an advanced investment support system that takes the user's emotional state into account. The terminal first interacts with the user and extracts emotional data in real time from the user's facial expressions and voice through an emotion engine. This process utilizes a camera and microphone to collect the user's facial expressions and voice. The emotion engine analyzes the data in real time and identifies positive or negative emotional states. For example, if the user is feeling anxious about market trends, this emotional data is immediately transmitted to the server.

[0386] The server collects market information and news from external data sources. The collected data is analyzed using a generative AI model. The generative AI model uses natural language processing and machine learning to generate an optimal investment strategy based on the user's emotional state. Using the previous example, if the server detects that the user is in a high-stress state, it generates a "risk-reduced, conservative investment strategy" and sends it to the terminal.

[0387] The device visually displays the received investment strategy to the user. The interface is designed to allow the user to intuitively understand the proposed investment strategy, with key elements of the strategy color-coded. Furthermore, the user can review the proposed strategy and make adjustments as needed.

[0388] As a concrete example, when using a prompt, information is provided to the generating AI model in the form of, "Please suggest an investment strategy. The user is currently stressed by the market situation. A conservative approach using emotion engine data is needed." In this way, the system supports investment decisions that reflect the user's psychological tendencies.

[0389] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0390] Step 1:

[0391] The server collects market information and news from external data sources. Input consists of financial data and the latest news obtained via an API. Data processing involves storing the data in an analytical database and formatting it for use in subsequent analysis steps. Specifically, a program runs at regular intervals to call the API and retrieve the necessary information.

[0392] Step 2:

[0393] The device captures the user's facial expressions and voice in real time. Input consists of the user's facial expressions and voice data acquired from the camera and microphone. An emotion engine analyzes this data to extract the user's emotional state (e.g., positive, negative). Output is the user's emotional state data. The specific operation involves an emotion estimation process using image processing algorithms and voice analysis algorithms.

[0394] Step 3:

[0395] The server uses a generative AI model to integrate market information collected in Step 1 with emotional state data obtained in Step 2. The inputs are market information and emotional data. As a data calculation, the AI ​​model uses this information to generate an investment strategy suitable for the user. The output is the proposed investment strategy. Specific operations include a process that outputs a risk-reducing strategy when the emotional state is "high stress."

[0396] Step 4:

[0397] The terminal presents the user with investment strategies received from the server. The input is the data for the proposed investment strategies. Color coding and icons are used to visually represent the strategies to the user in an easily understandable way. The output is a screen display that the user can easily understand and use. Specifically, an interface is in operation that highlights different aspects of the strategy.

[0398] Step 5:

[0399] The user reviews the presented investment strategy and agrees to or adjusts it. The input is the investment strategy information displayed on the screen. The user adjusts the proposed strategy as needed and makes a final decision. The output is the investment policy adjusted by the user. Specific actions include using an input interface for adjustments and sending the changes to the server.

[0400] (Application Example 2)

[0401] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0402] In modern investment activities, decisions based on individual emotions can significantly influence the outcome. However, traditional systems have struggled to personalize investment decisions while considering the user's emotional state. Therefore, there is a need to provide risk management and investment strategies tailored to each user.

[0403] 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.

[0404] In this invention, the server includes means for recognizing the user's emotional state and adjusting the plan based on that emotional state, means for collecting market data and new information from external sources, and means for analyzing the market data and new information to generate a plan. This makes it possible to propose appropriate risk management and investment strategies that are in line with the user's emotions.

[0405] A "user" refers to an individual or organization that engages in investment activities within the system.

[0406] "Input" refers to the information or instructions that a user provides to the system.

[0407] "Purpose" refers to the individual investment goals or intentions that the user hopes to achieve.

[0408] "Risk tolerance" is an indicator that shows the degree of risk an individual user can tolerate in their investments.

[0409] "External information sources" refer to information providers or media from which market data and related new information are collected.

[0410] "Market data" refers to detailed information about prices, trends, indices, and other factors in financial markets.

[0411] "New information" refers to the latest information based on market fluctuations and socioeconomic factors.

[0412] A "plan" refers to the strategies and policies generated to guide the user's investment activities.

[0413] "Trading activity" refers to the buying and selling of financial products conducted according to a plan.

[0414] "Emotional state" refers to a temporary psychological state recognized through analysis of the user's facial expressions and voice.

[0415] A "server" refers to a computer device that collects, processes, and analyzes data, and manages the entire system.

[0416] This invention incorporates an emotion engine into an investment support system for individual investors, enabling real-time detection of the user's emotional state and personalized investment decisions. The system consists of a server, a terminal, and user operation.

[0417] The server is a computing device that collects market data and new information from external sources, analyzes this data, and generates investment plans. This plan generation utilizes a generative AI model. The server receives data from an emotion engine that recognizes the user's emotional state and adjusts the plan accordingly. For example, if the emotion engine detects the user's stress level, the server can generate a conservative investment plan with reduced risk.

[0418] The terminal is a device for users to interact with the system and plays a role in understanding the user's emotional state in real time. The terminal is equipped with a camera and microphone, which are used to analyze the user's facial expressions and voice tone. Facial expressions are analyzed using facial recognition technology with OpenCV, and emotional states are detected through voice analysis using the Google Cloud Speech-to-Text API. The results are visually fed back to the user, and a screen is displayed to confirm and consent to changes in the investment plan based on their emotions.

[0419] Users input investment instructions through their devices and select risk management and investment strategies based on sentiment analysis feedback. For example, if a user receives a sentiment analysis result indicating they are "highly stressed by a market crash," they can adopt the suggested risk avoidance plan. This allows users to make flexible investment decisions that align with their own emotional state.

[0420] As a concrete example, if a user becomes confused due to sudden market fluctuations after making an investment decision, an emotion engine could be used to detect that stress, and the server could automatically generate and present a conservative plan based on that.

[0421] Example prompt: "Design an AI application that analyzes the user's facial expressions and voice tone, and advises on how to assist them in their daily life based on the emotion estimation results."

[0422] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0423] Step 1:

[0424] The terminal receives investment-related input from the user and retrieves registered investment goals and risk tolerance levels. Based on the entered information, it queries the database for the user's risk profile and retrieves that data.

[0425] Step 2:

[0426] The device collects facial image and audio data from the user using its camera and microphone. This raw data is then used as input to initiate face recognition and speech analysis. OpenCV is used to extract facial features, and the Google Cloud Speech-to-Text API is used to analyze tone and tempo from the audio. The resulting emotion data is then generated and sent to the server.

[0427] Step 3:

[0428] The server analyzes emotional data received from the terminal to identify the user's emotional state. Using the emotional state as input, a generative AI model is used to create an appropriate investment plan tailored to the current market conditions. New market data and information are acquired from external sources and incorporated into the plan.

[0429] Step 4:

[0430] The server adjusts the newly generated investment plan and its risk level to match the user's emotional state. After adjusting the plan, it sends it to the terminal and notifies the user. As a result, the plan's risk settings take into account the user's stress level.

[0431] Step 5:

[0432] The device visually displays the details of the adjusted investment plan to the user and provides a screen requesting confirmation and acceptance of the plan. Once the user reviews the plan and presses the accept button, the plan becomes actionable.

[0433] Step 6:

[0434] If the user accepts the plan, the server will execute automated trading based on that plan. The terminal will provide real-time feedback on the results of the executed trades and display the trading results to the user.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] [Third Embodiment]

[0439] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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".

[0451] This invention relates to a system for providing advanced asset management support to individual investors. The system utilizes a generative AI model to automatically formulate and manage investment strategies that take into account the user's investment goals and risk tolerance. The program processing of this system is described below in natural language.

[0452] Server operation

[0453] The server provides core data processing capabilities. Initially, it collects market and new information from external data sources via APIs from securities firms and market information providers. The acquired data is preprocessed and then analyzed by a generative AI model. The AI ​​model predicts investment market trends and designs optimal investment strategies tailored to the user's goals and risk tolerance. After the strategy is formulated, the server automatically executes trading activities in the market. Furthermore, the server monitors portfolio performance and performs rebalancing as needed.

[0454] As a concrete example, when formulating an investment strategy for growth stocks, the AI ​​model analyzes recent financial reports and news articles of companies to identify sectors that it deems to have high growth potential. Based on this, the server sends buy / sell instructions to the brokerage firm to invest in those specific stocks.

[0455] Terminal operation

[0456] The terminal handles user interaction. Users set investment goals and risk tolerance from the terminal, and this information is sent to the server. The latest investment strategy and portfolio information received from the server is visualized and displayed to the user in an easy-to-understand format. The terminal provides the user with information on the progress of asset management and adjustments to the strategy using graphs and dashboards.

[0457] User actions

[0458] Users set investment goals and input their risk tolerance into the system via their terminal. They then check the performance of their displayed portfolio and provide feedback as needed. This feedback is used to adjust strategies on the server. For example, if a user determines they can tolerate higher risk, a new strategy is redesigned and implemented to align with their preferences.

[0459] This enables users to efficiently and individually manage their assets according to their own goals, and to make socially meaningful investments that take ESG scores into consideration.

[0460] The following describes the processing flow.

[0461] Step 1:

[0462] The server collects market information and new information from external data sources. It retrieves data from stock exchanges and financial news providers via APIs and organizes it chronologically.

[0463] Step 2:

[0464] The server preprocesses the acquired data. It fills in missing data and handles outliers to format the data into a format suitable for analysis.

[0465] Step 3:

[0466] The server analyzes pre-processed data using a generative AI model. It predicts market trends, assesses risks, and generates the optimal investment strategy for the user.

[0467] Step 4:

[0468] The server automatically sends buy and sell orders to brokerage firms based on the generated investment strategy. Buy and sell orders are issued via API.

[0469] Step 5:

[0470] The server monitors portfolio performance in real time. If a pre-configured risk threshold is exceeded, the portfolio is rebalanced.

[0471] Step 6:

[0472] The terminal provides an interface to the user. It displays a screen to the user where they can input their investment goals and risk tolerance.

[0473] Step 7:

[0474] The terminal receives investment strategy and performance information sent from the server. This information is then visually displayed to the user in the form of diagrams and dashboards.

[0475] Step 8:

[0476] Users input their goals and risk tolerance levels via their device. Once input is complete, the information is sent to the server and incorporated into the strategy design.

[0477] Step 9:

[0478] Users can review investment status and strategy details and provide feedback through their devices. The server receives this feedback and uses it to adjust future strategies.

[0479] (Example 1)

[0480] 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."

[0481] Modern individual investors are required to manage their assets efficiently and customized based on market and trend information gathered from a wide range of sources. However, there is currently a lack of systems that provide sophisticated investment strategies that can be easily used by users who do not require specialized investment knowledge. In this situation, there is a need to provide a system that automatically generates optimal investment strategies based on the user's investment goals and risk tolerance, and manages assets efficiently and individually.

[0482] 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.

[0483] In this invention, the server includes means for obtaining investment targets and risk tolerance based on user input; means for collecting market information and trend information from external information sources; means for analyzing the market information and trend information and generating an investment strategy using prompt statements in a generating AI model; means for automatically executing trading activities based on the generated investment strategy; means for modifying the investment strategy as necessary and notifying the user of the changes; means for visually displaying the investment strategy and asset management results to the user; means for receiving user feedback and adjusting the investment strategy based on that feedback; and means for monitoring the portfolio with an information processing device and adjusting asset allocation as necessary. This makes it possible for users to manage their assets efficiently and on an individual basis without requiring specialized knowledge.

[0484] A "user" refers to an individual or legal entity that uses this system to conduct investment activities through automated asset management.

[0485] "External information sources" refer to external data sources that provide market information and trend information, such as securities companies and market information providers.

[0486] "Market information" refers to information related to investment activities, such as stock prices, corporate financial information, and economic indicators.

[0487] "Trend information" refers to information that may affect the market, such as economic fluctuations, corporate news, and political events.

[0488] A "generative AI model" refers to an artificial intelligence model that analyzes the aforementioned market information and trend information to generate investment strategies.

[0489] A "prompt statement" refers to an instruction statement used to generate a specific investment strategy for a generative AI model.

[0490] An "investment strategy" refers to a plan for asset management generated based on the user's investment goals and risk tolerance.

[0491] The term "automatic execution" refers to a process in which a system carries out buying and selling activities in the market without human intervention.

[0492] "Visual display" refers to presenting investment strategies and asset management results to users in an easy-to-understand format using graphs and dashboards.

[0493] "Feedback" refers to the opinions and requests provided by users, and the input information used by the system to adjust its investment strategy based on this feedback.

[0494] "Information processing equipment" refers to devices, including digital computers, used for acquiring, analyzing, storing, and displaying information.

[0495] A "portfolio" refers to a combination of multiple financial products held by a user, and the asset allocation of that portfolio is managed.

[0496] This invention relates to a system that provides automated asset management for individual investors. Specific embodiments are described below.

[0497] Server operation

[0498] The server functions as the core of the entire system and is responsible for several key processes. First, the server retrieves market and trend information from external sources. Specifically, it uses APIs from securities companies and market information providers to automatically retrieve stock price information, financial reports, economic indicators, and market news, and stores this data in a database.

[0499] Next, the server preprocesses the collected data. Preprocessing includes removing outliers, standardizing data formats, and supplementing missing data. The processed data is then input into a generative AI model, which performs analysis based on prompt messages. The server uses the generative AI model to design an optimal investment strategy tailored to the user's investment goals and risk tolerance. An example of a prompt message used in this process is, "Design an optimal tech stock investment strategy for a user with high risk tolerance."

[0500] The server generates buy and sell orders based on the designed investment strategy and places them on the market via the brokerage firm's API. The server also monitors the portfolio performance in real time and adjusts asset allocation as needed.

[0501] Terminal operation

[0502] The terminal functions as an interface with the user. The user uses the terminal to set investment goals and risk tolerance and send them to the server. The terminal visually displays the latest investment strategies and portfolio updates returned from the server. The terminal includes graphs and dashboards, allowing the user to intuitively understand the progress of their asset management.

[0503] User actions

[0504] Users can provide investment feedback through their devices. For example, users can reset their risk tolerance, and this information is used to readjust strategies on the server. This allows users to manage their assets in a way that reflects their own intentions.

[0505] In this way, the server, terminals, and users cooperate with each other to achieve efficient and personalized asset management. This system allows users to manage their assets with peace of mind without requiring advanced expertise.

[0506] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0507] Step 1:

[0508] The server collects market and trend information from external sources. Specifically, it retrieves stock prices, corporate financial data, economic indicators, and news articles through APIs from securities companies and market information providers. The input is API access information, and the output is market and trend information stored in the database.

[0509] Step 2:

[0510] The server preprocesses the acquired market and trend information. It cleans the data, removes outliers, and standardizes the data format. It also supplements missing data with historical information and estimates. The input is raw data, and the output is well-formed data that has been cleaned and processed.

[0511] Step 3:

[0512] The server inputs well-formed data into a generating AI model for analysis. During this process, it uses prompt statements to generate an investment strategy. In this process, the input consists of well-formed data and prompt statements, while the output is an optimal investment strategy that takes into account the user's investment goals and risk tolerance.

[0513] Step 4:

[0514] The server executes automated trades based on the generated investment strategy. Specifically, it generates buy and sell instructions and sends them to the market via the brokerage firm's API. This results in the execution of trades in financial instruments in accordance with the specified investment strategy. The input is the investment strategy, and the output is a record of the executed trades.

[0515] Step 5:

[0516] The server monitors portfolio performance in real time. Necessary adjustments are made in response to market fluctuations, and rebalancing is performed to optimize asset allocation. Inputs are market information and the portfolio's current asset allocation, while output is the adjusted asset allocation.

[0517] Step 6:

[0518] The terminal visually displays the latest information on investment strategies and portfolios to the user. Specifically, it provides information through graphs and dashboards, making it easier for users to understand the progress of their investments. The input is portfolio data from the server, and the output is visualized information.

[0519] Step 7:

[0520] Users provide feedback through their devices and adjust their investment goals and risk tolerance as needed. This feedback is sent to the server and incorporated into the next investment strategy. The input is the user's feedback information, and the output is the adjusted investment strategy.

[0521] (Application Example 1)

[0522] 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."

[0523] For individual investors, developing and managing optimal investment strategies based on their own investment goals and risk tolerance, and then automatically executing specific fund allocation adjustments, is difficult for the average user who lacks investment expertise and time. Furthermore, in dynamic market environments, rapid changes in investment strategies and reallocation of funds are necessary, but doing this manually is inefficient.

[0524] 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.

[0525] In this invention, the server includes means for acquiring investment targets and risk tolerance based on user input; means for collecting market information and new information from external data sources; means for generating an investment strategy by analyzing the market information and new information; means for automatically executing trading activities according to the generated investment strategy; means for modifying the investment strategy as necessary and notifying the user of the changes; means for visually displaying the investment strategy and asset management results to the user; and means for automatically adjusting the allocation of funds based on the user's investment strategy. This enables the user to efficiently and quickly manage assets in response to market fluctuations.

[0526] "User input" refers to information that users provide to the system regarding their investment goals and risk tolerance.

[0527] An "external data source" refers to an external information source that is accessed to provide market information or new information.

[0528] "Gathering market information and new information" refers to the process of acquiring necessary data from external data sources and making it available within the system.

[0529] "Investment strategy generation" refers to constructing an investment policy that is suitable for the user's goals and risk level, based on the collected information.

[0530] "Automated execution of trading activities" refers to the automatic execution of stock and asset transactions in the market according to a generated investment strategy.

[0531] A "notification of changes to investment strategy" refers to modifying an investment strategy based on market changes or user feedback and communicating those changes to the user.

[0532] "Visual presentation" refers to providing users with an easy-to-understand presentation of investment strategies and asset management results using graphs, dashboards, and other visual aids.

[0533] "Automatic execution of fund allocation adjustments" refers to the process of optimizing fund allocation based on the user's investment strategy and automatically moving funds.

[0534] The system for realizing this invention is built on interaction between three parties: a server, a terminal, and a user.

[0535] The server connects to external data sources to collect market and new information. This includes obtaining real-time data from brokerage firms and market data providers via APIs. The collected data is preprocessed using Python and major libraries (NumPy, Pandas) and analyzed using a generative AI model. Based on the analysis results, an investment strategy optimized for the user's investment goals and risk tolerance is generated, and trading activities in the market are automatically executed. Furthermore, the strategy is updated as needed in response to changes in the investment strategy or new information, and the user is notified accordingly. For example, when growth in the agricultural sector is predicted, an investment strategy for related stocks is formulated.

[0536] The terminal serves as the direct interface with the user. Here, the user can input their investment goals and risk tolerance, and this information is immediately transmitted to the server. Furthermore, the terminal visually displays the received investment strategies and asset management results, presenting them in an easy-to-understand manner for the user. This includes visual displays using graphs and dashboards.

[0537] Users can reflect their intentions in the system by providing feedback on their investment goals and risk tolerance entered through their terminal. This feedback is analyzed on the server and incorporated into the investment strategy as needed. For example, if a user changes their intention towards accepting higher risk, the new investment strategy will be adjusted based on that feedback.

[0538] An example of a specific prompt for the generated AI model is, "Considering current market trends in the agricultural sector, please design the optimal investment strategy for my portfolio." By using such prompts, users can manage their assets in line with market trends while receiving advice from the system.

[0539] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0540] Step 1:

[0541] The server accesses external data sources and collects market and new information via APIs. The collected data is imported into the server as raw data. The input data is real-time data from the API, and the output data is pre-processed. The server uses Python and NumPy to impute missing values ​​and standardize the raw data.

[0542] Step 2:

[0543] The server inputs pre-processed data into the generated AI model and begins the analysis. The AI ​​model performs complex analyses to predict investment market trends and generates an initial investment strategy. The input is pre-processed market data, and the output is an investment strategy tailored to the user's investment goals and risk tolerance. Here, the AI ​​applies an algorithm to predict market trends and calculate investment priorities.

[0544] Step 3:

[0545] The server executes buy and sell orders in the market via an automated trading function based on the generated investment strategy. The target assets are optimized according to the investment strategy. The input is the investment strategy output by the generating AI model, and the output is the actual trade order. The trade is linked to the brokerage firm's API, and funds are transferred to the specified portfolio.

[0546] Step 4:

[0547] The terminal retrieves the user's investment goals and risk tolerance and sends this information to the server. The input is the investment goals and risk tolerance set by the user on the terminal, and the output is feedback data to the server. The terminal allows users to intuitively configure these settings via a user interface.

[0548] Step 5:

[0549] The server re-analyzes the investment strategy as needed based on user feedback and generates a new strategy. The input is user feedback information, and the output is the adjusted investment strategy. At this stage, the server performs a re-evaluation process of the generated AI model and formulates a strategy that reflects the user's new intentions.

[0550] Step 6:

[0551] The terminal visually displays and provides the user with the latest investment strategies and portfolio performance received from the server. The input is investment strategy information sent from the server, and the output is the user-viewed interface for the investment status. The terminal uses graphs and charts to visualize the information in an intuitive and easy-to-understand manner.

[0552] 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.

[0553] This invention enhances the user experience and further personalizes investment decisions by incorporating an emotion engine that recognizes user emotions into an investment support system for individual investors. This system detects the user's emotional state in real time and uses that data to adjust investment strategies and re-evaluate risk tolerance.

[0554] Server operation

[0555] The server processes and analyzes investment-related data. Its basic functions include collecting market and new information from external data sources and designing investment strategies using generative AI models. In addition, the server receives data from the emotion engine and analyzes the user's emotional state. This emotional data is used to adjust investment strategies and set risk tolerance levels. For example, if the emotion engine detects user stress, it can suggest a conservative investment strategy with reduced risk.

[0556] How the emotion engine works

[0557] The emotion engine is installed on the device and recognizes emotions by analyzing the user's facial expressions and voice. The engine updates the user's emotional state in real time and sends that data to the server. For example, it may analyze the tone and tempo of the user's voice input to identify positive or negative emotions.

[0558] Terminal operation

[0559] The device provides users with feedback on their emotional state. It not only presents users with an interface for setting investment goals and risk tolerance, but also visually displays the results of emotional analysis by an emotion engine. The device also provides a screen for users to review and agree to changes in their emotionally-based investment strategy.

[0560] User actions

[0561] Users input investment information via their devices and receive real-time sentiment analysis results. For example, if the sentiment engine analysis indicates that the user is "highly stressed by a sharp market decline," the user can adopt the suggested risk-averse strategy. This system allows users to make flexible investment decisions that align with their own emotional state.

[0562] The following describes the processing flow.

[0563] Step 1:

[0564] The server regularly collects market information and new data through APIs from securities firms and market information providers. This allows it to obtain the latest financial data and prepare for subsequent analysis.

[0565] Step 2:

[0566] The server preprocesses the collected data and designs investment strategies using a generative AI model. Data integrity is ensured during preprocessing, after which the predictive model begins its analysis.

[0567] Step 3:

[0568] The server receives emotion engine data transmitted in real time from the terminal and analyzes the user's emotional state. This information is essential for adjusting investment strategies.

[0569] Step 4:

[0570] The emotion engine analyzes the user's facial expressions and voice to recognize their emotions. This data is transmitted to the server via the device. For example, the emotion engine can use the camera to determine the user's facial expressions.

[0571] Step 5:

[0572] The server re-evaluates the current investment strategy based on emotional data and makes adjustments as needed. For example, it might suggest a strategy to invest in lower-risk assets to users with unstable emotions.

[0573] Step 6:

[0574] The terminal displays updated investment strategies and sentiment analysis results from the server to the user. Visual dashboards and alerts are used to make it easy for the user to understand.

[0575] Step 7:

[0576] Users review the presented information and provide feedback via their device if necessary. For example, they can agree to or reject proposed changes to the strategy.

[0577] Step 8:

[0578] User feedback is sent to the server and used to design future strategies. This enables flexible portfolio management that reflects user opinions.

[0579] (Example 2)

[0580] 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."

[0581] Traditional investment support systems failed to reflect users' emotional factors in investment strategies, making it difficult to respond flexibly to individual stress levels and risk tolerances. This sometimes resulted in users being unable to make optimal investment decisions. In particular, there was a need to consider users' psychological reactions to market fluctuations and rapid changes in information.

[0582] 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.

[0583] In this invention, the server includes means for detecting the user's emotional state in real time and transmitting emotional data to the server, means for generating an investment strategy using a generative AI model, and means for adjusting the investment strategy and re-evaluating risk tolerance using the emotional data. This makes it possible to provide a flexible investment strategy based on the user's real-time emotional state.

[0584] "User emotional state" refers to information that represents the user's psychological and emotional responses in real time, and is data obtained from facial expressions, tone of voice, speaking speed, etc.

[0585] A "generative AI model" is a collection of algorithms that analyze data and generate results tailored to a specific purpose, and is based on machine learning and artificial intelligence technologies.

[0586] "Market information" refers to information about factors that may influence the market, such as price trends, trading volume, and economic news in financial markets.

[0587] "Risk tolerance" is a measure that indicates the range of risk a user is willing to accept when making an investment, and it is one of the important criteria in selecting an investment strategy.

[0588] An "investment strategy" is a plan or method set out to achieve investment objectives, and includes the selection of financial products and the construction of a portfolio.

[0589] An "emotion engine" is a system or program that analyzes a user's emotions and acquires and utilizes that data in real time.

[0590] In embodiments of the present invention, a user, a terminal, and a server collaborate to provide an advanced investment support system that takes the user's emotional state into account. The terminal first interacts with the user and extracts emotional data in real time from the user's facial expressions and voice through an emotion engine. This process utilizes a camera and microphone to collect the user's facial expressions and voice. The emotion engine analyzes the data in real time and identifies positive or negative emotional states. For example, if the user is feeling anxious about market trends, this emotional data is immediately transmitted to the server.

[0591] The server collects market information and news from external data sources. The collected data is analyzed using a generative AI model. The generative AI model uses natural language processing and machine learning to generate an optimal investment strategy based on the user's emotional state. Using the previous example, if the server detects that the user is in a high-stress state, it generates a "risk-reduced, conservative investment strategy" and sends it to the terminal.

[0592] The device visually displays the received investment strategy to the user. The interface is designed to allow the user to intuitively understand the proposed investment strategy, with key elements of the strategy color-coded. Furthermore, the user can review the proposed strategy and make adjustments as needed.

[0593] As a concrete example, when using a prompt, information is provided to the generating AI model in the form of, "Please suggest an investment strategy. The user is currently stressed by the market situation. A conservative approach using emotion engine data is needed." In this way, the system supports investment decisions that reflect the user's psychological tendencies.

[0594] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0595] Step 1:

[0596] The server collects market information and news from external data sources. Input consists of financial data and the latest news obtained via an API. Data processing involves storing the data in an analytical database and formatting it for use in subsequent analysis steps. Specifically, a program runs at regular intervals to call the API and retrieve the necessary information.

[0597] Step 2:

[0598] The device captures the user's facial expressions and voice in real time. Input consists of the user's facial expressions and voice data acquired from the camera and microphone. An emotion engine analyzes this data to extract the user's emotional state (e.g., positive, negative). Output is the user's emotional state data. The specific operation involves an emotion estimation process using image processing algorithms and voice analysis algorithms.

[0599] Step 3:

[0600] The server uses a generative AI model to integrate market information collected in Step 1 with emotional state data obtained in Step 2. The inputs are market information and emotional data. As a data calculation, the AI ​​model uses this information to generate an investment strategy suitable for the user. The output is the proposed investment strategy. Specific operations include a process that outputs a risk-reducing strategy when the emotional state is "high stress."

[0601] Step 4:

[0602] The terminal presents the user with investment strategies received from the server. The input is the data for the proposed investment strategies. Color coding and icons are used to visually represent the strategies to the user in an easily understandable way. The output is a screen display that the user can easily understand and use. Specifically, an interface is in operation that highlights different aspects of the strategy.

[0603] Step 5:

[0604] The user reviews the presented investment strategy and agrees to or adjusts it. The input is the investment strategy information displayed on the screen. The user adjusts the proposed strategy as needed and makes a final decision. The output is the investment policy adjusted by the user. Specific actions include using an input interface for adjustments and sending the changes to the server.

[0605] (Application Example 2)

[0606] 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."

[0607] In modern investment activities, decisions based on individual emotions can significantly influence the outcome. However, traditional systems have struggled to personalize investment decisions while considering the user's emotional state. Therefore, there is a need to provide risk management and investment strategies tailored to each user.

[0608] 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.

[0609] In this invention, the server includes means for recognizing the user's emotional state and adjusting the plan based on that emotional state, means for collecting market data and new information from external sources, and means for analyzing the market data and new information to generate a plan. This makes it possible to propose appropriate risk management and investment strategies that are in line with the user's emotions.

[0610] A "user" refers to an individual or organization that engages in investment activities within the system.

[0611] "Input" refers to the information or instructions that a user provides to the system.

[0612] "Purpose" refers to the individual investment goals or intentions that the user hopes to achieve.

[0613] "Risk tolerance" is an indicator that shows the degree of risk an individual user can tolerate in their investments.

[0614] "External information sources" refer to information providers or media from which market data and related new information are collected.

[0615] "Market data" refers to detailed information about prices, trends, indices, and other factors in financial markets.

[0616] "New information" refers to the latest information based on market fluctuations and socioeconomic factors.

[0617] A "plan" refers to the strategies and policies generated to guide the user's investment activities.

[0618] "Trading activity" refers to the buying and selling of financial products conducted according to a plan.

[0619] "Emotional state" refers to a temporary psychological state recognized through analysis of the user's facial expressions and voice.

[0620] A "server" refers to a computer device that collects, processes, and analyzes data, and manages the entire system.

[0621] This invention incorporates an emotion engine into an investment support system for individual investors, enabling real-time detection of the user's emotional state and personalized investment decisions. The system consists of a server, a terminal, and user operation.

[0622] The server is a computing device that collects market data and new information from external sources, analyzes this data, and generates investment plans. This plan generation utilizes a generative AI model. The server receives data from an emotion engine that recognizes the user's emotional state and adjusts the plan accordingly. For example, if the emotion engine detects the user's stress level, the server can generate a conservative investment plan with reduced risk.

[0623] The terminal is a device for users to interact with the system and plays a role in understanding the user's emotional state in real time. The terminal is equipped with a camera and microphone, which are used to analyze the user's facial expressions and voice tone. Facial expressions are analyzed using facial recognition technology with OpenCV, and emotional states are detected through voice analysis using the Google Cloud Speech-to-Text API. The results are visually fed back to the user, and a screen is displayed to confirm and consent to changes in the investment plan based on their emotions.

[0624] Users input investment instructions through their devices and select risk management and investment strategies based on sentiment analysis feedback. For example, if a user receives a sentiment analysis result indicating they are "highly stressed by a market crash," they can adopt the suggested risk avoidance plan. This allows users to make flexible investment decisions that align with their own emotional state.

[0625] As a concrete example, if a user becomes confused due to sudden market fluctuations after making an investment decision, an emotion engine could be used to detect that stress, and the server could automatically generate and present a conservative plan based on that.

[0626] Example prompt: "Design an AI application that analyzes the user's facial expressions and voice tone, and advises on how to assist them in their daily life based on the emotion estimation results."

[0627] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0628] Step 1:

[0629] The terminal receives investment-related input from the user and retrieves registered investment goals and risk tolerance levels. Based on the entered information, it queries the database for the user's risk profile and retrieves that data.

[0630] Step 2:

[0631] The device collects facial image and audio data from the user using its camera and microphone. This raw data is then used as input to initiate face recognition and speech analysis. OpenCV is used to extract facial features, and the Google Cloud Speech-to-Text API is used to analyze tone and tempo from the audio. The resulting emotion data is then generated and sent to the server.

[0632] Step 3:

[0633] The server analyzes emotional data received from the terminal to identify the user's emotional state. Using the emotional state as input, a generative AI model is used to create an appropriate investment plan tailored to the current market conditions. New market data and information are acquired from external sources and incorporated into the plan.

[0634] Step 4:

[0635] The server adjusts the newly generated investment plan and its risk level to match the user's emotional state. After adjusting the plan, it sends it to the terminal and notifies the user. As a result, the plan's risk settings take into account the user's stress level.

[0636] Step 5:

[0637] The device visually displays the details of the adjusted investment plan to the user and provides a screen requesting confirmation and acceptance of the plan. Once the user reviews the plan and presses the accept button, the plan becomes actionable.

[0638] Step 6:

[0639] If the user accepts the plan, the server will execute automated trading based on that plan. The terminal will provide real-time feedback on the results of the executed trades and display the trading results to the user.

[0640] 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.

[0641] 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.

[0642] 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.

[0643] [Fourth Embodiment]

[0644] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0645] 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.

[0646] 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).

[0647] 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.

[0648] 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.

[0649] 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).

[0650] 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.

[0651] 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.

[0652] 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.

[0653] 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.

[0654] 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.

[0655] 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.

[0656] 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".

[0657] This invention relates to a system for providing advanced asset management support to individual investors. The system utilizes a generative AI model to automatically formulate and manage investment strategies that take into account the user's investment goals and risk tolerance. The program processing of this system is described below in natural language.

[0658] Server operation

[0659] The server provides core data processing capabilities. Initially, it collects market and new information from external data sources via APIs from securities firms and market information providers. The acquired data is preprocessed and then analyzed by a generative AI model. The AI ​​model predicts investment market trends and designs optimal investment strategies tailored to the user's goals and risk tolerance. After the strategy is formulated, the server automatically executes trading activities in the market. Furthermore, the server monitors portfolio performance and performs rebalancing as needed.

[0660] As a concrete example, when formulating an investment strategy for growth stocks, the AI ​​model analyzes recent financial reports and news articles of companies to identify sectors that it deems to have high growth potential. Based on this, the server sends buy / sell instructions to the brokerage firm to invest in those specific stocks.

[0661] Terminal operation

[0662] The terminal handles user interaction. Users set investment goals and risk tolerance from the terminal, and this information is sent to the server. The latest investment strategy and portfolio information received from the server is visualized and displayed to the user in an easy-to-understand format. The terminal provides the user with information on the progress of asset management and adjustments to the strategy using graphs and dashboards.

[0663] User actions

[0664] Users set investment goals and input their risk tolerance into the system via their terminal. They then check the performance of their displayed portfolio and provide feedback as needed. This feedback is used to adjust strategies on the server. For example, if a user determines they can tolerate higher risk, a new strategy is redesigned and implemented to align with their preferences.

[0665] This enables users to efficiently and individually manage their assets according to their own goals, and to make socially meaningful investments that take ESG scores into consideration.

[0666] The following describes the processing flow.

[0667] Step 1:

[0668] The server collects market information and new information from external data sources. It retrieves data from stock exchanges and financial news providers via APIs and organizes it chronologically.

[0669] Step 2:

[0670] The server preprocesses the acquired data. It fills in missing data and handles outliers to format the data into a format suitable for analysis.

[0671] Step 3:

[0672] The server analyzes pre-processed data using a generative AI model. It predicts market trends, assesses risks, and generates the optimal investment strategy for the user.

[0673] Step 4:

[0674] The server automatically sends buy and sell orders to brokerage firms based on the generated investment strategy. Buy and sell orders are issued via API.

[0675] Step 5:

[0676] The server monitors portfolio performance in real time. If a pre-configured risk threshold is exceeded, the portfolio is rebalanced.

[0677] Step 6:

[0678] The terminal provides an interface to the user. It displays a screen to the user where they can input their investment goals and risk tolerance.

[0679] Step 7:

[0680] The terminal receives investment strategy and performance information sent from the server. This information is then visually displayed to the user in the form of diagrams and dashboards.

[0681] Step 8:

[0682] Users input their goals and risk tolerance levels via their device. Once input is complete, the information is sent to the server and incorporated into the strategy design.

[0683] Step 9:

[0684] Users can review investment status and strategy details and provide feedback through their devices. The server receives this feedback and uses it to adjust future strategies.

[0685] (Example 1)

[0686] 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".

[0687] Modern individual investors are required to manage their assets efficiently and customized based on market and trend information gathered from a wide range of sources. However, there is currently a lack of systems that provide sophisticated investment strategies that can be easily used by users who do not require specialized investment knowledge. In this situation, there is a need to provide a system that automatically generates optimal investment strategies based on the user's investment goals and risk tolerance, and manages assets efficiently and individually.

[0688] 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.

[0689] In this invention, the server includes means for obtaining investment targets and risk tolerance based on user input; means for collecting market information and trend information from external information sources; means for analyzing the market information and trend information and generating an investment strategy using prompt statements in a generating AI model; means for automatically executing trading activities based on the generated investment strategy; means for modifying the investment strategy as necessary and notifying the user of the changes; means for visually displaying the investment strategy and asset management results to the user; means for receiving user feedback and adjusting the investment strategy based on that feedback; and means for monitoring the portfolio with an information processing device and adjusting asset allocation as necessary. This makes it possible for users to manage their assets efficiently and on an individual basis without requiring specialized knowledge.

[0690] A "user" refers to an individual or legal entity that uses this system to conduct investment activities through automated asset management.

[0691] "External information sources" refer to external data sources that provide market information and trend information, such as securities companies and market information providers.

[0692] "Market information" refers to information related to investment activities, such as stock prices, corporate financial information, and economic indicators.

[0693] "Trend information" refers to information that may affect the market, such as economic fluctuations, corporate news, and political events.

[0694] A "generative AI model" refers to an artificial intelligence model that analyzes the aforementioned market information and trend information to generate investment strategies.

[0695] A "prompt statement" refers to an instruction statement used to generate a specific investment strategy for a generative AI model.

[0696] An "investment strategy" refers to a plan for asset management generated based on the user's investment goals and risk tolerance.

[0697] The term "automatic execution" refers to a process in which a system carries out buying and selling activities in the market without human intervention.

[0698] "Visual display" refers to presenting investment strategies and asset management results to users in an easy-to-understand format using graphs and dashboards.

[0699] "Feedback" refers to the opinions and requests provided by users, and the input information used by the system to adjust its investment strategy based on this feedback.

[0700] "Information processing equipment" refers to devices, including digital computers, used for acquiring, analyzing, storing, and displaying information.

[0701] A "portfolio" refers to a combination of multiple financial products held by a user, and the asset allocation of that portfolio is managed.

[0702] This invention relates to a system that provides automated asset management for individual investors. Specific embodiments are described below.

[0703] Server operation

[0704] The server functions as the core of the entire system and is responsible for several key processes. First, the server retrieves market and trend information from external sources. Specifically, it uses APIs from securities companies and market information providers to automatically retrieve stock price information, financial reports, economic indicators, and market news, and stores this data in a database.

[0705] Next, the server preprocesses the collected data. Preprocessing includes removing outliers, standardizing data formats, and supplementing missing data. The processed data is then input into a generative AI model, which performs analysis based on prompt messages. The server uses the generative AI model to design an optimal investment strategy tailored to the user's investment goals and risk tolerance. An example of a prompt message used in this process is, "Design an optimal tech stock investment strategy for a user with high risk tolerance."

[0706] The server generates buy and sell orders based on the designed investment strategy and places them on the market via the brokerage firm's API. The server also monitors the portfolio performance in real time and adjusts asset allocation as needed.

[0707] Terminal operation

[0708] The terminal functions as an interface with the user. The user uses the terminal to set investment goals and risk tolerance and send them to the server. The terminal visually displays the latest investment strategies and portfolio updates returned from the server. The terminal includes graphs and dashboards, allowing the user to intuitively understand the progress of their asset management.

[0709] User actions

[0710] Users can provide investment feedback through their devices. For example, users can reset their risk tolerance, and this information is used to readjust strategies on the server. This allows users to manage their assets in a way that reflects their own intentions.

[0711] In this way, the server, terminals, and users cooperate with each other to achieve efficient and personalized asset management. This system allows users to manage their assets with peace of mind without requiring advanced expertise.

[0712] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0713] Step 1:

[0714] The server collects market and trend information from external sources. Specifically, it retrieves stock prices, corporate financial data, economic indicators, and news articles through APIs from securities companies and market information providers. The input is API access information, and the output is market and trend information stored in the database.

[0715] Step 2:

[0716] The server preprocesses the acquired market and trend information. It cleans the data, removes outliers, and standardizes the data format. It also supplements missing data with historical information and estimates. The input is raw data, and the output is well-formed data that has been cleaned and processed.

[0717] Step 3:

[0718] The server inputs well-formed data into a generating AI model for analysis. During this process, it uses prompt statements to generate an investment strategy. In this process, the input consists of well-formed data and prompt statements, while the output is an optimal investment strategy that takes into account the user's investment goals and risk tolerance.

[0719] Step 4:

[0720] The server executes automated trades based on the generated investment strategy. Specifically, it generates buy and sell instructions and sends them to the market via the brokerage firm's API. This results in the execution of trades in financial instruments in accordance with the specified investment strategy. The input is the investment strategy, and the output is a record of the executed trades.

[0721] Step 5:

[0722] The server monitors portfolio performance in real time. Necessary adjustments are made in response to market fluctuations, and rebalancing is performed to optimize asset allocation. Inputs are market information and the portfolio's current asset allocation, while output is the adjusted asset allocation.

[0723] Step 6:

[0724] The terminal visually displays the latest information on investment strategies and portfolios to the user. Specifically, it provides information through graphs and dashboards, making it easier for users to understand the progress of their investments. The input is portfolio data from the server, and the output is visualized information.

[0725] Step 7:

[0726] Users provide feedback through their devices and adjust their investment goals and risk tolerance as needed. This feedback is sent to the server and incorporated into the next investment strategy. The input is the user's feedback information, and the output is the adjusted investment strategy.

[0727] (Application Example 1)

[0728] 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".

[0729] For individual investors, developing and managing optimal investment strategies based on their own investment goals and risk tolerance, and then automatically executing specific fund allocation adjustments, is difficult for the average user who lacks investment expertise and time. Furthermore, in dynamic market environments, rapid changes in investment strategies and reallocation of funds are necessary, but doing this manually is inefficient.

[0730] 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.

[0731] In this invention, the server includes means for acquiring investment targets and risk tolerance based on user input; means for collecting market information and new information from external data sources; means for generating an investment strategy by analyzing the market information and new information; means for automatically executing trading activities according to the generated investment strategy; means for modifying the investment strategy as necessary and notifying the user of the changes; means for visually displaying the investment strategy and asset management results to the user; and means for automatically adjusting the allocation of funds based on the user's investment strategy. This enables the user to efficiently and quickly manage assets in response to market fluctuations.

[0732] "User input" refers to information that users provide to the system regarding their investment goals and risk tolerance.

[0733] An "external data source" refers to an external information source that is accessed to provide market information or new information.

[0734] "Gathering market information and new information" refers to the process of acquiring necessary data from external data sources and making it available within the system.

[0735] "Investment strategy generation" refers to constructing an investment policy that is suitable for the user's goals and risk level, based on the collected information.

[0736] "Automated execution of trading activities" refers to the automatic execution of stock and asset transactions in the market according to a generated investment strategy.

[0737] A "notification of changes to investment strategy" refers to modifying an investment strategy based on market changes or user feedback and communicating those changes to the user.

[0738] "Visual presentation" refers to providing users with an easy-to-understand presentation of investment strategies and asset management results using graphs, dashboards, and other visual aids.

[0739] "Automatic execution of fund allocation adjustments" refers to the process of optimizing fund allocation based on the user's investment strategy and automatically moving funds.

[0740] The system for realizing this invention is built on interaction between three parties: a server, a terminal, and a user.

[0741] The server connects to external data sources to collect market and new information. This includes obtaining real-time data from brokerage firms and market data providers via APIs. The collected data is preprocessed using Python and major libraries (NumPy, Pandas) and analyzed using a generative AI model. Based on the analysis results, an investment strategy optimized for the user's investment goals and risk tolerance is generated, and trading activities in the market are automatically executed. Furthermore, the strategy is updated as needed in response to changes in the investment strategy or new information, and the user is notified accordingly. For example, when growth in the agricultural sector is predicted, an investment strategy for related stocks is formulated.

[0742] The terminal serves as the direct interface with the user. Here, the user can input their investment goals and risk tolerance, and this information is immediately transmitted to the server. Furthermore, the terminal visually displays the received investment strategies and asset management results, presenting them in an easy-to-understand manner for the user. This includes visual displays using graphs and dashboards.

[0743] Users can reflect their intentions in the system by providing feedback on their investment goals and risk tolerance entered through their terminal. This feedback is analyzed on the server and incorporated into the investment strategy as needed. For example, if a user changes their intention towards accepting higher risk, the new investment strategy will be adjusted based on that feedback.

[0744] An example of a specific prompt for the generated AI model is, "Considering current market trends in the agricultural sector, please design the optimal investment strategy for my portfolio." By using such prompts, users can manage their assets in line with market trends while receiving advice from the system.

[0745] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0746] Step 1:

[0747] The server accesses external data sources and collects market and new information via APIs. The collected data is imported into the server as raw data. The input data is real-time data from the API, and the output data is pre-processed. The server uses Python and NumPy to impute missing values ​​and standardize the raw data.

[0748] Step 2:

[0749] The server inputs pre-processed data into the generated AI model and begins the analysis. The AI ​​model performs complex analyses to predict investment market trends and generates an initial investment strategy. The input is pre-processed market data, and the output is an investment strategy tailored to the user's investment goals and risk tolerance. Here, the AI ​​applies an algorithm to predict market trends and calculate investment priorities.

[0750] Step 3:

[0751] The server executes buy and sell orders in the market via an automated trading function based on the generated investment strategy. The target assets are optimized according to the investment strategy. The input is the investment strategy output by the generating AI model, and the output is the actual trade order. The trade is linked to the brokerage firm's API, and funds are transferred to the specified portfolio.

[0752] Step 4:

[0753] The terminal retrieves the user's investment goals and risk tolerance and sends this information to the server. The input is the investment goals and risk tolerance set by the user on the terminal, and the output is feedback data to the server. The terminal allows users to intuitively configure these settings via a user interface.

[0754] Step 5:

[0755] The server re-analyzes the investment strategy as needed based on user feedback and generates a new strategy. The input is user feedback information, and the output is the adjusted investment strategy. At this stage, the server performs a re-evaluation process of the generated AI model and formulates a strategy that reflects the user's new intentions.

[0756] Step 6:

[0757] The terminal visually displays and provides the user with the latest investment strategies and portfolio performance received from the server. The input is investment strategy information sent from the server, and the output is the user-viewed interface for the investment status. The terminal uses graphs and charts to visualize the information in an intuitive and easy-to-understand manner.

[0758] 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.

[0759] This invention enhances the user experience and further personalizes investment decisions by incorporating an emotion engine that recognizes user emotions into an investment support system for individual investors. This system detects the user's emotional state in real time and uses that data to adjust investment strategies and re-evaluate risk tolerance.

[0760] Server operation

[0761] The server processes and analyzes investment-related data. Its basic functions include collecting market and new information from external data sources and designing investment strategies using generative AI models. In addition, the server receives data from the emotion engine and analyzes the user's emotional state. This emotional data is used to adjust investment strategies and set risk tolerance levels. For example, if the emotion engine detects user stress, it can suggest a conservative investment strategy with reduced risk.

[0762] How the emotion engine works

[0763] The emotion engine is installed on the device and recognizes emotions by analyzing the user's facial expressions and voice. The engine updates the user's emotional state in real time and sends that data to the server. For example, it may analyze the tone and tempo of the user's voice input to identify positive or negative emotions.

[0764] Terminal operation

[0765] The device provides users with feedback on their emotional state. It not only presents users with an interface for setting investment goals and risk tolerance, but also visually displays the results of emotional analysis by an emotion engine. The device also provides a screen for users to review and agree to changes in their emotionally-based investment strategy.

[0766] User actions

[0767] Users input investment information via their devices and receive real-time sentiment analysis results. For example, if the sentiment engine analysis indicates that the user is "highly stressed by a sharp market decline," the user can adopt the suggested risk-averse strategy. This system allows users to make flexible investment decisions that align with their own emotional state.

[0768] The following describes the processing flow.

[0769] Step 1:

[0770] The server regularly collects market information and new data through APIs from securities firms and market information providers. This allows it to obtain the latest financial data and prepare for subsequent analysis.

[0771] Step 2:

[0772] The server preprocesses the collected data and designs investment strategies using a generative AI model. Data integrity is ensured during preprocessing, after which the predictive model begins its analysis.

[0773] Step 3:

[0774] The server receives emotion engine data transmitted in real time from the terminal and analyzes the user's emotional state. This information is essential for adjusting investment strategies.

[0775] Step 4:

[0776] The emotion engine analyzes the user's facial expressions and voice to recognize their emotions. This data is transmitted to the server via the device. For example, the emotion engine can use the camera to determine the user's facial expressions.

[0777] Step 5:

[0778] The server re-evaluates the current investment strategy based on emotional data and makes adjustments as needed. For example, it might suggest a strategy to invest in lower-risk assets to users with unstable emotions.

[0779] Step 6:

[0780] The terminal displays updated investment strategies and sentiment analysis results from the server to the user. Visual dashboards and alerts are used to make it easy for the user to understand.

[0781] Step 7:

[0782] Users review the presented information and provide feedback via their device if necessary. For example, they can agree to or reject proposed changes to the strategy.

[0783] Step 8:

[0784] User feedback is sent to the server and used to design future strategies. This enables flexible portfolio management that reflects user opinions.

[0785] (Example 2)

[0786] 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".

[0787] Traditional investment support systems failed to reflect users' emotional factors in investment strategies, making it difficult to respond flexibly to individual stress levels and risk tolerances. This sometimes resulted in users being unable to make optimal investment decisions. In particular, there was a need to consider users' psychological reactions to market fluctuations and rapid changes in information.

[0788] 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.

[0789] In this invention, the server includes means for detecting the user's emotional state in real time and transmitting emotional data to the server, means for generating an investment strategy using a generative AI model, and means for adjusting the investment strategy and re-evaluating risk tolerance using the emotional data. This makes it possible to provide a flexible investment strategy based on the user's real-time emotional state.

[0790] "User emotional state" refers to information that represents the user's psychological and emotional responses in real time, and is data obtained from facial expressions, tone of voice, speaking speed, etc.

[0791] A "generative AI model" is a collection of algorithms that analyze data and generate results tailored to a specific purpose, and is based on machine learning and artificial intelligence technologies.

[0792] "Market information" refers to information about factors that may influence the market, such as price trends, trading volume, and economic news in financial markets.

[0793] "Risk tolerance" is a measure that indicates the range of risk a user is willing to accept when making an investment, and it is one of the important criteria in selecting an investment strategy.

[0794] An "investment strategy" is a plan or method set out to achieve investment objectives, and includes the selection of financial products and the construction of a portfolio.

[0795] An "emotion engine" is a system or program that analyzes a user's emotions and acquires and utilizes that data in real time.

[0796] In embodiments of the present invention, a user, a terminal, and a server collaborate to provide an advanced investment support system that takes the user's emotional state into account. The terminal first interacts with the user and extracts emotional data in real time from the user's facial expressions and voice through an emotion engine. This process utilizes a camera and microphone to collect the user's facial expressions and voice. The emotion engine analyzes the data in real time and identifies positive or negative emotional states. For example, if the user is feeling anxious about market trends, this emotional data is immediately transmitted to the server.

[0797] The server collects market information and news from external data sources. The collected data is analyzed using a generative AI model. The generative AI model uses natural language processing and machine learning to generate an optimal investment strategy based on the user's emotional state. Using the previous example, if the server detects that the user is in a high-stress state, it generates a "risk-reduced, conservative investment strategy" and sends it to the terminal.

[0798] The device visually displays the received investment strategy to the user. The interface is designed to allow the user to intuitively understand the proposed investment strategy, with key elements of the strategy color-coded. Furthermore, the user can review the proposed strategy and make adjustments as needed.

[0799] As a concrete example, when using a prompt, information is provided to the generating AI model in the form of, "Please suggest an investment strategy. The user is currently stressed by the market situation. A conservative approach using emotion engine data is needed." In this way, the system supports investment decisions that reflect the user's psychological tendencies.

[0800] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0801] Step 1:

[0802] The server collects market information and news from external data sources. Input consists of financial data and the latest news obtained via an API. Data processing involves storing the data in an analytical database and formatting it for use in subsequent analysis steps. Specifically, a program runs at regular intervals to call the API and retrieve the necessary information.

[0803] Step 2:

[0804] The device captures the user's facial expressions and voice in real time. Input consists of the user's facial expressions and voice data acquired from the camera and microphone. An emotion engine analyzes this data to extract the user's emotional state (e.g., positive, negative). Output is the user's emotional state data. The specific operation involves an emotion estimation process using image processing algorithms and voice analysis algorithms.

[0805] Step 3:

[0806] The server uses a generative AI model to integrate market information collected in Step 1 with emotional state data obtained in Step 2. The inputs are market information and emotional data. As a data calculation, the AI ​​model uses this information to generate an investment strategy suitable for the user. The output is the proposed investment strategy. Specific operations include a process that outputs a risk-reducing strategy when the emotional state is "high stress."

[0807] Step 4:

[0808] The terminal presents the user with investment strategies received from the server. The input is the data for the proposed investment strategies. Color coding and icons are used to visually represent the strategies to the user in an easily understandable way. The output is a screen display that the user can easily understand and use. Specifically, an interface is in operation that highlights different aspects of the strategy.

[0809] Step 5:

[0810] The user reviews the presented investment strategy and agrees to or adjusts it. The input is the investment strategy information displayed on the screen. The user adjusts the proposed strategy as needed and makes a final decision. The output is the investment policy adjusted by the user. Specific actions include using an input interface for adjustments and sending the changes to the server.

[0811] (Application Example 2)

[0812] 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".

[0813] In modern investment activities, decisions based on individual emotions can significantly influence the outcome. However, traditional systems have struggled to personalize investment decisions while considering the user's emotional state. Therefore, there is a need to provide risk management and investment strategies tailored to each user.

[0814] 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.

[0815] In this invention, the server includes means for recognizing the user's emotional state and adjusting the plan based on that emotional state, means for collecting market data and new information from external sources, and means for analyzing the market data and new information to generate a plan. This makes it possible to propose appropriate risk management and investment strategies that are in line with the user's emotions.

[0816] A "user" refers to an individual or organization that engages in investment activities within the system.

[0817] "Input" refers to the information or instructions that a user provides to the system.

[0818] "Purpose" refers to the individual investment goals or intentions that the user hopes to achieve.

[0819] "Risk tolerance" is an indicator that shows the degree of risk an individual user can tolerate in their investments.

[0820] "External information sources" refer to information providers or media from which market data and related new information are collected.

[0821] "Market data" refers to detailed information about prices, trends, indices, and other factors in financial markets.

[0822] "New information" refers to the latest information based on market fluctuations and socioeconomic factors.

[0823] A "plan" refers to the strategies and policies generated to guide the user's investment activities.

[0824] "Trading activity" refers to the buying and selling of financial products conducted according to a plan.

[0825] "Emotional state" refers to a temporary psychological state recognized through analysis of the user's facial expressions and voice.

[0826] A "server" refers to a computer device that collects, processes, and analyzes data, and manages the entire system.

[0827] This invention incorporates an emotion engine into an investment support system for individual investors, enabling real-time detection of the user's emotional state and personalized investment decisions. The system consists of a server, a terminal, and user operation.

[0828] The server is a computing device that collects market data and new information from external sources, analyzes this data, and generates investment plans. This plan generation utilizes a generative AI model. The server receives data from an emotion engine that recognizes the user's emotional state and adjusts the plan accordingly. For example, if the emotion engine detects the user's stress level, the server can generate a conservative investment plan with reduced risk.

[0829] The terminal is a device for users to interact with the system and plays a role in understanding the user's emotional state in real time. The terminal is equipped with a camera and microphone, which are used to analyze the user's facial expressions and voice tone. Facial expressions are analyzed using facial recognition technology with OpenCV, and emotional states are detected through voice analysis using the Google Cloud Speech-to-Text API. The results are visually fed back to the user, and a screen is displayed to confirm and consent to changes in the investment plan based on their emotions.

[0830] Users input investment instructions through their devices and select risk management and investment strategies based on sentiment analysis feedback. For example, if a user receives a sentiment analysis result indicating they are "highly stressed by a market crash," they can adopt the suggested risk avoidance plan. This allows users to make flexible investment decisions that align with their own emotional state.

[0831] As a concrete example, if a user becomes confused due to sudden market fluctuations after making an investment decision, an emotion engine could be used to detect that stress, and the server could automatically generate and present a conservative plan based on that.

[0832] Example prompt: "Design an AI application that analyzes the user's facial expressions and voice tone, and advises on how to assist them in their daily life based on the emotion estimation results."

[0833] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0834] Step 1:

[0835] The terminal receives investment-related input from the user and retrieves registered investment goals and risk tolerance levels. Based on the entered information, it queries the database for the user's risk profile and retrieves that data.

[0836] Step 2:

[0837] The device collects facial image and audio data from the user using its camera and microphone. This raw data is then used as input to initiate face recognition and speech analysis. OpenCV is used to extract facial features, and the Google Cloud Speech-to-Text API is used to analyze tone and tempo from the audio. The resulting emotion data is then generated and sent to the server.

[0838] Step 3:

[0839] The server analyzes emotional data received from the terminal to identify the user's emotional state. Using the emotional state as input, a generative AI model is used to create an appropriate investment plan tailored to the current market conditions. New market data and information are acquired from external sources and incorporated into the plan.

[0840] Step 4:

[0841] The server adjusts the newly generated investment plan and its risk level to match the user's emotional state. After adjusting the plan, it sends it to the terminal and notifies the user. As a result, the plan's risk settings take into account the user's stress level.

[0842] Step 5:

[0843] The device visually displays the details of the adjusted investment plan to the user and provides a screen requesting confirmation and acceptance of the plan. Once the user reviews the plan and presses the accept button, the plan becomes actionable.

[0844] Step 6:

[0845] If the user accepts the plan, the server will execute automated trading based on that plan. The terminal will provide real-time feedback on the results of the executed trades and display the trading results to the user.

[0846] 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.

[0847] 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.

[0848] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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."

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0867] The following is further disclosed regarding the embodiments described above.

[0868] (Claim 1)

[0869] A means of obtaining investment targets and risk tolerance based on user input,

[0870] Means for collecting market information and new information from external data sources,

[0871] A means for generating an investment strategy by analyzing the aforementioned market information and new information,

[0872] A means of automatically executing trading activities according to the generated investment strategy,

[0873] A means of making changes to the investment strategy as needed and notifying the user of those changes,

[0874] A means of visually displaying investment strategies and asset management results to users,

[0875] A system that includes this.

[0876] (Claim 2)

[0877] The system according to claim 1, further comprising means for considering ESG scores in the generated investment strategy.

[0878] (Claim 3)

[0879] The system according to claim 1, further comprising means for receiving user feedback and adjusting the investment strategy based thereon.

[0880] "Example 1"

[0881] (Claim 1)

[0882] A means of obtaining investment targets and risk tolerance based on user input,

[0883] Means for collecting market information and trend information from external sources,

[0884] A means for analyzing the aforementioned market information and trend information and generating an investment strategy using prompt sentences in a generating AI model,

[0885] A means of automatically executing trading activities based on the generated investment strategy,

[0886] A means of making changes to the investment strategy as needed and notifying the user of those changes,

[0887] A means of visually displaying investment strategies and asset management results to users,

[0888] A means of receiving user feedback and adjusting investment strategies based on it,

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, further comprising means for considering social indicators in the generated investment strategy.

[0892] (Claim 3)

[0893] The system according to claim 1, further comprising means for monitoring a portfolio using an information processing device and adjusting asset allocation as necessary.

[0894] "Application Example 1"

[0895] (Claim 1)

[0896] A means of obtaining investment targets and risk tolerance based on user input,

[0897] Means for collecting market information and new information from external data sources,

[0898] A means for generating an investment strategy by analyzing the aforementioned market information and new information,

[0899] A means of automatically executing trading activities according to the generated investment strategy,

[0900] A means of making changes to the investment strategy as needed and notifying the user of those changes,

[0901] A means of visually displaying investment strategies and asset management results to users,

[0902] A means to automatically perform fund allocation adjustments based on the user's investment strategy,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, further comprising means for considering ESG scores in the generated investment strategy.

[0906] (Claim 3)

[0907] The system according to claim 1, further comprising means for receiving user feedback and adjusting the investment strategy based thereon.

[0908] "Example 2 of combining an emotion engine"

[0909] (Claim 1)

[0910] A means of obtaining investment targets and risk tolerance based on user input,

[0911] Means for collecting market information and new information from external data sources,

[0912] A means for generating an investment strategy by analyzing the aforementioned market information and new information and utilizing a generated AI model,

[0913] A means for detecting the user's emotional state in real time and sending emotional data to a server,

[0914] A means for adjusting investment strategies and reassessing risk tolerance using the aforementioned sentiment data,

[0915] A means of automatically executing trading activities according to the generated investment strategy,

[0916] A means of making changes to the investment strategy as needed and notifying the user of those changes,

[0917] A means of visually displaying investment strategies and asset management results to users,

[0918] A system that includes this.

[0919] (Claim 2)

[0920] The system according to claim 1, further comprising means for considering ESG scores in the generated investment strategy.

[0921] (Claim 3)

[0922] The system according to claim 1, further comprising means for receiving user feedback and adjusting the investment strategy based thereon.

[0923] "Application example 2 when combining with an emotional engine"

[0924] (Claim 1)

[0925] A means of obtaining the purpose and risk tolerance based on user input,

[0926] Means for collecting market data and new information from external sources,

[0927] Means for generating a plan by analyzing the aforementioned market data and new information,

[0928] A means of automatically executing trading activities according to the generated plan,

[0929] A means of making changes to the plan as needed and notifying the user of those changes,

[0930] A means of visually displaying the results of the plan and asset management to the user,

[0931] A means for recognizing the user's emotional state and adjusting the plan based on that emotional state,

[0932] A system that includes this.

[0933] (Claim 2)

[0934] The system according to claim 1, further comprising means for considering environmental, social, and governance assessments in the generated plan.

[0935] (Claim 3)

[0936] The system according to claim 1, further comprising means for receiving user feedback and adjusting the plan based thereon. [Explanation of symbols]

[0937] 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. A means of obtaining investment targets and risk tolerance based on user input, Means for collecting market information and new information from external data sources, A means for generating an investment strategy by analyzing the aforementioned market information and new information, A means of automatically executing trading activities according to the generated investment strategy, A means of making changes to the investment strategy as needed and notifying the user of those changes, A means of visually displaying investment strategies and asset management results to users, A means for automatically adjusting the allocation of funds based on the user's investment strategy, A system that includes this.

2. The system according to claim 1, further comprising means for considering ESG scores in the generated investment strategy.

3. The system according to claim 1, further comprising means for receiving user feedback and adjusting the investment strategy based thereon.

Images