system

Abstract

We provide the system. [Solution] Means for collecting user attribute information, Means for constructing an investment profile based on said attribute information, A means for generating an optimal investment proposal based on the aforementioned investment profile, A means of presenting the proposal to the user and accepting the user's choice, A means of automatically executing investment transactions based on user selection, A means to track users' investment status and update analysis results, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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] Many modern individuals lack knowledge about asset management, so they have the problem of difficulty in making efficient investment decisions. In addition, it is not easy to constantly track the trends in the financial market and make investment decisions in line with market changes, and specialized knowledge and techniques are required. Against this background, there is a demand for a system that can construct an investment profile suitable for individual conditions and provide an optimal investment proposal.

Means for Solving the Problems

[0005] This invention provides a means for collecting user attribute information and constructing an investment profile based on it. This means allows for the accurate setting of the user's risk tolerance and investment goals. Furthermore, it includes a means for generating and presenting optimal investment proposals to the user based on the investment profile. Based on the user's selection, investment execution can be automated, reducing the user's effort. In addition, it supports flexible and appropriate investment reviews by tracking investment status and updating analysis results. As a result, users can effectively manage their assets even without specialized knowledge.

[0006] "User attribute information" refers to data about an individual, such as age, asset status, and investment preferences, and is used to build an investment profile.

[0007] An "investment profile" is a framework for individual investment strategies designed based on the user's risk tolerance and investment goals.

[0008] An "investment proposal" is an investment strategy or product recommendation generated by AI based on the user's investment profile and presented to the user.

[0009] "Automated execution of investment transactions" refers to the process where the system automatically executes transactions such as buying or selling based on investment proposals selected by the user.

[0010] "Tracking investment performance" refers to the act of monitoring a user's asset management results at regular intervals and updating and evaluating those results.

[0011] "Updating analysis results" refers to the data update procedure implemented by the system to review the effectiveness of current investment strategies and make new recommendations in response to the user's investment status and market fluctuations. [Brief explanation of the drawing]

[0012] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] The present invention provides an AI-driven financial advisor function to support users in managing their financial assets. To implement this system, the server, terminal, and user must cooperate with each other to achieve personalized investment management for each user, as described below.

[0034] Server Embodiment

[0035] The server first collects user attribute information, including the user's age, financial status, and investment intentions. Based on this data, the server uses an AI algorithm to build an investment profile for each user. This profile reflects the user's risk tolerance and investment goals. Next, the server generates optimal investment recommendations based on this profile. These recommendations take into account financial market data and economic indicators. Finally, the server monitors the user's investment transactions and assists in ensuring smooth transactions.

[0036] Terminal embodiment

[0037] The terminal prompts the user for input via a user interface. This interface is intuitive and easy to use, designed to quickly provide the user with all the information they need. The terminal presents investment proposals received from the server to the user, displaying the proposal details in a visually clear manner. It also accepts approval or modification requests from the user and sends them to the server as information necessary for the next processing step.

[0038] User Embodiment

[0039] Upon initial login to the system, users enter their age, asset status, investment intentions, etc., into a terminal. This allows users to confirm that detailed information about their investments is reflected in the system. Through the terminal, users can review investment proposals presented by the server and select the proposal best suited to their investment strategy. They can also periodically check the progress of their investment management and request a review of their investment strategy as needed.

[0040] Specific example

[0041] User A, a 30-year-old, currently possesses 10 million yen in assets and desires long-term investments with reduced risk. When User A inputs information into the system, the server analyzes this information and proposes an index-type mutual fund that aims for solid returns while reducing risk. User A approves the proposal, and the system automatically starts investing. Subsequently, User A can periodically check the investment performance through their terminal, allowing them to continue investing with peace of mind.

[0042] This invention provides an effective means for individual investors to improve the efficiency of their asset management and achieve better investment results by leveraging the power of AI when making complex investment decisions.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server begins collecting user attribute information. The server receives information such as age, financial status, and investment intentions entered by the user and stores it in a database. This ensures that the basic data necessary for future analysis is secured.

[0046] Step 2:

[0047] The server uses the collected user information to perform data analysis using AI algorithms. The server evaluates the user's risk tolerance and investment goals, and constructs an individual investment profile. This investment profile forms a model of the user's financial behavior.

[0048] Step 3:

[0049] The server generates optimal investment recommendations based on the user's investment profile. The server considers market data and economic indicators to create recommendations that include appropriate investment products and portfolios. These recommendations address specific risk levels and timeframes.

[0050] Step 4:

[0051] The server sends the generated investment proposal to the terminal. The terminal displays the proposal details clearly to the user through its user interface. This allows the user to consider the proposal in detail.

[0052] Step 5:

[0053] The user reviews the investment proposal presented through their device. The user evaluates the proposal and either approves it or requests adjustments to the presented options. The user's selection is then sent from the device to the server for the next process.

[0054] Step 6:

[0055] Based on the investment proposal approved by the user, the server automatically initiates the process of executing investment transactions. The server makes the necessary fund transfers and handles the purchase and sale of investment products online. Afterwards, it records the transaction results and updates the user's asset status.

[0056] Step 7:

[0057] The server periodically tracks the user's investment activity and evaluates investment performance. Considering market data fluctuations and investment results, the server generates new analysis results to determine whether to revise investment recommendations.

[0058] Step 8:

[0059] The terminal notifies the user of the latest investment status and feedback received from the server. The user can check the operational results via the terminal and request new proposals as needed. This allows the user to continuously maintain an appropriate investment strategy.

[0060] (Example 1)

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

[0062] In today's investment environment, individuals need to properly analyze vast and complex information and make accurate investment decisions in order to manage their financial assets efficiently and effectively. However, for individuals without specialized knowledge, this process is extremely difficult, and there is a risk of making incorrect decisions. Furthermore, they are required to respond immediately to rapid market fluctuations and necessitate real-time revisions of their investment strategies. There is a need to solve these challenges and provide individual investors with a means to manage their assets with peace of mind.

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

[0064] In this invention, the server includes means for collecting user attribute information, means for constructing an investment profile using a generation algorithm based on the attribute information, and means for generating optimal investment proposals based on the investment profile and market information. This enables users to make decisions based on investment proposals provided by the system, even without specialized knowledge, and allows for effective asset management while minimizing risk by having the server continuously evaluate market movements and modify proposals as needed.

[0065] "User attribute information" refers to specific personal data about individual investors, such as their age, financial status, and investment intentions.

[0066] A "generative algorithm" is a computational procedure that derives specific patterns or rules based on collected data to form an investment profile.

[0067] An "investment profile" is a collection of information that outlines a framework for an asset management strategy, built based on a user's risk tolerance and investment goals.

[0068] "Market information" refers to various data in financial markets, such as stock prices, interest rates, and economic indicators—data on the external environment necessary for investment analysis.

[0069] An "investment proposal" refers to the specific investment product options and portfolio configurations presented to the user according to the generated investment profile.

[0070] A "user terminal" refers to electronic devices such as computers and smartphones that users use to input information or view presented investment proposals.

[0071] "Automatic execution" refers to a process where the system executes trading operations non-manually based on the user's selection and completes the process.

[0072] "Record updating" refers to database changes made to keep users' investment history and related data up-to-date, based on transaction results and subsequent market fluctuations.

[0073] "Reviewing analysis results" refers to the process of re-evaluating existing strategies and proposals in response to changes in the investment environment and making modifications as necessary.

[0074] "Means of notification" refers to communication methods and technologies that a system uses to inform users of new information or suggestions, such as email or push notifications.

[0075] This invention relates to a system that supports users in managing their financial assets. In implementing the invention, a server, a terminal, and a user cooperate to perform the following process.

[0076] The server receives data entered by the user on the device in order to collect user attribute information. This information includes the user's age, financial status, and investment intentions. The server securely stores this information in a database and uses it as the basis for analysis. The server uses a generative AI model to build the user's investment profile based on this information. The generative algorithm performs an analysis that takes into account the user's risk tolerance and investment goals to shape this profile.

[0077] Next, the server references external data such as market information and economic indicators to generate investment suggestions tailored to the user. These suggestions include specific financial product options and portfolio configuration proposals. For example, if a 30-year-old user wants to invest long-term with 10 million yen in assets, the server will recommend an index fund that aims for steady returns while minimizing risk.

[0078] The generated investment proposals are presented to the user via a terminal. The terminal displays the proposals visually and clearly using graphs and charts. This allows users to easily understand the proposals and make choices that suit their investment strategy.

[0079] The user reviews the investment proposal presented via their terminal. If they approve the proposal, the user simply authorizes its execution, instructing the server to automatically execute the trade. The investment process is automated by the server, ensuring efficiency and security.

[0080] Furthermore, the server continuously monitors market fluctuations and notifies users of the operational results. The server reviews the analysis results as needed and provides users with suggestions to optimize their investment strategies. Users can periodically check the operational status through their terminals and request changes to their strategies as necessary.

[0081] As a concrete example, by inputting the prompt "Generate the optimal investment proposal for a 30-year-old user with 10 million yen in assets who desires long-term investment with reduced risk" into the AI ​​model, the system can automatically generate and propose an investment plan suitable for the user. This system utilizes the capabilities of AI to improve the efficiency of asset management when individual investors make complex investment decisions.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] Users enter attribute information such as their age, financial status, and investment intentions through the terminal's user interface. This input is intuitive, using text fields and dropdown menus. At this stage, the user's information is ready to be transmitted to the system.

[0085] Step 2:

[0086] The terminal securely encrypts the attribute information entered by the user and sends it to the server. This process maintains data confidentiality using security protocols such as SSL / TLS. Once the transmitted data is received by the server, it is ready for the next processing step.

[0087] Step 3:

[0088] The server stores user attribute information received from the terminal and analyzes the data using a generative AI model. This process records the information in a database and constructs an investment profile that takes into account the user's risk tolerance and investment goals. As a result of the analysis, a specific investment strategy is defined for each user.

[0089] Step 4:

[0090] The server collects market information and economic indicators, and uses an AI model to generate optimal investment recommendations based on this data. Referring to the user's input investment profile, the system processes the data to create recommended financial products and portfolio compositions. This output becomes the specific investment proposal later presented to the user.

[0091] Step 5:

[0092] The terminal presents the generated investment proposal to the user. This process uses visually easy-to-understand formats such as graphs and charts, and utilizes data visualization tools to aid user comprehension. The presented proposal then awaits user confirmation.

[0093] Step 6:

[0094] The user reviews the investment proposal presented through the terminal and approves or requests changes. The user's selected actions are sent to the server as input information necessary for the next process, preparing the investment strategy for execution.

[0095] Step 7:

[0096] The server automatically executes investment transactions based on user approval. The system executes trades in the financial markets according to the selected proposals and updates the database with the results. This output includes whether the trades were successful or not, as well as actual asset changes.

[0097] Step 8:

[0098] The server continuously monitors the market, re-evaluates investment strategies as needed, and revises recommendations to users. When market fluctuations occur, it utilizes generative AI models to perform new analyses and notifies users of the results as prompts. This allows users to manage their assets while always keeping up with the latest investment environment.

[0099] Step 9:

[0100] Users regularly check their investment performance via their devices. The system provides an up-to-date dashboard that reflects the user's investment history and market conditions, making it easy for users to understand their investment progress. This allows users to continue long-term asset management with peace of mind.

[0101] (Application Example 1)

[0102] 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."

[0103] In modern society, it is a challenging task for users to effectively link asset management with their daily financial transactions to make optimal investment decisions. In particular, there is a need for a system that allows users to instantly understand how their daily spending impacts their asset management and to make appropriate adjustments. To solve this problem, a means is needed to reflect users' daily payment information in their investment management profiles.

[0104] 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.

[0105] In this invention, the server includes means for collecting user attribute information, means for constructing an investment profile based on said attribute information, and means for collecting user payment information and adjusting investments. This allows users to understand in real time how their daily payment activities affect their investment strategy and to manage their assets appropriately.

[0106] "User attribute information" refers to data that shows the individual characteristics of a user, such as age, asset status, and investment intentions.

[0107] An "investment profile" is a framework for investment strategies built based on attribute information, reflecting a user's risk tolerance and investment goals.

[0108] An "investment proposal" is suggested investment action or product selection information generated based on the user's investment profile.

[0109] "Payment information" refers to data related to payments made by users in their daily transaction activities.

[0110] "Investment adjustment" refers to the action of making appropriate modifications to existing investment profiles and strategies based on a user's payment information.

[0111] "Investment transactions" refer to activities involving the buying and selling of financial products.

[0112] "Analysis results" refer to information that includes the outcomes and conclusions of analyses performed using collected data.

[0113] This invention realizes an AI-driven system to support users' financial asset management. The system supports investment decisions through the coordinated operation of the server, terminal, and user.

[0114] The server first collects user attribute information, including age, financial status, and investment intentions. Based on this information, the server uses an AI algorithm to build an investment profile for each user. This profile reflects the user's risk tolerance and investment goals. Next, the server collects the user's settlement information in real time and makes investment adjustments based on it.

[0115] The terminal provides an intuitive user interface, allowing users to easily input information. Through the terminal, users can review investment proposals generated from the server and request approval or modifications. The proposals are presented in a visually easy-to-understand format, enabling users to assess the impact of their daily payment activities on their investment strategy.

[0116] Users enter their personal information into the terminal upon their initial login. Subsequently, when making regular payments, the system immediately suggests appropriate investment adjustments based on the amount the user has paid. This allows users to manage their assets with confidence and effectively achieve their investment goals.

[0117] For example, when a user purchases a high-priced product, the system prompts the AI ​​model with a question such as, "Please advise how this increased purchase amount will affect future investments." This allows the server to then suggest to the user, "This purchase will reduce your investment by 5%, and you will recover that amount after your next bonus payment."

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The server collects user attribute information. It receives the user's age, financial status, and investment intentions as input, and uses this information to generate the data necessary to build an investment profile for each user. The data is then integrated and passed on to the next profile build.

[0121] Step 2:

[0122] The server uses an AI algorithm to construct an investment profile based on the collected information. The input includes user attribute information generated in Step 1, and the output generates an investment profile that reflects risk tolerance and investment goals. The AI ​​model analyzes the data to create a precise profile.

[0123] Step 3:

[0124] The server collects user payment information in real time. The input consists of the user's daily transaction data, which is used to build initial data for investment adjustments. The data is managed while maintaining consistency.

[0125] Step 4:

[0126] The server combines the investment profile from step 2 and the settlement information from step 3 to generate the optimal investment adjustment. The input requires the profile and settlement information, and the output is a recommended investment adjustment for the user. The AI ​​uses prompts to accurately create the adjustment proposal.

[0127] Step 5:

[0128] The terminal visually presents the investment adjustment proposal received from the server in step 4 to the user. The input is the adjustment proposal data, and the output is visual information in a user-friendly format. The user can easily understand, approve, or modify it.

[0129] Step 6:

[0130] The user reviews the presented investment adjustment proposal via the terminal and approves or modifies it as needed. Input information is provided by the terminal, and the finalized investment proposal is sent to the server as output. The user's decision is reflected immediately.

[0131] Step 7:

[0132] The server automatically executes investment transactions based on investment proposals ultimately approved by the user, and tracks the results. The input is the finalized investment proposal, and the output is the actual transaction data and subsequent analysis results. The transaction history is continuously updated, enabling highly accurate investment management.

[0133] 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.

[0134] This invention provides an AI-driven financial advisor system that recognizes and takes into account the user's emotions, in addition to their attribute information, when making investment recommendations. To implement this system, the server, terminal, user, and emotion engine must cooperate with each other, and the process unfolds as follows.

[0135] Server Embodiment

[0136] The server collects user attribute information and builds an initial investment profile based on it. This includes age, financial status, and investment intentions. Next, it receives user sentiment data collected via the sentiment engine and evaluates how the user's sentiments affect the investment profile. Using this information-incorporated profile, the server generates investment recommendations that are best suited to the user.

[0137] Terminal embodiment

[0138] The terminal provides an interface designed to make it easy for users to input information. It sends user information and sentiment data to the sentiment engine and visually displays investment suggestions received from the server to the user. The terminal accepts selection input from the user and provides feedback based on that input.

[0139] User's Embodiment

[0140] Users regularly provide necessary attribute information and sentiment data through their devices. Based on this data, the system presents investment suggestions optimized for the user. Users review the suggested investment options and make their selections using their devices. When users make investment decisions, they are also provided with advice that takes into account the emotional factors analyzed by the sentiment engine, enabling them to make more precise decisions.

[0141] Emotional Engine Implementation

[0142] The emotion engine analyzes the user's voice, text, and other biometric signals to determine their emotional state. It then estimates the potential impact of the user's emotions on their investment willingness or risk tolerance and sends this information to the server.

[0143] Specific example

[0144] For example, consider user B, who has 5 million yen in assets and is hesitant to make high-risk investments, joining this system. In addition to regular attribute information of user B, the emotion engine detects signs of stress from his statements and facial expressions. Based on this information, the server generates investment suggestions for low-risk products in addition to regular investment suggestions, emphasizing emotional reassurance. User B can review these suggestions on their terminal and, because they are emotionally responsive to their investment needs, can proceed with investments with greater confidence.

[0145] This system allows for the provision of comprehensive investment strategies that include emotional aspects, thereby improving the user's investment experience.

[0146] The following describes the processing flow.

[0147] Step 1:

[0148] The server collects user attribute information. This information includes the user's age, financial status, and investment intentions, and is stored in the user profile within the system.

[0149] Step 2:

[0150] The device uses a user interface to collect user emotional data via an emotion engine. The collected data includes biosignals such as voice and facial expression analysis results.

[0151] Step 3:

[0152] The emotion engine analyzes emotional data received from the device and evaluates the user's emotional state. This evaluation result is sent to the server and used to take into account the emotional impact on investment decisions.

[0153] Step 4:

[0154] The server integrates user attribute information and sentiment data to build an investment profile optimized for the user. This takes into account the influence of emotional factors on risk tolerance and investment willingness.

[0155] Step 5:

[0156] The server generates optimal investment recommendations based on the investment profile. The generated recommendations are tailored to the user's individual risk profile and their emotional state at that time.

[0157] Step 6:

[0158] The server sends the generated investment proposal to the terminal. The terminal visually presents the proposal to the user, clearly displaying the options.

[0159] Step 7:

[0160] The user reviews the investment proposals presented through their device and selects one that aligns with their investment strategy. After selection, the user's decision is transmitted from the device to the server.

[0161] Step 8:

[0162] The server initiates the process of automatically executing investment transactions based on the investment proposal selected by the user. The server refers to market data and makes appropriate trades. The results are reflected in and recorded in the user's asset status.

[0163] Step 9:

[0164] The server periodically tracks users' investment activity, including their sentiment data, and evaluates their performance. It then considers new market and sentiment data to generate new analysis results and update investment recommendations.

[0165] Step 10:

[0166] The terminal notifies the user of feedback received from the server and the latest investment status. Based on the feedback, the user can review and adjust their investment policy as needed.

[0167] (Example 2)

[0168] 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".

[0169] Investment decisions often depend heavily not only on user attribute information but also on emotional factors. However, conventional systems have struggled to provide investment recommendations that take user emotions into account. Therefore, there is a need to provide more sophisticated investment recommendations that take user emotional states into account and support optimal decision-making.

[0170] 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.

[0171] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's emotional state and generating emotional data, and means for generating optimal investment proposals considering the emotional data. This makes it possible to provide users with investment proposals that take emotional factors into consideration.

[0172] A "user" is an individual or organization that inputs information and receives investment proposals.

[0173] "Attribute information" refers to basic data such as the user's age, financial status, and investment intentions.

[0174] "Emotional state" refers to data obtained by analyzing a user's emotions from sources such as voice, facial expressions, and text.

[0175] "Emotional data" refers to information that quantitatively or qualitatively represents an emotional state.

[0176] An "investment profile" is the foundational information for an investment strategy, built based on the user's attribute information and sentiment data.

[0177] An "investment proposal" refers to the specific investment products or plans presented to the user.

[0178] A "generative AI model" is an artificial intelligence model used to generate optimal investment proposals based on user input information.

[0179] A "prompt message" is the text of instructions or questions that are input into a generative AI model.

[0180] This invention is a system that combines a user-friendly terminal, a server for data processing, and an emotion engine for sentiment analysis. This system makes it possible to generate investment proposals by utilizing user attribute information and sentiment data.

[0181] Server Embodiment

[0182] The server receives user attribute information and stores it in a database. Using this foundational data, the server builds an initial investment profile for each user. Furthermore, it utilizes a generative AI model to generate investment suggestions tailored to the user's data. This process also incorporates sentiment data obtained from the sentiment engine. The generative AI model uses prompts to guide an investment strategy optimized for the user. An example of such a prompt is: "Generate risk-reducing investment suggestions based on the user's attribute information and sentiment data. Please consider the user's latest sentiment analysis data."

[0183] Terminal embodiment

[0184] The terminal provides an interface for receiving user input and has the functionality to send the entered data to the server and sentiment engine. It also displays investment proposals sent from the server, visualizing them with charts and graphs for easy user understanding. The terminal's role is to facilitate smooth interaction with the user.

[0185] User's Embodiment

[0186] Users provide attribute information and sentiment data via their devices and receive generated investment proposals. Users can examine the proposals and make choices that suit their intentions and emotional state. By receiving feedback based on data obtained through sentiment analysis, users can make healthier investment decisions.

[0187] In this way, this system enables sophisticated, data-driven investment recommendations and aims to promote investment in a way that resonates with users' emotions.

[0188] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0189] Step 1:

[0190] The server receives attribute information submitted by the user and stores it in a database. This input includes age, asset status, and investment intentions. Based on this information, the server organizes the information in the database and generates an initial investment profile. The server then uses this profile in the next step.

[0191] Step 2:

[0192] The device allows users to input emotional data using an interface. This input data includes voice, text, and facial expression data. The device sends this data to an emotion engine. The emotion engine uses multiple emotion recognition algorithms to analyze this data and determine the user's emotional state. It then sends the analysis results to a server.

[0193] Step 3:

[0194] When the server receives sentiment data, it analyzes it in combination with the user's investment profile. Using a generative AI model, it generates optimal investment recommendations that take into account the impact of the sentiment data. In this scenario, a prompt such as "Generate investment recommendations for risk reduction based on the user's attribute information and sentiment data" is used. This output is a formatted investment recommendation to be presented to the user.

[0195] Step 4:

[0196] The terminal receives proposals sent from the server and displays them in a format that the user can visually understand. The terminal converts the proposals into graphs and charts, visualizing them to make them easier for the user to understand. The user then considers which investment option to choose.

[0197] Step 5:

[0198] The user makes a selection from the options suggested via the terminal. The terminal sends this selection data to the server. The server, upon receiving the user's selection, automatically executes the next stage of the investment transaction and generates and saves analysis results to update the user's investment status.

[0199] (Application Example 2)

[0200] 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".

[0201] Traditional investment advisory systems provided recommendations based on user attribute information, but failed to take into account the user's emotional state. Therefore, emotional factors could potentially lead to inappropriate investment decisions. Similarly, online shopping also posed a risk of users being influenced by their emotions and making unfavorable transactions. This highlights the need for more sophisticated and adaptable investment recommendations and purchase advice that reflect user emotions.

[0202] 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.

[0203] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's emotional state, and means for modifying investment proposals based on the emotional state to generate optimal investment proposals. This enables investment and purchase support that is adapted to the user's emotions.

[0204] "User attribute information" refers to personal data about the user, such as age, financial status, and investment intentions.

[0205] An "investment profile" is information that indicates a user's investment preferences and risk tolerance, built based on their attribute information.

[0206] "Emotional state" refers to the emotional state of the user at that time, as analyzed from their voice, facial expressions, and biosignals.

[0207] An "optimal investment proposal" is the most suitable investment suggestion calculated based on the user's attribute information and emotional state.

[0208] "Means of accepting selection" refers to interfaces or technologies that allow users to choose one option from the suggestions provided.

[0209] "Means of automatically executing investment transactions" refers to a system or process that automatically executes instructed investments based on the user's selections.

[0210] "A means of tracking users' investment status and updating analysis results" refers to a process of meticulously recording the results of investment activities, repeatedly analyzing them, and maintaining up-to-date information.

[0211] "External environmental data" refers to external information that affects investment, such as fluctuations in financial markets and economic conditions.

[0212] To implement this invention, the system includes a server, a terminal, a user, and an emotion engine. The server uses Python to collect user attribute information and build an investment profile based on it. The emotion engine uses the Affectiva SDK to analyze the user's facial expression data from the camera built into the terminal and extract their emotional state. Combining this information, the server generates investment recommendations optimized for the user.

[0213] The terminal uses Flask as its backend and displays and accepts user input through a JavaScript® interface. Users can review and select investment proposals, which may be modified based on their own sentiments, via the terminal. Based on the selections, investment transactions are executed automatically, and the results are analyzed and tracked by the server.

[0214] For example, if the emotion engine detects that a user is stressed while purchasing home appliances on an e-commerce site, the device will display a message such as "Would you like to think about it a little more?" to encourage a calmer purchase decision. An example of the prompt message would be: "The user is experiencing stress while online shopping, but by calming down and being presented with new promotions, they may be able to make a better purchase decision."

[0215] Thus, the invention utilizes user emotional information to provide more appropriate and personalized advice in online trading and investment.

[0216] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0217] Step 1:

[0218] The server retrieves user attribute information. This input includes personal data provided by the user, such as age, asset status, and investment intentions. Based on this data, an investment profile is constructed. This profile serves as the foundation for defining the user's basic investment tendencies and risk tolerance.

[0219] Step 2:

[0220] The device analyzes the user's emotional data using an emotion engine. The input consists of biometric signals and audio data acquired from the device's built-in camera and microphone. By analyzing this data using the Affectiva SDK, the user's current emotional state is quantified and output. This enables real-time emotion analysis.

[0221] Step 3:

[0222] The server integrates emotional state data obtained from the emotion engine with investment profiles constructed based on attribute information. Based on this input data, it uses a generative AI model to generate investment suggestions optimized for the user. In other words, it performs data processing and calculations according to the user's emotional state and outputs investment suggestions that take emotions into consideration.

[0223] Step 4:

[0224] The terminal visualizes and presents investment proposals sent from the server to the user. The input is proposal data from the server, and the output is a visual display in a user-customized GUI. Based on these proposals, the user can intuitively make investment choices.

[0225] Step 5:

[0226] The user selects an investment option from the investment proposals presented on the terminal. The user's input is the selected investment option, which is sent to the server. The server automatically executes the investment transaction based on this information and records the results in real time.

[0227] Step 6:

[0228] The server monitors investment results and user investment status, and updates analysis results in real time. Inputs include performance data from executed investments and market fluctuation information, which are used to evaluate new investment opportunities and risks. This then outputs optimized information that will be reflected in future recommendations. By repeating this process, a better user experience is provided.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] [Second Embodiment]

[0233] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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".

[0245] The present invention provides an AI-driven financial advisor function to support users in managing their financial assets. To implement this system, the server, terminal, and user must cooperate with each other to achieve personalized investment management for each user, as described below.

[0246] Server Embodiment

[0247] The server first collects user attribute information, including the user's age, financial status, and investment intentions. Based on this data, the server uses an AI algorithm to build an investment profile for each user. This profile reflects the user's risk tolerance and investment goals. Next, the server generates optimal investment recommendations based on this profile. These recommendations take into account financial market data and economic indicators. Finally, the server monitors the user's investment transactions and assists in ensuring smooth transactions.

[0248] Terminal embodiment

[0249] The terminal prompts the user for input via a user interface. This interface is intuitive and easy to use, designed to quickly provide the user with all the information they need. The terminal presents investment proposals received from the server to the user, displaying the proposal details in a visually clear manner. It also accepts approval or modification requests from the user and sends them to the server as information necessary for the next processing step.

[0250] User Embodiment

[0251] Upon initial login to the system, users enter their age, asset status, investment intentions, etc., into a terminal. This allows users to confirm that detailed information about their investments is reflected in the system. Through the terminal, users can review investment proposals presented by the server and select the proposal best suited to their investment strategy. They can also periodically check the progress of their investment management and request a review of their investment strategy as needed.

[0252] Specific example

[0253] User A, a 30-year-old, currently possesses 10 million yen in assets and desires long-term investments with reduced risk. When User A inputs information into the system, the server analyzes this information and proposes an index-type mutual fund that aims for solid returns while reducing risk. User A approves the proposal, and the system automatically starts investing. Subsequently, User A can periodically check the investment performance through their terminal, allowing them to continue investing with peace of mind.

[0254] This invention provides an effective means for individual investors to improve the efficiency of their asset management and achieve better investment results by leveraging the power of AI when making complex investment decisions.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The server begins collecting user attribute information. The server receives information such as age, financial status, and investment intentions entered by the user and stores it in a database. This ensures that the basic data necessary for future analysis is secured.

[0258] Step 2:

[0259] The server uses the collected user information to perform data analysis using AI algorithms. The server evaluates the user's risk tolerance and investment goals, and constructs an individual investment profile. This investment profile forms a model of the user's financial behavior.

[0260] Step 3:

[0261] The server generates optimal investment recommendations based on the user's investment profile. The server considers market data and economic indicators to create recommendations that include appropriate investment products and portfolios. These recommendations address specific risk levels and timeframes.

[0262] Step 4:

[0263] The server sends the generated investment proposal to the terminal. The terminal displays the proposal details clearly to the user through its user interface. This allows the user to consider the proposal in detail.

[0264] Step 5:

[0265] The user reviews the investment proposal presented through their device. The user evaluates the proposal and either approves it or requests adjustments to the presented options. The user's selection is then sent from the device to the server for the next process.

[0266] Step 6:

[0267] Based on the investment proposal approved by the user, the server automatically initiates the process of executing investment transactions. The server makes the necessary fund transfers and handles the purchase and sale of investment products online. Afterwards, it records the transaction results and updates the user's asset status.

[0268] Step 7:

[0269] The server periodically tracks the user's investment activity and evaluates investment performance. Considering market data fluctuations and investment results, the server generates new analysis results to determine whether to revise investment recommendations.

[0270] Step 8:

[0271] The terminal notifies the user of the latest investment status and feedback received from the server. The user can check the operational results via the terminal and request new proposals as needed. This allows the user to continuously maintain an appropriate investment strategy.

[0272] (Example 1)

[0273] 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."

[0274] In today's investment environment, individuals need to properly analyze vast and complex information and make accurate investment decisions in order to manage their financial assets efficiently and effectively. However, for individuals without specialized knowledge, this process is extremely difficult, and there is a risk of making incorrect decisions. Furthermore, they are required to respond immediately to rapid market fluctuations and necessitate real-time revisions of their investment strategies. There is a need to solve these challenges and provide individual investors with a means to manage their assets with peace of mind.

[0275] 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.

[0276] In this invention, the server includes means for collecting user attribute information, means for constructing an investment profile using a generation algorithm based on the attribute information, and means for generating optimal investment proposals based on the investment profile and market information. This enables users to make decisions based on investment proposals provided by the system, even without specialized knowledge, and allows for effective asset management while minimizing risk by having the server continuously evaluate market movements and modify proposals as needed.

[0277] "User attribute information" refers to specific personal data about individual investors, such as their age, financial status, and investment intentions.

[0278] A "generative algorithm" is a computational procedure that derives specific patterns or rules based on collected data to form an investment profile.

[0279] An "investment profile" is a collection of information that outlines a framework for an asset management strategy, built based on a user's risk tolerance and investment goals.

[0280] "Market information" refers to various data in the financial market, such as stock prices, interest rates, economic indicators, etc., which are data on the external environment required for investment analysis.

[0281] "Investment proposal" refers to specific investment product options or portfolio composition plans presented to users according to the generated investment profile.

[0282] "User terminal" refers to electronic devices such as computers and smartphones used by users to input information or view presented investment proposals.

[0283] "Automatically execute" refers to the process in which the system non-manually executes trading operations and completes the process based on the user's selection.

[0284] "Record update" refers to database changes to keep the user's investment history and related data up-to-date based on the results of transactions and subsequent market fluctuations.

[0285] "Review of analysis results" refers to the process of re-evaluating existing strategies and proposals and making corrections as needed in response to changes in the investment environment.

[0286] "Means of notification" refers to communication methods and technologies used by the system to notify users of new information and proposals, such as emails and push notifications. 7]

[0287] This invention relates to a system for assisting users in managing financial assets. In implementing the invention, a server, a terminal, and a user cooperate to implement the following process.

[0288] The server receives data entered by the user on the device in order to collect user attribute information. This information includes the user's age, financial status, and investment intentions. The server securely stores this information in a database and uses it as the basis for analysis. The server uses a generative AI model to build the user's investment profile based on this information. The generative algorithm performs an analysis that takes into account the user's risk tolerance and investment goals to shape this profile.

[0289] Next, the server references external data such as market information and economic indicators to generate investment suggestions tailored to the user. These suggestions include specific financial product options and portfolio configuration proposals. For example, if a 30-year-old user wants to invest long-term with 10 million yen in assets, the server will recommend an index fund that aims for steady returns while minimizing risk.

[0290] The generated investment proposals are presented to the user via a terminal. The terminal displays the proposals visually and clearly using graphs and charts. This allows users to easily understand the proposals and make choices that suit their investment strategy.

[0291] The user reviews the investment proposal presented via their terminal. If they approve the proposal, the user simply authorizes its execution, instructing the server to automatically execute the trade. The investment process is automated by the server, ensuring efficiency and security.

[0292] Furthermore, the server continuously monitors market fluctuations and notifies users of the operational results. The server reviews the analysis results as needed and provides users with suggestions to optimize their investment strategies. Users can periodically check the operational status through their terminals and request changes to their strategies as necessary.

[0293] As a concrete example, by inputting the prompt "Generate the optimal investment proposal for a 30-year-old user with 10 million yen in assets who desires long-term investment with reduced risk" into the AI ​​model, the system can automatically generate and propose an investment plan suitable for the user. This system utilizes the capabilities of AI to improve the efficiency of asset management when individual investors make complex investment decisions.

[0294] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0295] Step 1:

[0296] Users enter attribute information such as their age, financial status, and investment intentions through the terminal's user interface. This input is intuitive, using text fields and dropdown menus. At this stage, the user's information is ready to be transmitted to the system.

[0297] Step 2:

[0298] The terminal securely encrypts the attribute information entered by the user and sends it to the server. This process maintains data confidentiality using security protocols such as SSL / TLS. Once the transmitted data is received by the server, it is ready for the next processing step.

[0299] Step 3:

[0300] The server stores user attribute information received from the terminal and analyzes the data using a generative AI model. This process records the information in a database and constructs an investment profile that takes into account the user's risk tolerance and investment goals. As a result of the analysis, a specific investment strategy is defined for each user.

[0301] Step 4:

[0302] The server collects market information and economic indicators, and based on that, utilizes the generated AI model to generate optimal investment proposals. While referring to the input user investment profile, the system creates recommended financial products and portfolio composition plans through data processing. This output becomes the specific investment proposal presented to the user later.

[0303] Step 5:

[0304] The terminal presents the generated investment proposal to the user. In this process, the investment proposal is displayed in a visually understandable form such as graphs and charts, and data visualization tools are utilized to assist the user's understanding. The presented proposal moves to the stage of waiting for the user's confirmation.

[0305] Step 6:

[0306] The user checks the investment proposal presented through the terminal and makes an approval or change request. The operation selected by the user is sent to the server as the input information required for the next process, preparing for the execution of the investment strategy.

[0307] Step 7:

[0308] The server automatically executes investment transactions based on the user's approval. The system conducts transactions in the financial market according to the selected proposal and records and updates the results in the database. This output includes the success or failure of the transaction and the actual asset fluctuations.

[0309] Step 8:

[0310] The server continuously monitors the market, re-evaluates the investment strategy as needed, and conducts a review of the proposal for the user. When market fluctuations occur, new analysis is performed using the generated AI model, and the results are notified to the user as a prompt. This enables the user to manage assets while always adapting to the latest investment environment.

[0311] Step 9:

[0312] Users regularly check their investment performance via their devices. The system provides an up-to-date dashboard that reflects the user's investment history and market conditions, making it easy for users to understand their investment progress. This allows users to continue long-term asset management with peace of mind.

[0313] (Application Example 1)

[0314] 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."

[0315] In modern society, it is a challenging task for users to effectively link asset management with their daily financial transactions to make optimal investment decisions. In particular, there is a need for a system that allows users to instantly understand how their daily spending impacts their asset management and to make appropriate adjustments. To solve this problem, a means is needed to reflect users' daily payment information in their investment management profiles.

[0316] 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.

[0317] In this invention, the server includes means for collecting user attribute information, means for constructing an investment profile based on said attribute information, and means for collecting user payment information and adjusting investments. This allows users to understand in real time how their daily payment activities affect their investment strategy and to manage their assets appropriately.

[0318] "User attribute information" refers to data that shows the individual characteristics of a user, such as age, asset status, and investment intentions.

[0319] An "investment profile" is a framework for investment strategies built based on attribute information, reflecting a user's risk tolerance and investment goals.

[0320] An "investment proposal" is suggested investment action or product selection information generated based on the user's investment profile.

[0321] "Payment information" refers to data related to payments made by users in their daily transaction activities.

[0322] "Investment adjustment" refers to the action of making appropriate modifications to existing investment profiles and strategies based on a user's payment information.

[0323] "Investment transactions" refer to activities involving the buying and selling of financial products.

[0324] "Analysis results" refer to information that includes the outcomes and conclusions of analyses performed using collected data.

[0325] This invention realizes an AI-driven system to support users' financial asset management. The system supports investment decisions through the coordinated operation of the server, terminal, and user.

[0326] The server first collects user attribute information, including age, financial status, and investment intentions. Based on this information, the server uses an AI algorithm to build an investment profile for each user. This profile reflects the user's risk tolerance and investment goals. Next, the server collects the user's settlement information in real time and makes investment adjustments based on it.

[0327] The terminal provides an intuitive user interface, allowing users to easily input information. Through the terminal, users can review investment proposals generated from the server and request approval or modifications. The proposals are presented in a visually easy-to-understand format, enabling users to assess the impact of their daily payment activities on their investment strategy.

[0328] Users enter their personal information into the terminal upon their initial login. Subsequently, when making regular payments, the system immediately suggests appropriate investment adjustments based on the amount the user has paid. This allows users to manage their assets with confidence and effectively achieve their investment goals.

[0329] For example, when a user purchases a high-priced product, the system prompts the AI ​​model with a question such as, "Please advise how this increased purchase amount will affect future investments." This allows the server to then suggest to the user, "This purchase will reduce your investment by 5%, and you will recover that amount after your next bonus payment."

[0330] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0331] Step 1:

[0332] The server collects user attribute information. It receives the user's age, financial status, and investment intentions as input, and uses this information to generate the data necessary to build an investment profile for each user. The data is then integrated and passed on to the next profile build.

[0333] Step 2:

[0334] The server uses an AI algorithm to construct an investment profile based on the collected information. The input includes user attribute information generated in Step 1, and the output generates an investment profile that reflects risk tolerance and investment goals. The AI ​​model analyzes the data to create a precise profile.

[0335] Step 3:

[0336] The server collects user payment information in real time. The input consists of the user's daily transaction data, which is used to build initial data for investment adjustments. The data is managed while maintaining consistency.

[0337] Step 4:

[0338] The server combines the investment profile from step 2 and the settlement information from step 3 to generate the optimal investment adjustment. The input requires the profile and settlement information, and the output is a recommended investment adjustment for the user. The AI ​​uses prompts to accurately create the adjustment proposal.

[0339] Step 5:

[0340] The terminal visually presents the investment adjustment proposal received from the server in step 4 to the user. The input is the adjustment proposal data, and the output is visual information in a user-friendly format. The user can easily understand, approve, or modify it.

[0341] Step 6:

[0342] The user reviews the presented investment adjustment proposal via the terminal and approves or modifies it as needed. Input information is provided by the terminal, and the finalized investment proposal is sent to the server as output. The user's decision is reflected immediately.

[0343] Step 7:

[0344] The server automatically executes investment transactions based on investment proposals ultimately approved by the user, and tracks the results. The input is the finalized investment proposal, and the output is the actual transaction data and subsequent analysis results. The transaction history is continuously updated, enabling highly accurate investment management.

[0345] 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.

[0346] This invention provides an AI-driven financial advisor system that recognizes and takes into account the user's emotions, in addition to their attribute information, when making investment recommendations. To implement this system, the server, terminal, user, and emotion engine must cooperate with each other, and the process unfolds as follows.

[0347] Server Embodiment

[0348] The server collects user attribute information and builds an initial investment profile based on it. This includes age, financial status, and investment intentions. Next, it receives user sentiment data collected via the sentiment engine and evaluates how the user's sentiments affect the investment profile. Using this information-incorporated profile, the server generates investment recommendations that are best suited to the user.

[0349] Terminal embodiment

[0350] The terminal provides an interface designed to make it easy for users to input information. It sends user information and sentiment data to the sentiment engine and visually displays investment suggestions received from the server to the user. The terminal accepts selection input from the user and provides feedback based on that input.

[0351] User's Embodiment

[0352] Users regularly provide necessary attribute information and sentiment data through their devices. Based on this data, the system presents investment suggestions optimized for the user. Users review the suggested investment options and make their selections using their devices. When users make investment decisions, they are also provided with advice that takes into account the emotional factors analyzed by the sentiment engine, enabling them to make more precise decisions.

[0353] Emotional Engine Implementation

[0354] The emotion engine analyzes the user's voice, text, and other biometric signals to determine their emotional state. It then estimates the potential impact of the user's emotions on their investment willingness or risk tolerance and sends this information to the server.

[0355] Specific example

[0356] For example, consider user B, who has 5 million yen in assets and is hesitant to make high-risk investments, joining this system. In addition to regular attribute information of user B, the emotion engine detects signs of stress from his statements and facial expressions. Based on this information, the server generates investment suggestions for low-risk products in addition to regular investment suggestions, emphasizing emotional reassurance. User B can review these suggestions on their terminal and, because they are emotionally responsive to their investment needs, can proceed with investments with greater confidence.

[0357] This system allows for the provision of comprehensive investment strategies that include emotional aspects, thereby improving the user's investment experience.

[0358] The following describes the processing flow.

[0359] Step 1:

[0360] The server collects user attribute information. This information includes the user's age, financial status, and investment intentions, and is stored in the user profile within the system.

[0361] Step 2:

[0362] The device uses a user interface to collect user emotional data via an emotion engine. The collected data includes biosignals such as voice and facial expression analysis results.

[0363] Step 3:

[0364] The emotion engine analyzes emotional data received from the device and evaluates the user's emotional state. This evaluation result is sent to the server and used to take into account the emotional impact on investment decisions.

[0365] Step 4:

[0366] The server integrates user attribute information and sentiment data to build an investment profile optimized for the user. This takes into account the influence of emotional factors on risk tolerance and investment willingness.

[0367] Step 5:

[0368] The server generates optimal investment recommendations based on the investment profile. The generated recommendations are tailored to the user's individual risk profile and their emotional state at that time.

[0369] Step 6:

[0370] The server sends the generated investment proposal to the terminal. The terminal visually presents the proposal to the user, clearly displaying the options.

[0371] Step 7:

[0372] The user reviews the investment proposals presented through their device and selects one that aligns with their investment strategy. After selection, the user's decision is transmitted from the device to the server.

[0373] Step 8:

[0374] The server initiates the process of automatically executing investment transactions based on the investment proposal selected by the user. The server refers to market data and makes appropriate trades. The results are reflected in and recorded in the user's asset status.

[0375] Step 9:

[0376] The server periodically tracks users' investment activity, including their sentiment data, and evaluates their performance. It then considers new market and sentiment data to generate new analysis results and update investment recommendations.

[0377] Step 10:

[0378] The terminal notifies the user of feedback received from the server and the latest investment status. Based on the feedback, the user can review and adjust their investment policy as needed.

[0379] (Example 2)

[0380] 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".

[0381] Investment decisions often depend heavily not only on user attribute information but also on emotional factors. However, conventional systems have struggled to provide investment recommendations that take user emotions into account. Therefore, there is a need to provide more sophisticated investment recommendations that take user emotional states into account and support optimal decision-making.

[0382] 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.

[0383] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's emotional state and generating emotional data, and means for generating optimal investment proposals considering the emotional data. This makes it possible to provide users with investment proposals that take emotional factors into consideration.

[0384] A "user" is an individual or organization that inputs information and receives investment proposals.

[0385] "Attribute information" refers to basic data such as the user's age, financial status, and investment intentions.

[0386] "Emotional state" refers to data obtained by analyzing a user's emotions from sources such as voice, facial expressions, and text.

[0387] "Emotional data" refers to information that quantitatively or qualitatively represents an emotional state.

[0388] An "investment profile" is the foundational information for an investment strategy, built based on the user's attribute information and sentiment data.

[0389] An "investment proposal" refers to the specific investment products or plans presented to the user.

[0390] A "generative AI model" is an artificial intelligence model used to generate optimal investment proposals based on user input information.

[0391] A "prompt message" is the text of instructions or questions that are input into a generative AI model.

[0392] This invention is a system that combines a user-friendly terminal, a server for data processing, and an emotion engine for sentiment analysis. This system makes it possible to generate investment proposals by utilizing user attribute information and sentiment data.

[0393] Server Embodiment

[0394] The server receives user attribute information and stores it in a database. Using this foundational data, the server builds an initial investment profile for each user. Furthermore, it utilizes a generative AI model to generate investment suggestions tailored to the user's data. This process also incorporates sentiment data obtained from the sentiment engine. The generative AI model uses prompts to guide an investment strategy optimized for the user. An example of such a prompt is: "Generate risk-reducing investment suggestions based on the user's attribute information and sentiment data. Please consider the user's latest sentiment analysis data."

[0395] Terminal embodiment

[0396] The terminal provides an interface for receiving user input and has the functionality to send the entered data to the server and sentiment engine. It also displays investment proposals sent from the server, visualizing them with charts and graphs for easy user understanding. The terminal's role is to facilitate smooth interaction with the user.

[0397] User's Embodiment

[0398] Users provide attribute information and sentiment data via their devices and receive generated investment proposals. Users can examine the proposals and make choices that suit their intentions and emotional state. By receiving feedback based on data obtained through sentiment analysis, users can make healthier investment decisions.

[0399] In this way, this system enables sophisticated, data-driven investment recommendations and aims to promote investment in a way that resonates with users' emotions.

[0400] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0401] Step 1:

[0402] The server receives attribute information submitted by the user and stores it in a database. This input includes age, asset status, and investment intentions. Based on this information, the server organizes the information in the database and generates an initial investment profile. The server then uses this profile in the next step.

[0403] Step 2:

[0404] The device allows users to input emotional data using an interface. This input data includes voice, text, and facial expression data. The device sends this data to an emotion engine. The emotion engine uses multiple emotion recognition algorithms to analyze this data and determine the user's emotional state. It then sends the analysis results to a server.

[0405] Step 3:

[0406] When the server receives sentiment data, it analyzes it in combination with the user's investment profile. Using a generative AI model, it generates optimal investment recommendations that take into account the impact of the sentiment data. In this scenario, a prompt such as "Generate investment recommendations for risk reduction based on the user's attribute information and sentiment data" is used. This output is a formatted investment recommendation to be presented to the user.

[0407] Step 4:

[0408] The terminal receives proposals sent from the server and displays them in a format that the user can visually understand. The terminal converts the proposals into graphs and charts, visualizing them to make them easier for the user to understand. The user then considers which investment option to choose.

[0409] Step 5:

[0410] The user makes a selection from the options suggested via the terminal. The terminal sends this selection data to the server. The server, upon receiving the user's selection, automatically executes the next stage of the investment transaction and generates and saves analysis results to update the user's investment status.

[0411] (Application Example 2)

[0412] 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."

[0413] Traditional investment advisory systems provided recommendations based on user attribute information, but failed to take into account the user's emotional state. Therefore, emotional factors could potentially lead to inappropriate investment decisions. Similarly, online shopping also posed a risk of users being influenced by their emotions and making unfavorable transactions. This highlights the need for more sophisticated and adaptable investment recommendations and purchase advice that reflect user emotions.

[0414] 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.

[0415] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's emotional state, and means for modifying investment proposals based on the emotional state to generate optimal investment proposals. This enables investment and purchase support that is adapted to the user's emotions.

[0416] "User attribute information" refers to personal data about the user, such as age, financial status, and investment intentions.

[0417] An "investment profile" is information that indicates a user's investment preferences and risk tolerance, built based on their attribute information.

[0418] "Emotional state" refers to the emotional state of the user at that time, as analyzed from their voice, facial expressions, and biosignals.

[0419] An "optimal investment proposal" is the most suitable investment suggestion calculated based on the user's attribute information and emotional state.

[0420] "Means of accepting selection" refers to interfaces or technologies that allow users to choose one option from the suggestions provided.

[0421] "Means of automatically executing investment transactions" refers to a system or process that automatically executes instructed investments based on the user's selections.

[0422] "A means of tracking users' investment status and updating analysis results" refers to a process of meticulously recording the results of investment activities, repeatedly analyzing them, and maintaining up-to-date information.

[0423] "External environmental data" refers to external information that affects investment, such as fluctuations in financial markets and economic conditions.

[0424] To implement this invention, the system includes a server, a terminal, a user, and an emotion engine. The server uses Python to collect user attribute information and build an investment profile based on it. The emotion engine uses the Affectiva SDK to analyze the user's facial expression data from the camera built into the terminal and extract their emotional state. Combining this information, the server generates investment recommendations optimized for the user.

[0425] The terminal uses Flask as its backend and displays and accepts user input through a JavaScript-based interface. Users can review and select investment proposals that have been modified based on their own sentiments via the terminal. Based on the selections, investment transactions are executed automatically, and the results are analyzed and tracked by the server.

[0426] For example, if the emotion engine detects that a user is stressed while purchasing home appliances on an e-commerce site, the device will display a message such as "Would you like to think about it a little more?" to encourage a calmer purchase decision. An example of the prompt message would be: "The user is experiencing stress while online shopping, but by calming down and being presented with new promotions, they may be able to make a better purchase decision."

[0427] Thus, the invention utilizes user emotional information to provide more appropriate and personalized advice in online trading and investment.

[0428] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0429] Step 1:

[0430] The server retrieves user attribute information. This input includes personal data provided by the user, such as age, asset status, and investment intentions. Based on this data, an investment profile is constructed. This profile serves as the foundation for defining the user's basic investment tendencies and risk tolerance.

[0431] Step 2:

[0432] The device analyzes the user's emotional data using an emotion engine. The input consists of biometric signals and audio data acquired from the device's built-in camera and microphone. By analyzing this data using the Affectiva SDK, the user's current emotional state is quantified and output. This enables real-time emotion analysis.

[0433] Step 3:

[0434] The server integrates emotional state data obtained from the emotion engine with investment profiles constructed based on attribute information. Based on this input data, it uses a generative AI model to generate investment suggestions optimized for the user. In other words, it performs data processing and calculations according to the user's emotional state and outputs investment suggestions that take emotions into consideration.

[0435] Step 4:

[0436] The terminal visualizes and presents investment proposals sent from the server to the user. The input is proposal data from the server, and the output is a visual display in a user-customized GUI. Based on these proposals, the user can intuitively make investment choices.

[0437] Step 5:

[0438] The user selects an investment option from the investment proposals presented on the terminal. The user's input is the selected investment option, which is sent to the server. The server automatically executes the investment transaction based on this information and records the results in real time.

[0439] Step 6:

[0440] The server monitors investment results and user investment status, and updates analysis results in real time. Inputs include performance data from executed investments and market fluctuation information, which are used to evaluate new investment opportunities and risks. This then outputs optimized information that will be reflected in future recommendations. By repeating this process, a better user experience is provided.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] [Third Embodiment]

[0445] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0446] 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.

[0447] 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).

[0448] 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.

[0449] 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.

[0450] 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).

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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.

[0456] 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".

[0457] The present invention provides an AI-driven financial advisor function to support users in managing their financial assets. To implement this system, the server, terminal, and user must cooperate with each other to achieve personalized investment management for each user, as described below.

[0458] Server Embodiment

[0459] The server first collects user attribute information, including the user's age, financial status, and investment intentions. Based on this data, the server uses an AI algorithm to build an investment profile for each user. This profile reflects the user's risk tolerance and investment goals. Next, the server generates optimal investment recommendations based on this profile. These recommendations take into account financial market data and economic indicators. Finally, the server monitors the user's investment transactions and assists in ensuring smooth transactions.

[0460] Terminal embodiment

[0461] The terminal prompts the user for input via a user interface. This interface is intuitive and easy to use, designed to quickly provide the user with all the information they need. The terminal presents investment proposals received from the server to the user, displaying the proposal details in a visually clear manner. It also accepts approval or modification requests from the user and sends them to the server as information necessary for the next processing step.

[0462] User Embodiment

[0463] Upon initial login to the system, users enter their age, asset status, investment intentions, etc., into a terminal. This allows users to confirm that detailed information about their investments is reflected in the system. Through the terminal, users can review investment proposals presented by the server and select the proposal best suited to their investment strategy. They can also periodically check the progress of their investment management and request a review of their investment strategy as needed.

[0464] Specific example

[0465] User A, a 30-year-old, currently possesses 10 million yen in assets and desires long-term investments with reduced risk. When User A inputs information into the system, the server analyzes this information and proposes an index-type mutual fund that aims for solid returns while reducing risk. User A approves the proposal, and the system automatically starts investing. Subsequently, User A can periodically check the investment performance through their terminal, allowing them to continue investing with peace of mind.

[0466] This invention provides an effective means for individual investors to improve the efficiency of their asset management and achieve better investment results by leveraging the power of AI when making complex investment decisions.

[0467] The following describes the processing flow.

[0468] Step 1:

[0469] The server begins collecting user attribute information. The server receives information such as age, financial status, and investment intentions entered by the user and stores it in a database. This ensures that the basic data necessary for future analysis is secured.

[0470] Step 2:

[0471] The server uses the collected user information to perform data analysis using AI algorithms. The server evaluates the user's risk tolerance and investment goals, and constructs an individual investment profile. This investment profile forms a model of the user's financial behavior.

[0472] Step 3:

[0473] The server generates optimal investment recommendations based on the user's investment profile. The server considers market data and economic indicators to create recommendations that include appropriate investment products and portfolios. These recommendations address specific risk levels and timeframes.

[0474] Step 4:

[0475] The server sends the generated investment proposal to the terminal. The terminal displays the proposal details clearly to the user through its user interface. This allows the user to consider the proposal in detail.

[0476] Step 5:

[0477] The user reviews the investment proposal presented through their device. The user evaluates the proposal and either approves it or requests adjustments to the presented options. The user's selection is then sent from the device to the server for the next process.

[0478] Step 6:

[0479] Based on the investment proposal approved by the user, the server automatically initiates the process of executing investment transactions. The server makes the necessary fund transfers and handles the purchase and sale of investment products online. Afterwards, it records the transaction results and updates the user's asset status.

[0480] Step 7:

[0481] The server periodically tracks the user's investment activity and evaluates investment performance. Considering market data fluctuations and investment results, the server generates new analysis results to determine whether to revise investment recommendations.

[0482] Step 8:

[0483] The terminal notifies the user of the latest investment status and feedback received from the server. The user can check the operational results via the terminal and request new proposals as needed. This allows the user to continuously maintain an appropriate investment strategy.

[0484] (Example 1)

[0485] 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."

[0486] In today's investment environment, individuals need to properly analyze vast and complex information and make accurate investment decisions in order to manage their financial assets efficiently and effectively. However, for individuals without specialized knowledge, this process is extremely difficult, and there is a risk of making incorrect decisions. Furthermore, they are required to respond immediately to rapid market fluctuations and necessitate real-time revisions of their investment strategies. There is a need to solve these challenges and provide individual investors with a means to manage their assets with peace of mind.

[0487] 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.

[0488] In this invention, the server includes means for collecting user attribute information, means for constructing an investment profile using a generation algorithm based on the attribute information, and means for generating optimal investment proposals based on the investment profile and market information. This enables users to make decisions based on investment proposals provided by the system, even without specialized knowledge, and allows for effective asset management while minimizing risk by having the server continuously evaluate market movements and modify proposals as needed.

[0489] "User attribute information" refers to specific personal data about individual investors, such as their age, financial status, and investment intentions.

[0490] A "generative algorithm" is a computational procedure that derives specific patterns or rules based on collected data to form an investment profile.

[0491] An "investment profile" is a collection of information that outlines a framework for an asset management strategy, built based on a user's risk tolerance and investment goals.

[0492] "Market information" refers to various data in financial markets, such as stock prices, interest rates, and economic indicators—data on the external environment necessary for investment analysis.

[0493] An "investment proposal" refers to the specific investment product options and portfolio configurations presented to the user according to the generated investment profile.

[0494] A "user terminal" refers to electronic devices such as computers and smartphones that users use to input information or view presented investment proposals.

[0495] "Automatic execution" refers to a process where the system executes trading operations non-manually based on the user's selection and completes the process.

[0496] "Record updating" refers to database changes made to keep users' investment history and related data up-to-date, based on transaction results and subsequent market fluctuations.

[0497] "Reviewing analysis results" refers to the process of re-evaluating existing strategies and proposals in response to changes in the investment environment and making modifications as necessary.

[0498] "Means of notification" refers to communication methods and technologies that a system uses to inform users of new information or suggestions, such as email or push notifications.

[0499] This invention relates to a system that supports users in managing their financial assets. In implementing the invention, a server, a terminal, and a user cooperate to perform the following process.

[0500] The server receives data entered by the user on the device in order to collect user attribute information. This information includes the user's age, financial status, and investment intentions. The server securely stores this information in a database and uses it as the basis for analysis. The server uses a generative AI model to build the user's investment profile based on this information. The generative algorithm performs an analysis that takes into account the user's risk tolerance and investment goals to shape this profile.

[0501] Next, the server references external data such as market information and economic indicators to generate investment suggestions tailored to the user. These suggestions include specific financial product options and portfolio configuration proposals. For example, if a 30-year-old user wants to invest long-term with 10 million yen in assets, the server will recommend an index fund that aims for steady returns while minimizing risk.

[0502] The generated investment proposals are presented to the user via a terminal. The terminal displays the proposals visually and clearly using graphs and charts. This allows users to easily understand the proposals and make choices that suit their investment strategy.

[0503] The user reviews the investment proposal presented via their terminal. If they approve the proposal, the user simply authorizes its execution, instructing the server to automatically execute the trade. The investment process is automated by the server, ensuring efficiency and security.

[0504] Furthermore, the server continuously monitors market fluctuations and notifies users of the operational results. The server reviews the analysis results as needed and provides users with suggestions to optimize their investment strategies. Users can periodically check the operational status through their terminals and request changes to their strategies as necessary.

[0505] As a concrete example, by inputting the prompt "Generate the optimal investment proposal for a 30-year-old user with 10 million yen in assets who desires long-term investment with reduced risk" into the AI ​​model, the system can automatically generate and propose an investment plan suitable for the user. This system utilizes the capabilities of AI to improve the efficiency of asset management when individual investors make complex investment decisions.

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

[0507] Step 1:

[0508] Users enter attribute information such as their age, financial status, and investment intentions through the terminal's user interface. This input is intuitive, using text fields and dropdown menus. At this stage, the user's information is ready to be transmitted to the system.

[0509] Step 2:

[0510] The terminal securely encrypts the attribute information entered by the user and sends it to the server. This process maintains data confidentiality using security protocols such as SSL / TLS. Once the transmitted data is received by the server, it is ready for the next processing step.

[0511] Step 3:

[0512] The server stores user attribute information received from the terminal and analyzes the data using a generative AI model. This process records the information in a database and constructs an investment profile that takes into account the user's risk tolerance and investment goals. As a result of the analysis, a specific investment strategy is defined for each user.

[0513] Step 4:

[0514] The server collects market information and economic indicators, and uses an AI model to generate optimal investment recommendations based on this data. Referring to the user's input investment profile, the system processes the data to create recommended financial products and portfolio compositions. This output becomes the specific investment proposal later presented to the user.

[0515] Step 5:

[0516] The terminal presents the generated investment proposal to the user. This process uses visually easy-to-understand formats such as graphs and charts, and utilizes data visualization tools to aid user comprehension. The presented proposal then awaits user confirmation.

[0517] Step 6:

[0518] The user reviews the investment proposal presented through the terminal and approves or requests changes. The user's selected actions are sent to the server as input information necessary for the next process, preparing the investment strategy for execution.

[0519] Step 7:

[0520] The server automatically executes investment transactions based on user approval. The system executes trades in the financial markets according to the selected proposals and updates the database with the results. This output includes whether the trades were successful or not, as well as actual asset changes.

[0521] Step 8:

[0522] The server continuously monitors the market, re-evaluates investment strategies as needed, and revises recommendations to users. When market fluctuations occur, it utilizes generative AI models to perform new analyses and notifies users of the results as prompts. This allows users to manage their assets while always keeping up with the latest investment environment.

[0523] Step 9:

[0524] Users regularly check their investment performance via their devices. The system provides an up-to-date dashboard that reflects the user's investment history and market conditions, making it easy for users to understand their investment progress. This allows users to continue long-term asset management with peace of mind.

[0525] (Application Example 1)

[0526] 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."

[0527] In modern society, it is a challenging task for users to effectively link asset management with their daily financial transactions to make optimal investment decisions. In particular, there is a need for a system that allows users to instantly understand how their daily spending impacts their asset management and to make appropriate adjustments. To solve this problem, a means is needed to reflect users' daily payment information in their investment management profiles.

[0528] 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.

[0529] In this invention, the server includes means for collecting user attribute information, means for constructing an investment profile based on said attribute information, and means for collecting user payment information and adjusting investments. This allows users to understand in real time how their daily payment activities affect their investment strategy and to manage their assets appropriately.

[0530] "User attribute information" refers to data that shows the individual characteristics of a user, such as age, asset status, and investment intentions.

[0531] An "investment profile" is a framework for investment strategies built based on attribute information, reflecting a user's risk tolerance and investment goals.

[0532] An "investment proposal" is suggested investment action or product selection information generated based on the user's investment profile.

[0533] "Payment information" refers to data related to payments made by users in their daily transaction activities.

[0534] "Investment adjustment" refers to the action of making appropriate modifications to existing investment profiles and strategies based on a user's payment information.

[0535] "Investment transactions" refer to activities involving the buying and selling of financial products.

[0536] "Analysis results" refer to information that includes the outcomes and conclusions of analyses performed using collected data.

[0537] This invention realizes an AI-driven system to support users' financial asset management. The system supports investment decisions through the coordinated operation of the server, terminal, and user.

[0538] The server first collects user attribute information, including age, financial status, and investment intentions. Based on this information, the server uses an AI algorithm to build an investment profile for each user. This profile reflects the user's risk tolerance and investment goals. Next, the server collects the user's settlement information in real time and makes investment adjustments based on it.

[0539] The terminal provides an intuitive user interface, allowing users to easily input information. Through the terminal, users can review investment proposals generated from the server and request approval or modifications. The proposals are presented in a visually easy-to-understand format, enabling users to assess the impact of their daily payment activities on their investment strategy.

[0540] Users enter their personal information into the terminal upon their initial login. Subsequently, when making regular payments, the system immediately suggests appropriate investment adjustments based on the amount the user has paid. This allows users to manage their assets with confidence and effectively achieve their investment goals.

[0541] For example, when a user purchases a high-priced product, the system prompts the AI ​​model with a question such as, "Please advise how this increased purchase amount will affect future investments." This allows the server to then suggest to the user, "This purchase will reduce your investment by 5%, and you will recover that amount after your next bonus payment."

[0542] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0543] Step 1:

[0544] The server collects user attribute information. It receives the user's age, financial status, and investment intentions as input, and uses this information to generate the data necessary to build an investment profile for each user. The data is then integrated and passed on to the next profile build.

[0545] Step 2:

[0546] The server uses an AI algorithm to construct an investment profile based on the collected information. The input includes user attribute information generated in Step 1, and the output generates an investment profile that reflects risk tolerance and investment goals. The AI ​​model analyzes the data to create a precise profile.

[0547] Step 3:

[0548] The server collects user payment information in real time. The input consists of the user's daily transaction data, which is used to build initial data for investment adjustments. The data is managed while maintaining consistency.

[0549] Step 4:

[0550] The server combines the investment profile from step 2 and the settlement information from step 3 to generate the optimal investment adjustment. The input requires the profile and settlement information, and the output is a recommended investment adjustment for the user. The AI ​​uses prompts to accurately create the adjustment proposal.

[0551] Step 5:

[0552] The terminal visually presents the investment adjustment proposal received from the server in step 4 to the user. The input is the adjustment proposal data, and the output is visual information in a user-friendly format. The user can easily understand, approve, or modify it.

[0553] Step 6:

[0554] The user reviews the presented investment adjustment proposal via the terminal and approves or modifies it as needed. Input information is provided by the terminal, and the finalized investment proposal is sent to the server as output. The user's decision is reflected immediately.

[0555] Step 7:

[0556] The server automatically executes investment transactions based on investment proposals ultimately approved by the user, and tracks the results. The input is the finalized investment proposal, and the output is the actual transaction data and subsequent analysis results. The transaction history is continuously updated, enabling highly accurate investment management.

[0557] 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.

[0558] This invention provides an AI-driven financial advisor system that recognizes and takes into account the user's emotions, in addition to their attribute information, when making investment recommendations. To implement this system, the server, terminal, user, and emotion engine must cooperate with each other, and the process unfolds as follows.

[0559] Server Embodiment

[0560] The server collects user attribute information and builds an initial investment profile based on it. This includes age, financial status, and investment intentions. Next, it receives user sentiment data collected via the sentiment engine and evaluates how the user's sentiments affect the investment profile. Using this information-incorporated profile, the server generates investment recommendations that are best suited to the user.

[0561] Terminal embodiment

[0562] The terminal provides an interface designed to make it easy for users to input information. It sends user information and sentiment data to the sentiment engine and visually displays investment suggestions received from the server to the user. The terminal accepts selection input from the user and provides feedback based on that input.

[0563] User's Embodiment

[0564] Users regularly provide necessary attribute information and sentiment data through their devices. Based on this data, the system presents investment suggestions optimized for the user. Users review the suggested investment options and make their selections using their devices. When users make investment decisions, they are also provided with advice that takes into account the emotional factors analyzed by the sentiment engine, enabling them to make more precise decisions.

[0565] Emotional Engine Implementation

[0566] The emotion engine analyzes the user's voice, text, and other biometric signals to determine their emotional state. It then estimates the potential impact of the user's emotions on their investment willingness or risk tolerance and sends this information to the server.

[0567] Specific example

[0568] For example, consider user B, who has 5 million yen in assets and is hesitant to make high-risk investments, joining this system. In addition to regular attribute information of user B, the emotion engine detects signs of stress from his statements and facial expressions. Based on this information, the server generates investment suggestions for low-risk products in addition to regular investment suggestions, emphasizing emotional reassurance. User B can review these suggestions on their terminal and, because they are emotionally responsive to their investment needs, can proceed with investments with greater confidence.

[0569] This system allows for the provision of comprehensive investment strategies that include emotional aspects, thereby improving the user's investment experience.

[0570] The following describes the processing flow.

[0571] Step 1:

[0572] The server collects user attribute information. This information includes the user's age, financial status, and investment intentions, and is stored in the user profile within the system.

[0573] Step 2:

[0574] The device uses a user interface to collect user emotional data via an emotion engine. The collected data includes biosignals such as voice and facial expression analysis results.

[0575] Step 3:

[0576] The emotion engine analyzes emotional data received from the device and evaluates the user's emotional state. This evaluation result is sent to the server and used to take into account the emotional impact on investment decisions.

[0577] Step 4:

[0578] The server integrates user attribute information and sentiment data to build an investment profile optimized for the user. This takes into account the influence of emotional factors on risk tolerance and investment willingness.

[0579] Step 5:

[0580] The server generates optimal investment recommendations based on the investment profile. The generated recommendations are tailored to the user's individual risk profile and their emotional state at that time.

[0581] Step 6:

[0582] The server sends the generated investment proposal to the terminal. The terminal visually presents the proposal to the user, clearly displaying the options.

[0583] Step 7:

[0584] The user reviews the investment proposals presented through their device and selects one that aligns with their investment strategy. After selection, the user's decision is transmitted from the device to the server.

[0585] Step 8:

[0586] The server initiates the process of automatically executing investment transactions based on the investment proposal selected by the user. The server refers to market data and makes appropriate trades. The results are reflected in and recorded in the user's asset status.

[0587] Step 9:

[0588] The server periodically tracks users' investment activity, including their sentiment data, and evaluates their performance. It then considers new market and sentiment data to generate new analysis results and update investment recommendations.

[0589] Step 10:

[0590] The terminal notifies the user of feedback received from the server and the latest investment status. Based on the feedback, the user can review and adjust their investment policy as needed.

[0591] (Example 2)

[0592] 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."

[0593] Investment decisions often depend heavily not only on user attribute information but also on emotional factors. However, conventional systems have struggled to provide investment recommendations that take user emotions into account. Therefore, there is a need to provide more sophisticated investment recommendations that take user emotional states into account and support optimal decision-making.

[0594] 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.

[0595] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's emotional state and generating emotional data, and means for generating optimal investment proposals considering the emotional data. This makes it possible to provide users with investment proposals that take emotional factors into consideration.

[0596] A "user" is an individual or organization that inputs information and receives investment proposals.

[0597] "Attribute information" refers to basic data such as the user's age, financial status, and investment intentions.

[0598] "Emotional state" refers to data obtained by analyzing a user's emotions from sources such as voice, facial expressions, and text.

[0599] "Emotional data" refers to information that quantitatively or qualitatively represents an emotional state.

[0600] An "investment profile" is the foundational information for an investment strategy, built based on the user's attribute information and sentiment data.

[0601] An "investment proposal" refers to the specific investment products or plans presented to the user.

[0602] A "generative AI model" is an artificial intelligence model used to generate optimal investment proposals based on user input information.

[0603] A "prompt message" is the text of instructions or questions that are input into a generative AI model.

[0604] This invention is a system that combines a user-friendly terminal, a server for data processing, and an emotion engine for sentiment analysis. This system makes it possible to generate investment proposals by utilizing user attribute information and sentiment data.

[0605] Server Embodiment

[0606] The server receives user attribute information and stores it in a database. Using this foundational data, the server builds an initial investment profile for each user. Furthermore, it utilizes a generative AI model to generate investment suggestions tailored to the user's data. This process also incorporates sentiment data obtained from the sentiment engine. The generative AI model uses prompts to guide an investment strategy optimized for the user. An example of such a prompt is: "Generate risk-reducing investment suggestions based on the user's attribute information and sentiment data. Please consider the user's latest sentiment analysis data."

[0607] Terminal embodiment

[0608] The terminal provides an interface for receiving user input and has the functionality to send the entered data to the server and sentiment engine. It also displays investment proposals sent from the server, visualizing them with charts and graphs for easy user understanding. The terminal's role is to facilitate smooth interaction with the user.

[0609] User's Embodiment

[0610] Users provide attribute information and sentiment data via their devices and receive generated investment proposals. Users can examine the proposals and make choices that suit their intentions and emotional state. By receiving feedback based on data obtained through sentiment analysis, users can make healthier investment decisions.

[0611] In this way, this system enables sophisticated, data-driven investment recommendations and aims to promote investment in a way that resonates with users' emotions.

[0612] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0613] Step 1:

[0614] The server receives attribute information submitted by the user and stores it in a database. This input includes age, asset status, and investment intentions. Based on this information, the server organizes the information in the database and generates an initial investment profile. The server then uses this profile in the next step.

[0615] Step 2:

[0616] The device allows users to input emotional data using an interface. This input data includes voice, text, and facial expression data. The device sends this data to an emotion engine. The emotion engine uses multiple emotion recognition algorithms to analyze this data and determine the user's emotional state. It then sends the analysis results to a server.

[0617] Step 3:

[0618] When the server receives sentiment data, it analyzes it in combination with the user's investment profile. Using a generative AI model, it generates optimal investment recommendations that take into account the impact of the sentiment data. In this scenario, a prompt such as "Generate investment recommendations for risk reduction based on the user's attribute information and sentiment data" is used. This output is a formatted investment recommendation to be presented to the user.

[0619] Step 4:

[0620] The terminal receives proposals sent from the server and displays them in a format that the user can visually understand. The terminal converts the proposals into graphs and charts, visualizing them to make them easier for the user to understand. The user then considers which investment option to choose.

[0621] Step 5:

[0622] The user makes a selection from the options suggested via the terminal. The terminal sends this selection data to the server. The server, upon receiving the user's selection, automatically executes the next stage of the investment transaction and generates and saves analysis results to update the user's investment status.

[0623] (Application Example 2)

[0624] 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."

[0625] Traditional investment advisory systems provided recommendations based on user attribute information, but failed to take into account the user's emotional state. Therefore, emotional factors could potentially lead to inappropriate investment decisions. Similarly, online shopping also posed a risk of users being influenced by their emotions and making unfavorable transactions. This highlights the need for more sophisticated and adaptable investment recommendations and purchase advice that reflect user emotions.

[0626] 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.

[0627] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's emotional state, and means for modifying investment proposals based on the emotional state to generate optimal investment proposals. This enables investment and purchase support that is adapted to the user's emotions.

[0628] "User attribute information" refers to personal data about the user, such as age, financial status, and investment intentions.

[0629] An "investment profile" is information that indicates a user's investment preferences and risk tolerance, built based on their attribute information.

[0630] "Emotional state" refers to the emotional state of the user at that time, as analyzed from their voice, facial expressions, and biosignals.

[0631] An "optimal investment proposal" is the most suitable investment suggestion calculated based on the user's attribute information and emotional state.

[0632] "Means of accepting selection" refers to interfaces or technologies that allow users to choose one option from the suggestions provided.

[0633] "Means of automatically executing investment transactions" refers to a system or process that automatically executes instructed investments based on the user's selections.

[0634] "A means of tracking users' investment status and updating analysis results" refers to a process of meticulously recording the results of investment activities, repeatedly analyzing them, and maintaining up-to-date information.

[0635] "External environmental data" refers to external information that affects investment, such as fluctuations in financial markets and economic conditions.

[0636] To implement this invention, the system includes a server, a terminal, a user, and an emotion engine. The server uses Python to collect user attribute information and build an investment profile based on it. The emotion engine uses the Affectiva SDK to analyze the user's facial expression data from the camera built into the terminal and extract their emotional state. Combining this information, the server generates investment recommendations optimized for the user.

[0637] The terminal uses Flask as its backend and displays and accepts user input through a JavaScript-based interface. Users can review and select investment proposals that have been modified based on their own sentiments via the terminal. Based on the selections, investment transactions are executed automatically, and the results are analyzed and tracked by the server.

[0638] For example, if the emotion engine detects that a user is stressed while purchasing home appliances on an e-commerce site, the device will display a message such as "Would you like to think about it a little more?" to encourage a calmer purchase decision. An example of the prompt message would be: "The user is experiencing stress while online shopping, but by calming down and being presented with new promotions, they may be able to make a better purchase decision."

[0639] Thus, the invention utilizes user emotional information to provide more appropriate and personalized advice in online trading and investment.

[0640] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0641] Step 1:

[0642] The server retrieves user attribute information. This input includes personal data provided by the user, such as age, asset status, and investment intentions. Based on this data, an investment profile is constructed. This profile serves as the foundation for defining the user's basic investment tendencies and risk tolerance.

[0643] Step 2:

[0644] The device analyzes the user's emotional data using an emotion engine. The input consists of biometric signals and audio data acquired from the device's built-in camera and microphone. By analyzing this data using the Affectiva SDK, the user's current emotional state is quantified and output. This enables real-time emotion analysis.

[0645] Step 3:

[0646] The server integrates emotional state data obtained from the emotion engine with investment profiles constructed based on attribute information. Based on this input data, it uses a generative AI model to generate investment suggestions optimized for the user. In other words, it performs data processing and calculations according to the user's emotional state and outputs investment suggestions that take emotions into consideration.

[0647] Step 4:

[0648] The terminal visualizes and presents investment proposals sent from the server to the user. The input is proposal data from the server, and the output is a visual display in a user-customized GUI. Based on these proposals, the user can intuitively make investment choices.

[0649] Step 5:

[0650] The user selects an investment option from the investment proposals presented on the terminal. The user's input is the selected investment option, which is sent to the server. The server automatically executes the investment transaction based on this information and records the results in real time.

[0651] Step 6:

[0652] The server monitors investment results and user investment status, and updates analysis results in real time. Inputs include performance data from executed investments and market fluctuation information, which are used to evaluate new investment opportunities and risks. This then outputs optimized information that will be reflected in future recommendations. By repeating this process, a better user experience is provided.

[0653] 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.

[0654] 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.

[0655] 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.

[0656] [Fourth Embodiment]

[0657] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0658] 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.

[0659] 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).

[0660] 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.

[0661] 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.

[0662] 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).

[0663] 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.

[0664] 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.

[0665] 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.

[0666] 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.

[0667] 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.

[0668] 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.

[0669] 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".

[0670] The present invention provides an AI-driven financial advisor function to support users in managing their financial assets. To implement this system, the server, terminal, and user must cooperate with each other to achieve personalized investment management for each user, as described below.

[0671] Server Embodiment

[0672] The server first collects user attribute information, including the user's age, financial status, and investment intentions. Based on this data, the server uses an AI algorithm to build an investment profile for each user. This profile reflects the user's risk tolerance and investment goals. Next, the server generates optimal investment recommendations based on this profile. These recommendations take into account financial market data and economic indicators. Finally, the server monitors the user's investment transactions and assists in ensuring smooth transactions.

[0673] Terminal embodiment

[0674] The terminal prompts the user for input via a user interface. This interface is intuitive and easy to use, designed to quickly provide the user with all the information they need. The terminal presents investment proposals received from the server to the user, displaying the proposal details in a visually clear manner. It also accepts approval or modification requests from the user and sends them to the server as information necessary for the next processing step.

[0675] User Embodiment

[0676] Upon initial login to the system, users enter their age, asset status, investment intentions, etc., into a terminal. This allows users to confirm that detailed information about their investments is reflected in the system. Through the terminal, users can review investment proposals presented by the server and select the proposal best suited to their investment strategy. They can also periodically check the progress of their investment management and request a review of their investment strategy as needed.

[0677] Specific example

[0678] User A, a 30-year-old, currently possesses 10 million yen in assets and desires long-term investments with reduced risk. When User A inputs information into the system, the server analyzes this information and proposes an index-type mutual fund that aims for solid returns while reducing risk. User A approves the proposal, and the system automatically starts investing. Subsequently, User A can periodically check the investment performance through their terminal, allowing them to continue investing with peace of mind.

[0679] This invention provides an effective means for individual investors to improve the efficiency of their asset management and achieve better investment results by leveraging the power of AI when making complex investment decisions.

[0680] The following describes the processing flow.

[0681] Step 1:

[0682] The server begins collecting user attribute information. The server receives information such as age, financial status, and investment intentions entered by the user and stores it in a database. This ensures that the basic data necessary for future analysis is secured.

[0683] Step 2:

[0684] The server uses the collected user information to perform data analysis using AI algorithms. The server evaluates the user's risk tolerance and investment goals, and constructs an individual investment profile. This investment profile forms a model of the user's financial behavior.

[0685] Step 3:

[0686] The server generates optimal investment recommendations based on the user's investment profile. The server considers market data and economic indicators to create recommendations that include appropriate investment products and portfolios. These recommendations address specific risk levels and timeframes.

[0687] Step 4:

[0688] The server sends the generated investment proposal to the terminal. The terminal displays the proposal details clearly to the user through its user interface. This allows the user to consider the proposal in detail.

[0689] Step 5:

[0690] The user reviews the investment proposal presented through their device. The user evaluates the proposal and either approves it or requests adjustments to the presented options. The user's selection is then sent from the device to the server for the next process.

[0691] Step 6:

[0692] Based on the investment proposal approved by the user, the server automatically initiates the process of executing investment transactions. The server makes the necessary fund transfers and handles the purchase and sale of investment products online. Afterwards, it records the transaction results and updates the user's asset status.

[0693] Step 7:

[0694] The server periodically tracks the user's investment activity and evaluates investment performance. Considering market data fluctuations and investment results, the server generates new analysis results to determine whether to revise investment recommendations.

[0695] Step 8:

[0696] The terminal notifies the user of the latest investment status and feedback received from the server. The user can check the operational results via the terminal and request new proposals as needed. This allows the user to continuously maintain an appropriate investment strategy.

[0697] (Example 1)

[0698] 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".

[0699] In today's investment environment, individuals need to properly analyze vast and complex information and make accurate investment decisions in order to manage their financial assets efficiently and effectively. However, for individuals without specialized knowledge, this process is extremely difficult, and there is a risk of making incorrect decisions. Furthermore, they are required to respond immediately to rapid market fluctuations and necessitate real-time revisions of their investment strategies. There is a need to solve these challenges and provide individual investors with a means to manage their assets with peace of mind.

[0700] 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.

[0701] In this invention, the server includes means for collecting user attribute information, means for constructing an investment profile using a generation algorithm based on the attribute information, and means for generating optimal investment proposals based on the investment profile and market information. This enables users to make decisions based on investment proposals provided by the system, even without specialized knowledge, and allows for effective asset management while minimizing risk by having the server continuously evaluate market movements and modify proposals as needed.

[0702] "User attribute information" refers to specific personal data about individual investors, such as their age, financial status, and investment intentions.

[0703] A "generative algorithm" is a computational procedure that derives specific patterns or rules based on collected data to form an investment profile.

[0704] An "investment profile" is a collection of information that outlines a framework for an asset management strategy, built based on a user's risk tolerance and investment goals.

[0705] "Market information" refers to various data in financial markets, such as stock prices, interest rates, and economic indicators—data on the external environment necessary for investment analysis.

[0706] An "investment proposal" refers to the specific investment product options and portfolio configurations presented to the user according to the generated investment profile.

[0707] A "user terminal" refers to electronic devices such as computers and smartphones that users use to input information or view presented investment proposals.

[0708] "Automatic execution" refers to a process where the system executes trading operations non-manually based on the user's selection and completes the process.

[0709] "Record updating" refers to database changes made to keep users' investment history and related data up-to-date, based on transaction results and subsequent market fluctuations.

[0710] "Reviewing analysis results" refers to the process of re-evaluating existing strategies and proposals in response to changes in the investment environment and making modifications as necessary.

[0711] "Means of notification" refers to communication methods and technologies that a system uses to inform users of new information or suggestions, such as email or push notifications.

[0712] This invention relates to a system that supports users in managing their financial assets. In implementing the invention, a server, a terminal, and a user cooperate to perform the following process.

[0713] The server receives data entered by the user on the device in order to collect user attribute information. This information includes the user's age, financial status, and investment intentions. The server securely stores this information in a database and uses it as the basis for analysis. The server uses a generative AI model to build the user's investment profile based on this information. The generative algorithm performs an analysis that takes into account the user's risk tolerance and investment goals to shape this profile.

[0714] Next, the server references external data such as market information and economic indicators to generate investment suggestions tailored to the user. These suggestions include specific financial product options and portfolio configuration proposals. For example, if a 30-year-old user wants to invest long-term with 10 million yen in assets, the server will recommend an index fund that aims for steady returns while minimizing risk.

[0715] The generated investment proposals are presented to the user via a terminal. The terminal displays the proposals visually and clearly using graphs and charts. This allows users to easily understand the proposals and make choices that suit their investment strategy.

[0716] The user reviews the investment proposal presented via their terminal. If they approve the proposal, the user simply authorizes its execution, instructing the server to automatically execute the trade. The investment process is automated by the server, ensuring efficiency and security.

[0717] Furthermore, the server continuously monitors market fluctuations and notifies users of the operational results. The server reviews the analysis results as needed and provides users with suggestions to optimize their investment strategies. Users can periodically check the operational status through their terminals and request changes to their strategies as necessary.

[0718] As a concrete example, by inputting the prompt "Generate the optimal investment proposal for a 30-year-old user with 10 million yen in assets who desires long-term investment with reduced risk" into the AI ​​model, the system can automatically generate and propose an investment plan suitable for the user. This system utilizes the capabilities of AI to improve the efficiency of asset management when individual investors make complex investment decisions.

[0719] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0720] Step 1:

[0721] Users enter attribute information such as their age, financial status, and investment intentions through the terminal's user interface. This input is intuitive, using text fields and dropdown menus. At this stage, the user's information is ready to be transmitted to the system.

[0722] Step 2:

[0723] The terminal securely encrypts the attribute information entered by the user and sends it to the server. This process maintains data confidentiality using security protocols such as SSL / TLS. Once the transmitted data is received by the server, it is ready for the next processing step.

[0724] Step 3:

[0725] The server stores user attribute information received from the terminal and analyzes the data using a generative AI model. This process records the information in a database and constructs an investment profile that takes into account the user's risk tolerance and investment goals. As a result of the analysis, a specific investment strategy is defined for each user.

[0726] Step 4:

[0727] The server collects market information and economic indicators, and uses an AI model to generate optimal investment recommendations based on this data. Referring to the user's input investment profile, the system processes the data to create recommended financial products and portfolio compositions. This output becomes the specific investment proposal later presented to the user.

[0728] Step 5:

[0729] The terminal presents the generated investment proposal to the user. This process uses visually easy-to-understand formats such as graphs and charts, and utilizes data visualization tools to aid user comprehension. The presented proposal then awaits user confirmation.

[0730] Step 6:

[0731] The user reviews the investment proposal presented through the terminal and approves or requests changes. The user's selected actions are sent to the server as input information necessary for the next process, preparing the investment strategy for execution.

[0732] Step 7:

[0733] The server automatically executes investment transactions based on user approval. The system executes trades in the financial markets according to the selected proposals and updates the database with the results. This output includes whether the trades were successful or not, as well as actual asset changes.

[0734] Step 8:

[0735] The server continuously monitors the market, re-evaluates investment strategies as needed, and revises recommendations to users. When market fluctuations occur, it utilizes generative AI models to perform new analyses and notifies users of the results as prompts. This allows users to manage their assets while always keeping up with the latest investment environment.

[0736] Step 9:

[0737] Users regularly check their investment performance via their devices. The system provides an up-to-date dashboard that reflects the user's investment history and market conditions, making it easy for users to understand their investment progress. This allows users to continue long-term asset management with peace of mind.

[0738] (Application Example 1)

[0739] 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".

[0740] In modern society, it is a challenging task for users to effectively link asset management with their daily financial transactions to make optimal investment decisions. In particular, there is a need for a system that allows users to instantly understand how their daily spending impacts their asset management and to make appropriate adjustments. To solve this problem, a means is needed to reflect users' daily payment information in their investment management profiles.

[0741] 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.

[0742] In this invention, the server includes means for collecting user attribute information, means for constructing an investment profile based on said attribute information, and means for collecting user payment information and adjusting investments. This allows users to understand in real time how their daily payment activities affect their investment strategy and to manage their assets appropriately.

[0743] "User attribute information" refers to data that shows the individual characteristics of a user, such as age, asset status, and investment intentions.

[0744] An "investment profile" is a framework for investment strategies built based on attribute information, reflecting a user's risk tolerance and investment goals.

[0745] An "investment proposal" is suggested investment action or product selection information generated based on the user's investment profile.

[0746] "Payment information" refers to data related to payments made by users in their daily transaction activities.

[0747] "Investment adjustment" refers to the action of making appropriate modifications to existing investment profiles and strategies based on a user's payment information.

[0748] "Investment transactions" refer to activities involving the buying and selling of financial products.

[0749] "Analysis results" refer to information that includes the outcomes and conclusions of analyses performed using collected data.

[0750] This invention realizes an AI-driven system to support users' financial asset management. The system supports investment decisions through the coordinated operation of the server, terminal, and user.

[0751] The server first collects user attribute information, including age, financial status, and investment intentions. Based on this information, the server uses an AI algorithm to build an investment profile for each user. This profile reflects the user's risk tolerance and investment goals. Next, the server collects the user's settlement information in real time and makes investment adjustments based on it.

[0752] The terminal provides an intuitive user interface, allowing users to easily input information. Through the terminal, users can review investment proposals generated from the server and request approval or modifications. The proposals are presented in a visually easy-to-understand format, enabling users to assess the impact of their daily payment activities on their investment strategy.

[0753] Users enter their personal information into the terminal upon their initial login. Subsequently, when making regular payments, the system immediately suggests appropriate investment adjustments based on the amount the user has paid. This allows users to manage their assets with confidence and effectively achieve their investment goals.

[0754] For example, when a user purchases a high-priced product, the system prompts the AI ​​model with a question such as, "Please advise how this increased purchase amount will affect future investments." This allows the server to then suggest to the user, "This purchase will reduce your investment by 5%, and you will recover that amount after your next bonus payment."

[0755] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0756] Step 1:

[0757] The server collects user attribute information. It receives the user's age, financial status, and investment intentions as input, and uses this information to generate the data necessary to build an investment profile for each user. The data is then integrated and passed on to the next profile build.

[0758] Step 2:

[0759] The server uses an AI algorithm to construct an investment profile based on the collected information. The input includes user attribute information generated in Step 1, and the output generates an investment profile that reflects risk tolerance and investment goals. The AI ​​model analyzes the data to create a precise profile.

[0760] Step 3:

[0761] The server collects user payment information in real time. The input consists of the user's daily transaction data, which is used to build initial data for investment adjustments. The data is managed while maintaining consistency.

[0762] Step 4:

[0763] The server combines the investment profile from step 2 and the settlement information from step 3 to generate the optimal investment adjustment. The input requires the profile and settlement information, and the output is a recommended investment adjustment for the user. The AI ​​uses prompts to accurately create the adjustment proposal.

[0764] Step 5:

[0765] The terminal visually presents the investment adjustment proposal received from the server in step 4 to the user. The input is the adjustment proposal data, and the output is visual information in a user-friendly format. The user can easily understand, approve, or modify it.

[0766] Step 6:

[0767] The user reviews the presented investment adjustment proposal via the terminal and approves or modifies it as needed. Input information is provided by the terminal, and the finalized investment proposal is sent to the server as output. The user's decision is reflected immediately.

[0768] Step 7:

[0769] The server automatically executes investment transactions based on investment proposals ultimately approved by the user, and tracks the results. The input is the finalized investment proposal, and the output is the actual transaction data and subsequent analysis results. The transaction history is continuously updated, enabling highly accurate investment management.

[0770] 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.

[0771] This invention provides an AI-driven financial advisor system that recognizes and takes into account the user's emotions, in addition to their attribute information, when making investment recommendations. To implement this system, the server, terminal, user, and emotion engine must cooperate with each other, and the process unfolds as follows.

[0772] Server Embodiment

[0773] The server collects user attribute information and builds an initial investment profile based on it. This includes age, financial status, and investment intentions. Next, it receives user sentiment data collected via the sentiment engine and evaluates how the user's sentiments affect the investment profile. Using this information-incorporated profile, the server generates investment recommendations that are best suited to the user.

[0774] Terminal embodiment

[0775] The terminal provides an interface designed to make it easy for users to input information. It sends user information and sentiment data to the sentiment engine and visually displays investment suggestions received from the server to the user. The terminal accepts selection input from the user and provides feedback based on that input.

[0776] User's Embodiment

[0777] Users regularly provide necessary attribute information and sentiment data through their devices. Based on this data, the system presents investment suggestions optimized for the user. Users review the suggested investment options and make their selections using their devices. When users make investment decisions, they are also provided with advice that takes into account the emotional factors analyzed by the sentiment engine, enabling them to make more precise decisions.

[0778] Emotional Engine Implementation

[0779] The emotion engine analyzes the user's voice, text, and other biometric signals to determine their emotional state. It then estimates the potential impact of the user's emotions on their investment willingness or risk tolerance and sends this information to the server.

[0780] Specific example

[0781] For example, consider user B, who has 5 million yen in assets and is hesitant to make high-risk investments, joining this system. In addition to regular attribute information of user B, the emotion engine detects signs of stress from his statements and facial expressions. Based on this information, the server generates investment suggestions for low-risk products in addition to regular investment suggestions, emphasizing emotional reassurance. User B can review these suggestions on their terminal and, because they are emotionally responsive to their investment needs, can proceed with investments with greater confidence.

[0782] This system allows for the provision of comprehensive investment strategies that include emotional aspects, thereby improving the user's investment experience.

[0783] The following describes the processing flow.

[0784] Step 1:

[0785] The server collects user attribute information. This information includes the user's age, financial status, and investment intentions, and is stored in the user profile within the system.

[0786] Step 2:

[0787] The device uses a user interface to collect user emotional data via an emotion engine. The collected data includes biosignals such as voice and facial expression analysis results.

[0788] Step 3:

[0789] The emotion engine analyzes emotional data received from the device and evaluates the user's emotional state. This evaluation result is sent to the server and used to take into account the emotional impact on investment decisions.

[0790] Step 4:

[0791] The server integrates user attribute information and sentiment data to build an investment profile optimized for the user. This takes into account the influence of emotional factors on risk tolerance and investment willingness.

[0792] Step 5:

[0793] The server generates optimal investment recommendations based on the investment profile. The generated recommendations are tailored to the user's individual risk profile and their emotional state at that time.

[0794] Step 6:

[0795] The server sends the generated investment proposal to the terminal. The terminal visually presents the proposal to the user, clearly displaying the options.

[0796] Step 7:

[0797] The user reviews the investment proposals presented through their device and selects one that aligns with their investment strategy. After selection, the user's decision is transmitted from the device to the server.

[0798] Step 8:

[0799] The server initiates the process of automatically executing investment transactions based on the investment proposal selected by the user. The server refers to market data and makes appropriate trades. The results are reflected in and recorded in the user's asset status.

[0800] Step 9:

[0801] The server periodically tracks users' investment activity, including their sentiment data, and evaluates their performance. It then considers new market and sentiment data to generate new analysis results and update investment recommendations.

[0802] Step 10:

[0803] The terminal notifies the user of feedback received from the server and the latest investment status. Based on the feedback, the user can review and adjust their investment policy as needed.

[0804] (Example 2)

[0805] 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".

[0806] Investment decisions often depend heavily not only on user attribute information but also on emotional factors. However, conventional systems have struggled to provide investment recommendations that take user emotions into account. Therefore, there is a need to provide more sophisticated investment recommendations that take user emotional states into account and support optimal decision-making.

[0807] 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.

[0808] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's emotional state and generating emotional data, and means for generating optimal investment proposals considering the emotional data. This makes it possible to provide users with investment proposals that take emotional factors into consideration.

[0809] A "user" is an individual or organization that inputs information and receives investment proposals.

[0810] "Attribute information" refers to basic data such as the user's age, financial status, and investment intentions.

[0811] "Emotional state" refers to data obtained by analyzing a user's emotions from sources such as voice, facial expressions, and text.

[0812] "Emotional data" refers to information that quantitatively or qualitatively represents an emotional state.

[0813] An "investment profile" is the foundational information for an investment strategy, built based on the user's attribute information and sentiment data.

[0814] An "investment proposal" refers to the specific investment products or plans presented to the user.

[0815] A "generative AI model" is an artificial intelligence model used to generate optimal investment proposals based on user input information.

[0816] A "prompt message" is the text of instructions or questions that are input into a generative AI model.

[0817] This invention is a system that combines a user-friendly terminal, a server for data processing, and an emotion engine for sentiment analysis. This system makes it possible to generate investment proposals by utilizing user attribute information and sentiment data.

[0818] Server Embodiment

[0819] The server receives user attribute information and stores it in a database. Using this foundational data, the server builds an initial investment profile for each user. Furthermore, it utilizes a generative AI model to generate investment suggestions tailored to the user's data. This process also incorporates sentiment data obtained from the sentiment engine. The generative AI model uses prompts to guide an investment strategy optimized for the user. An example of such a prompt is: "Generate risk-reducing investment suggestions based on the user's attribute information and sentiment data. Please consider the user's latest sentiment analysis data."

[0820] Terminal embodiment

[0821] The terminal provides an interface for receiving user input and has the functionality to send the entered data to the server and sentiment engine. It also displays investment proposals sent from the server, visualizing them with charts and graphs for easy user understanding. The terminal's role is to facilitate smooth interaction with the user.

[0822] User's Embodiment

[0823] Users provide attribute information and sentiment data via their devices and receive generated investment proposals. Users can examine the proposals and make choices that suit their intentions and emotional state. By receiving feedback based on data obtained through sentiment analysis, users can make healthier investment decisions.

[0824] In this way, this system enables sophisticated, data-driven investment recommendations and aims to promote investment in a way that resonates with users' emotions.

[0825] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0826] Step 1:

[0827] The server receives attribute information submitted by the user and stores it in a database. This input includes age, asset status, and investment intentions. Based on this information, the server organizes the information in the database and generates an initial investment profile. The server then uses this profile in the next step.

[0828] Step 2:

[0829] The device allows users to input emotional data using an interface. This input data includes voice, text, and facial expression data. The device sends this data to an emotion engine. The emotion engine uses multiple emotion recognition algorithms to analyze this data and determine the user's emotional state. It then sends the analysis results to a server.

[0830] Step 3:

[0831] When the server receives sentiment data, it analyzes it in combination with the user's investment profile. Using a generative AI model, it generates optimal investment recommendations that take into account the impact of the sentiment data. In this scenario, a prompt such as "Generate investment recommendations for risk reduction based on the user's attribute information and sentiment data" is used. This output is a formatted investment recommendation to be presented to the user.

[0832] Step 4:

[0833] The terminal receives proposals sent from the server and displays them in a format that the user can visually understand. The terminal converts the proposals into graphs and charts, visualizing them to make them easier for the user to understand. The user then considers which investment option to choose.

[0834] Step 5:

[0835] The user makes a selection from the options suggested via the terminal. The terminal sends this selection data to the server. The server, upon receiving the user's selection, automatically executes the next stage of the investment transaction and generates and saves analysis results to update the user's investment status.

[0836] (Application Example 2)

[0837] 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".

[0838] Traditional investment advisory systems provided recommendations based on user attribute information, but failed to take into account the user's emotional state. Therefore, emotional factors could potentially lead to inappropriate investment decisions. Similarly, online shopping also posed a risk of users being influenced by their emotions and making unfavorable transactions. This highlights the need for more sophisticated and adaptable investment recommendations and purchase advice that reflect user emotions.

[0839] 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.

[0840] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's emotional state, and means for modifying investment proposals based on the emotional state to generate optimal investment proposals. This enables investment and purchase support that is adapted to the user's emotions.

[0841] "User attribute information" refers to personal data about the user, such as age, financial status, and investment intentions.

[0842] An "investment profile" is information that indicates a user's investment preferences and risk tolerance, built based on their attribute information.

[0843] "Emotional state" refers to the emotional state of the user at that time, as analyzed from their voice, facial expressions, and biosignals.

[0844] An "optimal investment proposal" is the most suitable investment suggestion calculated based on the user's attribute information and emotional state.

[0845] "Means of accepting selection" refers to interfaces or technologies that allow users to choose one option from the suggestions provided.

[0846] "Means of automatically executing investment transactions" refers to a system or process that automatically executes instructed investments based on the user's selections.

[0847] "A means of tracking users' investment status and updating analysis results" refers to a process of meticulously recording the results of investment activities, repeatedly analyzing them, and maintaining up-to-date information.

[0848] "External environmental data" refers to external information that affects investment, such as fluctuations in financial markets and economic conditions.

[0849] To implement this invention, the system includes a server, a terminal, a user, and an emotion engine. The server uses Python to collect user attribute information and build an investment profile based on it. The emotion engine uses the Affectiva SDK to analyze the user's facial expression data from the camera built into the terminal and extract their emotional state. Combining this information, the server generates investment recommendations optimized for the user.

[0850] The terminal uses Flask as its backend and displays and accepts user input through a JavaScript-based interface. Users can review and select investment proposals that have been modified based on their own sentiments via the terminal. Based on the selections, investment transactions are executed automatically, and the results are analyzed and tracked by the server.

[0851] For example, if the emotion engine detects that a user is stressed while purchasing home appliances on an e-commerce site, the device will display a message such as "Would you like to think about it a little more?" to encourage a calmer purchase decision. An example of the prompt message would be: "The user is experiencing stress while online shopping, but by calming down and being presented with new promotions, they may be able to make a better purchase decision."

[0852] Thus, the invention utilizes user emotional information to provide more appropriate and personalized advice in online trading and investment.

[0853] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0854] Step 1:

[0855] The server retrieves user attribute information. This input includes personal data provided by the user, such as age, asset status, and investment intentions. Based on this data, an investment profile is constructed. This profile serves as the foundation for defining the user's basic investment tendencies and risk tolerance.

[0856] Step 2:

[0857] The device analyzes the user's emotional data using an emotion engine. The input consists of biometric signals and audio data acquired from the device's built-in camera and microphone. By analyzing this data using the Affectiva SDK, the user's current emotional state is quantified and output. This enables real-time emotion analysis.

[0858] Step 3:

[0859] The server integrates emotional state data obtained from the emotion engine with investment profiles constructed based on attribute information. Based on this input data, it uses a generative AI model to generate investment suggestions optimized for the user. In other words, it performs data processing and calculations according to the user's emotional state and outputs investment suggestions that take emotions into consideration.

[0860] Step 4:

[0861] The terminal visualizes and presents investment proposals sent from the server to the user. The input is proposal data from the server, and the output is a visual display in a user-customized GUI. Based on these proposals, the user can intuitively make investment choices.

[0862] Step 5:

[0863] The user selects an investment option from the investment proposals presented on the terminal. The user's input is the selected investment option, which is sent to the server. The server automatically executes the investment transaction based on this information and records the results in real time.

[0864] Step 6:

[0865] The server monitors investment results and user investment status, and updates analysis results in real time. Inputs include performance data from executed investments and market fluctuation information, which are used to evaluate new investment opportunities and risks. This then outputs optimized information that will be reflected in future recommendations. By repeating this process, a better user experience is provided.

[0866] 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.

[0867] 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.

[0868] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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."

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] The following is further disclosed regarding the embodiments described above.

[0888] (Claim 1)

[0889] Means for collecting user attribute information,

[0890] Means for constructing an investment profile based on said attribute information,

[0891] A means for generating an optimal investment proposal based on the aforementioned investment profile,

[0892] A means of presenting the proposal to the user and accepting the user's choice,

[0893] A means of automatically executing investment transactions based on user selection,

[0894] A means to track users' investment status and update analysis results,

[0895] A system that includes this.

[0896] (Claim 2)

[0897] The system according to claim 1, wherein the investment profile construction means evaluates investment risk using external environmental data in addition to collected user attribute information.

[0898] (Claim 3)

[0899] The system according to claim 1, wherein the investment proposal presents a number of different investment products that correspond to the user's asset management goals.

[0900] "Example 1"

[0901] (Claim 1)

[0902] Means for collecting user attribute information,

[0903] Means for constructing an investment profile using a generation algorithm based on said attribute information,

[0904] A means for generating an optimal investment proposal based on the aforementioned investment profile and market information,

[0905] A means for presenting the proposal to the user's terminal, accepting the user's selection, and sending an approval or change request to the server,

[0906] A means of automatically executing investment transactions based on user selections and recording and updating the results,

[0907] A means to track users' investment status, revise proposals based on analysis results and market fluctuations, and notify users accordingly.

[0908] A system that includes this.

[0909] (Claim 2)

[0910] The system according to claim 1, wherein the investment profile building means evaluates and generates investment risk using external environmental data and economic indicators in addition to the collected user attribute information.

[0911] (Claim 3)

[0912] The system according to claim 1, wherein the investment proposal presents multiple different financial products corresponding to the user's asset management goals and visualizes them using graphs and charts to aid understanding.

[0913] "Application Example 1"

[0914] (Claim 1)

[0915] Means for collecting user attribute information,

[0916] Means for constructing an investment profile based on said attribute information,

[0917] A means for generating an optimal investment proposal based on the aforementioned investment profile,

[0918] A means of presenting the proposal to the user and accepting the user's choice,

[0919] A means of collecting user payment information and making investment adjustments,

[0920] A means of automatically executing investment transactions based on user selection,

[0921] A means to track users' investment status and update analysis results,

[0922] A system that includes this.

[0923] (Claim 2)

[0924] The system according to claim 1, wherein the investment profile construction means evaluates investment risk using external environmental data in addition to collected user attribute information.

[0925] (Claim 3)

[0926] The system according to claim 1, wherein the investment proposal presents a number of different investment products that correspond to the user's asset management goals.

[0927] "Example 2 of combining an emotion engine"

[0928] (Claim 1)

[0929] Means for collecting user attribute information,

[0930] Means for constructing an investment profile based on said attribute information,

[0931] A means for analyzing a user's emotional state and generating emotional data,

[0932] A means of generating optimal investment proposals by considering emotional data,

[0933] A means of presenting the proposal to the user and accepting the user's choice,

[0934] A means of automatically executing investment transactions based on user selection,

[0935] A means to track users' investment status and update analysis results,

[0936] A system that includes this.

[0937] (Claim 2)

[0938] The system according to claim 1, wherein the investment profile construction means evaluates investment risk using sentiment analysis data in addition to collected user attribute information.

[0939] (Claim 3)

[0940] The system according to claim 1, wherein the aforementioned investment proposal is generated by converting user attribute information and sentiment data into prompt sentences using a generative AI model.

[0941] "Application example 2 when combining with an emotional engine"

[0942] (Claim 1)

[0943] Means for collecting user attribute information,

[0944] Means for constructing an investment profile based on said attribute information,

[0945] A means of analyzing the emotional state of users,

[0946] A means of modifying investment proposals based on emotional states and generating optimal investment proposals,

[0947] A means of presenting the proposal to the user and accepting the user's choice,

[0948] A means of automatically executing investment transactions based on user selection,

[0949] A means to track users' investment status and update analysis results,

[0950] A system that includes this.

[0951] (Claim 2)

[0952] The system according to claim 1, wherein the investment profile construction means evaluates investment risk using external environmental data and user sentiment data in addition to collected user attribute information.

[0953] (Claim 3)

[0954] The system according to claim 1, wherein the investment proposal presents multiple different investment products that correspond to the user's asset management goals and take into account the user's emotional state. [Explanation of Symbols]

[0955] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting user attribute information, Means for constructing an investment profile based on said attribute information, A means for generating an optimal investment proposal based on the aforementioned investment profile, A means of presenting the proposal to the user and accepting the user's choice, A means of automatically executing investment transactions based on user selection, A means to track users' investment status and update analysis results, A system that includes this.

2. The system according to claim 1, wherein the investment profile construction means evaluates investment risk using external environmental data in addition to collected user attribute information.

3. The system according to claim 1, wherein the investment proposal presents a number of different investment products that correspond to the user's asset management goals.

Images