system

Abstract

We provide the system. [Solution] Means for collecting user attribute information, A means for generating a risk profile by analyzing user asset data and consumption data, A means for generating proposals for financial products and asset management plans based on analysis results, A means of executing financial transactions and asset adjustments based on user approval, A means of continuously monitoring the user's assets and spending status and making dynamic suggestions, A system that includes this.

Description

Technical Field

[0001] The technology of this 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] An object is to solve the problem that it is difficult for a user to effectively manage financial assets and obtain information for making appropriate investment decisions. In particular, among many users lacking financial knowledge, it is difficult to select an optimal financial product or investment portfolio according to individual situations. For this reason, there is a demand for a system that can timely propose an optimized financial product according to the risk tolerance and goals of the user himself / herself and move on to execution.

Means for Solving the Problems

[0005] This invention collects basic user information and asset information, and uses this information to generate a user risk profile using an AI engine. It then provides a means for generating financial product recommendations based on the analysis results. Furthermore, it provides a means for executing financial product transactions based on the user's consent. These transactions are completed quickly through an API interface with financial institutions. In addition, it continuously monitors the user's asset status and provides new recommendations in response to market fluctuations, thereby achieving consistently optimized asset management.

[0006] A "user" refers to an individual or legal entity that uses the system to manage or invest in financial assets.

[0007] "Basic information" refers to information necessary to understand each user's individual circumstances, such as age, annual income, investment experience, and intentions for wealth creation.

[0008] "Asset information" refers to information about the types, total amount, and income / expense status of financial assets held by a user.

[0009] "Analysis" refers to the data analysis process performed by the AI ​​engine based on the collected user information.

[0010] A "risk profile" refers to a set of criteria that indicate a user's investment behavior and acceptable risk level, and the information generated through analysis.

[0011] "Financial products" refer to various financial transactions used for asset management by users, such as investment trusts, stocks, bonds, and insurance products.

[0012] "Recommendations" refer to the recommendations generated by the AI ​​engine based on the analysis results, regarding the selection of financial products and investment strategies for the user.

[0013] "Transaction" refers to the purchase, sale, or contractual procedure for financial products carried out with the user's consent.

[0014] "API interface" refers to an application program interface for smooth data exchange and transactions between a system and a financial institution.

[0015] "Monitoring" refers to the process in which a system continuously observes the user's asset status and market fluctuations and makes new proposals as necessary.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. <> [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Embodiments for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory where information is temporarily stored and is used as a work memory by the processor.

[0021] 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 disk (e.g., hard disk), or magnetic tape, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention is an AI-powered system that enables users to effectively manage their assets and make investments. The system consists of server and terminal components, and seamlessly facilitates the suggestion and trading of financial products by the user.

[0038] The user first enters their basic information and asset information using a terminal. Information such as age, income, asset details, and investment preferences is sent to the server. The server receives this information and stores it in a database.

[0039] Next, the server analyzes this data using an AI engine to create a user risk profile. This profile details the user's risk tolerance, investment objectives, and investment timeframe, forming the basis for future recommendations.

[0040] Based on the analysis, the server selects the most suitable financial product for the user and generates a proposal. This proposal is presented to the user via their terminal. The proposal includes information on the selected financial product, as well as expected risks and returns. The user can then use this information to make a trading decision.

[0041] If a user agrees to a proposal and indicates their intention to proceed with a transaction, the server will quickly execute the purchase or sale of financial products. Transactions with financial institutions are conducted via an API interface, ensuring secure and efficient data communication.

[0042] This system also continuously monitors the user's asset status and generates new suggestions in response to market trends and fluctuations. This allows users to constantly optimize their asset management and investment strategies to suit their current situation.

[0043] As a concrete example, a user in their mid-20s registers with the system and inputs their current savings and investment experience, after which the AI ​​suggests a medium-risk investment trust. Subsequently, if investment conditions change due to market fluctuations, the server suggests rebalancing to stable bonds, and if the user agrees, the transaction is executed immediately. Through this entire process, users can effectively manage their assets and enjoy optimized investments.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user accesses the device and enters basic and asset information. This includes age, income, existing assets, investment experience, and goals. The device then sends this information to the server.

[0047] Step 2:

[0048] The server records the information it receives in a database. Furthermore, if additional information is needed from financial institutions, it is obtained via API. This allows for a comprehensive understanding of the user's asset status.

[0049] Step 3:

[0050] The server activates the AI ​​engine to analyze the data. The AI ​​generates a risk profile considering the user's risk tolerance, investment objectives, and time goals. This profile is then used to make subsequent recommendations.

[0051] Step 4:

[0052] The server analyzes market data and financial product information based on the risk profile and selects recommended financial products and investment strategies for the user. The selection results are sent to the terminal and displayed to the user.

[0053] Step 5:

[0054] The user reviews the proposal through their device. The proposal includes details about the financial product, risk level, expected return, and fees. Based on this, the user decides whether or not to proceed with the transaction.

[0055] Step 6:

[0056] If the user agrees to the proposal, an instruction to execute the transaction is sent from the terminal to the server.

[0057] Step 7:

[0058] The server confirms consent and executes the transaction. The purchase or sale procedure is carried out via the financial institution's API, and the transaction is completed.

[0059] Step 8:

[0060] The server notifies the user of the completion of a transaction and then monitors the financial markets and the user's asset status. If it determines that new recommendations are necessary in response to market fluctuations, it repeats steps 4 and beyond. This process ensures that the user always receives recommendations based on the latest investment performance.

[0061] (Example 1)

[0062] 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."

[0063] In today's financial markets, a challenge exists in that it is difficult for individual investors to achieve optimized investment strategies and risk management. There is a need to select appropriate investment products that take into account each investor's different asset situation, risk tolerance, and investment objectives, and to respond quickly to market trends in real time. However, traditional systems have struggled to meet such complex needs.

[0064] 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.

[0065] In this invention, the server includes means for acquiring basic user information, information processing means for analyzing the user's asset information and generating a risk profile, means for creating financial product proposals based on the analyzed profile, execution means for trading financial products based on user approval, means for continuously monitoring the user's asset status and presenting new proposals, and means for monitoring market conditions in real time and storing information in a database. This enables the provision of an optimized investment strategy for each individual user and supports efficient asset management and investment decisions based on the user's asset status.

[0066] "Means for obtaining basic user information" refers to a device or method for collecting personal information provided by a user and converting that information into a format usable within the system.

[0067] "Information processing means for generating risk profiles" refers to a processing device or method for analyzing a user's asset information and investment preferences, and based on the results, evaluating each user's risk tolerance and investment objectives to create a profile.

[0068] "Means for creating financial product proposals" refers to a device or method that selects the most suitable financial product for a user based on an analyzed risk profile and market conditions, and generates a proposal based on the selection results.

[0069] "Execution means for conducting financial product transactions" refers to a device or method for actually purchasing or selling selected financial products based on user approval.

[0070] "Means for continuously monitoring asset status and presenting new proposals" refers to a device or method that continuously tracks a user's asset history and market trends, and generates and proposes new investment strategies to the user as needed.

[0071] "Means for monitoring market conditions and storing information in a database" refers to a device or method that acquires financial market fluctuations and related information in real time and records that information in a database, making it available for future analysis and proposals.

[0072] To implement this invention, an advanced information processing system consisting of a server and a terminal is required. The server is equipped with a database system that receives basic information and asset information entered by the user using the terminal and stores it in a secure manner. Specifically, the SSL / TLS protocol is used for transmitting information, and MySQL® or MongoDB is used for the database to ensure secure and consistent data management.

[0073] The server uses AI engines such as TENSORFLOW® and PyTorch to analyze the user's asset information. This allows for the creation of the user's risk profile, which reflects the user's risk tolerance, investment objectives, and investment timeframe.

[0074] Furthermore, the server selects financial products based on the risk profile. Because the algorithm incorporates the latest financial market data in real time, the selected financial products include expected risks and returns. The selection results are sent to the user's terminal and displayed in an easy-to-understand visual format.

[0075] If the user agrees to the proposal, the server executes the transaction with the financial institution via the API interface. This ensures transparent and efficient transactions.

[0076] Furthermore, the server continuously monitors the user's asset status. This allows it to generate new investment suggestions in response to market fluctuations and notify the user. As a result, the user can always maintain the optimal investment strategy.

[0077] As a concrete example, a scenario could be envisioned where a user in their 20s is offered a medium-risk investment trust based on their input information. During market fluctuations, rebalancing to stable bonds would be suggested. Through this process, the user can effectively manage their assets.

[0078] Examples of specific prompts for the generating AI model include, "Based on the asset information entered by a user in their 20s, please suggest a medium-risk investment product," and "Consider market fluctuations and generate advice for rebalancing the user's investment portfolio."

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

[0080] Step 1:

[0081] Users enter their basic and financial information via their device. This information includes age, income, asset details, and investment preferences. The device then transmits this information to the server using a secure communication protocol. For example, SSL / TLS protocol is used to ensure the secure transfer of data.

[0082] Step 2:

[0083] The server stores the received input data in a database. The database management system used is either MySQL or MongoDB. To maintain data consistency, the server assigns a unique identifier to each user to organize the information. As a result, user information is stored and available for subsequent processing.

[0084] Step 3:

[0085] The server uses an AI engine to analyze the user's asset information. This process utilizes machine learning models powered by TensorFlow and PyTorch. The user's asset information is used as input, and a risk profile is generated as output. This profile indicates the user's risk tolerance, investment objectives, and investment timeframe.

[0086] Step 4:

[0087] The server selects the optimal financial instruments based on the generated risk profile. At this stage, an algorithm makes the selection based on real-time data collected from the market. As a result, a list of selected financial instruments and their associated risk and return predictions are created. This information is then organized for the user to receive.

[0088] Step 5:

[0089] The server sends the selected financial product proposal to the terminal. The terminal displays the received information to the user. The user can then use this information to evaluate the proposed financial product in detail.

[0090] Step 6:

[0091] If the user agrees to the proposal, the device sends that information back to the server. The server uses an API interface to coordinate with the corresponding financial institution and execute the transaction. Once the transaction is complete, the server records the transaction results in a database and updates the user's asset status.

[0092] Step 7:

[0093] Subsequently, the server continuously monitors the user's asset status and market trends. It comprehensively analyzes the information in the database and proposes new financial products and investment strategies as needed. The generated new proposals are then notified to the user again via the terminal.

[0094] (Application Example 1)

[0095] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0096] In modern society, it is crucial for individuals to effectively manage their assets while efficiently handling daily expenses. However, many people find it difficult to understand their own asset situation and spending patterns, and to develop optimal investment strategies. Furthermore, the lack of widespread systems that integrate spending and asset management presents a challenge in dynamically optimizing one's assets.

[0097] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0098] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's asset data and consumption data to generate a risk profile, and means for generating suggestions for financial products and asset management plans based on the analysis results. This enables users to dynamically manage their assets and optimize their asset management based on their daily spending data and asset information.

[0099] "User attribute information" refers to data that shows personal characteristics of the user, such as age, income, and investment preferences.

[0100] "Asset data" refers to information about the financial assets owned by the user, including bank deposits, investment trusts, stocks, etc.

[0101] "Consumption data" refers to information about a user's daily spending, including data on living expenses, hobbies, and entertainment.

[0102] A "risk profile" is information compiled as a result of analyzing an individual user's risk tolerance and investment objectives.

[0103] "Analysis results" refer to the results of an analysis performed by AI based on information collected from users, and this data will serve as the basis for future suggestions.

[0104] "Financial products" refer to items such as investment trusts, stocks, and bonds that are traded by users for asset management purposes.

[0105] An "asset management plan" is a plan that outlines a user's asset management and investment strategy, created based on collected and analyzed data.

[0106] "Dynamic asset management" is a management method that aims to monitor the user's asset status and market changes in real time and to allocate assets optimally at that moment.

[0107] In a form for carrying out the invention, this system is implemented based on a terminal, including a smartphone, and a server. The user inputs their attribute information, asset data, and consumption data using the terminal. In this process, the terminal is responsible for transmitting the input information to the server.

[0108] The server uses an advanced AI engine to analyze the collected data. Specifically, it leverages machine learning frameworks such as TensorFlow and PyTorch to generate a unique risk profile for each user. This profile serves as crucial foundational data for the user's asset management plan.

[0109] Furthermore, based on the analysis results, the server generates financial products and asset management plans optimized for the user and delivers the proposals to the terminal. To conduct transactions with financial institutions, secure and efficient communication is achieved using interfaces such as RESTful APIs.

[0110] As a concrete example, a new employee can use the app to register their monthly income and expenses, and the AI ​​will suggest appropriate investment trusts. When a user experiences a life event such as marriage, the system dynamically suggests adjustments to the investment balance in response to increased expenses. In this way, the system enables personalized asset management tailored to the user's lifestyle and market trends.

[0111] Example prompt for a generating AI model: "A user in their 20s working for a company enters their monthly expenses into the app. Based on their current income and savings, please suggest an investment plan suitable for future wealth building."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] Users input attribute information, asset data, and consumption data via their terminal. This input data undergoes basic formatting on the terminal before being sent to the server. The input data is stored in the database as the user's profile information.

[0115] Step 2:

[0116] The server starts analyzing user attribute information, asset data, and consumption data collected from the database using its AI engine. The AI ​​model generates a risk profile using historical training data. This analysis result is output as data showing each user's customized risk tolerance and investment suitability.

[0117] Step 3:

[0118] The server uses the risk profile obtained through analysis as input to generate optimal financial products and asset management plans for each user. This process utilizes predictive models that leverage current market information and historical pattern data. The server delivers the generated proposals to the terminal and presents them to the user. The output takes the form of a specific investment plan or proposal document.

[0119] Step 4:

[0120] Users review the financial products and investment plans presented on their devices and, if they wish to approve them, indicate their approval through the device. This indication is sent to the server and treated as data that triggers the next processing step.

[0121] Step 5:

[0122] The server, upon user authorization, securely and quickly executes financial transactions with financial institutions via API. A transaction completion notification and proof data are generated as output and returned to the user's terminal. Once the transaction is complete, the user can verify that their asset status has been updated.

[0123] Step 6:

[0124] The server continuously monitors the user's assets and market trends, and sends new suggestions to the user in real time if there are significant changes. This monitoring and suggestions are executed at the appropriate time based on a generative AI model. Throughout the entire workflow, an example of a prompt message generated by the server might be, "Please propose an appropriate plan for additional investment to users whose revenue has increased."

[0125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0126] This invention combines a system that suggests appropriate financial products based on a user's basic information and asset information with an emotion engine that recognizes the user's emotions. This system works in conjunction with an AI engine to provide users with a more personalized investment experience.

[0127] Users input their basic and asset information through their device. In addition, an emotion engine analyzes the user's emotions in real time. As a result, the user's current emotional state is incorporated into the system, and the AI ​​engine reflects this emotional data in constructing the risk profile.

[0128] The server uses an AI engine to analyze data, including emotional information, to generate a more detailed user risk profile. This profile is then used to suggest financial products and investment portfolios tailored to the user. By considering the impact of user emotions on risk tolerance, more accurate suggestions can be made.

[0129] If the user reviews and agrees to the proposal, the transaction will be executed based on that agreement. The transaction is executed using an API interface with financial institutions, ensuring a secure and efficient process.

[0130] Furthermore, the server aims to reduce the psychological burden of investment decision-making by providing feedback based on the user's emotions. If market fluctuations cause a change in the user's emotions, the risk profile will be updated based on that, and new recommendations will be made.

[0131] For example, when a user is considering a proposal on their device, if the emotion engine detects the user's anxiety, the server will use this information to suggest lower-risk investment options. Furthermore, if a successful investment experience has positively impacted the user's emotions, this emotion data will be used to improve future proposals. In this way, the system provides investment strategies that take user emotions into account, improving the investment experience.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The user inputs basic and asset information using a device. In addition, an emotion engine uses the device's sensors to collect the user's emotions in real time. This data is then sent to a server.

[0135] Step 2:

[0136] The server stores the received data in a database. The server then activates an AI engine to analyze asset information and sentiment data to generate a user risk profile. This risk profile takes the user's emotional state into account and forms the basis for investment recommendations.

[0137] Step 3:

[0138] Based on the risk profile generated by the server, appropriate financial products and investment portfolios are selected. These recommendations are adjusted based on the user's emotional state. For example, if the emotion engine detects user anxiety, the server prioritizes suggesting safer products. The selection results are sent to the terminal and presented to the user.

[0139] Step 4:

[0140] The user reviews the proposal on their device and uses the system's simulation function to consider the risks and returns. If the user agrees to the proposal, they send a trade execution instruction from their device to the server.

[0141] Step 5:

[0142] Once the server confirms the user's consent, it initiates the process of executing financial instrument transactions. Through an API interface with financial institutions, it quickly and securely completes purchases or sales and reflects the transaction results in the database.

[0143] Step 6:

[0144] The server notifies the user of the completion of a transaction and monitors the user's asset status and market conditions. The sentiment engine continuously detects changes in the user's emotions and dynamically updates the risk profile. This allows the server to send new suggestions to the terminal when necessary. Through this process, the user receives an investment strategy customized to the market and their own emotions.

[0145] (Example 2)

[0146] 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".

[0147] Traditionally, investment experiences for users have relied primarily on objective financial information, failing to reflect individual users' emotional states and resulting in inconsistent investment choices. Furthermore, since risk tolerance changes with user emotions, there is a need for investment recommendations that take this into account.

[0148] 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.

[0149] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's asset information to generate risk characteristics, and means for an emotion analysis unit that analyzes the user's emotional state and reflects the emotional data in the risk characteristics. This makes it possible to provide more accurate investment proposals that take the user's emotional state into consideration.

[0150] "Attribute information" refers to basic personal information about a user, including data such as name, age, gender, and occupation.

[0151] "Asset information" refers to information about a user's financial assets, including total assets, income, and investment history.

[0152] "Risk characteristics" refer to data that indicates a user's risk tolerance and tendencies regarding investments, and this serves as the basis for proposing financial products.

[0153] The "emotion analysis unit" is a part of a device or program that has the function of analyzing the user's emotional state, and evaluates the user's emotions through facial recognition and voice analysis.

[0154] "Emotional data" refers to information that indicates a user's current emotional state and is used as a component of risk characteristics.

[0155] "Artificial intelligence" refers to algorithms or systems that use machine learning and data analysis technologies to perform advanced decision-making and predictions.

[0156] A "programming interface" refers to the rules and protocols used to link data and functions with external software and services, and plays a crucial role in completing transactions.

[0157] This invention is a system that proposes personalized financial products based on the user's attribute information, asset information, and emotional state. This system is implemented using a server, terminals, and an emotional analysis unit.

[0158] The user inputs their personal attribute and asset information through a terminal. This terminal incorporates input / output devices such as a camera and microphone, which the emotion analysis unit uses to collect the user's emotional data and analyze their emotional state in real time. Specifically, the camera is used to analyze facial expressions, and the microphone is used to analyze the intonation of the voice. Based on this, the user's emotional state is determined.

[0159] The server integrates attribute information, asset information, and sentiment data received from the terminal and performs a comprehensive analysis using various artificial intelligence algorithms. During this process, prompt sentences are generated via a generative AI model to aid in the analysis. As a result of the analysis, risk characteristics optimized for the user are generated, and financial products are suggested that match the user's investment tendencies.

[0160] The proposal is displayed on the terminal, and the user reviews its contents. If the user agrees to the proposal, the server communicates with the trading institution via a programming interface in the backend, based on instructions from the terminal, and executes the financial product transaction securely and quickly.

[0161] As a concrete example, if the emotion analysis unit detects anxiety while a user is managing their assets on their device, the server will present investment recommendations with reduced risk. In this process, a prompt such as "If the user is feeling anxious, please provide suggestions to avoid risk" is input to the generating AI model.

[0162] This system allows users to receive investment support that takes their emotions into account, enabling them to make more appropriate and confident investment decisions.

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] Users enter their personal information and asset information using a device. They enter information such as their name, age, occupation, and asset amount into a form displayed on the device screen, and then press the "Submit" button to send the data to the server. Once the input data reaches the server, it is encrypted and stored securely.

[0166] Step 2:

[0167] The emotion analysis unit uses the device's camera and microphone to collect data on the user's emotional state. Specifically, the camera captures facial expression data, which is then used to analyze smiles, serious expressions, and other similar expressions. The microphone analyzes voice tone to assess the user's level of excitement or calmness. This collected data is then analyzed in real time by the emotion analysis unit and transmitted to the server as emotional state data.

[0168] Step 3:

[0169] The server integrates received attribute information, asset information, and emotional state data, and uses a generative AI model to analyze the data. The generative AI model is given instructions such as, "Analyze this user's risk characteristics and generate appropriate investment proposals." Based on these instructions, the AI ​​engine calculates the risk characteristics and outputs an optimized risk profile, taking into account the correlation of each data item and the emotional state.

[0170] Step 4:

[0171] The server creates a list of financial products optimized for the user based on the generated risk profile. In this process, the AI ​​engine refers to market data and past investment examples to list products that match the asset allocation and risk level. The generating AI model then concretizes the proposal based on the prompt "Suggest high-safety investment options."

[0172] Step 5:

[0173] The proposed financial product is displayed on the terminal, and the user reviews its contents. If the user agrees to the proposal, they press the "Approve" button. Upon approval, the terminal sends consent data to the server, which then uses this information to initiate communication with the trading institution via a programming interface. Finally, the transaction of the financial product is completed through a secure process.

[0174] (Application Example 2)

[0175] 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".

[0176] In modern financial services, users sometimes make irrational investment decisions due to emotional factors. This increases the risk of disappointing investment results. On the other hand, because there are no suggestions that reflect users' emotions, it is difficult to provide users with a sufficiently personalized investment experience. This challenge needs to be addressed.

[0177] 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.

[0178] In this invention, the server includes means for analyzing the user's emotional information in real time and generating emotional data, means for optimizing the suggested content using the emotional data, and means for providing feedback based on the user's emotions. This makes it possible to suggest financial products that take the user's emotional state into consideration and to reduce the psychological burden in investment decision-making.

[0179] "User basic information" refers to personally identifiable information about the user, such as name, age, and address.

[0180] "Asset information" refers to financial data, including financial assets and liabilities, that a user owns.

[0181] A "risk profile" is data that indicates a user's risk tolerance in their investments.

[0182] "Emotional information" refers to data that indicates the user's emotional state and is analyzed in real time.

[0183] "Emotional data" refers to numerical data generated from a user's emotional information.

[0184] "Proposed content" refers to information about financial products and investment portfolios presented to the user.

[0185] "Feedback" refers to information and advice provided based on a user's behavior and emotional state.

[0186] An "API interface" is a standardized connection method for communication between different systems.

[0187] An "AI engine" is a system that analyzes data based on artificial intelligence and generates personalized suggestions.

[0188] To implement this invention, the process begins with the user providing basic and asset information using a mobile device. The user is required to provide their emotional information in real time using the camera and microphone of their smart device. This emotional information is analyzed by emotion analysis software such as Affectiva or Microsoft® Azure® Emotion API, and quantified emotional data is generated.

[0189] Upon receiving this information, the server first uses an AI engine to generate a user risk profile. This AI engine leverages machine learning frameworks such as TensorFlow and PyTorch to analyze asset information and sentiment data. As a result, the user's risk tolerance in investments is quantified.

[0190] Next, the server generates recommendations. These recommendations are optimized based on the user's risk profile and emotional data, suggesting financial products and investment portfolios that are optimized for the user. This process can improve the probability of investment success by taking the user's emotional state into account.

[0191] Furthermore, integration with financial institutions is possible via an API interface, and if the user agrees to the proposed terms, the transaction can be automatically executed based on that agreement. By utilizing existing payment solutions such as Stripe and PayPal APIs through this API interface, fast and secure transactions can be achieved.

[0192] For example, if the system determines that a user is feeling down, the server will present low-risk investment options. Furthermore, if a positive emotional shift resulting from a successful investment is detected, this will be reflected in the user's profile, improving future recommendations.

[0193] A good example of a prompt for a generative AI model would be a question like, "What approaches would be effective in encouraging a customer to make a purchase when they are feeling stressed? Please provide an example."

[0194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0195] Step 1:

[0196] Users input basic and asset information using their mobile devices. This input data, including the user's personal identification information and financial information, is sent to the server. The server receives this information and stores it in a database.

[0197] Step 2:

[0198] The device uses its camera and microphone to collect real-time emotional data from the user. The collected emotional information is analyzed through Affectiva or the Microsoft Azure Emotion API and passed to the server as quantified emotional data.

[0199] Step 3:

[0200] The server uses an AI engine to integrate basic information, asset information, and sentiment data to generate a user risk profile. Analysis is performed using machine learning frameworks such as TensorFlow and PyTorch, which are employed by the AI ​​engine, and the resulting output is a numerical risk tolerance score.

[0201] Step 4:

[0202] The server presents the user with optimized recommendations based on the generated risk profile and sentiment data. These recommendations, which include recommendations for financial products and investment portfolios, aim to maximize user safety and satisfaction.

[0203] Step 5:

[0204] If the user agrees to the presented proposal, the device sends that agreement to the server. Based on this agreement, the server uses an API interface to execute a transaction with financial institutions with which the system is integrated. Payment services such as Stripe and PayPal are used as APIs here, ensuring fast and secure transactions.

[0205] Step 6:

[0206] The server re-analyzes the user's emotional changes after the transaction is completed, uses a generative AI model to prepare prompt messages, and provides the user with emotional feedback on their investment experience. This allows the user to emotionally reflect on their investment decisions, and the feedback is reflected in future suggestions.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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".

[0223] This invention is an AI-powered system that enables users to effectively manage their assets and make investments. The system consists of server and terminal components, and seamlessly facilitates the suggestion and trading of financial products by the user.

[0224] The user first enters their basic information and asset information using a terminal. Information such as age, income, asset details, and investment preferences is sent to the server. The server receives this information and stores it in a database.

[0225] Next, the server analyzes this data using an AI engine to create a user risk profile. This profile details the user's risk tolerance, investment objectives, and investment timeframe, forming the basis for future recommendations.

[0226] Based on the analysis, the server selects the most suitable financial product for the user and generates a proposal. This proposal is presented to the user via their terminal. The proposal includes information on the selected financial product, as well as expected risks and returns. The user can then use this information to make a trading decision.

[0227] If a user agrees to a proposal and indicates their intention to proceed with a transaction, the server will quickly execute the purchase or sale of financial products. Transactions with financial institutions are conducted via an API interface, ensuring secure and efficient data communication.

[0228] This system also continuously monitors the user's asset status and generates new suggestions in response to market trends and fluctuations. This allows users to constantly optimize their asset management and investment strategies to suit their current situation.

[0229] As a concrete example, a user in their mid-20s registers with the system and inputs their current savings and investment experience, after which the AI ​​suggests a medium-risk investment trust. Subsequently, if investment conditions change due to market fluctuations, the server suggests rebalancing to stable bonds, and if the user agrees, the transaction is executed immediately. Through this entire process, users can effectively manage their assets and enjoy optimized investments.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] The user accesses the device and enters basic and asset information. This includes age, income, existing assets, investment experience, and goals. The device then sends this information to the server.

[0233] Step 2:

[0234] The server records the information it receives in a database. Furthermore, if additional information is needed from financial institutions, it is obtained via API. This allows for a comprehensive understanding of the user's asset status.

[0235] Step 3:

[0236] The server activates the AI ​​engine to analyze the data. The AI ​​generates a risk profile considering the user's risk tolerance, investment objectives, and time goals. This profile is then used to make subsequent recommendations.

[0237] Step 4:

[0238] The server analyzes market data and financial product information based on the risk profile and selects recommended financial products and investment strategies for the user. The selection results are sent to the terminal and displayed to the user.

[0239] Step 5:

[0240] The user reviews the proposal through their device. The proposal includes details about the financial product, risk level, expected return, and fees. Based on this, the user decides whether or not to proceed with the transaction.

[0241] Step 6:

[0242] If the user agrees to the proposal, an instruction to execute the transaction is sent from the terminal to the server.

[0243] Step 7:

[0244] The server confirms consent and executes the transaction. The purchase or sale procedure is carried out via the financial institution's API, and the transaction is completed.

[0245] Step 8:

[0246] The server notifies the user of the completion of a transaction and then monitors the financial markets and the user's asset status. If it determines that new recommendations are necessary in response to market fluctuations, it repeats steps 4 and beyond. This process ensures that the user always receives recommendations based on the latest investment performance.

[0247] (Example 1)

[0248] 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."

[0249] In today's financial markets, a challenge exists in that it is difficult for individual investors to achieve optimized investment strategies and risk management. There is a need to select appropriate investment products that take into account each investor's different asset situation, risk tolerance, and investment objectives, and to respond quickly to market trends in real time. However, traditional systems have struggled to meet such complex needs.

[0250] 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.

[0251] In this invention, the server includes means for acquiring basic user information, information processing means for analyzing the user's asset information and generating a risk profile, means for creating financial product proposals based on the analyzed profile, execution means for trading financial products based on user approval, means for continuously monitoring the user's asset status and presenting new proposals, and means for monitoring market conditions in real time and storing information in a database. This enables the provision of an optimized investment strategy for each individual user and supports efficient asset management and investment decisions based on the user's asset status.

[0252] "Means for obtaining basic user information" refers to a device or method for collecting personal information provided by a user and converting that information into a format usable within the system.

[0253] "Information processing means for generating risk profiles" refers to a processing device or method for analyzing a user's asset information and investment preferences, and based on the results, evaluating each user's risk tolerance and investment objectives to create a profile.

[0254] "Means for creating financial product proposals" refers to a device or method that selects the most suitable financial product for a user based on an analyzed risk profile and market conditions, and generates a proposal based on the selection results.

[0255] "Execution means for conducting financial product transactions" refers to a device or method for actually purchasing or selling selected financial products based on user approval.

[0256] "Means for continuously monitoring asset status and presenting new proposals" refers to a device or method that continuously tracks a user's asset history and market trends, and generates and proposes new investment strategies to the user as needed.

[0257] "Means for monitoring market conditions and storing information in a database" refers to a device or method that acquires financial market fluctuations and related information in real time and records that information in a database, making it available for future analysis and proposals.

[0258] To implement this invention, an advanced information processing system consisting of a server and a terminal is required. The server has a database system that receives basic information and asset information entered by the user using the terminal and stores it in a secure manner. Specifically, secure and consistent data management is achieved by using the SSL / TLS protocol for information transmission and MySQL or MongoDB for the database.

[0259] The server uses AI engines such as TensorFlow and PyTorch to analyze the user's asset information. This allows it to create a user risk profile, which reflects the user's risk tolerance, investment objectives, and investment timeframe.

[0260] Furthermore, the server selects financial products based on the risk profile. Because the algorithm incorporates the latest financial market data in real time, the selected financial products include expected risks and returns. The selection results are sent to the user's terminal and displayed in an easy-to-understand visual format.

[0261] If the user agrees to the proposal, the server executes the transaction with the financial institution via the API interface. This ensures transparent and efficient transactions.

[0262] Furthermore, the server continuously monitors the user's asset status. This allows it to generate new investment suggestions in response to market fluctuations and notify the user. As a result, the user can always maintain the optimal investment strategy.

[0263] As a concrete example, a scenario could be envisioned where a user in their 20s is offered a medium-risk investment trust based on their input information. During market fluctuations, rebalancing to stable bonds would be suggested. Through this process, the user can effectively manage their assets.

[0264] Examples of specific prompts for the generating AI model include, "Based on the asset information entered by a user in their 20s, please suggest a medium-risk investment product," and "Consider market fluctuations and generate advice for rebalancing the user's investment portfolio."

[0265] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0266] Step 1:

[0267] Users enter their basic and financial information via their device. This information includes age, income, asset details, and investment preferences. The device then transmits this information to the server using a secure communication protocol. For example, SSL / TLS protocol is used to ensure the secure transfer of data.

[0268] Step 2:

[0269] The server stores the received input data in a database. The database management system used is either MySQL or MongoDB. To maintain data consistency, the server assigns a unique identifier to each user to organize the information. As a result, user information is stored and available for subsequent processing.

[0270] Step 3:

[0271] The server uses an AI engine to analyze the user's asset information. This process utilizes machine learning models powered by TensorFlow and PyTorch. The user's asset information is used as input, and a risk profile is generated as output. This profile indicates the user's risk tolerance, investment objectives, and investment timeframe.

[0272] Step 4:

[0273] The server selects the optimal financial instruments based on the generated risk profile. At this stage, an algorithm makes the selection based on real-time data collected from the market. As a result, a list of selected financial instruments and their associated risk and return predictions are created. This information is then organized for the user to receive.

[0274] Step 5:

[0275] The server sends the selected financial product proposal to the terminal. The terminal displays the received information to the user. The user can then use this information to evaluate the proposed financial product in detail.

[0276] Step 6:

[0277] If the user agrees to the proposal, the device sends that information back to the server. The server uses an API interface to coordinate with the corresponding financial institution and execute the transaction. Once the transaction is complete, the server records the transaction results in a database and updates the user's asset status.

[0278] Step 7:

[0279] Subsequently, the server continuously monitors the user's asset status and market trends. It comprehensively analyzes the information in the database and proposes new financial products and investment strategies as needed. The generated new proposals are then notified to the user again via the terminal.

[0280] (Application Example 1)

[0281] 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."

[0282] In modern society, it is crucial for individuals to effectively manage their assets while efficiently handling daily expenses. However, many people find it difficult to understand their own asset situation and spending patterns, and to develop optimal investment strategies. Furthermore, the lack of widespread systems that integrate spending and asset management presents a challenge in dynamically optimizing one's assets.

[0283] 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.

[0284] In this invention, the server includes means for collecting the user's attribute information, means for analyzing the user's asset data and consumption data to generate a risk profile, and means for generating proposals for financial products and asset management plans based on the analysis results. As a result, the user can optimize dynamic asset management and asset allocation based on daily expenditure data and asset information.

[0285] The "user's attribute information" refers to data indicating personal characteristics of the user, such as age, income, and investment orientation.

[0286] The "asset data" refers to information on the financial assets owned by the user, including bank deposits, investment trusts, stocks, etc.

[0287] The "consumption data" refers to information on the user's daily expenditures, including expenditure data related to living expenses, hobbies, and entertainment.

[0288] The "risk profile" is information compiled as a result of analyzing the user's individual risk tolerance and investment objectives for investment.

[0289] The "analysis result" is the result of analysis performed by AI based on the information collected from the user, and is data that serves as the basis for future proposals.

[0290] The "financial product" refers to products such as investment trusts, stocks, and bonds that are traded for the user to conduct asset management.

[0291] The "asset management plan" is a plan indicating the user's asset management and investment policies created based on the collected and analyzed data.

[0292] "Dynamic asset management" is a management method aimed at monitoring the user's asset status and market changes in real time and performing optimal asset allocation at that time.

[0293] In a form for carrying out the invention, this system is implemented based on a terminal, including a smartphone, and a server. The user inputs their attribute information, asset data, and consumption data using the terminal. In this process, the terminal is responsible for transmitting the input information to the server.

[0294] The server uses an advanced AI engine to analyze the collected data. Specifically, it leverages machine learning frameworks such as TensorFlow and PyTorch to generate a unique risk profile for each user. This profile serves as crucial foundational data for the user's asset management plan.

[0295] Furthermore, based on the analysis results, the server generates financial products and asset management plans optimized for the user and delivers the proposals to the terminal. To conduct transactions with financial institutions, secure and efficient communication is achieved using interfaces such as RESTful APIs.

[0296] As a concrete example, a new employee can use the app to register their monthly income and expenses, and the AI ​​will suggest appropriate investment trusts. When a user experiences a life event such as marriage, the system dynamically suggests adjustments to the investment balance in response to increased expenses. In this way, the system enables personalized asset management tailored to the user's lifestyle and market trends.

[0297] Example prompt for a generating AI model: "A user in their 20s working for a company enters their monthly expenses into the app. Based on their current income and savings, please suggest an investment plan suitable for future wealth building."

[0298] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0299] Step 1:

[0300] The user inputs attribute information, asset data, and consumption data via the terminal. After basic formatting processing is performed on the terminal side, these input data are sent to the server. The input data are stored in the database as the user's profile information.

[0301] Step 2:

[0302] The server starts analyzing the user's attribute information, asset data, and consumption data collected from the database using the AI engine as input. The AI model generates a risk profile using past learning data. The analysis results are output as data indicating the customized risk tolerance and investment suitability for each user.

[0303] Step 3:

[0304] Using the risk profile obtained by analysis as input, the server generates an optimal financial product and asset management plan for each user. In this process, a prediction model that utilizes current market information and past pattern data is used. The server distributes the generated proposal to the terminal and presents it to the user. The output is in the form of a specific investment plan or proposal document.

[0305] Step 4:

[0306] The user checks the financial products and asset management plans presented on the terminal and, if approving, makes an approval indication through the terminal. This indication is sent to the server and treated as data that triggers the progress to the next processing step.

[0307] Step 5:

[0308] Upon receiving the user's approval, the server securely and quickly executes a financial transaction with the financial institution through the API. As output, a transaction completion notice and certification data are generated and returned to the user's terminal. Once the transaction is completed, the user can confirm that their asset status has been updated.

[0309] Step 6:

[0310] The server continuously monitors the user's assets and market trends, and sends new suggestions to the user in real time if there are significant changes. This monitoring and suggestions are executed at the appropriate time based on a generative AI model. Throughout the entire workflow, an example of a prompt message generated by the server might be, "Please propose an appropriate plan for additional investment to users whose revenue has increased."

[0311] 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.

[0312] This invention combines a system that suggests appropriate financial products based on a user's basic information and asset information with an emotion engine that recognizes the user's emotions. This system works in conjunction with an AI engine to provide users with a more personalized investment experience.

[0313] Users input their basic and asset information through their device. In addition, an emotion engine analyzes the user's emotions in real time. As a result, the user's current emotional state is incorporated into the system, and the AI ​​engine reflects this emotional data in constructing the risk profile.

[0314] The server uses an AI engine to analyze data, including emotional information, to generate a more detailed user risk profile. This profile is then used to suggest financial products and investment portfolios tailored to the user. By considering the impact of user emotions on risk tolerance, more accurate suggestions can be made.

[0315] If the user reviews and agrees to the proposal, the transaction will be executed based on that agreement. The transaction is executed using an API interface with financial institutions, ensuring a secure and efficient process.

[0316] Furthermore, the server aims to reduce the psychological burden of investment decision-making by providing feedback based on the user's emotions. If market fluctuations cause a change in the user's emotions, the risk profile will be updated based on that, and new recommendations will be made.

[0317] For example, when a user is considering a proposal on their device, if the emotion engine detects the user's anxiety, the server will use this information to suggest lower-risk investment options. Furthermore, if a successful investment experience has positively impacted the user's emotions, this emotion data will be used to improve future proposals. In this way, the system provides investment strategies that take user emotions into account, improving the investment experience.

[0318] The following describes the processing flow.

[0319] Step 1:

[0320] The user inputs basic and asset information using a device. In addition, an emotion engine uses the device's sensors to collect the user's emotions in real time. This data is then sent to a server.

[0321] Step 2:

[0322] The server stores the received data in a database. The server then activates an AI engine to analyze asset information and sentiment data to generate a user risk profile. This risk profile takes the user's emotional state into account and forms the basis for investment recommendations.

[0323] Step 3:

[0324] Based on the risk profile generated by the server, appropriate financial products and investment portfolios are selected. These recommendations are adjusted based on the user's emotional state. For example, if the emotion engine detects user anxiety, the server prioritizes suggesting safer products. The selection results are sent to the terminal and presented to the user.

[0325] Step 4:

[0326] The user reviews the proposal on their device and uses the system's simulation function to consider the risks and returns. If the user agrees to the proposal, they send a trade execution instruction from their device to the server.

[0327] Step 5:

[0328] Once the server confirms the user's consent, it initiates the process of executing financial instrument transactions. Through an API interface with financial institutions, it quickly and securely completes purchases or sales and reflects the transaction results in the database.

[0329] Step 6:

[0330] The server notifies the user of the completion of a transaction and monitors the user's asset status and market conditions. The sentiment engine continuously detects changes in the user's emotions and dynamically updates the risk profile. This allows the server to send new suggestions to the terminal when necessary. Through this process, the user receives an investment strategy customized to the market and their own emotions.

[0331] (Example 2)

[0332] 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".

[0333] Traditionally, investment experiences for users have relied primarily on objective financial information, failing to reflect individual users' emotional states and resulting in inconsistent investment choices. Furthermore, since risk tolerance changes with user emotions, there is a need for investment recommendations that take this into account.

[0334] 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.

[0335] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's asset information to generate risk characteristics, and means for an emotion analysis unit that analyzes the user's emotional state and reflects the emotional data in the risk characteristics. This makes it possible to provide more accurate investment proposals that take the user's emotional state into consideration.

[0336] "Attribute information" refers to basic personal information about a user, including data such as name, age, gender, and occupation.

[0337] "Asset information" refers to information about a user's financial assets, including total assets, income, and investment history.

[0338] "Risk characteristics" refer to data that indicates a user's risk tolerance and tendencies regarding investments, and this serves as the basis for proposing financial products.

[0339] The "emotion analysis unit" is a part of a device or program that has the function of analyzing the user's emotional state, and evaluates the user's emotions through facial recognition and voice analysis.

[0340] "Emotional data" refers to information that indicates a user's current emotional state and is used as a component of risk characteristics.

[0341] "Artificial intelligence" refers to algorithms or systems that use machine learning and data analysis technologies to perform advanced decision-making and predictions.

[0342] A "programming interface" refers to the rules and protocols used to link data and functions with external software and services, and plays a crucial role in completing transactions.

[0343] This invention is a system that proposes personalized financial products based on the user's attribute information, asset information, and emotional state. This system is implemented using a server, terminals, and an emotional analysis unit.

[0344] The user inputs their personal attribute and asset information through a terminal. This terminal incorporates input / output devices such as a camera and microphone, which the emotion analysis unit uses to collect the user's emotional data and analyze their emotional state in real time. Specifically, the camera is used to analyze facial expressions, and the microphone is used to analyze the intonation of the voice. Based on this, the user's emotional state is determined.

[0345] The server integrates attribute information, asset information, and sentiment data received from the terminal and performs a comprehensive analysis using various artificial intelligence algorithms. During this process, prompt sentences are generated via a generative AI model to aid in the analysis. As a result of the analysis, risk characteristics optimized for the user are generated, and financial products are suggested that match the user's investment tendencies.

[0346] The proposal is displayed on the terminal, and the user reviews its contents. If the user agrees to the proposal, the server communicates with the trading institution via a programming interface in the backend, based on instructions from the terminal, and executes the financial product transaction securely and quickly.

[0347] As a concrete example, if the emotion analysis unit detects anxiety while a user is managing their assets on their device, the server will present investment recommendations with reduced risk. In this process, a prompt such as "If the user is feeling anxious, please provide suggestions to avoid risk" is input to the generating AI model.

[0348] This system allows users to receive investment support that takes their emotions into account, enabling them to make more appropriate and confident investment decisions.

[0349] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0350] Step 1:

[0351] Users enter their personal information and asset information using a device. They enter information such as their name, age, occupation, and asset amount into a form displayed on the device screen, and then press the "Submit" button to send the data to the server. Once the input data reaches the server, it is encrypted and stored securely.

[0352] Step 2:

[0353] The emotion analysis unit uses the device's camera and microphone to collect data on the user's emotional state. Specifically, the camera captures facial expression data, which is then used to analyze smiles, serious expressions, and other similar expressions. The microphone analyzes voice tone to assess the user's level of excitement or calmness. This collected data is then analyzed in real time by the emotion analysis unit and transmitted to the server as emotional state data.

[0354] Step 3:

[0355] The server integrates received attribute information, asset information, and emotional state data, and uses a generative AI model to analyze the data. The generative AI model is given instructions such as, "Analyze this user's risk characteristics and generate appropriate investment proposals." Based on these instructions, the AI ​​engine calculates the risk characteristics and outputs an optimized risk profile, taking into account the correlation of each data item and the emotional state.

[0356] Step 4:

[0357] The server creates a list of financial products optimized for the user based on the generated risk profile. In this process, the AI ​​engine refers to market data and past investment examples to list products that match the asset allocation and risk level. The generating AI model then concretizes the proposal based on the prompt "Suggest high-safety investment options."

[0358] Step 5:

[0359] The proposed financial product is displayed on the terminal, and the user reviews its contents. If the user agrees to the proposal, they press the "Approve" button. Upon approval, the terminal sends consent data to the server, which then uses this information to initiate communication with the trading institution via a programming interface. Finally, the transaction of the financial product is completed through a secure process.

[0360] (Application Example 2)

[0361] 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."

[0362] In modern financial services, users sometimes make irrational investment decisions due to emotional factors. This increases the risk of disappointing investment results. On the other hand, because there are no suggestions that reflect users' emotions, it is difficult to provide users with a sufficiently personalized investment experience. This challenge needs to be addressed.

[0363] 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.

[0364] In this invention, the server includes means for analyzing the user's emotional information in real time and generating emotional data, means for optimizing the suggested content using the emotional data, and means for providing feedback based on the user's emotions. This makes it possible to suggest financial products that take the user's emotional state into consideration and to reduce the psychological burden in investment decision-making.

[0365] "User basic information" refers to personally identifiable information about the user, such as name, age, and address.

[0366] "Asset information" refers to financial data, including financial assets and liabilities, that a user owns.

[0367] A "risk profile" is data that indicates a user's risk tolerance in their investments.

[0368] "Emotional information" refers to data that indicates the user's emotional state and is analyzed in real time.

[0369] "Emotional data" refers to numerical data generated from a user's emotional information.

[0370] "Proposed content" refers to information about financial products and investment portfolios presented to the user.

[0371] "Feedback" refers to information and advice provided based on a user's behavior and emotional state.

[0372] An "API interface" is a standardized connection method for communication between different systems.

[0373] An "AI engine" is a system that analyzes data based on artificial intelligence and generates personalized suggestions.

[0374] To implement this invention, the process begins with the user providing basic and asset information using a mobile device. The user is required to provide their emotional information in real time using the camera and microphone of their smart device. This emotional information is analyzed by emotion analysis software, such as Affectiva or Microsoft Azure Emotion API, to generate quantified emotional data.

[0375] Upon receiving this information, the server first uses an AI engine to generate a user risk profile. This AI engine leverages machine learning frameworks such as TensorFlow and PyTorch to analyze asset information and sentiment data. As a result, the user's risk tolerance in investments is quantified.

[0376] Next, the server generates recommendations. These recommendations are optimized based on the user's risk profile and emotional data, suggesting financial products and investment portfolios that are optimized for the user. This process can improve the probability of investment success by taking the user's emotional state into account.

[0377] Furthermore, integration with financial institutions is possible via an API interface, and if the user agrees to the proposed terms, the transaction can be automatically executed based on that agreement. By utilizing existing payment solutions such as Stripe and PayPal APIs through this API interface, fast and secure transactions can be achieved.

[0378] For example, if the system determines that a user is feeling down, the server will present low-risk investment options. Furthermore, if a positive emotional shift resulting from a successful investment is detected, this will be reflected in the user's profile, improving future recommendations.

[0379] A good example of a prompt for a generative AI model would be a question like, "What approaches would be effective in encouraging a customer to make a purchase when they are feeling stressed? Please provide an example."

[0380] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0381] Step 1:

[0382] Users input basic and asset information using their mobile devices. This input data, including the user's personal identification information and financial information, is sent to the server. The server receives this information and stores it in a database.

[0383] Step 2:

[0384] The device uses its camera and microphone to collect real-time emotional data from the user. The collected emotional information is analyzed through Affectiva or the Microsoft Azure Emotion API and passed to the server as quantified emotional data.

[0385] Step 3:

[0386] The server uses an AI engine to integrate basic information, asset information, and sentiment data to generate a user risk profile. Analysis is performed using machine learning frameworks such as TensorFlow and PyTorch, which are employed by the AI ​​engine, and the resulting output is a numerical risk tolerance score.

[0387] Step 4:

[0388] The server presents the user with optimized recommendations based on the generated risk profile and sentiment data. These recommendations, which include recommendations for financial products and investment portfolios, aim to maximize user safety and satisfaction.

[0389] Step 5:

[0390] If the user agrees to the presented proposal, the device sends that agreement to the server. Based on this agreement, the server uses an API interface to execute a transaction with financial institutions with which the system is integrated. Payment services such as Stripe and PayPal are used as APIs here, ensuring fast and secure transactions.

[0391] Step 6:

[0392] The server re-analyzes the user's emotional changes after the transaction is completed, uses a generative AI model to prepare prompt messages, and provides the user with emotional feedback on their investment experience. This allows the user to emotionally reflect on their investment decisions, and the feedback is reflected in future suggestions.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] [Third Embodiment]

[0397] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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".

[0409] This invention is an AI-powered system that enables users to effectively manage their assets and make investments. The system consists of server and terminal components, and seamlessly facilitates the suggestion and trading of financial products by the user.

[0410] The user first enters their basic information and asset information using a terminal. Information such as age, income, asset details, and investment preferences is sent to the server. The server receives this information and stores it in a database.

[0411] Next, the server analyzes this data using an AI engine to create a user risk profile. This profile details the user's risk tolerance, investment objectives, and investment timeframe, forming the basis for future recommendations.

[0412] Based on the analysis, the server selects the most suitable financial product for the user and generates a proposal. This proposal is presented to the user via their terminal. The proposal includes information on the selected financial product, as well as expected risks and returns. The user can then use this information to make a trading decision.

[0413] If a user agrees to a proposal and indicates their intention to proceed with a transaction, the server will quickly execute the purchase or sale of financial products. Transactions with financial institutions are conducted via an API interface, ensuring secure and efficient data communication.

[0414] This system also continuously monitors the user's asset status and generates new suggestions in response to market trends and fluctuations. This allows users to constantly optimize their asset management and investment strategies to suit their current situation.

[0415] As a concrete example, a user in their mid-20s registers with the system and inputs their current savings and investment experience, after which the AI ​​suggests a medium-risk investment trust. Subsequently, if investment conditions change due to market fluctuations, the server suggests rebalancing to stable bonds, and if the user agrees, the transaction is executed immediately. Through this entire process, users can effectively manage their assets and enjoy optimized investments.

[0416] The following describes the processing flow.

[0417] Step 1:

[0418] The user accesses the device and enters basic and asset information. This includes age, income, existing assets, investment experience, and goals. The device then sends this information to the server.

[0419] Step 2:

[0420] The server records the information it receives in a database. Furthermore, if additional information is needed from financial institutions, it is obtained via API. This allows for a comprehensive understanding of the user's asset status.

[0421] Step 3:

[0422] The server activates the AI ​​engine to analyze the data. The AI ​​generates a risk profile considering the user's risk tolerance, investment objectives, and time goals. This profile is then used to make subsequent recommendations.

[0423] Step 4:

[0424] The server analyzes market data and financial product information based on the risk profile and selects recommended financial products and investment strategies for the user. The selection results are sent to the terminal and displayed to the user.

[0425] Step 5:

[0426] The user reviews the proposal through their device. The proposal includes details about the financial product, risk level, expected return, and fees. Based on this, the user decides whether or not to proceed with the transaction.

[0427] Step 6:

[0428] If the user agrees to the proposal, an instruction to execute the transaction is sent from the terminal to the server.

[0429] Step 7:

[0430] The server confirms consent and executes the transaction. The purchase or sale procedure is carried out via the financial institution's API, and the transaction is completed.

[0431] Step 8:

[0432] The server notifies the user of the completion of a transaction and then monitors the financial markets and the user's asset status. If it determines that new recommendations are necessary in response to market fluctuations, it repeats steps 4 and beyond. This process ensures that the user always receives recommendations based on the latest investment performance.

[0433] (Example 1)

[0434] 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."

[0435] In today's financial markets, a challenge exists in that it is difficult for individual investors to achieve optimized investment strategies and risk management. There is a need to select appropriate investment products that take into account each investor's different asset situation, risk tolerance, and investment objectives, and to respond quickly to market trends in real time. However, traditional systems have struggled to meet such complex needs.

[0436] 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.

[0437] In this invention, the server includes means for acquiring basic user information, information processing means for analyzing the user's asset information and generating a risk profile, means for creating financial product proposals based on the analyzed profile, execution means for trading financial products based on user approval, means for continuously monitoring the user's asset status and presenting new proposals, and means for monitoring market conditions in real time and storing information in a database. This enables the provision of an optimized investment strategy for each individual user and supports efficient asset management and investment decisions based on the user's asset status.

[0438] "Means for obtaining basic user information" refers to a device or method for collecting personal information provided by a user and converting that information into a format usable within the system.

[0439] "Information processing means for generating risk profiles" refers to a processing device or method for analyzing a user's asset information and investment preferences, and based on the results, evaluating each user's risk tolerance and investment objectives to create a profile.

[0440] "Means for creating financial product proposals" refers to a device or method that selects the most suitable financial product for a user based on an analyzed risk profile and market conditions, and generates a proposal based on the selection results.

[0441] "Execution means for conducting financial product transactions" refers to a device or method for actually purchasing or selling selected financial products based on user approval.

[0442] "Means for continuously monitoring asset status and presenting new proposals" refers to a device or method that continuously tracks a user's asset history and market trends, and generates and proposes new investment strategies to the user as needed.

[0443] "Means for monitoring market conditions and storing information in a database" refers to a device or method that acquires financial market fluctuations and related information in real time and records that information in a database, making it available for future analysis and proposals.

[0444] To implement this invention, an advanced information processing system consisting of a server and a terminal is required. The server has a database system that receives basic information and asset information entered by the user using the terminal and stores it in a secure manner. Specifically, secure and consistent data management is achieved by using the SSL / TLS protocol for information transmission and MySQL or MongoDB for the database.

[0445] The server uses AI engines such as TensorFlow and PyTorch to analyze the user's asset information. This allows it to create a user risk profile, which reflects the user's risk tolerance, investment objectives, and investment timeframe.

[0446] Furthermore, the server selects financial products based on the risk profile. Because the algorithm incorporates the latest financial market data in real time, the selected financial products include expected risks and returns. The selection results are sent to the user's terminal and displayed in an easy-to-understand visual format.

[0447] If the user agrees to the proposal, the server executes the transaction with the financial institution via the API interface. This ensures transparent and efficient transactions.

[0448] Furthermore, the server continuously monitors the user's asset status. This allows it to generate new investment suggestions in response to market fluctuations and notify the user. As a result, the user can always maintain the optimal investment strategy.

[0449] As a concrete example, a scenario could be envisioned where a user in their 20s is offered a medium-risk investment trust based on their input information. During market fluctuations, rebalancing to stable bonds would be suggested. Through this process, the user can effectively manage their assets.

[0450] Examples of specific prompts for the generating AI model include, "Based on the asset information entered by a user in their 20s, please suggest a medium-risk investment product," and "Consider market fluctuations and generate advice for rebalancing the user's investment portfolio."

[0451] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0452] Step 1:

[0453] Users enter their basic and financial information via their device. This information includes age, income, asset details, and investment preferences. The device then transmits this information to the server using a secure communication protocol. For example, SSL / TLS protocol is used to ensure the secure transfer of data.

[0454] Step 2:

[0455] The server stores the received input data in a database. The database management system used is either MySQL or MongoDB. To maintain data consistency, the server assigns a unique identifier to each user to organize the information. As a result, user information is stored and available for subsequent processing.

[0456] Step 3:

[0457] The server uses an AI engine to analyze the user's asset information. This process utilizes machine learning models powered by TensorFlow and PyTorch. The user's asset information is used as input, and a risk profile is generated as output. This profile indicates the user's risk tolerance, investment objectives, and investment timeframe.

[0458] Step 4:

[0459] The server selects the optimal financial instruments based on the generated risk profile. At this stage, an algorithm makes the selection based on real-time data collected from the market. As a result, a list of selected financial instruments and their associated risk and return predictions are created. This information is then organized for the user to receive.

[0460] Step 5:

[0461] The server sends the selected financial product proposal to the terminal. The terminal displays the received information to the user. The user can then use this information to evaluate the proposed financial product in detail.

[0462] Step 6:

[0463] If the user agrees to the proposal, the device sends that information back to the server. The server uses an API interface to coordinate with the corresponding financial institution and execute the transaction. Once the transaction is complete, the server records the transaction results in a database and updates the user's asset status.

[0464] Step 7:

[0465] Subsequently, the server continuously monitors the user's asset status and market trends. It comprehensively analyzes the information in the database and proposes new financial products and investment strategies as needed. The generated new proposals are then notified to the user again via the terminal.

[0466] (Application Example 1)

[0467] 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."

[0468] In modern society, it is crucial for individuals to effectively manage their assets while efficiently handling daily expenses. However, many people find it difficult to understand their own asset situation and spending patterns, and to develop optimal investment strategies. Furthermore, the lack of widespread systems that integrate spending and asset management presents a challenge in dynamically optimizing one's assets.

[0469] 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.

[0470] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's asset data and consumption data to generate a risk profile, and means for generating suggestions for financial products and asset management plans based on the analysis results. This enables users to dynamically manage their assets and optimize their asset management based on their daily spending data and asset information.

[0471] "User attribute information" refers to data that shows personal characteristics of the user, such as age, income, and investment preferences.

[0472] "Asset data" refers to information about the financial assets owned by the user, including bank deposits, investment trusts, stocks, etc.

[0473] "Consumption data" refers to information about a user's daily spending, including data on living expenses, hobbies, and entertainment.

[0474] A "risk profile" is information compiled as a result of analyzing an individual user's risk tolerance and investment objectives.

[0475] "Analysis results" refer to the results of an analysis performed by AI based on information collected from users, and this data will serve as the basis for future suggestions.

[0476] "Financial products" refer to items such as investment trusts, stocks, and bonds that are traded by users for asset management purposes.

[0477] An "asset management plan" is a plan that outlines a user's asset management and investment strategy, created based on collected and analyzed data.

[0478] "Dynamic asset management" is a management method that aims to monitor the user's asset status and market changes in real time and to allocate assets optimally at that moment.

[0479] In a form for carrying out the invention, this system is implemented based on a terminal, including a smartphone, and a server. The user inputs their attribute information, asset data, and consumption data using the terminal. In this process, the terminal is responsible for transmitting the input information to the server.

[0480] The server uses an advanced AI engine to analyze the collected data. Specifically, it leverages machine learning frameworks such as TensorFlow and PyTorch to generate a unique risk profile for each user. This profile serves as crucial foundational data for the user's asset management plan.

[0481] Furthermore, based on the analysis results, the server generates financial products and asset management plans optimized for the user and delivers the proposals to the terminal. To conduct transactions with financial institutions, secure and efficient communication is achieved using interfaces such as RESTful APIs.

[0482] As a concrete example, a new employee can use the app to register their monthly income and expenses, and the AI ​​will suggest appropriate investment trusts. When a user experiences a life event such as marriage, the system dynamically suggests adjustments to the investment balance in response to increased expenses. In this way, the system enables personalized asset management tailored to the user's lifestyle and market trends.

[0483] Example prompt for a generating AI model: "A user in their 20s working for a company enters their monthly expenses into the app. Based on their current income and savings, please suggest an investment plan suitable for future wealth building."

[0484] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0485] Step 1:

[0486] Users input attribute information, asset data, and consumption data via their terminal. This input data undergoes basic formatting on the terminal before being sent to the server. The input data is stored in the database as the user's profile information.

[0487] Step 2:

[0488] The server starts analyzing user attribute information, asset data, and consumption data collected from the database using its AI engine. The AI ​​model generates a risk profile using historical training data. This analysis result is output as data showing each user's customized risk tolerance and investment suitability.

[0489] Step 3:

[0490] The server uses the risk profile obtained through analysis as input to generate optimal financial products and asset management plans for each user. This process utilizes predictive models that leverage current market information and historical pattern data. The server delivers the generated proposals to the terminal and presents them to the user. The output takes the form of a specific investment plan or proposal document.

[0491] Step 4:

[0492] Users review the financial products and investment plans presented on their devices and, if they wish to approve them, indicate their approval through the device. This indication is sent to the server and treated as data that triggers the next processing step.

[0493] Step 5:

[0494] The server, upon user authorization, securely and quickly executes financial transactions with financial institutions via API. A transaction completion notification and proof data are generated as output and returned to the user's terminal. Once the transaction is complete, the user can verify that their asset status has been updated.

[0495] Step 6:

[0496] The server continuously monitors the user's assets and market trends, and sends new suggestions to the user in real time if there are significant changes. This monitoring and suggestions are executed at the appropriate time based on a generative AI model. Throughout the entire workflow, an example of a prompt message generated by the server might be, "Please propose an appropriate plan for additional investment to users whose revenue has increased."

[0497] 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.

[0498] This invention combines a system that suggests appropriate financial products based on a user's basic information and asset information with an emotion engine that recognizes the user's emotions. This system works in conjunction with an AI engine to provide users with a more personalized investment experience.

[0499] Users input their basic and asset information through their device. In addition, an emotion engine analyzes the user's emotions in real time. As a result, the user's current emotional state is incorporated into the system, and the AI ​​engine reflects this emotional data in constructing the risk profile.

[0500] The server uses an AI engine to analyze data, including emotional information, to generate a more detailed user risk profile. This profile is then used to suggest financial products and investment portfolios tailored to the user. By considering the impact of user emotions on risk tolerance, more accurate suggestions can be made.

[0501] If the user reviews and agrees to the proposal, the transaction will be executed based on that agreement. The transaction is executed using an API interface with financial institutions, ensuring a secure and efficient process.

[0502] Furthermore, the server aims to reduce the psychological burden of investment decision-making by providing feedback based on the user's emotions. If market fluctuations cause a change in the user's emotions, the risk profile will be updated based on that, and new recommendations will be made.

[0503] For example, when a user is considering a proposal on their device, if the emotion engine detects the user's anxiety, the server will use this information to suggest lower-risk investment options. Furthermore, if a successful investment experience has positively impacted the user's emotions, this emotion data will be used to improve future proposals. In this way, the system provides investment strategies that take user emotions into account, improving the investment experience.

[0504] The following describes the processing flow.

[0505] Step 1:

[0506] The user inputs basic and asset information using a device. In addition, an emotion engine uses the device's sensors to collect the user's emotions in real time. This data is then sent to a server.

[0507] Step 2:

[0508] The server stores the received data in a database. The server then activates an AI engine to analyze asset information and sentiment data to generate a user risk profile. This risk profile takes the user's emotional state into account and forms the basis for investment recommendations.

[0509] Step 3:

[0510] Based on the risk profile generated by the server, appropriate financial products and investment portfolios are selected. These recommendations are adjusted based on the user's emotional state. For example, if the emotion engine detects user anxiety, the server prioritizes suggesting safer products. The selection results are sent to the terminal and presented to the user.

[0511] Step 4:

[0512] The user reviews the proposal on their device and uses the system's simulation function to consider the risks and returns. If the user agrees to the proposal, they send a trade execution instruction from their device to the server.

[0513] Step 5:

[0514] Once the server confirms the user's consent, it initiates the process of executing financial instrument transactions. Through an API interface with financial institutions, it quickly and securely completes purchases or sales and reflects the transaction results in the database.

[0515] Step 6:

[0516] The server notifies the user of the completion of a transaction and monitors the user's asset status and market conditions. The sentiment engine continuously detects changes in the user's emotions and dynamically updates the risk profile. This allows the server to send new suggestions to the terminal when necessary. Through this process, the user receives an investment strategy customized to the market and their own emotions.

[0517] (Example 2)

[0518] 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."

[0519] Traditionally, investment experiences for users have relied primarily on objective financial information, failing to reflect individual users' emotional states and resulting in inconsistent investment choices. Furthermore, since risk tolerance changes with user emotions, there is a need for investment recommendations that take this into account.

[0520] 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.

[0521] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's asset information to generate risk characteristics, and means for an emotion analysis unit that analyzes the user's emotional state and reflects the emotional data in the risk characteristics. This makes it possible to provide more accurate investment proposals that take the user's emotional state into consideration.

[0522] "Attribute information" refers to basic personal information about a user, including data such as name, age, gender, and occupation.

[0523] "Asset information" refers to information about a user's financial assets, including total assets, income, and investment history.

[0524] "Risk characteristics" refer to data that indicates a user's risk tolerance and tendencies regarding investments, and this serves as the basis for proposing financial products.

[0525] The "emotion analysis unit" is a part of a device or program that has the function of analyzing the user's emotional state, and evaluates the user's emotions through facial recognition and voice analysis.

[0526] "Emotional data" refers to information that indicates a user's current emotional state and is used as a component of risk characteristics.

[0527] "Artificial intelligence" refers to algorithms or systems that use machine learning and data analysis technologies to perform advanced decision-making and predictions.

[0528] A "programming interface" refers to the rules and protocols used to link data and functions with external software and services, and plays a crucial role in completing transactions.

[0529] This invention is a system that proposes personalized financial products based on the user's attribute information, asset information, and emotional state. This system is implemented using a server, terminals, and an emotional analysis unit.

[0530] The user inputs their personal attribute and asset information through a terminal. This terminal incorporates input / output devices such as a camera and microphone, which the emotion analysis unit uses to collect the user's emotional data and analyze their emotional state in real time. Specifically, the camera is used to analyze facial expressions, and the microphone is used to analyze the intonation of the voice. Based on this, the user's emotional state is determined.

[0531] The server integrates attribute information, asset information, and sentiment data received from the terminal and performs a comprehensive analysis using various artificial intelligence algorithms. During this process, prompt sentences are generated via a generative AI model to aid in the analysis. As a result of the analysis, risk characteristics optimized for the user are generated, and financial products are suggested that match the user's investment tendencies.

[0532] The proposal is displayed on the terminal, and the user reviews its contents. If the user agrees to the proposal, the server communicates with the trading institution via a programming interface in the backend, based on instructions from the terminal, and executes the financial product transaction securely and quickly.

[0533] As a concrete example, if the emotion analysis unit detects anxiety while a user is managing their assets on their device, the server will present investment recommendations with reduced risk. In this process, a prompt such as "If the user is feeling anxious, please provide suggestions to avoid risk" is input to the generating AI model.

[0534] This system allows users to receive investment support that takes their emotions into account, enabling them to make more appropriate and confident investment decisions.

[0535] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0536] Step 1:

[0537] Users enter their personal information and asset information using a device. They enter information such as their name, age, occupation, and asset amount into a form displayed on the device screen, and then press the "Submit" button to send the data to the server. Once the input data reaches the server, it is encrypted and stored securely.

[0538] Step 2:

[0539] The emotion analysis unit uses the device's camera and microphone to collect data on the user's emotional state. Specifically, the camera captures facial expression data, which is then used to analyze smiles, serious expressions, and other similar expressions. The microphone analyzes voice tone to assess the user's level of excitement or calmness. This collected data is then analyzed in real time by the emotion analysis unit and transmitted to the server as emotional state data.

[0540] Step 3:

[0541] The server integrates received attribute information, asset information, and emotional state data, and uses a generative AI model to analyze the data. The generative AI model is given instructions such as, "Analyze this user's risk characteristics and generate appropriate investment proposals." Based on these instructions, the AI ​​engine calculates the risk characteristics and outputs an optimized risk profile, taking into account the correlation of each data item and the emotional state.

[0542] Step 4:

[0543] The server creates a list of financial products optimized for the user based on the generated risk profile. In this process, the AI ​​engine refers to market data and past investment examples to list products that match the asset allocation and risk level. The generating AI model then concretizes the proposal based on the prompt "Suggest high-safety investment options."

[0544] Step 5:

[0545] The proposed financial product is displayed on the terminal, and the user reviews its contents. If the user agrees to the proposal, they press the "Approve" button. Upon approval, the terminal sends consent data to the server, which then uses this information to initiate communication with the trading institution via a programming interface. Finally, the transaction of the financial product is completed through a secure process.

[0546] (Application Example 2)

[0547] 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."

[0548] In modern financial services, users sometimes make irrational investment decisions due to emotional factors. This increases the risk of disappointing investment results. On the other hand, because there are no suggestions that reflect users' emotions, it is difficult to provide users with a sufficiently personalized investment experience. This challenge needs to be addressed.

[0549] 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.

[0550] In this invention, the server includes means for analyzing the user's emotional information in real time and generating emotional data, means for optimizing the suggested content using the emotional data, and means for providing feedback based on the user's emotions. This makes it possible to suggest financial products that take the user's emotional state into consideration and to reduce the psychological burden in investment decision-making.

[0551] "User basic information" refers to personally identifiable information about the user, such as name, age, and address.

[0552] "Asset information" refers to financial data, including financial assets and liabilities, that a user owns.

[0553] A "risk profile" is data that indicates a user's risk tolerance in their investments.

[0554] "Emotional information" refers to data that indicates the user's emotional state and is analyzed in real time.

[0555] "Emotional data" refers to numerical data generated from a user's emotional information.

[0556] "Proposed content" refers to information about financial products and investment portfolios presented to the user.

[0557] "Feedback" refers to information and advice provided based on a user's behavior and emotional state.

[0558] An "API interface" is a standardized connection method for communication between different systems.

[0559] An "AI engine" is a system that analyzes data based on artificial intelligence and generates personalized suggestions.

[0560] To implement this invention, the process begins with the user providing basic and asset information using a mobile device. The user is required to provide their emotional information in real time using the camera and microphone of their smart device. This emotional information is analyzed by emotion analysis software, such as Affectiva or Microsoft Azure Emotion API, to generate quantified emotional data.

[0561] Upon receiving this information, the server first uses an AI engine to generate a user risk profile. This AI engine leverages machine learning frameworks such as TensorFlow and PyTorch to analyze asset information and sentiment data. As a result, the user's risk tolerance in investments is quantified.

[0562] Next, the server generates recommendations. These recommendations are optimized based on the user's risk profile and emotional data, suggesting financial products and investment portfolios that are optimized for the user. This process can improve the probability of investment success by taking the user's emotional state into account.

[0563] Furthermore, integration with financial institutions is possible via an API interface, and if the user agrees to the proposed terms, the transaction can be automatically executed based on that agreement. By utilizing existing payment solutions such as Stripe and PayPal APIs through this API interface, fast and secure transactions can be achieved.

[0564] For example, if the system determines that a user is feeling down, the server will present low-risk investment options. Furthermore, if a positive emotional shift resulting from a successful investment is detected, this will be reflected in the user's profile, improving future recommendations.

[0565] A good example of a prompt for a generative AI model would be a question like, "What approaches would be effective in encouraging a customer to make a purchase when they are feeling stressed? Please provide an example."

[0566] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0567] Step 1:

[0568] Users input basic and asset information using their mobile devices. This input data, including the user's personal identification information and financial information, is sent to the server. The server receives this information and stores it in a database.

[0569] Step 2:

[0570] The device uses its camera and microphone to collect real-time emotional data from the user. The collected emotional information is analyzed through Affectiva or the Microsoft Azure Emotion API and passed to the server as quantified emotional data.

[0571] Step 3:

[0572] The server uses an AI engine to integrate basic information, asset information, and sentiment data to generate a user risk profile. Analysis is performed using machine learning frameworks such as TensorFlow and PyTorch, which are employed by the AI ​​engine, and the resulting output is a numerical risk tolerance score.

[0573] Step 4:

[0574] The server presents the user with optimized recommendations based on the generated risk profile and sentiment data. These recommendations, which include recommendations for financial products and investment portfolios, aim to maximize user safety and satisfaction.

[0575] Step 5:

[0576] If the user agrees to the presented proposal, the device sends that agreement to the server. Based on this agreement, the server uses an API interface to execute a transaction with financial institutions with which the system is integrated. Payment services such as Stripe and PayPal are used as APIs here, ensuring fast and secure transactions.

[0577] Step 6:

[0578] The server re-analyzes the user's emotional changes after the transaction is completed, uses a generative AI model to prepare prompt messages, and provides the user with emotional feedback on their investment experience. This allows the user to emotionally reflect on their investment decisions, and the feedback is reflected in future suggestions.

[0579] 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.

[0580] 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.

[0581] 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.

[0582] [Fourth Embodiment]

[0583] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0584] 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.

[0585] 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).

[0586] 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.

[0587] 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.

[0588] 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).

[0589] 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.

[0590] 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.

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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".

[0596] This invention is an AI-powered system that enables users to effectively manage their assets and make investments. The system consists of server and terminal components, and seamlessly facilitates the suggestion and trading of financial products by the user.

[0597] The user first enters their basic information and asset information using a terminal. Information such as age, income, asset details, and investment preferences is sent to the server. The server receives this information and stores it in a database.

[0598] Next, the server analyzes this data using an AI engine to create a user risk profile. This profile details the user's risk tolerance, investment objectives, and investment timeframe, forming the basis for future recommendations.

[0599] Based on the analysis, the server selects the most suitable financial product for the user and generates a proposal. This proposal is presented to the user via their terminal. The proposal includes information on the selected financial product, as well as expected risks and returns. The user can then use this information to make a trading decision.

[0600] If a user agrees to a proposal and indicates their intention to proceed with a transaction, the server will quickly execute the purchase or sale of financial products. Transactions with financial institutions are conducted via an API interface, ensuring secure and efficient data communication.

[0601] This system also continuously monitors the user's asset status and generates new suggestions in response to market trends and fluctuations. This allows users to constantly optimize their asset management and investment strategies to suit their current situation.

[0602] As a concrete example, a user in their mid-20s registers with the system and inputs their current savings and investment experience, after which the AI ​​suggests a medium-risk investment trust. Subsequently, if investment conditions change due to market fluctuations, the server suggests rebalancing to stable bonds, and if the user agrees, the transaction is executed immediately. Through this entire process, users can effectively manage their assets and enjoy optimized investments.

[0603] The following describes the processing flow.

[0604] Step 1:

[0605] The user accesses the device and enters basic and asset information. This includes age, income, existing assets, investment experience, and goals. The device then sends this information to the server.

[0606] Step 2:

[0607] The server records the information it receives in a database. Furthermore, if additional information is needed from financial institutions, it is obtained via API. This allows for a comprehensive understanding of the user's asset status.

[0608] Step 3:

[0609] The server activates the AI ​​engine to analyze the data. The AI ​​generates a risk profile considering the user's risk tolerance, investment objectives, and time goals. This profile is then used to make subsequent recommendations.

[0610] Step 4:

[0611] The server analyzes market data and financial product information based on the risk profile and selects recommended financial products and investment strategies for the user. The selection results are sent to the terminal and displayed to the user.

[0612] Step 5:

[0613] The user reviews the proposal through their device. The proposal includes details about the financial product, risk level, expected return, and fees. Based on this, the user decides whether or not to proceed with the transaction.

[0614] Step 6:

[0615] If the user agrees to the proposal, an instruction to execute the transaction is sent from the terminal to the server.

[0616] Step 7:

[0617] The server confirms consent and executes the transaction. The purchase or sale procedure is carried out via the financial institution's API, and the transaction is completed.

[0618] Step 8:

[0619] The server notifies the user of the completion of a transaction and then monitors the financial markets and the user's asset status. If it determines that new recommendations are necessary in response to market fluctuations, it repeats steps 4 and beyond. This process ensures that the user always receives recommendations based on the latest investment performance.

[0620] (Example 1)

[0621] 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".

[0622] In today's financial markets, a challenge exists in that it is difficult for individual investors to achieve optimized investment strategies and risk management. There is a need to select appropriate investment products that take into account each investor's different asset situation, risk tolerance, and investment objectives, and to respond quickly to market trends in real time. However, traditional systems have struggled to meet such complex needs.

[0623] 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.

[0624] In this invention, the server includes means for acquiring basic user information, information processing means for analyzing the user's asset information and generating a risk profile, means for creating financial product proposals based on the analyzed profile, execution means for trading financial products based on user approval, means for continuously monitoring the user's asset status and presenting new proposals, and means for monitoring market conditions in real time and storing information in a database. This enables the provision of an optimized investment strategy for each individual user and supports efficient asset management and investment decisions based on the user's asset status.

[0625] "Means for obtaining basic user information" refers to a device or method for collecting personal information provided by a user and converting that information into a format usable within the system.

[0626] "Information processing means for generating risk profiles" refers to a processing device or method for analyzing a user's asset information and investment preferences, and based on the results, evaluating each user's risk tolerance and investment objectives to create a profile.

[0627] "Means for creating financial product proposals" refers to a device or method that selects the most suitable financial product for a user based on an analyzed risk profile and market conditions, and generates a proposal based on the selection results.

[0628] "Execution means for conducting financial product transactions" refers to a device or method for actually purchasing or selling selected financial products based on user approval.

[0629] "Means for continuously monitoring asset status and presenting new proposals" refers to a device or method that continuously tracks a user's asset history and market trends, and generates and proposes new investment strategies to the user as needed.

[0630] "Means for monitoring market conditions and storing information in a database" refers to a device or method that acquires financial market fluctuations and related information in real time and records that information in a database, making it available for future analysis and proposals.

[0631] To implement this invention, an advanced information processing system consisting of a server and a terminal is required. The server has a database system that receives basic information and asset information entered by the user using the terminal and stores it in a secure manner. Specifically, secure and consistent data management is achieved by using the SSL / TLS protocol for information transmission and MySQL or MongoDB for the database.

[0632] The server uses AI engines such as TensorFlow and PyTorch to analyze the user's asset information. This allows it to create a user risk profile, which reflects the user's risk tolerance, investment objectives, and investment timeframe.

[0633] Furthermore, the server selects financial products based on the risk profile. Because the algorithm incorporates the latest financial market data in real time, the selected financial products include expected risks and returns. The selection results are sent to the user's terminal and displayed in an easy-to-understand visual format.

[0634] If the user agrees to the proposal, the server executes the transaction with the financial institution via the API interface. This ensures transparent and efficient transactions.

[0635] Furthermore, the server continuously monitors the user's asset status. This allows it to generate new investment suggestions in response to market fluctuations and notify the user. As a result, the user can always maintain the optimal investment strategy.

[0636] As a concrete example, a scenario could be envisioned where a user in their 20s is offered a medium-risk investment trust based on their input information. During market fluctuations, rebalancing to stable bonds would be suggested. Through this process, the user can effectively manage their assets.

[0637] Examples of specific prompts for the generating AI model include, "Based on the asset information entered by a user in their 20s, please suggest a medium-risk investment product," and "Consider market fluctuations and generate advice for rebalancing the user's investment portfolio."

[0638] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0639] Step 1:

[0640] Users enter their basic and financial information via their device. This information includes age, income, asset details, and investment preferences. The device then transmits this information to the server using a secure communication protocol. For example, SSL / TLS protocol is used to ensure the secure transfer of data.

[0641] Step 2:

[0642] The server stores the received input data in a database. The database management system used is either MySQL or MongoDB. To maintain data consistency, the server assigns a unique identifier to each user to organize the information. As a result, user information is stored and available for subsequent processing.

[0643] Step 3:

[0644] The server uses an AI engine to analyze the user's asset information. This process utilizes machine learning models powered by TensorFlow and PyTorch. The user's asset information is used as input, and a risk profile is generated as output. This profile indicates the user's risk tolerance, investment objectives, and investment timeframe.

[0645] Step 4:

[0646] The server selects the optimal financial instruments based on the generated risk profile. At this stage, an algorithm makes the selection based on real-time data collected from the market. As a result, a list of selected financial instruments and their associated risk and return predictions are created. This information is then organized for the user to receive.

[0647] Step 5:

[0648] The server sends the selected financial product proposal to the terminal. The terminal displays the received information to the user. The user can then use this information to evaluate the proposed financial product in detail.

[0649] Step 6:

[0650] If the user agrees to the proposal, the device sends that information back to the server. The server uses an API interface to coordinate with the corresponding financial institution and execute the transaction. Once the transaction is complete, the server records the transaction results in a database and updates the user's asset status.

[0651] Step 7:

[0652] Subsequently, the server continuously monitors the user's asset status and market trends. It comprehensively analyzes the information in the database and proposes new financial products and investment strategies as needed. The generated new proposals are then notified to the user again via the terminal.

[0653] (Application Example 1)

[0654] 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".

[0655] In modern society, it is crucial for individuals to effectively manage their assets while efficiently handling daily expenses. However, many people find it difficult to understand their own asset situation and spending patterns, and to develop optimal investment strategies. Furthermore, the lack of widespread systems that integrate spending and asset management presents a challenge in dynamically optimizing one's assets.

[0656] 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.

[0657] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's asset data and consumption data to generate a risk profile, and means for generating suggestions for financial products and asset management plans based on the analysis results. This enables users to dynamically manage their assets and optimize their asset management based on their daily spending data and asset information.

[0658] "User attribute information" refers to data that shows personal characteristics of the user, such as age, income, and investment preferences.

[0659] "Asset data" refers to information about the financial assets owned by the user, including bank deposits, investment trusts, stocks, etc.

[0660] "Consumption data" refers to information about a user's daily spending, including data on living expenses, hobbies, and entertainment.

[0661] A "risk profile" is information compiled as a result of analyzing an individual user's risk tolerance and investment objectives.

[0662] "Analysis results" refer to the results of an analysis performed by AI based on information collected from users, and this data will serve as the basis for future suggestions.

[0663] "Financial products" refer to items such as investment trusts, stocks, and bonds that are traded by users for asset management purposes.

[0664] An "asset management plan" is a plan that outlines a user's asset management and investment strategy, created based on collected and analyzed data.

[0665] "Dynamic asset management" is a management method that aims to monitor the user's asset status and market changes in real time and to allocate assets optimally at that moment.

[0666] In a form for carrying out the invention, this system is implemented based on a terminal, including a smartphone, and a server. The user inputs their attribute information, asset data, and consumption data using the terminal. In this process, the terminal is responsible for transmitting the input information to the server.

[0667] The server uses an advanced AI engine to analyze the collected data. Specifically, it leverages machine learning frameworks such as TensorFlow and PyTorch to generate a unique risk profile for each user. This profile serves as crucial foundational data for the user's asset management plan.

[0668] Furthermore, based on the analysis results, the server generates financial products and asset management plans optimized for the user and delivers the proposals to the terminal. To conduct transactions with financial institutions, secure and efficient communication is achieved using interfaces such as RESTful APIs.

[0669] As a concrete example, a new employee can use the app to register their monthly income and expenses, and the AI ​​will suggest appropriate investment trusts. When a user experiences a life event such as marriage, the system dynamically suggests adjustments to the investment balance in response to increased expenses. In this way, the system enables personalized asset management tailored to the user's lifestyle and market trends.

[0670] Example prompt for a generating AI model: "A user in their 20s working for a company enters their monthly expenses into the app. Based on their current income and savings, please suggest an investment plan suitable for future wealth building."

[0671] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0672] Step 1:

[0673] Users input attribute information, asset data, and consumption data via their terminal. This input data undergoes basic formatting on the terminal before being sent to the server. The input data is stored in the database as the user's profile information.

[0674] Step 2:

[0675] The server starts analyzing user attribute information, asset data, and consumption data collected from the database using its AI engine. The AI ​​model generates a risk profile using historical training data. This analysis result is output as data showing each user's customized risk tolerance and investment suitability.

[0676] Step 3:

[0677] The server uses the risk profile obtained through analysis as input to generate optimal financial products and asset management plans for each user. This process utilizes predictive models that leverage current market information and historical pattern data. The server delivers the generated proposals to the terminal and presents them to the user. The output takes the form of a specific investment plan or proposal document.

[0678] Step 4:

[0679] Users review the financial products and investment plans presented on their devices and, if they wish to approve them, indicate their approval through the device. This indication is sent to the server and treated as data that triggers the next processing step.

[0680] Step 5:

[0681] The server, upon user authorization, securely and quickly executes financial transactions with financial institutions via API. A transaction completion notification and proof data are generated as output and returned to the user's terminal. Once the transaction is complete, the user can verify that their asset status has been updated.

[0682] Step 6:

[0683] The server continuously monitors the user's assets and market trends, and sends new suggestions to the user in real time if there are significant changes. This monitoring and suggestions are executed at the appropriate time based on a generative AI model. Throughout the entire workflow, an example of a prompt message generated by the server might be, "Please propose an appropriate plan for additional investment to users whose revenue has increased."

[0684] 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.

[0685] This invention combines a system that suggests appropriate financial products based on a user's basic information and asset information with an emotion engine that recognizes the user's emotions. This system works in conjunction with an AI engine to provide users with a more personalized investment experience.

[0686] Users input their basic and asset information through their device. In addition, an emotion engine analyzes the user's emotions in real time. As a result, the user's current emotional state is incorporated into the system, and the AI ​​engine reflects this emotional data in constructing the risk profile.

[0687] The server uses an AI engine to analyze data, including emotional information, to generate a more detailed user risk profile. This profile is then used to suggest financial products and investment portfolios tailored to the user. By considering the impact of user emotions on risk tolerance, more accurate suggestions can be made.

[0688] If the user reviews and agrees to the proposal, the transaction will be executed based on that agreement. The transaction is executed using an API interface with financial institutions, ensuring a secure and efficient process.

[0689] Furthermore, the server aims to reduce the psychological burden of investment decision-making by providing feedback based on the user's emotions. If market fluctuations cause a change in the user's emotions, the risk profile will be updated based on that, and new recommendations will be made.

[0690] For example, when a user is considering a proposal on their device, if the emotion engine detects the user's anxiety, the server will use this information to suggest lower-risk investment options. Furthermore, if a successful investment experience has positively impacted the user's emotions, this emotion data will be used to improve future proposals. In this way, the system provides investment strategies that take user emotions into account, improving the investment experience.

[0691] The following describes the processing flow.

[0692] Step 1:

[0693] The user inputs basic and asset information using a device. In addition, an emotion engine uses the device's sensors to collect the user's emotions in real time. This data is then sent to a server.

[0694] Step 2:

[0695] The server stores the received data in a database. The server then activates an AI engine to analyze asset information and sentiment data to generate a user risk profile. This risk profile takes the user's emotional state into account and forms the basis for investment recommendations.

[0696] Step 3:

[0697] Based on the risk profile generated by the server, appropriate financial products and investment portfolios are selected. These recommendations are adjusted based on the user's emotional state. For example, if the emotion engine detects user anxiety, the server prioritizes suggesting safer products. The selection results are sent to the terminal and presented to the user.

[0698] Step 4:

[0699] The user reviews the proposal on their device and uses the system's simulation function to consider the risks and returns. If the user agrees to the proposal, they send a trade execution instruction from their device to the server.

[0700] Step 5:

[0701] Once the server confirms the user's consent, it initiates the process of executing financial instrument transactions. Through an API interface with financial institutions, it quickly and securely completes purchases or sales and reflects the transaction results in the database.

[0702] Step 6:

[0703] The server notifies the user of the completion of a transaction and monitors the user's asset status and market conditions. The sentiment engine continuously detects changes in the user's emotions and dynamically updates the risk profile. This allows the server to send new suggestions to the terminal when necessary. Through this process, the user receives an investment strategy customized to the market and their own emotions.

[0704] (Example 2)

[0705] 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".

[0706] Traditionally, investment experiences for users have relied primarily on objective financial information, failing to reflect individual users' emotional states and resulting in inconsistent investment choices. Furthermore, since risk tolerance changes with user emotions, there is a need for investment recommendations that take this into account.

[0707] 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.

[0708] In this invention, the server includes means for collecting user attribute information, means for analyzing the user's asset information to generate risk characteristics, and means for an emotion analysis unit that analyzes the user's emotional state and reflects the emotional data in the risk characteristics. This makes it possible to provide more accurate investment proposals that take the user's emotional state into consideration.

[0709] "Attribute information" refers to basic personal information about a user, including data such as name, age, gender, and occupation.

[0710] "Asset information" refers to information about a user's financial assets, including total assets, income, and investment history.

[0711] "Risk characteristics" refer to data that indicates a user's risk tolerance and tendencies regarding investments, and this serves as the basis for proposing financial products.

[0712] The "emotion analysis unit" is a part of a device or program that has the function of analyzing the user's emotional state, and evaluates the user's emotions through facial recognition and voice analysis.

[0713] "Emotional data" refers to information that indicates a user's current emotional state and is used as a component of risk characteristics.

[0714] "Artificial intelligence" refers to algorithms or systems that use machine learning and data analysis technologies to perform advanced decision-making and predictions.

[0715] A "programming interface" refers to the rules and protocols used to link data and functions with external software and services, and plays a crucial role in completing transactions.

[0716] This invention is a system that proposes personalized financial products based on the user's attribute information, asset information, and emotional state. This system is implemented using a server, terminals, and an emotional analysis unit.

[0717] The user inputs their personal attribute and asset information through a terminal. This terminal incorporates input / output devices such as a camera and microphone, which the emotion analysis unit uses to collect the user's emotional data and analyze their emotional state in real time. Specifically, the camera is used to analyze facial expressions, and the microphone is used to analyze the intonation of the voice. Based on this, the user's emotional state is determined.

[0718] The server integrates attribute information, asset information, and sentiment data received from the terminal and performs a comprehensive analysis using various artificial intelligence algorithms. During this process, prompt sentences are generated via a generative AI model to aid in the analysis. As a result of the analysis, risk characteristics optimized for the user are generated, and financial products are suggested that match the user's investment tendencies.

[0719] The proposal is displayed on the terminal, and the user reviews its contents. If the user agrees to the proposal, the server communicates with the trading institution via a programming interface in the backend, based on instructions from the terminal, and executes the financial product transaction securely and quickly.

[0720] As a concrete example, if the emotion analysis unit detects anxiety while a user is managing their assets on their device, the server will present investment recommendations with reduced risk. In this process, a prompt such as "If the user is feeling anxious, please provide suggestions to avoid risk" is input to the generating AI model.

[0721] This system allows users to receive investment support that takes their emotions into account, enabling them to make more appropriate and confident investment decisions.

[0722] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0723] Step 1:

[0724] Users enter their personal information and asset information using a device. They enter information such as their name, age, occupation, and asset amount into a form displayed on the device screen, and then press the "Submit" button to send the data to the server. Once the input data reaches the server, it is encrypted and stored securely.

[0725] Step 2:

[0726] The emotion analysis unit uses the device's camera and microphone to collect data on the user's emotional state. Specifically, the camera captures facial expression data, which is then used to analyze smiles, serious expressions, and other similar expressions. The microphone analyzes voice tone to assess the user's level of excitement or calmness. This collected data is then analyzed in real time by the emotion analysis unit and transmitted to the server as emotional state data.

[0727] Step 3:

[0728] The server integrates received attribute information, asset information, and emotional state data, and uses a generative AI model to analyze the data. The generative AI model is given instructions such as, "Analyze this user's risk characteristics and generate appropriate investment proposals." Based on these instructions, the AI ​​engine calculates the risk characteristics and outputs an optimized risk profile, taking into account the correlation of each data item and the emotional state.

[0729] Step 4:

[0730] The server creates a list of financial products optimized for the user based on the generated risk profile. In this process, the AI ​​engine refers to market data and past investment examples to list products that match the asset allocation and risk level. The generating AI model then concretizes the proposal based on the prompt "Suggest high-safety investment options."

[0731] Step 5:

[0732] The proposed financial product is displayed on the terminal, and the user reviews its contents. If the user agrees to the proposal, they press the "Approve" button. Upon approval, the terminal sends consent data to the server, which then uses this information to initiate communication with the trading institution via a programming interface. Finally, the transaction of the financial product is completed through a secure process.

[0733] (Application Example 2)

[0734] 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".

[0735] In modern financial services, users sometimes make irrational investment decisions due to emotional factors. This increases the risk of disappointing investment results. On the other hand, because there are no suggestions that reflect users' emotions, it is difficult to provide users with a sufficiently personalized investment experience. This challenge needs to be addressed.

[0736] 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.

[0737] In this invention, the server includes means for analyzing the user's emotional information in real time and generating emotional data, means for optimizing the suggested content using the emotional data, and means for providing feedback based on the user's emotions. This makes it possible to suggest financial products that take the user's emotional state into consideration and to reduce the psychological burden in investment decision-making.

[0738] "User basic information" refers to personally identifiable information about the user, such as name, age, and address.

[0739] "Asset information" refers to financial data, including financial assets and liabilities, that a user owns.

[0740] A "risk profile" is data that indicates a user's risk tolerance in their investments.

[0741] "Emotional information" refers to data that indicates the user's emotional state and is analyzed in real time.

[0742] "Emotional data" refers to numerical data generated from a user's emotional information.

[0743] "Proposed content" refers to information about financial products and investment portfolios presented to the user.

[0744] "Feedback" refers to information and advice provided based on a user's behavior and emotional state.

[0745] An "API interface" is a standardized connection method for communication between different systems.

[0746] An "AI engine" is a system that analyzes data based on artificial intelligence and generates personalized suggestions.

[0747] To implement this invention, the process begins with the user providing basic and asset information using a mobile device. The user is required to provide their emotional information in real time using the camera and microphone of their smart device. This emotional information is analyzed by emotion analysis software, such as Affectiva or Microsoft Azure Emotion API, to generate quantified emotional data.

[0748] Upon receiving this information, the server first uses an AI engine to generate a user risk profile. This AI engine leverages machine learning frameworks such as TensorFlow and PyTorch to analyze asset information and sentiment data. As a result, the user's risk tolerance in investments is quantified.

[0749] Next, the server generates recommendations. These recommendations are optimized based on the user's risk profile and emotional data, suggesting financial products and investment portfolios that are optimized for the user. This process can improve the probability of investment success by taking the user's emotional state into account.

[0750] Furthermore, integration with financial institutions is possible via an API interface, and if the user agrees to the proposed terms, the transaction can be automatically executed based on that agreement. By utilizing existing payment solutions such as Stripe and PayPal APIs through this API interface, fast and secure transactions can be achieved.

[0751] For example, if the system determines that a user is feeling down, the server will present low-risk investment options. Furthermore, if a positive emotional shift resulting from a successful investment is detected, this will be reflected in the user's profile, improving future recommendations.

[0752] A good example of a prompt for a generative AI model would be a question like, "What approaches would be effective in encouraging a customer to make a purchase when they are feeling stressed? Please provide an example."

[0753] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0754] Step 1:

[0755] Users input basic and asset information using their mobile devices. This input data, including the user's personal identification information and financial information, is sent to the server. The server receives this information and stores it in a database.

[0756] Step 2:

[0757] The device uses its camera and microphone to collect real-time emotional data from the user. The collected emotional information is analyzed through Affectiva or the Microsoft Azure Emotion API and passed to the server as quantified emotional data.

[0758] Step 3:

[0759] The server uses an AI engine to integrate basic information, asset information, and sentiment data to generate a user risk profile. Analysis is performed using machine learning frameworks such as TensorFlow and PyTorch, which are employed by the AI ​​engine, and the resulting output is a numerical risk tolerance score.

[0760] Step 4:

[0761] The server presents the user with optimized recommendations based on the generated risk profile and sentiment data. These recommendations, which include recommendations for financial products and investment portfolios, aim to maximize user safety and satisfaction.

[0762] Step 5:

[0763] If the user agrees to the presented proposal, the device sends that agreement to the server. Based on this agreement, the server uses an API interface to execute a transaction with financial institutions with which the system is integrated. Payment services such as Stripe and PayPal are used as APIs here, ensuring fast and secure transactions.

[0764] Step 6:

[0765] The server re-analyzes the user's emotional changes after the transaction is completed, uses a generative AI model to prepare prompt messages, and provides the user with emotional feedback on their investment experience. This allows the user to emotionally reflect on their investment decisions, and the feedback is reflected in future suggestions.

[0766] 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.

[0767] 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.

[0768] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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."

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0787] The following is further disclosed regarding the embodiments described above.

[0788] (Claim 1)

[0789] Means for collecting basic user information,

[0790] A means of analyzing a user's asset information to generate a risk profile,

[0791] A means for generating financial product proposals based on analysis results,

[0792] A means of executing financial product transactions based on the user's consent,

[0793] A means of continuously monitoring the user's asset status and making new suggestions,

[0794] A system that includes this.

[0795] (Claim 2)

[0796] The system according to claim 1, comprising an API interface for completing transactions in cooperation with financial institutions.

[0797] (Claim 3)

[0798] The system according to claim 1, comprising an AI engine for proposing an optimized investment portfolio to a user.

[0799] "Example 1"

[0800] (Claim 1)

[0801] Means of obtaining basic user information,

[0802] Information processing means for analyzing user asset information and generating a risk profile,

[0803] A means of creating financial product proposals based on the analyzed profile,

[0804] An execution mechanism for conducting transactions of financial products based on user approval,

[0805] A means to continuously monitor the user's asset status and propose new suggestions,

[0806] A means of monitoring market conditions in real time and storing the information in a database,

[0807] A system that includes this.

[0808] (Claim 2)

[0809] The system according to claim 1, comprising a standardized interface for completing transactions in cooperation with the financial industry.

[0810] (Claim 3)

[0811] The system according to claim 1, comprising an artificial intelligence processing unit for proposing an optimized investment strategy to a user.

[0812] "Application Example 1"

[0813] (Claim 1)

[0814] Means for collecting user attribute information,

[0815] A means for generating a risk profile by analyzing user asset data and consumption data,

[0816] A means for generating proposals for financial products and asset management plans based on analysis results,

[0817] A means of executing financial transactions and asset adjustments based on user approval,

[0818] A means of continuously monitoring the user's assets and spending status and making dynamic suggestions,

[0819] A system that includes this.

[0820] (Claim 2)

[0821] The system according to claim 1, comprising an API interface for managing transactions and expenditures in cooperation with financial institutions.

[0822] (Claim 3)

[0823] The system according to claim 1, comprising an AI engine for proposing an optimized asset management plan and expenditure management to the user.

[0824] "Example 2 of combining an emotion engine"

[0825] (Claim 1)

[0826] Means for collecting user attribute information,

[0827] A means of analyzing a user's asset information to generate risk characteristics,

[0828] It includes an emotion analysis unit that analyzes the user's emotional state, and means for reflecting emotional data in risk characteristics,

[0829] A means for generating financial product proposals based on analysis results,

[0830] A means of executing financial product transactions based on the user's consent,

[0831] A means of continuously monitoring the user's financial situation and making new suggestions,

[0832] A system that includes this.

[0833] (Claim 2)

[0834] The system according to claim 1, comprising a programming interface for completing transactions in cooperation with trading institutions.

[0835] (Claim 3)

[0836] The system according to claim 1, comprising artificial intelligence for proposing an optimized investment allocation to a user.

[0837] "Application example 2 when combining with an emotional engine"

[0838] (Claim 1)

[0839] Means for collecting basic user information,

[0840] A means of analyzing a user's asset information to generate a risk profile,

[0841] A means for generating financial product proposals based on analysis results,

[0842] A means of executing financial product transactions based on the user's consent,

[0843] A means of analyzing user emotional information in real time and generating emotional data,

[0844] A method for optimizing proposals using sentiment data,

[0845] A means of continuously monitoring the user's asset status and making new suggestions,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, comprising an API interface for completing transactions in cooperation with financial institutions.

[0849] (Claim 3)

[0850] The system according to claim 1, comprising an AI engine for proposing an optimized investment portfolio to a user, and providing user-emotion-based feedback using emotional data. [Explanation of symbols]

[0851] 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, A means for generating a risk profile by analyzing user asset data and consumption data, A means for generating proposals for financial products and asset management plans based on analysis results, A means of executing financial transactions and asset adjustments based on user approval, A means of continuously monitoring the user's assets and spending status and making dynamic suggestions, A system that includes this.

2. The system according to claim 1, comprising an API interface for managing transactions and expenditures in cooperation with financial institutions.

3. The system according to claim 1, comprising an AI engine for proposing an optimized asset management plan and expenditure management to the user.

Images