system

Abstract

We provide the system. [Solution] Means of obtaining market information, A means of analyzing acquired market information to predict price fluctuations, Based on the analysis results, a means to automate the buying and selling of assets, A means of generating personalized suggestions through interaction with the user, A means of regularly reporting on the user's investment performance, A means of proposing ways to optimize consumer behavior based on feedback on investment results, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a need to solve the problems faced by individual investors, such as insufficient information and the inability to quickly respond to rapid market fluctuations. There are also problems that it is difficult for individuals without investment expertise to make optimal investment decisions for themselves and to obtain sustainable returns.

Means for Solving the Problems

[0005] This invention provides a system that acquires and analyzes market information and automates the buying and selling of investments based on the analysis results. This enables the provision of personalized investment suggestions tailored to each user's investment style. Furthermore, by incorporating a function to convert speech to text, interaction with the user is facilitated, and by providing a means to regularly report investment information, users can always stay informed of the latest investment situation. These means enable individual investors to make investment decisions more efficiently and quickly.

[0006] "Market information" refers to all data necessary for investment decisions in financial markets, including stock prices, exchange rates, economic indicators, and news articles.

[0007] "Means of acquisition" refers to technical methods or devices for collecting target data from external sources.

[0008] "Means of analysis" refer to algorithms and computational methods used to analyze collected data and derive patterns and trends.

[0009] "Price fluctuation forecasting" is the process of estimating future market price and exchange rate fluctuations based on the results of market data analysis.

[0010] "Means of automating buying and selling" refers to a program or device that allows a system to automatically buy and sell assets based on pre-set conditions.

[0011] "Means of generating suggestions through dialogue" refers to an interface and the underlying program that provides appropriate investment advice in response to user input and questions.

[0012] A "means of reporting investment performance" refers to a system that analyzes a user's asset management status and past investment performance, and provides it to them regularly in the form of reports.

[0013] "Means for converting audio data into text data" refers to speech recognition technology that analyzes input audio information and converts it into corresponding text data.

[0014] "Methods for optimizing investment timing" refer to algorithms that calculate and execute the optimal timing for buying and selling based on real-time market information. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 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.

Modes for Carrying Out the Invention

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] The system based on this invention is designed to enable individual investors to invest in the market more easily and effectively. Specific embodiments are described below.

[0037] Server operation:

[0038] The server is responsible for acquiring and analyzing market information. It obtains real-time market information such as stock prices, exchange rates, and related news from external financial APIs. The acquired data is analyzed using machine learning algorithms. This analysis calculates price fluctuation predictions. The analysis outputs include buy / sell recommendations, risk assessments, and future trend predictions. The server also manages user portfolio information and executes automated trades based on pre-set conditions.

[0039] Device operation:

[0040] The terminal functions as an interface between the user and the server. It uses speech recognition technology to receive user instructions and questions and converts them into text data. For example, if a user asks, "What stock should I buy next?", the terminal transcribes the voice into text and sends it to the server. Upon receiving the analysis results from the server, the terminal provides a response to the user in either voice or text. This is presented as a personalized investment suggestion based on objective data.

[0041] User interaction:

[0042] Users interact with the system via smartphones or computers. For example, they can request detailed information on specific stocks or check their current investment performance. If a user sets specific trading conditions, the server records them and automatically executes trades when the conditions are met. This allows users to focus on investing with peace of mind, without having to react immediately to market movements.

[0043] Specific example:

[0044] For example, suppose a user wants to invest in a technology company. The device sends the company's name and investment amount to the server. The server analyzes all data related to that company and provides specific advice via the device, such as, "It's a good time to buy, as the stock price is expected to rise by 10% in the next week." Also, if the stock price of the same company that the user already owns rises sharply, the server automatically sells it and notifies the user of the result.

[0045] In this way, this system allows individual investors to utilize advanced investment analysis and achieve efficient asset management without requiring specialized knowledge.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The server collects market information in real time from external financial APIs and news feeds. The data is stored in a database in the form of stock prices, economic indicators, and news articles.

[0049] Step 2:

[0050] The server applies machine learning algorithms to analyze the collected market information. It predicts price fluctuations and recognizes specific patterns, and as a result generates buy and sell recommendations.

[0051] Step 3:

[0052] The device uses voice recognition technology to receive questions and instructions from the user. For example, if a user says, "Which stocks should I buy now?", the device converts that voice into text data.

[0053] Step 4:

[0054] The terminal sends the converted text data to the server and requests the analysis results corresponding to that query.

[0055] Step 5:

[0056] The server identifies the optimal investment recommendations based on the user's request. For example, it selects forecast results and risk assessments for specific stocks and sends them back to the terminal.

[0057] Step 6:

[0058] The terminal reports information received from the server to the user. It informs the user of buy / sell suggestions and market conditions in voice or text format.

[0059] Step 7:

[0060] This system manages the user's portfolio and sets up automated trading. Based on the conditions set by the user, the server automatically executes trades.

[0061] Step 8:

[0062] The server records the results of a transaction in a database after it has been executed and notifies the user of the transaction results via the terminal.

[0063] Step 9:

[0064] The server periodically evaluates investment performance and generates reports for users. This allows users to check the latest asset status on their devices.

[0065] (Example 1)

[0066] 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."

[0067] It is not easy for individual investors to effectively collect and analyze market information, and as a result, they often miss appropriate buying and selling opportunities. Furthermore, a lack of expertise makes it difficult to make quick and accurate investment decisions. Users need a way to receive timely and personalized investment recommendations.

[0068] 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.

[0069] In this invention, the server includes means for acquiring market information, means for analyzing the acquired market information to predict price fluctuations, means for automating the buying and selling of assets, and means for converting user instructions into text data using speech recognition technology. This enables users to efficiently grasp market trends and make appropriate investment decisions without requiring specialized knowledge.

[0070] "Market information" refers to all data related to assets traded in financial markets, such as prices, exchange rates, and news.

[0071] "Analysis" refers to the process of analyzing acquired data to derive patterns and trends in price fluctuations.

[0072] "Price fluctuation prediction" refers to estimating future price trends using statistical methods and machine learning models based on market information.

[0073] "Automating asset trading" refers to a system where a program executes buy and sell transactions without manual intervention, based on predefined conditions.

[0074] "Speech recognition technology" refers to the technology that converts human speech into text data that a computer can understand.

[0075] "Personalized investment recommendations" refer to investment advice tailored to a specific individual, created based on the user's past investment history and current market conditions.

[0076] "Investment efficiency" refers to the optimization of the time and resources needed to increase the rate at which profits are generated from investment activities.

[0077] A "trading alert" refers to a warning message designed to notify investors of important market conditions and trading opportunities they should be aware of.

[0078] The system based on this invention combines multiple technical methods to enable individuals to conduct investment activities effectively. The implementation of the system is as follows:

[0079] Server operation:

[0080] The server periodically retrieves market information from financial information providers via APIs and stores it in a database. This process utilizes the Python requests library. The retrieved data is then analyzed using a machine learning model based on TENSORFLOW® to predict price fluctuations. The server also includes a program that automatically buys and sells assets according to user-defined conditions based on these analysis results.

[0081] Device operation:

[0082] The device receives voice input from the user and converts it into text data using speech recognition technology. A cloud-based speech recognition service is used for this conversion. For example, a user prompt such as "What stock should I buy next?" is converted and sent to the server. The analysis results from the server are then notified to the user by the device in both voice and text. To achieve this, the Python gTTS (Google® Text-to-Speech) library is used to generate the speech.

[0083] User interaction:

[0084] Users can interact with the system via smartphones or computers. They can make requests via voice or text when seeking information about specific stocks, overall market trends, or their own investment performance. For example, if a user asks, "What will happen to a certain company's stock price?", the system will provide an analyzed suggestion in response to that question.

[0085] Specific example:

[0086] If a user is interested in a particular industry, they can enter the names of related companies in that industry as a prompt, and the server can provide analysis results including market trend forecasts for those companies and the industry as a whole. For example, if a prompt such as "Please tell me about recommended investment opportunities in the medical technology sector" is sent from the terminal to the server, the analysis results will be returned to the user as optimized investment advice.

[0087] This system allows users to invest more intelligently and confidently, maximizing their performance.

[0088] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0089] Step 1:

[0090] The server retrieves market information from financial information providers. It uses raw data received from financial APIs as input. This data consists of stock prices, exchange rates, news articles, etc., and is retrieved via HTTP requests. The output is stored in a database as structured data. For example, the Python requests library is configured to retrieve data every hour.

[0091] Step 2:

[0092] The server analyzes acquired market information using a machine learning model to predict price fluctuations. Historical market data from a database is used as input. TensorFlow is used to power an LSTM model that performs price predictions. The output is generated as predicted price fluctuations, buy / sell recommendations, and risk assessments, and is further formatted for notifications. This process is executed at the end of the day, after the market closes.

[0093] Step 3:

[0094] The device uses speech recognition technology to convert user instructions from speech to text. The input is the user's voice command. The converted text data is sent to a server and used as analysis results. For example, if a user says, "Tell me the stock price prediction for a specific company," that voice is converted into text data through a cloud-based speech recognition service.

[0095] Step 4:

[0096] The server analyzes text data received from the terminal and generates appropriate investment information based on the user's request. The input is a text prompt resulting from speech recognition. Correspondingly, information is drawn from past analysis results, and relevant data is extracted. The output information is then constructed as a message to respond to the user.

[0097] Step 5:

[0098] The terminal notifies the user of the analysis information returned from the server via voice or text. The input is the analysis result from the server. The audio generated using the Python gTTS library is played for the user, and the text information is displayed on the terminal's screen. For example, information such as "These are the best value stocks" is presented in both voice and text.

[0099] This allows users to receive real-time investment advice based on the latest market information, enabling them to make investment decisions quickly.

[0100] (Application Example 1)

[0101] 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."

[0102] Traditional investment systems struggle to effectively link individual investment results to consumption behavior, resulting in a lack of coordination between investment and consumption. Furthermore, there is insufficient support for individuals to make optimal consumption decisions based on their investment results.

[0103] 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.

[0104] In this invention, the server includes means for acquiring market information, means for analyzing the acquired market information to predict price fluctuations, means for automating the buying and selling of assets based on the analysis results, and means for making suggestions to optimize consumption behavior based on the feedbacked investment results. This makes it possible to efficiently utilize the profits obtained from an individual's investment for consumption and to optimize consumption behavior based on investment results.

[0105] "Market information" refers to data that affects asset values ​​in financial markets, such as stock prices, exchange rates, and related news.

[0106] "Analysis" refers to data processing that uses market information to predict price fluctuations and derive buy / sell recommendations and risk assessments.

[0107] "Automation" refers to a system autonomously executing the buying and selling of assets based on specific conditions or analysis results.

[0108] "Dialogue" refers to the exchange of information between a user and a system via voice or text.

[0109] A "proposal" refers to investment and consumption options and strategies provided to users based on analyzed data.

[0110] "Reporting" refers to the sharing of information to periodically inform users of the results of their investment performance.

[0111] "Optimizing consumer behavior" means providing support to enable users to utilize their funds most effectively based on investment results.

[0112] The system for implementing this invention mainly consists of a server, a terminal, and user interaction. The server is responsible for collecting market information using external financial APIs and analyzing that data. Machine learning algorithms are used for analysis to predict trends and assess risk. Based on the acquired analysis results, the server provides a function to automate investment buying and selling. Furthermore, it periodically reports the user's investment performance through a feedback function.

[0113] The terminal provides an interface for the user to interact with the system. Speech recognition technology built into the terminal converts voice commands from the user into text and sends it to the server. This allows the user to engage in dialogue by asking questions such as, "What stock should I buy next?" The terminal receives the analysis results from the server and communicates them to the user as voice or text.

[0114] Users can utilize personalized investment suggestions provided by the system through devices such as smartphones. Furthermore, by receiving suggestions to optimize their spending based on investment performance, they can utilize their funds more efficiently. For example, a list of products that can be purchased with current funds may be presented based on investment profits.

[0115] An example of a prompt message might be: "Generate optimal consumption suggestions based on the user's return on investment. Consider how to balance profit management and consumption optimization."

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The server acquires market information through external financial APIs. It receives data such as stock prices, exchange rates, and related news as input, and stores this data as foundational information for analysis. The output is market information in raw data format.

[0119] Step 2:

[0120] The server analyzes acquired market information and uses machine learning models to predict price fluctuations. It receives market data as input, processes and analyzes it, performs trend prediction and risk assessment, and generates investment buy / sell recommendations and risk information as output.

[0121] Step 3:

[0122] The server executes automated asset trading based on the analysis results. It uses investment recommendation data generated by the server as input and buys and sells stocks and other assets based on pre-set conditions. The output is a record of the executed trades.

[0123] Step 4:

[0124] The terminal receives voice commands from the user and converts them into text data using speech recognition technology. Voice commands are provided as input and processed by the speech recognition engine. The output is the textualized user commands to be sent to the server.

[0125] Step 5:

[0126] The server processes textual instructions from the user and generates analysis results and investment recommendations. The input is user instruction data, and this data, along with the server's analysis results, is used to create personalized investment recommendations. The output is recommendation information in text and audio formats for the user.

[0127] Step 6:

[0128] The terminal communicates investment proposals received from the server to the user in voice or text format. It receives analysis results data from the server as input and notifies the user in a format they can understand. The output consists of investment information and consumption suggestions delivered to the user.

[0129] Step 7:

[0130] The user receives suggestions from the device, makes investment decisions, and optimizes their consumption behavior. The input is investment and consumption suggestions conveyed by the device, and the user decides on actions based on these suggestions. The output is the user's optimized investment and consumption patterns.

[0131] 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.

[0132] This invention's system is designed to allow individual investors to optimize their buying and selling in the market while taking into account their own emotions and investment attitudes. By incorporating an emotion engine, the system recognizes the user's emotions and dynamically adjusts personalized investment recommendations.

[0133] Server operation:

[0134] The server retrieves market information from financial APIs and news sources and analyzes the collected data. Machine learning models are used for analysis to predict price fluctuations and perform risk analysis. Based on the analysis results, the server automates the buying and selling of assets. Automated trading is executed according to pre-set conditions, but the user's emotional state may also be taken into consideration by an emotion engine.

[0135] Device operation:

[0136] The device establishes interaction with the user using speech recognition and emotion recognition technologies. The emotion engine, which reads emotions from speech, infers the user's emotional state from the content of their statements, tone of voice, and speaking speed. This allows the device to generate feedback tailored to the user's emotions. For example, if the user expresses anxiety, the device can offer more conservative investment proposals.

[0137] User interaction:

[0138] Users can interact with the system via voice commands and text through their smartphones or PCs. When the emotion engine detects the user's emotions, that information is used to adjust investment strategies. For example, if a user is indicated to have positive emotions, the system may suggest taking on risk and investing in new stocks.

[0139] Specific example:

[0140] For example, suppose a user asks about the current status of their portfolio. In this case, the device performs voice analysis, and the emotion engine recognizes that the user's voice sounds anxious. The server takes this emotional information into consideration and proposes an investment strategy that minimizes risk, and the device responds in a calm tone, saying, "Given the current market conditions, there are investment opportunities that can aim for steady profits while mitigating risk."

[0141] In this way, an emotionally sensitive approach becomes possible, enabling the creation of a system that reduces investor stress while providing asset management tailored to individual circumstances.

[0142] The following describes the processing flow.

[0143] Step 1:

[0144] The server collects market information in real time from financial APIs. Stock prices, exchange rates, and related news information are automatically stored in the database.

[0145] Step 2:

[0146] The server analyzes collected market information using machine learning algorithms to predict price fluctuations and assess risks. The analysis results are saved as reference material for future buy and sell recommendations.

[0147] Step 3:

[0148] The terminal receives voice input from the user and converts it into text data using speech recognition technology. The user inputs questions or instructions about investments they are interested in into the system.

[0149] Step 4:

[0150] The device uses emotion recognition technology to analyze the user's emotional state from their voice. For example, it determines the user's emotions from their tone and tempo and sends that data to a server.

[0151] Step 5:

[0152] The server integrates the user's emotional state with analyzed market data to generate personalized investment recommendations. For example, it might suggest a conservative investment strategy to a user who is feeling anxious.

[0153] Step 6:

[0154] The terminal presents investment proposals from the server to the user as audio or text. The proposals are delivered in a tone and content that is sensitive to the user's emotional state.

[0155] Step 7:

[0156] When a user decides to take action in response to a proposal, that action is notified to the server. For example, the user might approve the purchase of the proposed stock.

[0157] Step 8:

[0158] Based on the user's decision, the server activates the automated trading function and executes trades according to the set conditions. The trade details are then recorded again in the database.

[0159] Step 9:

[0160] The server analyzes the results of executed transactions and updates the user's portfolio status. It then reports the results via the terminal and notifies the user.

[0161] (Example 2)

[0162] 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".

[0163] When individual investors make investment decisions, emotions can have a significant influence, and irrational decisions based on emotions can negatively impact investment results. Furthermore, a lack of investment expertise makes it difficult to conduct proper market analysis and determine the right timing. The inability to seize investment opportunities in real time is also a challenge. To address these issues, there is a need for systems that provide personalized investment recommendations that take emotions into account, as well as automated trading.

[0164] 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.

[0165] In this invention, the server includes means for acquiring market data, means for analyzing the acquired market data to predict numerical fluctuations, means for automating asset transactions based on the analysis results, means for recognizing the user's emotional state and generating personalized investment proposals based on that information, means for providing emotionally appropriate responses through dialogue with the user, and means for periodically reporting the user's investment performance. This facilitates appropriate investment decisions that take the user's emotions into account and enables real-time optimization of market opportunities.

[0166] "Market data" refers to information about price fluctuations and trading volume in the market, and includes a variety of information such as economic indicators and news data.

[0167] "Analysis" refers to the activity of processing collected data to reveal trends and patterns in the information.

[0168] "Numerical fluctuation" refers to changes in numerical values ​​such as price or trading volume in a particular market over time.

[0169] "Asset trading" refers to the buying and selling of stocks, bonds, and other assets in financial markets, and is the act of increasing or decreasing their value through investment.

[0170] "Automation" refers to a state in which programs or machines perform actions independently without requiring manual operation.

[0171] "Users" refers to individuals or corporations that use this system, and specifically those interested in investment.

[0172] "Emotional state" refers to the user's current psychological state, including feelings of anxiety, joy, and security.

[0173] "Personalized investment recommendations" refer to providing specific investment strategies and advice based on the individual attributes and sentiments of each user.

[0174] "Dialogue" refers to communication between the user and the system, including communication conducted through voice and text.

[0175] "Real-time" refers to a situation where events unfold almost simultaneously, and reactions or processing occur immediately.

[0176] This system is designed to help individual investors optimize their market trading. The server is primarily responsible for collecting and analyzing market data. Specifically, it utilizes internet communication modules to obtain information from financial data provider APIs and news sites. The data is analyzed using machine learning libraries such as TensorFlow and PyTorch to predict fluctuation patterns and assess risk. Based on these analysis results, the buying and selling of assets is automated according to the user's settings.

[0177] The device functions to support interaction with the user. Specifically, it uses Google's speech recognition technology and Microsoft's cloud services to convert the user's voice commands into text and uses an emotion recognition algorithm to infer the emotional state. This device-side emotion engine determines the current emotional state based on the tone and content of the user's voice. Based on this, the device provides appropriate feedback through voice and screen displays.

[0178] Users can interact with the system via smartphones or personal computers. For example, if a user asks "What is the status of my portfolio?" using voice commands, the device analyzes the voice and queries the server. The server considers the analysis results and the user's emotional state to generate optimal investment suggestions. Specifically, if the user expresses anxiety, a conservative investment plan with reduced risk will be presented.

[0179] One example of a prompt generated using a generative AI model is the instruction, "Consider the emotions gleaned from the user's voice and generate the optimal investment proposal." This prompt allows the AI ​​to autonomously generate appropriate proposals while considering the user's emotional state. Through this series of operations, the system makes it easier for users to make emotionally conscious investment decisions, helping them achieve better investment performance.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The server retrieves market data via the market data provider's API. Inputs include price fluctuations and trading volume data from the API. Outputs are price and trend datasets necessary for analysis. Specifically, the server calls the API at regular intervals to keep the data up-to-date.

[0183] Step 2:

[0184] The server uses the acquired data to perform data analysis through a machine learning model. The input is the numerical data obtained in the previous step, and the output is the analysis results such as price prediction and risk assessment. The data is analyzed using TensorFlow or PyTorch, and the algorithm performs trend analysis of price fluctuations based on historical data.

[0185] Step 3:

[0186] The terminal receives voice commands from the user and uses speech recognition software to convert the commands into text. The input is the user's voice, and the output is the command text converted into text format. In its specific operation, the terminal collects voice through the microphone and processes the data in real time.

[0187] Step 4:

[0188] The device uses textual commands and voice data to analyze the user's emotions through an emotion engine. Input includes voice data and its textual commands, while output is the user's emotional state (e.g., reassured, excited, anxious). The device extracts emotions from voice tone and speed and sends feedback to the server.

[0189] Step 5:

[0190] The server generates investment proposals by combining analysis results and emotional states. The inputs are primarily analysis results and the user's emotional state, while the output is a customized investment proposal presented to the user. The server then uses a predefined generative AI model to generate prompts and construct the optimal investment plan.

[0191] Step 6:

[0192] The terminal provides investment suggestions to the user via voice or text. The input is investment suggestions from the server, and the output is easy-to-understand instructions presented to the user. Specifically, the terminal communicates the suggestions by either synthesizing the text into speech or displaying it on the screen. Based on this, the user can consider their next trading action.

[0193] (Application Example 2)

[0194] 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".

[0195] Traditional investment systems only provide objective analysis based on market data, lacking the ability to consider the emotional state of the user. This meant users could be influenced by their own emotions and attitudes, potentially leading to inappropriate investment decisions. Furthermore, while there is a demand for investment support that enhances convenience in a home environment, effective means to achieve this have been lacking.

[0196] 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.

[0197] In this invention, the server includes means for recognizing the user's emotions and adjusting the investment strategy based on the emotional state, means for mounting a device for generating personalized investment advice on a general-purpose machine for use in a home environment, and a device for converting voice information into text information. This enables the provision of investment strategies that take the user's emotions into consideration and allows for easy use in a home environment.

[0198] "Market data" refers to information including price information, trading volume, and trends in financial markets.

[0199] "Price fluctuation" refers to the rise or fall of asset prices in financial markets over time.

[0200] "Processing" refers to the calculations and analyses necessary to analyze market data and interpret or predict the information.

[0201] "Asset trading" refers to the buying and selling of stocks, bonds, and other investment assets in financial markets.

[0202] "Personalized investment advice" refers to investment suggestions that are customized based on the user's specific circumstances and emotional state.

[0203] "Recognizing the user's emotions" refers to using voice and other sensory data to determine the user's psychological state.

[0204] An "emotion analysis module" refers to software or hardware components that analyze a user's emotions from their voice and facial expressions to determine their emotional state.

[0205] A "speech recognition system" refers to a technology that converts speech data into text format.

[0206] A "general-purpose machine" refers to a hardware device that can be used for a variety of purposes, not just specific functions.

[0207] The system that realizes this invention optimizes asset trading in financial markets while taking into account the user's emotional state. It has the functionality to acquire, process, and analyze various data through the cooperation of a server and terminals.

[0208] The server retrieves market data in real time from financial APIs and news sources and runs processing programs to analyze it. Machine learning frameworks such as TensorFlow are used for analysis, including price fluctuation prediction and risk analysis. The results obtained from the analysis are used to make automated trading decisions.

[0209] Meanwhile, the device analyzes the user's emotions using Microsoft Azure's (registered trademark) emotion recognition API. When the user accesses the system through the voice interface, the voice data is converted to text by Google Cloud Speech-to-Text. This text data is combined with market analysis results to generate personalized investment advice.

[0210] These processes can be incorporated into general-purpose machines, such as household robots. The robots monitor the user's emotional state through continuous interaction and provide investment advice at appropriate times. In particular, if emotional analysis indicates the user is experiencing stress, the robots can suggest more conservative investment strategies.

[0211] For example, if a user uses a voice command such as "Tell me my recent investment performance," the voice recognition system processes the command, and the server analyzes the investment performance, taking into account the user's emotional state and current market conditions, and reports it to the user's device.

[0212] Examples of prompts for the generating AI model include, "Tell me your recommended investment strategy when an investor is relaxed." In this way, flexible investment support tailored to the user's needs becomes possible through emotion-based interaction.

[0213] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0214] Step 1:

[0215] The server retrieves market data from financial APIs and news sources. Input is raw data from the APIs, and output is formatted data including price information and market trends. This data is organized by date and category for subsequent data analysis.

[0216] Step 2:

[0217] The server uses a machine learning model to analyze the acquired market data. The input is formatted market data, and the output is price fluctuation predictions and risk analysis results. The generative AI model performs predictive calculations from multiple data patterns to identify potential market fluctuations.

[0218] Step 3:

[0219] The device receives voice input from the user. The input is the user's voice data, and the output is text data. Google Cloud Speech-to-Text is used to convert the speech to text, preparing it to accurately understand the user's intent.

[0220] Step 4:

[0221] The device performs sentiment analysis on text obtained from audio data. The input is text data, and the output is the user's emotional state. Using Microsoft Azure's sentiment recognition API, it identifies emotions from the user's voice tone and speech content to determine their current psychological state.

[0222] Step 5:

[0223] The server generates personalized investment advice based on analyzed market data and the user's emotional state. The inputs are market analysis results and emotional analysis results, and the output is a personalized investment proposal. It dynamically adjusts investment strategies based on emotions, creating proposals adapted to the user's feelings.

[0224] Step 6:

[0225] The terminal delivers generated investment proposals to the user via voice. The input is investment proposals from the server, and the output is voice feedback. Using the terminal's speech synthesis function, the proposals are presented in a way that is easy for the user to understand, and detailed information and further interaction are provided as needed.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] [Second Embodiment]

[0230] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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".

[0242] The system based on this invention is designed to enable individual investors to invest in the market more easily and effectively. Specific embodiments are described below.

[0243] Server operation:

[0244] The server is responsible for acquiring and analyzing market information. It obtains real-time market information such as stock prices, exchange rates, and related news from external financial APIs. The acquired data is analyzed using machine learning algorithms. This analysis calculates price fluctuation predictions. The analysis outputs include buy / sell recommendations, risk assessments, and future trend predictions. The server also manages user portfolio information and executes automated trades based on pre-set conditions.

[0245] Device operation:

[0246] The terminal functions as an interface between the user and the server. It uses speech recognition technology to receive user instructions and questions and converts them into text data. For example, if a user asks, "What stock should I buy next?", the terminal transcribes the voice into text and sends it to the server. Upon receiving the analysis results from the server, the terminal provides a response to the user in either voice or text. This is presented as a personalized investment suggestion based on objective data.

[0247] User interaction:

[0248] Users interact with the system via smartphones or computers. For example, they can request detailed information on specific stocks or check their current investment performance. If a user sets specific trading conditions, the server records them and automatically executes trades when the conditions are met. This allows users to focus on investing with peace of mind, without having to react immediately to market movements.

[0249] Specific example:

[0250] For example, suppose a user wants to invest in a technology company. The device sends the company's name and investment amount to the server. The server analyzes all data related to that company and provides specific advice via the device, such as, "It's a good time to buy, as the stock price is expected to rise by 10% in the next week." Also, if the stock price of the same company that the user already owns rises sharply, the server automatically sells it and notifies the user of the result.

[0251] In this way, this system allows individual investors to utilize advanced investment analysis and achieve efficient asset management without requiring specialized knowledge.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The server collects market information in real time from external financial APIs and news feeds. The data is stored in a database in the form of stock prices, economic indicators, and news articles.

[0255] Step 2:

[0256] The server applies machine learning algorithms to analyze the collected market information. It predicts price fluctuations and recognizes specific patterns, and as a result generates buy and sell recommendations.

[0257] Step 3:

[0258] The device uses voice recognition technology to receive questions and instructions from the user. For example, if a user says, "Which stocks should I buy now?", the device converts that voice into text data.

[0259] Step 4:

[0260] The terminal sends the converted text data to the server and requests the analysis results corresponding to that query.

[0261] Step 5:

[0262] The server identifies the optimal investment recommendations based on the user's request. For example, it selects forecast results and risk assessments for specific stocks and sends them back to the terminal.

[0263] Step 6:

[0264] The terminal reports information received from the server to the user. It informs the user of buy / sell suggestions and market conditions in voice or text format.

[0265] Step 7:

[0266] This system manages the user's portfolio and sets up automated trading. Based on the conditions set by the user, the server automatically executes trades.

[0267] Step 8:

[0268] The server records the results of a transaction in a database after it has been executed and notifies the user of the transaction results via the terminal.

[0269] Step 9:

[0270] The server periodically evaluates investment performance and generates reports for users. This allows users to check the latest asset status on their devices.

[0271] (Example 1)

[0272] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0273] It is not easy for individual investors to effectively collect and analyze market information, and as a result, they often miss appropriate buying and selling opportunities. Furthermore, a lack of expertise makes it difficult to make quick and accurate investment decisions. Users need a way to receive timely and personalized investment recommendations.

[0274] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0275] In this invention, the server includes means for acquiring market information, means for analyzing the acquired market information to predict price fluctuations, means for automating the buying and selling of assets, and means for converting user instructions into text data using speech recognition technology. This enables users to efficiently grasp market trends and make appropriate investment decisions without requiring specialized knowledge.

[0276] "Market information" refers to all data related to assets traded in financial markets, such as prices, exchange rates, and news.

[0277] "Analysis" refers to the process of analyzing acquired data to derive patterns and trends in price fluctuations.

[0278] "Price fluctuation prediction" refers to estimating future price trends using statistical methods and machine learning models based on market information.

[0279] "Automating asset trading" refers to a system where a program executes buy and sell transactions without manual intervention, based on predefined conditions.

[0280] "Speech recognition technology" refers to the technology that converts human speech into text data that a computer can understand.

[0281] "Personalized investment recommendations" refer to investment advice tailored to a specific individual, created based on the user's past investment history and current market conditions.

[0282] "Investment efficiency" refers to the optimization of time and resources necessary to increase the profit acquisition rate through investment activities.

[0283] "Trading alert" refers to a warning message for notifying investors of important market conditions and trading opportunities they should know.

[0284] The system based on this invention combines multiple technical methods to enable individuals to effectively conduct investment activities. The implementation of the system is as follows.

[0285] Server operation:

[0286] The server regularly obtains market information from a financial information provider via an API and stores it in a database. The Python requests library is used for this process. The acquired data is used to predict price fluctuations through analysis by a machine learning model using TensorFlow. The server also includes a program that automatically executes asset trading according to the conditions set by the user based on this analysis result.

[0287] Terminal operation:

[0288] The terminal receives voice input from the user and converts it into text data using voice recognition technology. A cloud-based voice recognition service is used for this conversion. For example, a prompt sentence from the user such as "What stocks should I buy next?" is converted and sent to the server. The analysis result from the server is notified to the user by voice and text by the terminal. For this purpose, the Python gTTS (Google Text-to-Speech) library is utilized to generate voice.

[0289] User interaction:

[0290] Users can interact with the system via smartphones or computers. They can make requests via voice or text when seeking information about specific stocks, overall market trends, or their own investment performance. For example, if a user asks, "What will happen to a certain company's stock price?", the system will provide an analyzed suggestion in response to that question.

[0291] Specific example:

[0292] If a user is interested in a particular industry, they can enter the names of related companies in that industry as a prompt, and the server can provide analysis results including market trend forecasts for those companies and the industry as a whole. For example, if a prompt such as "Please tell me about recommended investment opportunities in the medical technology sector" is sent from the terminal to the server, the analysis results will be returned to the user as optimized investment advice.

[0293] This system allows users to invest more intelligently and confidently, maximizing their performance.

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

[0295] Step 1:

[0296] The server retrieves market information from financial information providers. It uses raw data received from financial APIs as input. This data consists of stock prices, exchange rates, news articles, etc., and is retrieved via HTTP requests. The output is stored in a database as structured data. For example, the Python requests library is configured to retrieve data every hour.

[0297] Step 2:

[0298] The server analyzes acquired market information using a machine learning model to predict price fluctuations. Historical market data from a database is used as input. TensorFlow is used to power an LSTM model that performs price predictions. The output is generated as predicted price fluctuations, buy / sell recommendations, and risk assessments, and is further formatted for notifications. This process is executed at the end of the day, after the market closes.

[0299] Step 3:

[0300] The device uses speech recognition technology to convert user instructions from speech to text. The input is the user's voice command. The converted text data is sent to a server and used as analysis results. For example, if a user says, "Tell me the stock price prediction for a specific company," that voice is converted into text data through a cloud-based speech recognition service.

[0301] Step 4:

[0302] The server analyzes text data received from the terminal and generates appropriate investment information based on the user's request. The input is a text prompt resulting from speech recognition. Correspondingly, information is drawn from past analysis results, and relevant data is extracted. The output information is then constructed as a message to respond to the user.

[0303] Step 5:

[0304] The terminal notifies the user of the analysis information returned from the server via voice or text. The input is the analysis result from the server. The audio generated using the Python gTTS library is played for the user, and the text information is displayed on the terminal's screen. For example, information such as "These are the best value stocks" is presented in both voice and text.

[0305] This allows users to receive real-time investment advice based on the latest market information, enabling them to make investment decisions quickly.

[0306] (Application Example 1)

[0307] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0308] In the conventional investment system, it is difficult to effectively link an individual's investment results to consumption behavior, and there is a lack of coordination between investment and consumption. Also, there is a problem that the support for an individual to make optimal consumption based on investment results is insufficient.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0310] In this invention, the server includes means for acquiring market information, means for analyzing the acquired market information to predict price fluctuations, means for automating the buying and selling of assets based on the analysis results, and means for making a proposal to optimize consumption behavior based on the feedback investment results. Thereby, it becomes possible to efficiently utilize the profit obtained from an individual's investment for consumption and optimize the consumption behavior based on the investment results.

[0311] "Market information" is data that affects asset value, such as stock prices, exchange rates, related news, etc. in the financial market.

[0312] "Analysis" is data processing for predicting price fluctuations based on market information and leading to trading recommendations and risk assessments.

[0313] "Automation" refers to the system autonomously executing the buying and selling of assets based on certain specific conditions or analysis results.

[0314] "Dialogue" is the exchange of information between the user and the system via voice or text.

[0315] A "proposal" refers to investment and consumption options and strategies provided to users based on analyzed data.

[0316] "Reporting" refers to the sharing of information to periodically inform users of the results of their investment performance.

[0317] "Optimizing consumer behavior" means providing support to enable users to utilize their funds most effectively based on investment results.

[0318] The system for implementing this invention mainly consists of a server, a terminal, and user interaction. The server is responsible for collecting market information using external financial APIs and analyzing that data. Machine learning algorithms are used for analysis to predict trends and assess risk. Based on the acquired analysis results, the server provides a function to automate investment buying and selling. Furthermore, it periodically reports the user's investment performance through a feedback function.

[0319] The terminal provides an interface for the user to interact with the system. Speech recognition technology built into the terminal converts voice commands from the user into text and sends it to the server. This allows the user to engage in dialogue by asking questions such as, "What stock should I buy next?" The terminal receives the analysis results from the server and communicates them to the user as voice or text.

[0320] Users can utilize personalized investment suggestions provided by the system through devices such as smartphones. Furthermore, by receiving suggestions to optimize their spending based on investment performance, they can utilize their funds more efficiently. For example, a list of products that can be purchased with current funds may be presented based on investment profits.

[0321] An example of a prompt message might be: "Generate optimal consumption suggestions based on the user's return on investment. Consider how to balance profit management and consumption optimization."

[0322] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0323] Step 1:

[0324] The server acquires market information through external financial APIs. It receives data such as stock prices, exchange rates, and related news as input, and stores this data as foundational information for analysis. The output is market information in raw data format.

[0325] Step 2:

[0326] The server analyzes acquired market information and uses machine learning models to predict price fluctuations. It receives market data as input, processes and analyzes it, performs trend prediction and risk assessment, and generates investment buy / sell recommendations and risk information as output.

[0327] Step 3:

[0328] The server executes automated asset trading based on the analysis results. It uses investment recommendation data generated by the server as input and buys and sells stocks and other assets based on pre-set conditions. The output is a record of the executed trades.

[0329] Step 4:

[0330] The terminal receives voice commands from the user and converts them into text data using speech recognition technology. Voice commands are provided as input and processed by the speech recognition engine. The output is the textualized user commands to be sent to the server.

[0331] Step 5:

[0332] The server processes textual instructions from the user and generates analysis results and investment recommendations. The input is user instruction data, and this data, along with the server's analysis results, is used to create personalized investment recommendations. The output is recommendation information in text and audio formats for the user.

[0333] Step 6:

[0334] The terminal communicates investment proposals received from the server to the user in voice or text format. It receives analysis results data from the server as input and notifies the user in a format they can understand. The output consists of investment information and consumption suggestions delivered to the user.

[0335] Step 7:

[0336] The user receives suggestions from the device, makes investment decisions, and optimizes their consumption behavior. The input is investment and consumption suggestions conveyed by the device, and the user decides on actions based on these suggestions. The output is the user's optimized investment and consumption patterns.

[0337] 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.

[0338] This invention's system is designed to allow individual investors to optimize their buying and selling in the market while taking into account their own emotions and investment attitudes. By incorporating an emotion engine, the system recognizes the user's emotions and dynamically adjusts personalized investment recommendations.

[0339] Server operation:

[0340] The server retrieves market information from financial APIs and news sources and analyzes the collected data. Machine learning models are used for analysis to predict price fluctuations and perform risk analysis. Based on the analysis results, the server automates the buying and selling of assets. Automated trading is executed according to pre-set conditions, but the user's emotional state may also be taken into consideration by an emotion engine.

[0341] Device operation:

[0342] The device establishes interaction with the user using speech recognition and emotion recognition technologies. The emotion engine, which reads emotions from speech, infers the user's emotional state from the content of their statements, tone of voice, and speaking speed. This allows the device to generate feedback tailored to the user's emotions. For example, if the user expresses anxiety, the device can offer more conservative investment proposals.

[0343] User interaction:

[0344] Users can interact with the system via voice commands and text through their smartphones or PCs. When the emotion engine detects the user's emotions, that information is used to adjust investment strategies. For example, if a user is indicated to have positive emotions, the system may suggest taking on risk and investing in new stocks.

[0345] Specific example:

[0346] For example, suppose a user asks about the current status of their portfolio. In this case, the device performs voice analysis, and the emotion engine recognizes that the user's voice sounds anxious. The server takes this emotional information into consideration and proposes an investment strategy that minimizes risk, and the device responds in a calm tone, saying, "Given the current market conditions, there are investment opportunities that can aim for steady profits while mitigating risk."

[0347] In this way, an emotionally sensitive approach becomes possible, enabling the creation of a system that reduces investor stress while providing asset management tailored to individual circumstances.

[0348] The following describes the processing flow.

[0349] Step 1:

[0350] The server collects market information in real time from financial APIs. Stock prices, exchange rates, and related news information are automatically stored in the database.

[0351] Step 2:

[0352] The server analyzes collected market information using machine learning algorithms to predict price fluctuations and assess risks. The analysis results are saved as reference material for future buy and sell recommendations.

[0353] Step 3:

[0354] The terminal receives voice input from the user and converts it into text data using speech recognition technology. The user inputs questions or instructions about investments they are interested in into the system.

[0355] Step 4:

[0356] The device uses emotion recognition technology to analyze the user's emotional state from their voice. For example, it determines the user's emotions from their tone and tempo and sends that data to a server.

[0357] Step 5:

[0358] The server integrates the user's emotional state with analyzed market data to generate personalized investment recommendations. For example, it might suggest a conservative investment strategy to a user who is feeling anxious.

[0359] Step 6:

[0360] The terminal presents investment proposals from the server to the user as audio or text. The proposals are delivered in a tone and content that is sensitive to the user's emotional state.

[0361] Step 7:

[0362] When a user decides to take action in response to a proposal, that action is notified to the server. For example, the user might approve the purchase of the proposed stock.

[0363] Step 8:

[0364] Based on the user's decision, the server activates the automated trading function and executes trades according to the set conditions. The trade details are then recorded again in the database.

[0365] Step 9:

[0366] The server analyzes the results of executed transactions and updates the user's portfolio status. It then reports the results via the terminal and notifies the user.

[0367] (Example 2)

[0368] 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".

[0369] When individual investors make investment decisions, emotions can have a significant influence, and irrational decisions based on emotions can negatively impact investment results. Furthermore, a lack of investment expertise makes it difficult to conduct proper market analysis and determine the right timing. The inability to seize investment opportunities in real time is also a challenge. To address these issues, there is a need for systems that provide personalized investment recommendations that take emotions into account, as well as automated trading.

[0370] 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.

[0371] In this invention, the server includes means for acquiring market data, means for analyzing the acquired market data to predict numerical fluctuations, means for automating asset transactions based on the analysis results, means for recognizing the user's emotional state and generating personalized investment proposals based on that information, means for providing emotionally appropriate responses through dialogue with the user, and means for periodically reporting the user's investment performance. This facilitates appropriate investment decisions that take the user's emotions into account and enables real-time optimization of market opportunities.

[0372] "Market data" refers to information about price fluctuations and trading volume in the market, and includes a variety of information such as economic indicators and news data.

[0373] "Analysis" refers to the activity of processing collected data to reveal trends and patterns in the information.

[0374] "Numerical fluctuation" refers to changes in numerical values ​​such as price or trading volume in a particular market over time.

[0375] "Asset trading" refers to the buying and selling of stocks, bonds, and other assets in financial markets, and is the act of increasing or decreasing their value through investment.

[0376] "Automation" refers to a state in which programs or machines perform actions independently without requiring manual operation.

[0377] "Users" refers to individuals or corporations that use this system, and specifically those interested in investment.

[0378] "Emotional state" refers to the user's current psychological state, including feelings of anxiety, joy, and security.

[0379] "Personalized investment recommendations" refer to providing specific investment strategies and advice based on the individual attributes and sentiments of each user.

[0380] "Dialogue" refers to communication between the user and the system, including communication conducted through voice and text.

[0381] "Real-time" refers to a situation where events unfold almost simultaneously, and reactions or processing occur immediately.

[0382] This system is designed to help individual investors optimize their market trading. The server is primarily responsible for collecting and analyzing market data. Specifically, it utilizes internet communication modules to obtain information from financial data provider APIs and news sites. The data is analyzed using machine learning libraries such as TensorFlow and PyTorch to predict fluctuation patterns and assess risk. Based on these analysis results, the buying and selling of assets is automated according to the user's settings.

[0383] The device functions to support interaction with the user. Specifically, it uses Google's speech recognition technology and Microsoft's cloud services to convert the user's voice commands into text and uses an emotion recognition algorithm to infer the emotional state. This emotion engine on the device determines the current emotional state based on the tone and content of the user's voice. Based on this, the device provides appropriate feedback through voice and screen displays.

[0384] Users can interact with the system via smartphones or personal computers. For example, if a user asks "What is the status of my portfolio?" using voice commands, the device analyzes the voice and queries the server. The server considers the analysis results and the user's emotional state to generate optimal investment suggestions. Specifically, if the user expresses anxiety, a conservative investment plan with reduced risk will be presented.

[0385] One example of a prompt generated using a generative AI model is the instruction, "Consider the emotions gleaned from the user's voice and generate the optimal investment proposal." This prompt allows the AI ​​to autonomously generate appropriate proposals while considering the user's emotional state. Through this series of operations, the system makes it easier for users to make emotionally conscious investment decisions, helping them achieve better investment performance.

[0386] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0387] Step 1:

[0388] The server retrieves market data via the market data provider's API. Inputs include price fluctuations and trading volume data from the API. Outputs are price and trend datasets necessary for analysis. Specifically, the server calls the API at regular intervals to keep the data up-to-date.

[0389] Step 2:

[0390] The server uses the acquired data to perform data analysis through a machine learning model. The input is the numerical data obtained in the previous step, and the output is the analysis results such as price prediction and risk assessment. The data is analyzed using TensorFlow or PyTorch, and the algorithm performs trend analysis of price fluctuations based on historical data.

[0391] Step 3:

[0392] The terminal receives voice commands from the user and uses speech recognition software to convert the commands into text. The input is the user's voice, and the output is the command text converted into text format. In its specific operation, the terminal collects voice through the microphone and processes the data in real time.

[0393] Step 4:

[0394] The device uses textual commands and voice data to analyze the user's emotions through an emotion engine. Input includes voice data and its textual commands, while output is the user's emotional state (e.g., reassured, excited, anxious). The device extracts emotions from voice tone and speed and sends feedback to the server.

[0395] Step 5:

[0396] The server generates investment proposals by combining analysis results and emotional states. The inputs are primarily analysis results and the user's emotional state, while the output is a customized investment proposal presented to the user. The server then uses a predefined generative AI model to generate prompts and construct the optimal investment plan.

[0397] Step 6:

[0398] The terminal provides investment suggestions to the user via voice or text. The input is investment suggestions from the server, and the output is easy-to-understand instructions presented to the user. Specifically, the terminal communicates the suggestions by either synthesizing the text into speech or displaying it on the screen. Based on this, the user can consider their next trading action.

[0399] (Application Example 2)

[0400] 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."

[0401] Traditional investment systems only provide objective analysis based on market data, lacking the ability to consider the emotional state of the user. This meant users could be influenced by their own emotions and attitudes, potentially leading to inappropriate investment decisions. Furthermore, while there is a demand for investment support that enhances convenience in a home environment, effective means to achieve this have been lacking.

[0402] 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.

[0403] In this invention, the server includes means for recognizing the user's emotions and adjusting the investment strategy based on the emotional state, means for mounting a device for generating personalized investment advice on a general-purpose machine for use in a home environment, and a device for converting voice information into text information. This enables the provision of investment strategies that take the user's emotions into consideration and allows for easy use in a home environment.

[0404] "Market data" refers to information including price information, trading volume, and trends in financial markets.

[0405] "Price fluctuation" refers to the rise or fall of asset prices in financial markets over time.

[0406] "Processing" refers to the calculations and analyses necessary to analyze market data and interpret or predict the information.

[0407] "Asset trading" refers to the buying and selling of stocks, bonds, and other investment assets in financial markets.

[0408] "Personalized investment advice" refers to investment suggestions that are customized based on the user's specific circumstances and emotional state.

[0409] "Recognizing the user's emotions" refers to using voice and other sensory data to determine the user's psychological state.

[0410] An "emotion analysis module" refers to software or hardware components that analyze a user's emotions from their voice and facial expressions to determine their emotional state.

[0411] A "speech recognition system" refers to a technology that converts speech data into text format.

[0412] A "general-purpose machine" refers to a hardware device that can be used for a variety of purposes, not just specific functions.

[0413] The system that realizes this invention optimizes asset trading in financial markets while taking into account the user's emotional state. It has the functionality to acquire, process, and analyze various data through the cooperation of a server and terminals.

[0414] The server retrieves market data in real time from financial APIs and news sources and runs processing programs to analyze it. Machine learning frameworks such as TensorFlow are used for analysis, including price fluctuation prediction and risk analysis. The results obtained from the analysis are used to make automated trading decisions.

[0415] Meanwhile, the device analyzes the user's emotions using Microsoft Azure's emotion recognition API. When the user accesses the system through the voice interface, the voice data is converted to text by Google Cloud Speech-to-Text. This text data is combined with market analysis results to generate personalized investment advice.

[0416] These processes can be incorporated into general-purpose machines, such as household robots. The robots monitor the user's emotional state through continuous interaction and provide investment advice at appropriate times. In particular, if emotional analysis indicates the user is experiencing stress, the robots can suggest more conservative investment strategies.

[0417] For example, if a user uses a voice command such as "Tell me my recent investment performance," the voice recognition system processes the command, and the server analyzes the investment performance, taking into account the user's emotional state and current market conditions, and reports it to the user's device.

[0418] Examples of prompts for the generating AI model include, "Tell me your recommended investment strategy when an investor is relaxed." In this way, flexible investment support tailored to the user's needs becomes possible through emotion-based interaction.

[0419] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0420] Step 1:

[0421] The server retrieves market data from financial APIs and news sources. Input is raw data from the APIs, and output is formatted data including price information and market trends. This data is organized by date and category for subsequent data analysis.

[0422] Step 2:

[0423] The server uses a machine learning model to analyze the acquired market data. The input is formatted market data, and the output is price fluctuation predictions and risk analysis results. The generative AI model performs predictive calculations from multiple data patterns to identify potential market fluctuations.

[0424] Step 3:

[0425] The device receives voice input from the user. The input is the user's voice data, and the output is text data. Google Cloud Speech-to-Text is used to convert the speech to text, preparing it to accurately understand the user's intent.

[0426] Step 4:

[0427] The device performs sentiment analysis on text obtained from audio data. The input is text data, and the output is the user's emotional state. Using Microsoft Azure's sentiment recognition API, it identifies emotions from the user's voice tone and speech content to determine their current psychological state.

[0428] Step 5:

[0429] The server generates personalized investment advice based on analyzed market data and the user's emotional state. The inputs are market analysis results and emotional analysis results, and the output is a personalized investment proposal. It dynamically adjusts investment strategies based on emotions, creating proposals adapted to the user's feelings.

[0430] Step 6:

[0431] The terminal delivers generated investment proposals to the user via voice. The input is investment proposals from the server, and the output is voice feedback. Using the terminal's speech synthesis function, the proposals are presented in a way that is easy for the user to understand, and detailed information and further interaction are provided as needed.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] [Third Embodiment]

[0436] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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".

[0448] The system based on this invention is designed to enable individual investors to invest in the market more easily and effectively. Specific embodiments are described below.

[0449] Server operation:

[0450] The server is responsible for acquiring and analyzing market information. It obtains real-time market information such as stock prices, exchange rates, and related news from external financial APIs. The acquired data is analyzed using machine learning algorithms. This analysis calculates price fluctuation predictions. The analysis outputs include buy / sell recommendations, risk assessments, and future trend predictions. The server also manages user portfolio information and executes automated trades based on pre-set conditions.

[0451] Device operation:

[0452] The terminal functions as an interface between the user and the server. It uses speech recognition technology to receive user instructions and questions and converts them into text data. For example, if a user asks, "What stock should I buy next?", the terminal transcribes the voice into text and sends it to the server. Upon receiving the analysis results from the server, the terminal provides a response to the user in either voice or text. This is presented as a personalized investment suggestion based on objective data.

[0453] User interaction:

[0454] Users interact with the system via smartphones or computers. For example, they can request detailed information on specific stocks or check their current investment performance. If a user sets specific trading conditions, the server records them and automatically executes trades when the conditions are met. This allows users to focus on investing with peace of mind, without having to react immediately to market movements.

[0455] Specific example:

[0456] For example, suppose a user wants to invest in a technology company. The device sends the company's name and investment amount to the server. The server analyzes all data related to that company and provides specific advice via the device, such as, "It's a good time to buy, as the stock price is expected to rise by 10% in the next week." Also, if the stock price of the same company that the user already owns rises sharply, the server automatically sells it and notifies the user of the result.

[0457] In this way, this system allows individual investors to utilize advanced investment analysis and achieve efficient asset management without requiring specialized knowledge.

[0458] The following describes the processing flow.

[0459] Step 1:

[0460] The server collects market information in real time from external financial APIs and news feeds. The data is stored in a database in the form of stock prices, economic indicators, and news articles.

[0461] Step 2:

[0462] The server applies machine learning algorithms to analyze the collected market information. It predicts price fluctuations and recognizes specific patterns, and as a result generates buy and sell recommendations.

[0463] Step 3:

[0464] The device uses voice recognition technology to receive questions and instructions from the user. For example, if a user says, "Which stocks should I buy now?", the device converts that voice into text data.

[0465] Step 4:

[0466] The terminal sends the converted text data to the server and requests the analysis results corresponding to that query.

[0467] Step 5:

[0468] The server identifies the optimal investment recommendations based on the user's request. For example, it selects forecast results and risk assessments for specific stocks and sends them back to the terminal.

[0469] Step 6:

[0470] The terminal reports information received from the server to the user. It informs the user of buy / sell suggestions and market conditions in voice or text format.

[0471] Step 7:

[0472] This system manages the user's portfolio and sets up automated trading. Based on the conditions set by the user, the server automatically executes trades.

[0473] Step 8:

[0474] The server records the results of a transaction in a database after it has been executed and notifies the user of the transaction results via the terminal.

[0475] Step 9:

[0476] The server periodically evaluates investment performance and generates reports for users. This allows users to check the latest asset status on their devices.

[0477] (Example 1)

[0478] 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."

[0479] It is not easy for individual investors to effectively collect and analyze market information, and as a result, they often miss appropriate buying and selling opportunities. Furthermore, a lack of expertise makes it difficult to make quick and accurate investment decisions. Users need a way to receive timely and personalized investment recommendations.

[0480] 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.

[0481] In this invention, the server includes means for acquiring market information, means for analyzing the acquired market information to predict price fluctuations, means for automating the buying and selling of assets, and means for converting user instructions into text data using speech recognition technology. This enables users to efficiently grasp market trends and make appropriate investment decisions without requiring specialized knowledge.

[0482] "Market information" refers to all data related to assets traded in financial markets, such as prices, exchange rates, and news.

[0483] "Analysis" refers to the process of analyzing acquired data to derive patterns and trends in price fluctuations.

[0484] "Price fluctuation prediction" refers to estimating future price trends using statistical methods and machine learning models based on market information.

[0485] "Automating asset trading" refers to a system where a program executes buy and sell transactions without manual intervention, based on predefined conditions.

[0486] "Speech recognition technology" refers to the technology that converts human speech into text data that a computer can understand.

[0487] "Personalized investment recommendations" refer to investment advice tailored to a specific individual, created based on the user's past investment history and current market conditions.

[0488] "Investment efficiency" refers to the optimization of the time and resources needed to increase the rate at which profits are generated from investment activities.

[0489] A "trading alert" refers to a warning message designed to notify investors of important market conditions and trading opportunities they should be aware of.

[0490] The system based on this invention combines multiple technical methods to enable individuals to conduct investment activities effectively. The implementation of the system is as follows:

[0491] Server operation:

[0492] The server periodically retrieves market information from financial information providers via APIs and stores it in a database. This process utilizes the Python requests library. The retrieved data is then analyzed using a machine learning model based on TensorFlow to predict price fluctuations. The server also includes a program that automatically buys and sells assets according to user-defined conditions based on these analysis results.

[0493] Device operation:

[0494] The device receives voice input from the user and converts it into text data using speech recognition technology. This conversion uses a cloud-based speech recognition service. For example, a user prompt such as "What stock should I buy next?" is converted and sent to the server. The analysis results from the server are then notified to the user by the device in both voice and text. To achieve this, the Python gTTS (Google Text-to-Speech) library is used to generate the speech.

[0495] User interaction:

[0496] Users can interact with the system via smartphones or computers. They can make requests via voice or text when seeking information about specific stocks, overall market trends, or their own investment performance. For example, if a user asks, "What will happen to a certain company's stock price?", the system will provide an analyzed suggestion in response to that question.

[0497] Specific example:

[0498] If a user is interested in a particular industry, they can enter the names of related companies in that industry as a prompt, and the server can provide analysis results including market trend forecasts for those companies and the industry as a whole. For example, if a prompt such as "Please tell me about recommended investment opportunities in the medical technology sector" is sent from the terminal to the server, the analysis results will be returned to the user as optimized investment advice.

[0499] This system allows users to invest more intelligently and confidently, maximizing their performance.

[0500] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0501] Step 1:

[0502] The server retrieves market information from financial information providers. It uses raw data received from financial APIs as input. This data consists of stock prices, exchange rates, news articles, etc., and is retrieved via HTTP requests. The output is stored in a database as structured data. For example, the Python requests library is configured to retrieve data every hour.

[0503] Step 2:

[0504] The server analyzes acquired market information using a machine learning model to predict price fluctuations. Historical market data from a database is used as input. TensorFlow is used to power an LSTM model that performs price predictions. The output is generated as predicted price fluctuations, buy / sell recommendations, and risk assessments, and is further formatted for notifications. This process is executed at the end of the day, after the market closes.

[0505] Step 3:

[0506] The device uses speech recognition technology to convert user instructions from speech to text. The input is the user's voice command. The converted text data is sent to a server and used as analysis results. For example, if a user says, "Tell me the stock price prediction for a specific company," that voice is converted into text data through a cloud-based speech recognition service.

[0507] Step 4:

[0508] The server analyzes text data received from the terminal and generates appropriate investment information based on the user's request. The input is a text prompt resulting from speech recognition. Correspondingly, information is drawn from past analysis results, and relevant data is extracted. The output information is then constructed as a message to respond to the user.

[0509] Step 5:

[0510] The terminal notifies the user of the analysis information returned from the server via voice or text. The input is the analysis result from the server. The audio generated using the Python gTTS library is played for the user, and the text information is displayed on the terminal's screen. For example, information such as "These are the best value stocks" is presented in both voice and text.

[0511] This allows users to receive real-time investment advice based on the latest market information, enabling them to make investment decisions quickly.

[0512] (Application Example 1)

[0513] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0514] Traditional investment systems struggle to effectively link individual investment results to consumption behavior, resulting in a lack of coordination between investment and consumption. Furthermore, there is insufficient support for individuals to make optimal consumption decisions based on their investment results.

[0515] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0516] In this invention, the server includes means for acquiring market information, means for analyzing the acquired market information to predict price fluctuations, means for automating the buying and selling of assets based on the analysis results, and means for making suggestions to optimize consumption behavior based on the feedbacked investment results. This makes it possible to efficiently utilize the profits obtained from an individual's investment for consumption and to optimize consumption behavior based on investment results.

[0517] "Market information" refers to data that affects asset values ​​in financial markets, such as stock prices, exchange rates, and related news.

[0518] "Analysis" refers to data processing that uses market information to predict price fluctuations and derive buy / sell recommendations and risk assessments.

[0519] "Automation" refers to a system autonomously executing the buying and selling of assets based on specific conditions or analysis results.

[0520] "Dialogue" refers to the exchange of information between a user and a system via voice or text.

[0521] A "proposal" refers to investment and consumption options and strategies provided to users based on analyzed data.

[0522] "Reporting" refers to the sharing of information to periodically inform users of the results of their investment performance.

[0523] "Optimizing consumer behavior" means providing support to enable users to utilize their funds most effectively based on investment results.

[0524] The system for implementing this invention mainly consists of a server, a terminal, and user interaction. The server is responsible for collecting market information using external financial APIs and analyzing that data. Machine learning algorithms are used for analysis to predict trends and assess risk. Based on the acquired analysis results, the server provides a function to automate investment buying and selling. Furthermore, it periodically reports the user's investment performance through a feedback function.

[0525] The terminal provides an interface for the user to interact with the system. Speech recognition technology built into the terminal converts voice commands from the user into text and sends it to the server. This allows the user to engage in dialogue by asking questions such as, "What stock should I buy next?" The terminal receives the analysis results from the server and communicates them to the user as voice or text.

[0526] Users can utilize personalized investment suggestions provided by the system through devices such as smartphones. Furthermore, by receiving suggestions to optimize their spending based on investment performance, they can utilize their funds more efficiently. For example, a list of products that can be purchased with current funds may be presented based on investment profits.

[0527] An example of a prompt message might be: "Generate optimal consumption suggestions based on the user's return on investment. Consider how to balance profit management and consumption optimization."

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

[0529] Step 1:

[0530] The server acquires market information through external financial APIs. It receives data such as stock prices, exchange rates, and related news as input, and stores this data as foundational information for analysis. The output is market information in raw data format.

[0531] Step 2:

[0532] The server analyzes acquired market information and uses machine learning models to predict price fluctuations. It receives market data as input, processes and analyzes it, performs trend prediction and risk assessment, and generates investment buy / sell recommendations and risk information as output.

[0533] Step 3:

[0534] The server executes automated asset trading based on the analysis results. It uses investment recommendation data generated by the server as input and buys and sells stocks and other assets based on pre-set conditions. The output is a record of the executed trades.

[0535] Step 4:

[0536] The terminal receives voice commands from the user and converts them into text data using speech recognition technology. Voice commands are provided as input and processed by the speech recognition engine. The output is the textualized user commands to be sent to the server.

[0537] Step 5:

[0538] The server processes textual instructions from the user and generates analysis results and investment recommendations. The input is user instruction data, and this data, along with the server's analysis results, is used to create personalized investment recommendations. The output is recommendation information in text and audio formats for the user.

[0539] Step 6:

[0540] The terminal communicates investment proposals received from the server to the user in voice or text format. It receives analysis results data from the server as input and notifies the user in a format they can understand. The output consists of investment information and consumption suggestions delivered to the user.

[0541] Step 7:

[0542] The user receives suggestions from the device, makes investment decisions, and optimizes their consumption behavior. The input is investment and consumption suggestions conveyed by the device, and the user decides on actions based on these suggestions. The output is the user's optimized investment and consumption patterns.

[0543] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0544] This invention's system is designed to allow individual investors to optimize their buying and selling in the market while taking into account their own emotions and investment attitudes. By incorporating an emotion engine, the system recognizes the user's emotions and dynamically adjusts personalized investment recommendations.

[0545] Server operation:

[0546] The server retrieves market information from financial APIs and news sources and analyzes the collected data. Machine learning models are used for analysis to predict price fluctuations and perform risk analysis. Based on the analysis results, the server automates the buying and selling of assets. Automated trading is executed according to pre-set conditions, but the user's emotional state may also be taken into consideration by an emotion engine.

[0547] Device operation:

[0548] The device establishes interaction with the user using speech recognition and emotion recognition technologies. The emotion engine, which reads emotions from speech, infers the user's emotional state from the content of their statements, tone of voice, and speaking speed. This allows the device to generate feedback tailored to the user's emotions. For example, if the user expresses anxiety, the device can offer more conservative investment proposals.

[0549] User interaction:

[0550] Users can interact with the system via voice commands and text through their smartphones or PCs. When the emotion engine detects the user's emotions, that information is used to adjust investment strategies. For example, if a user is indicated to have positive emotions, the system may suggest taking on risk and investing in new stocks.

[0551] Specific example:

[0552] For example, suppose a user asks about the current status of their portfolio. In this case, the device performs voice analysis, and the emotion engine recognizes that the user's voice sounds anxious. The server takes this emotional information into consideration and proposes an investment strategy that minimizes risk, and the device responds in a calm tone, saying, "Given the current market conditions, there are investment opportunities that can aim for steady profits while mitigating risk."

[0553] In this way, an emotionally sensitive approach becomes possible, enabling the creation of a system that reduces investor stress while providing asset management tailored to individual circumstances.

[0554] The following describes the processing flow.

[0555] Step 1:

[0556] The server collects market information in real time from financial APIs. Stock prices, exchange rates, and related news information are automatically stored in the database.

[0557] Step 2:

[0558] The server analyzes collected market information using machine learning algorithms to predict price fluctuations and assess risks. The analysis results are saved as reference material for future buy and sell recommendations.

[0559] Step 3:

[0560] The terminal receives voice input from the user and converts it into text data using speech recognition technology. The user inputs questions or instructions about investments they are interested in into the system.

[0561] Step 4:

[0562] The device uses emotion recognition technology to analyze the user's emotional state from their voice. For example, it determines the user's emotions from their tone and tempo and sends that data to a server.

[0563] Step 5:

[0564] The server integrates the user's emotional state with analyzed market data to generate personalized investment recommendations. For example, it might suggest a conservative investment strategy to a user who is feeling anxious.

[0565] Step 6:

[0566] The terminal presents investment proposals from the server to the user as audio or text. The proposals are delivered in a tone and content that is sensitive to the user's emotional state.

[0567] Step 7:

[0568] When a user decides to take action in response to a proposal, that action is notified to the server. For example, the user might approve the purchase of the proposed stock.

[0569] Step 8:

[0570] Based on the user's decision, the server activates the automated trading function and executes trades according to the set conditions. The trade details are then recorded again in the database.

[0571] Step 9:

[0572] The server analyzes the results of executed transactions and updates the user's portfolio status. It then reports the results via the terminal and notifies the user.

[0573] (Example 2)

[0574] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0575] When individual investors make investment decisions, emotions can have a significant influence, and irrational decisions based on emotions can negatively impact investment results. Furthermore, a lack of investment expertise makes it difficult to conduct proper market analysis and determine the right timing. The inability to seize investment opportunities in real time is also a challenge. To address these issues, there is a need for systems that provide personalized investment recommendations that take emotions into account, as well as automated trading.

[0576] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0577] In this invention, the server includes means for acquiring market data, means for analyzing the acquired market data to predict numerical fluctuations, means for automating asset transactions based on the analysis results, means for recognizing the user's emotional state and generating personalized investment proposals based on that information, means for providing emotionally appropriate responses through dialogue with the user, and means for periodically reporting the user's investment performance. This facilitates appropriate investment decisions that take the user's emotions into account and enables real-time optimization of market opportunities.

[0578] "Market data" refers to information about price fluctuations and trading volume in the market, and includes a variety of information such as economic indicators and news data.

[0579] "Analysis" refers to the activity of processing collected data to reveal trends and patterns in the information.

[0580] "Numerical fluctuation" refers to changes in numerical values ​​such as price or trading volume in a particular market over time.

[0581] "Asset trading" refers to the buying and selling of stocks, bonds, and other assets in financial markets, and is the act of increasing or decreasing their value through investment.

[0582] "Automation" refers to a state in which programs or machines perform actions independently without requiring manual operation.

[0583] "Users" refers to individuals or corporations that use this system, and specifically those interested in investment.

[0584] "Emotional state" refers to the user's current psychological state, including feelings of anxiety, joy, and security.

[0585] "Personalized investment recommendations" refer to providing specific investment strategies and advice based on the individual attributes and sentiments of each user.

[0586] "Dialogue" refers to communication between the user and the system, including communication conducted through voice and text.

[0587] "Real-time" refers to a situation where events unfold almost simultaneously, and reactions or processing occur immediately.

[0588] This system is designed to help individual investors optimize their market trading. The server is primarily responsible for collecting and analyzing market data. Specifically, it utilizes internet communication modules to obtain information from financial data provider APIs and news sites. The data is analyzed using machine learning libraries such as TensorFlow and PyTorch to predict fluctuation patterns and assess risk. Based on these analysis results, the buying and selling of assets is automated according to the user's settings.

[0589] The device functions to support interaction with the user. Specifically, it uses Google's speech recognition technology and Microsoft's cloud services to convert the user's voice commands into text and uses an emotion recognition algorithm to infer the emotional state. This emotion engine on the device determines the current emotional state based on the tone and content of the user's voice. Based on this, the device provides appropriate feedback through voice and screen displays.

[0590] Users can interact with the system via smartphones or personal computers. For example, if a user asks "What is the status of my portfolio?" using voice commands, the device analyzes the voice and queries the server. The server considers the analysis results and the user's emotional state to generate optimal investment suggestions. Specifically, if the user expresses anxiety, a conservative investment plan with reduced risk will be presented.

[0591] One example of a prompt generated using a generative AI model is the instruction, "Consider the emotions gleaned from the user's voice and generate the optimal investment proposal." This prompt allows the AI ​​to autonomously generate appropriate proposals while considering the user's emotional state. Through this series of operations, the system makes it easier for users to make emotionally conscious investment decisions, helping them achieve better investment performance.

[0592] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0593] Step 1:

[0594] The server retrieves market data via the market data provider's API. Inputs include price fluctuations and trading volume data from the API. Outputs are price and trend datasets necessary for analysis. Specifically, the server calls the API at regular intervals to keep the data up-to-date.

[0595] Step 2:

[0596] The server uses the acquired data to perform data analysis through a machine learning model. The input is the numerical data obtained in the previous step, and the output is the analysis results such as price prediction and risk assessment. The data is analyzed using TensorFlow or PyTorch, and the algorithm performs trend analysis of price fluctuations based on historical data.

[0597] Step 3:

[0598] The terminal receives voice commands from the user and uses speech recognition software to convert the commands into text. The input is the user's voice, and the output is the command text converted into text format. In its specific operation, the terminal collects voice through the microphone and processes the data in real time.

[0599] Step 4:

[0600] The device uses textual commands and voice data to analyze the user's emotions through an emotion engine. Input includes voice data and its textual commands, while output is the user's emotional state (e.g., reassured, excited, anxious). The device extracts emotions from voice tone and speed and sends feedback to the server.

[0601] Step 5:

[0602] The server generates investment proposals by combining analysis results and emotional states. The inputs are primarily analysis results and the user's emotional state, while the output is a customized investment proposal presented to the user. The server then uses a predefined generative AI model to generate prompts and construct the optimal investment plan.

[0603] Step 6:

[0604] The terminal provides investment suggestions to the user via voice or text. The input is investment suggestions from the server, and the output is easy-to-understand instructions presented to the user. Specifically, the terminal communicates the suggestions by either synthesizing the text into speech or displaying it on the screen. Based on this, the user can consider their next trading action.

[0605] (Application Example 2)

[0606] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0607] Traditional investment systems only provide objective analysis based on market data, lacking the ability to consider the emotional state of the user. This meant users could be influenced by their own emotions and attitudes, potentially leading to inappropriate investment decisions. Furthermore, while there is a demand for investment support that enhances convenience in a home environment, effective means to achieve this have been lacking.

[0608] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0609] In this invention, the server includes means for recognizing the user's emotions and adjusting the investment strategy based on the emotional state, means for mounting a device for generating personalized investment advice on a general-purpose machine for use in a home environment, and a device for converting voice information into text information. This enables the provision of investment strategies that take the user's emotions into consideration and allows for easy use in a home environment.

[0610] "Market data" refers to information including price information, trading volume, and trends in financial markets.

[0611] "Price fluctuation" refers to the rise or fall of asset prices in financial markets over time.

[0612] "Processing" refers to the calculations and analyses necessary to analyze market data and interpret or predict the information.

[0613] "Asset trading" refers to the buying and selling of stocks, bonds, and other investment assets in financial markets.

[0614] "Personalized investment advice" refers to investment suggestions that are customized based on the user's specific circumstances and emotional state.

[0615] "Recognizing the user's emotions" refers to using voice and other sensory data to determine the user's psychological state.

[0616] An "emotion analysis module" refers to software or hardware components that analyze a user's emotions from their voice and facial expressions to determine their emotional state.

[0617] A "speech recognition system" refers to a technology that converts speech data into text format.

[0618] A "general-purpose machine" refers to a hardware device that can be used for a variety of purposes, not just specific functions.

[0619] The system that realizes this invention optimizes asset trading in financial markets while taking into account the user's emotional state. It has the functionality to acquire, process, and analyze various data through the cooperation of a server and terminals.

[0620] The server retrieves market data in real time from financial APIs and news sources and runs processing programs to analyze it. Machine learning frameworks such as TensorFlow are used for analysis, including price fluctuation prediction and risk analysis. The results obtained from the analysis are used to make automated trading decisions.

[0621] Meanwhile, the device analyzes the user's emotions using Microsoft Azure's emotion recognition API. When the user accesses the system through the voice interface, the voice data is converted to text by Google Cloud Speech-to-Text. This text data is combined with market analysis results to generate personalized investment advice.

[0622] These processes can be incorporated into general-purpose machines, such as household robots. The robots monitor the user's emotional state through continuous interaction and provide investment advice at appropriate times. In particular, if emotional analysis indicates the user is experiencing stress, the robots can suggest more conservative investment strategies.

[0623] For example, if a user uses a voice command such as "Tell me my recent investment performance," the voice recognition system processes the command, and the server analyzes the investment performance, taking into account the user's emotional state and current market conditions, and reports it to the user's device.

[0624] Examples of prompts for the generating AI model include, "Tell me your recommended investment strategy when an investor is relaxed." In this way, flexible investment support tailored to the user's needs becomes possible through emotion-based interaction.

[0625] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0626] Step 1:

[0627] The server retrieves market data from financial APIs and news sources. Input is raw data from the APIs, and output is formatted data including price information and market trends. This data is organized by date and category for subsequent data analysis.

[0628] Step 2:

[0629] The server uses a machine learning model to analyze the acquired market data. The input is formatted market data, and the output is price fluctuation predictions and risk analysis results. The generative AI model performs predictive calculations from multiple data patterns to identify potential market fluctuations.

[0630] Step 3:

[0631] The device receives voice input from the user. The input is the user's voice data, and the output is text data. Google Cloud Speech-to-Text is used to convert the speech to text, preparing it to accurately understand the user's intent.

[0632] Step 4:

[0633] The device performs sentiment analysis on text obtained from audio data. The input is text data, and the output is the user's emotional state. Using Microsoft Azure's sentiment recognition API, it identifies emotions from the user's voice tone and speech content to determine their current psychological state.

[0634] Step 5:

[0635] The server generates personalized investment advice based on analyzed market data and the user's emotional state. The inputs are market analysis results and emotional analysis results, and the output is a personalized investment proposal. It dynamically adjusts investment strategies based on emotions, creating proposals adapted to the user's feelings.

[0636] Step 6:

[0637] The terminal delivers generated investment proposals to the user via voice. The input is investment proposals from the server, and the output is voice feedback. Using the terminal's speech synthesis function, the proposals are presented in a way that is easy for the user to understand, and detailed information and further interaction are provided as needed.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] [Fourth Embodiment]

[0642] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0643] 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.

[0644] 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).

[0645] 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.

[0646] 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.

[0647] 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).

[0648] 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.

[0649] 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.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] 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.

[0654] 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".

[0655] The system based on this invention is designed to enable individual investors to invest in the market more easily and effectively. Specific embodiments are described below.

[0656] Server operation:

[0657] The server is responsible for acquiring and analyzing market information. It obtains real-time market information such as stock prices, exchange rates, and related news from external financial APIs. The acquired data is analyzed using machine learning algorithms. This analysis calculates price fluctuation predictions. The analysis outputs include buy / sell recommendations, risk assessments, and future trend predictions. The server also manages user portfolio information and executes automated trades based on pre-set conditions.

[0658] Device operation:

[0659] The terminal functions as an interface between the user and the server. It uses speech recognition technology to receive user instructions and questions and converts them into text data. For example, if a user asks, "What stock should I buy next?", the terminal transcribes the voice into text and sends it to the server. Upon receiving the analysis results from the server, the terminal provides a response to the user in either voice or text. This is presented as a personalized investment suggestion based on objective data.

[0660] User interaction:

[0661] Users interact with the system via smartphones or computers. For example, they can request detailed information on specific stocks or check their current investment performance. If a user sets specific trading conditions, the server records them and automatically executes trades when the conditions are met. This allows users to focus on investing with peace of mind, without having to react immediately to market movements.

[0662] Specific example:

[0663] For example, suppose a user wants to invest in a technology company. The device sends the company's name and investment amount to the server. The server analyzes all data related to that company and provides specific advice via the device, such as, "It's a good time to buy, as the stock price is expected to rise by 10% in the next week." Also, if the stock price of the same company that the user already owns rises sharply, the server automatically sells it and notifies the user of the result.

[0664] In this way, this system allows individual investors to utilize advanced investment analysis and achieve efficient asset management without requiring specialized knowledge.

[0665] The following describes the processing flow.

[0666] Step 1:

[0667] The server collects market information in real time from external financial APIs and news feeds. The data is stored in a database in the form of stock prices, economic indicators, and news articles.

[0668] Step 2:

[0669] The server applies machine learning algorithms to analyze the collected market information. It predicts price fluctuations and recognizes specific patterns, and as a result generates buy and sell recommendations.

[0670] Step 3:

[0671] The device uses voice recognition technology to receive questions and instructions from the user. For example, if a user says, "Which stocks should I buy now?", the device converts that voice into text data.

[0672] Step 4:

[0673] The terminal sends the converted text data to the server and requests the analysis results corresponding to that query.

[0674] Step 5:

[0675] The server identifies the optimal investment recommendations based on the user's request. For example, it selects forecast results and risk assessments for specific stocks and sends them back to the terminal.

[0676] Step 6:

[0677] The terminal reports information received from the server to the user. It informs the user of buy / sell suggestions and market conditions in voice or text format.

[0678] Step 7:

[0679] This system manages the user's portfolio and sets up automated trading. Based on the conditions set by the user, the server automatically executes trades.

[0680] Step 8:

[0681] The server records the results of a transaction in a database after it has been executed and notifies the user of the transaction results via the terminal.

[0682] Step 9:

[0683] The server periodically evaluates investment performance and generates reports for users. This allows users to check the latest asset status on their devices.

[0684] (Example 1)

[0685] 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".

[0686] It is not easy for individual investors to effectively collect and analyze market information, and as a result, they often miss appropriate buying and selling opportunities. Furthermore, a lack of expertise makes it difficult to make quick and accurate investment decisions. Users need a way to receive timely and personalized investment recommendations.

[0687] 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.

[0688] In this invention, the server includes means for acquiring market information, means for analyzing the acquired market information to predict price fluctuations, means for automating the buying and selling of assets, and means for converting user instructions into text data using speech recognition technology. This enables users to efficiently grasp market trends and make appropriate investment decisions without requiring specialized knowledge.

[0689] "Market information" refers to all data related to assets traded in financial markets, such as prices, exchange rates, and news.

[0690] "Analysis" refers to the process of analyzing acquired data to derive patterns and trends in price fluctuations.

[0691] "Price fluctuation prediction" refers to estimating future price trends using statistical methods and machine learning models based on market information.

[0692] "Automating asset trading" refers to a system where a program executes buy and sell transactions without manual intervention, based on predefined conditions.

[0693] "Speech recognition technology" refers to the technology that converts human speech into text data that a computer can understand.

[0694] "Personalized investment recommendations" refer to investment advice tailored to a specific individual, created based on the user's past investment history and current market conditions.

[0695] "Investment efficiency" refers to the optimization of the time and resources needed to increase the rate at which profits are generated from investment activities.

[0696] A "trading alert" refers to a warning message designed to notify investors of important market conditions and trading opportunities they should be aware of.

[0697] The system based on this invention combines multiple technical methods to enable individuals to conduct investment activities effectively. The implementation of the system is as follows:

[0698] Server operation:

[0699] The server periodically retrieves market information from financial information providers via APIs and stores it in a database. This process utilizes the Python requests library. The retrieved data is then analyzed using a machine learning model based on TensorFlow to predict price fluctuations. The server also includes a program that automatically buys and sells assets according to user-defined conditions based on these analysis results.

[0700] Device operation:

[0701] The device receives voice input from the user and converts it into text data using speech recognition technology. This conversion uses a cloud-based speech recognition service. For example, a user prompt such as "What stock should I buy next?" is converted and sent to the server. The analysis results from the server are then notified to the user by the device in both voice and text. To achieve this, the Python gTTS (Google Text-to-Speech) library is used to generate the speech.

[0702] User interaction:

[0703] Users can interact with the system via smartphones or computers. They can make requests via voice or text when seeking information about specific stocks, overall market trends, or their own investment performance. For example, if a user asks, "What will happen to a certain company's stock price?", the system will provide an analyzed suggestion in response to that question.

[0704] Specific example:

[0705] If a user is interested in a particular industry, they can enter the names of related companies in that industry as a prompt, and the server can provide analysis results including market trend forecasts for those companies and the industry as a whole. For example, if a prompt such as "Please tell me about recommended investment opportunities in the medical technology sector" is sent from the terminal to the server, the analysis results will be returned to the user as optimized investment advice.

[0706] This system allows users to invest more intelligently and confidently, maximizing their performance.

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

[0708] Step 1:

[0709] The server retrieves market information from financial information providers. It uses raw data received from financial APIs as input. This data consists of stock prices, exchange rates, news articles, etc., and is retrieved via HTTP requests. The output is stored in a database as structured data. For example, the Python requests library is configured to retrieve data every hour.

[0710] Step 2:

[0711] The server analyzes acquired market information using a machine learning model to predict price fluctuations. Historical market data from a database is used as input. TensorFlow is used to power an LSTM model that performs price predictions. The output is generated as predicted price fluctuations, buy / sell recommendations, and risk assessments, and is further formatted for notifications. This process is executed at the end of the day, after the market closes.

[0712] Step 3:

[0713] The device uses speech recognition technology to convert user instructions from speech to text. The input is the user's voice command. The converted text data is sent to a server and used as analysis results. For example, if a user says, "Tell me the stock price prediction for a specific company," that voice is converted into text data through a cloud-based speech recognition service.

[0714] Step 4:

[0715] The server analyzes text data received from the terminal and generates appropriate investment information based on the user's request. The input is a text prompt resulting from speech recognition. Correspondingly, information is drawn from past analysis results, and relevant data is extracted. The output information is then constructed as a message to respond to the user.

[0716] Step 5:

[0717] The terminal notifies the user of the analysis information returned from the server via voice or text. The input is the analysis result from the server. The audio generated using the Python gTTS library is played for the user, and the text information is displayed on the terminal's screen. For example, information such as "These are the best value stocks" is presented in both voice and text.

[0718] This allows users to receive real-time investment advice based on the latest market information, enabling them to make investment decisions quickly.

[0719] (Application Example 1)

[0720] 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".

[0721] Traditional investment systems struggle to effectively link individual investment results to consumption behavior, resulting in a lack of coordination between investment and consumption. Furthermore, there is insufficient support for individuals to make optimal consumption decisions based on their investment results.

[0722] 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.

[0723] In this invention, the server includes means for acquiring market information, means for analyzing the acquired market information to predict price fluctuations, means for automating the buying and selling of assets based on the analysis results, and means for making suggestions to optimize consumption behavior based on the feedbacked investment results. This makes it possible to efficiently utilize the profits obtained from an individual's investment for consumption and to optimize consumption behavior based on investment results.

[0724] "Market information" refers to data that affects asset values ​​in financial markets, such as stock prices, exchange rates, and related news.

[0725] "Analysis" refers to data processing that uses market information to predict price fluctuations and derive buy / sell recommendations and risk assessments.

[0726] "Automation" refers to a system autonomously executing the buying and selling of assets based on specific conditions or analysis results.

[0727] "Dialogue" refers to the exchange of information between a user and a system via voice or text.

[0728] A "proposal" refers to investment and consumption options and strategies provided to users based on analyzed data.

[0729] "Reporting" refers to the sharing of information to periodically inform users of the results of their investment performance.

[0730] "Optimizing consumer behavior" means providing support to enable users to utilize their funds most effectively based on investment results.

[0731] The system for implementing this invention mainly consists of a server, a terminal, and user interaction. The server is responsible for collecting market information using external financial APIs and analyzing that data. Machine learning algorithms are used for analysis to predict trends and assess risk. Based on the acquired analysis results, the server provides a function to automate investment buying and selling. Furthermore, it periodically reports the user's investment performance through a feedback function.

[0732] The terminal provides an interface for the user to interact with the system. Speech recognition technology built into the terminal converts voice commands from the user into text and sends it to the server. This allows the user to engage in dialogue by asking questions such as, "What stock should I buy next?" The terminal receives the analysis results from the server and communicates them to the user as voice or text.

[0733] Users can utilize personalized investment suggestions provided by the system through devices such as smartphones. Furthermore, by receiving suggestions to optimize their spending based on investment performance, they can utilize their funds more efficiently. For example, a list of products that can be purchased with current funds may be presented based on investment profits.

[0734] An example of a prompt message might be: "Generate optimal consumption suggestions based on the user's return on investment. Consider how to balance profit management and consumption optimization."

[0735] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0736] Step 1:

[0737] The server acquires market information through external financial APIs. It receives data such as stock prices, exchange rates, and related news as input, and stores this data as foundational information for analysis. The output is market information in raw data format.

[0738] Step 2:

[0739] The server analyzes acquired market information and uses machine learning models to predict price fluctuations. It receives market data as input, processes and analyzes it, performs trend prediction and risk assessment, and generates investment buy / sell recommendations and risk information as output.

[0740] Step 3:

[0741] The server executes automated asset trading based on the analysis results. It uses investment recommendation data generated by the server as input and buys and sells stocks and other assets based on pre-set conditions. The output is a record of the executed trades.

[0742] Step 4:

[0743] The terminal receives voice commands from the user and converts them into text data using speech recognition technology. Voice commands are provided as input and processed by the speech recognition engine. The output is the textualized user commands to be sent to the server.

[0744] Step 5:

[0745] The server processes textual instructions from the user and generates analysis results and investment recommendations. The input is user instruction data, and this data, along with the server's analysis results, is used to create personalized investment recommendations. The output is recommendation information in text and audio formats for the user.

[0746] Step 6:

[0747] The terminal communicates investment proposals received from the server to the user in voice or text format. It receives analysis results data from the server as input and notifies the user in a format they can understand. The output consists of investment information and consumption suggestions delivered to the user.

[0748] Step 7:

[0749] The user receives suggestions from the device, makes investment decisions, and optimizes their consumption behavior. The input is investment and consumption suggestions conveyed by the device, and the user decides on actions based on these suggestions. The output is the user's optimized investment and consumption patterns.

[0750] 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.

[0751] This invention's system is designed to allow individual investors to optimize their buying and selling in the market while taking into account their own emotions and investment attitudes. By incorporating an emotion engine, the system recognizes the user's emotions and dynamically adjusts personalized investment recommendations.

[0752] Server operation:

[0753] The server retrieves market information from financial APIs and news sources and analyzes the collected data. Machine learning models are used for analysis to predict price fluctuations and perform risk analysis. Based on the analysis results, the server automates the buying and selling of assets. Automated trading is executed according to pre-set conditions, but the user's emotional state may also be taken into consideration by an emotion engine.

[0754] Device operation:

[0755] The device establishes interaction with the user using speech recognition and emotion recognition technologies. The emotion engine, which reads emotions from speech, infers the user's emotional state from the content of their statements, tone of voice, and speaking speed. This allows the device to generate feedback tailored to the user's emotions. For example, if the user expresses anxiety, the device can offer more conservative investment proposals.

[0756] User interaction:

[0757] Users can interact with the system via voice commands and text through their smartphones or PCs. When the emotion engine detects the user's emotions, that information is used to adjust investment strategies. For example, if a user is indicated to have positive emotions, the system may suggest taking on risk and investing in new stocks.

[0758] Specific example:

[0759] For example, suppose a user asks about the current status of their portfolio. In this case, the device performs voice analysis, and the emotion engine recognizes that the user's voice sounds anxious. The server takes this emotional information into consideration and proposes an investment strategy that minimizes risk, and the device responds in a calm tone, saying, "Given the current market conditions, there are investment opportunities that can aim for steady profits while mitigating risk."

[0760] In this way, an emotionally sensitive approach becomes possible, enabling the creation of a system that reduces investor stress while providing asset management tailored to individual circumstances.

[0761] The following describes the processing flow.

[0762] Step 1:

[0763] The server collects market information in real time from financial APIs. Stock prices, exchange rates, and related news information are automatically stored in the database.

[0764] Step 2:

[0765] The server analyzes collected market information using machine learning algorithms to predict price fluctuations and assess risks. The analysis results are saved as reference material for future buy and sell recommendations.

[0766] Step 3:

[0767] The terminal receives voice input from the user and converts it into text data using speech recognition technology. The user inputs questions or instructions about investments they are interested in into the system.

[0768] Step 4:

[0769] The device uses emotion recognition technology to analyze the user's emotional state from their voice. For example, it determines the user's emotions from their tone and tempo and sends that data to a server.

[0770] Step 5:

[0771] The server integrates the user's emotional state with analyzed market data to generate personalized investment recommendations. For example, it might suggest a conservative investment strategy to a user who is feeling anxious.

[0772] Step 6:

[0773] The terminal presents investment proposals from the server to the user as audio or text. The proposals are delivered in a tone and content that is sensitive to the user's emotional state.

[0774] Step 7:

[0775] When a user decides to take action in response to a proposal, that action is notified to the server. For example, the user might approve the purchase of the proposed stock.

[0776] Step 8:

[0777] Based on the user's decision, the server activates the automated trading function and executes trades according to the set conditions. The trade details are then recorded again in the database.

[0778] Step 9:

[0779] The server analyzes the results of executed transactions and updates the user's portfolio status. It then reports the results via the terminal and notifies the user.

[0780] (Example 2)

[0781] 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".

[0782] When individual investors make investment decisions, emotions can have a significant influence, and irrational decisions based on emotions can negatively impact investment results. Furthermore, a lack of investment expertise makes it difficult to conduct proper market analysis and determine the right timing. The inability to seize investment opportunities in real time is also a challenge. To address these issues, there is a need for systems that provide personalized investment recommendations that take emotions into account, as well as automated trading.

[0783] 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.

[0784] In this invention, the server includes means for acquiring market data, means for analyzing the acquired market data to predict numerical fluctuations, means for automating asset transactions based on the analysis results, means for recognizing the user's emotional state and generating personalized investment proposals based on that information, means for providing emotionally appropriate responses through dialogue with the user, and means for periodically reporting the user's investment performance. This facilitates appropriate investment decisions that take the user's emotions into account and enables real-time optimization of market opportunities.

[0785] "Market data" refers to information about price fluctuations and trading volume in the market, and includes a variety of information such as economic indicators and news data.

[0786] "Analysis" refers to the activity of processing collected data to reveal trends and patterns in the information.

[0787] "Numerical fluctuation" refers to changes in numerical values ​​such as price or trading volume in a particular market over time.

[0788] "Asset trading" refers to the buying and selling of stocks, bonds, and other assets in financial markets, and is the act of increasing or decreasing their value through investment.

[0789] "Automation" refers to a state in which programs or machines perform actions independently without requiring manual operation.

[0790] "Users" refers to individuals or corporations that use this system, and specifically those interested in investment.

[0791] "Emotional state" refers to the user's current psychological state, including feelings of anxiety, joy, and security.

[0792] "Personalized investment recommendations" refer to providing specific investment strategies and advice based on the individual attributes and sentiments of each user.

[0793] "Dialogue" refers to communication between the user and the system, including communication conducted through voice and text.

[0794] "Real-time" refers to a situation where events unfold almost simultaneously, and reactions or processing occur immediately.

[0795] This system is designed to help individual investors optimize their market trading. The server is primarily responsible for collecting and analyzing market data. Specifically, it utilizes internet communication modules to obtain information from financial data provider APIs and news sites. The data is analyzed using machine learning libraries such as TensorFlow and PyTorch to predict fluctuation patterns and assess risk. Based on these analysis results, the buying and selling of assets is automated according to the user's settings.

[0796] The device functions to support interaction with the user. Specifically, it uses Google's speech recognition technology and Microsoft's cloud services to convert the user's voice commands into text and uses an emotion recognition algorithm to infer the emotional state. This emotion engine on the device determines the current emotional state based on the tone and content of the user's voice. Based on this, the device provides appropriate feedback through voice and screen displays.

[0797] Users can interact with the system via smartphones or personal computers. For example, if a user asks "What is the status of my portfolio?" using voice commands, the device analyzes the voice and queries the server. The server considers the analysis results and the user's emotional state to generate optimal investment suggestions. Specifically, if the user expresses anxiety, a conservative investment plan with reduced risk will be presented.

[0798] One example of a prompt generated using a generative AI model is the instruction, "Consider the emotions gleaned from the user's voice and generate the optimal investment proposal." This prompt allows the AI ​​to autonomously generate appropriate proposals while considering the user's emotional state. Through this series of operations, the system makes it easier for users to make emotionally conscious investment decisions, helping them achieve better investment performance.

[0799] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0800] Step 1:

[0801] The server retrieves market data via the market data provider's API. Inputs include price fluctuations and trading volume data from the API. Outputs are price and trend datasets necessary for analysis. Specifically, the server calls the API at regular intervals to keep the data up-to-date.

[0802] Step 2:

[0803] The server uses the acquired data to perform data analysis through a machine learning model. The input is the numerical data obtained in the previous step, and the output is the analysis results such as price prediction and risk assessment. The data is analyzed using TensorFlow or PyTorch, and the algorithm performs trend analysis of price fluctuations based on historical data.

[0804] Step 3:

[0805] The terminal receives voice commands from the user and uses speech recognition software to convert the commands into text. The input is the user's voice, and the output is the command text converted into text format. In its specific operation, the terminal collects voice through the microphone and processes the data in real time.

[0806] Step 4:

[0807] The device uses textual commands and voice data to analyze the user's emotions through an emotion engine. Input includes voice data and its textual commands, while output is the user's emotional state (e.g., reassured, excited, anxious). The device extracts emotions from voice tone and speed and sends feedback to the server.

[0808] Step 5:

[0809] The server generates investment proposals by combining analysis results and emotional states. The inputs are primarily analysis results and the user's emotional state, while the output is a customized investment proposal presented to the user. The server then uses a predefined generative AI model to generate prompts and construct the optimal investment plan.

[0810] Step 6:

[0811] The terminal provides investment suggestions to the user via voice or text. The input is investment suggestions from the server, and the output is easy-to-understand instructions presented to the user. Specifically, the terminal communicates the suggestions by either synthesizing the text into speech or displaying it on the screen. Based on this, the user can consider their next trading action.

[0812] (Application Example 2)

[0813] 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".

[0814] Traditional investment systems only provide objective analysis based on market data, lacking the ability to consider the emotional state of the user. This meant users could be influenced by their own emotions and attitudes, potentially leading to inappropriate investment decisions. Furthermore, while there is a demand for investment support that enhances convenience in a home environment, effective means to achieve this have been lacking.

[0815] 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.

[0816] In this invention, the server includes means for recognizing the user's emotions and adjusting the investment strategy based on the emotional state, means for mounting a device for generating personalized investment advice on a general-purpose machine for use in a home environment, and a device for converting voice information into text information. This enables the provision of investment strategies that take the user's emotions into consideration and allows for easy use in a home environment.

[0817] "Market data" refers to information including price information, trading volume, and trends in financial markets.

[0818] "Price fluctuation" refers to the rise or fall of asset prices in financial markets over time.

[0819] "Processing" refers to the calculations and analyses necessary to analyze market data and interpret or predict the information.

[0820] "Asset trading" refers to the buying and selling of stocks, bonds, and other investment assets in financial markets.

[0821] "Personalized investment advice" refers to investment suggestions that are customized based on the user's specific circumstances and emotional state.

[0822] "Recognizing the user's emotions" refers to using voice and other sensory data to determine the user's psychological state.

[0823] An "emotion analysis module" refers to software or hardware components that analyze a user's emotions from their voice and facial expressions to determine their emotional state.

[0824] A "speech recognition system" refers to a technology that converts speech data into text format.

[0825] A "general-purpose machine" refers to a hardware device that can be used for a variety of purposes, not just specific functions.

[0826] The system that realizes this invention optimizes asset trading in financial markets while taking into account the user's emotional state. It has the functionality to acquire, process, and analyze various data through the cooperation of a server and terminals.

[0827] The server retrieves market data in real time from financial APIs and news sources and runs processing programs to analyze it. Machine learning frameworks such as TensorFlow are used for analysis, including price fluctuation prediction and risk analysis. The results obtained from the analysis are used to make automated trading decisions.

[0828] Meanwhile, the device analyzes the user's emotions using Microsoft Azure's emotion recognition API. When the user accesses the system through the voice interface, the voice data is converted to text by Google Cloud Speech-to-Text. This text data is combined with market analysis results to generate personalized investment advice.

[0829] These processes can be incorporated into general-purpose machines, such as household robots. The robots monitor the user's emotional state through continuous interaction and provide investment advice at appropriate times. In particular, if emotional analysis indicates the user is experiencing stress, the robots can suggest more conservative investment strategies.

[0830] For example, if a user uses a voice command such as "Tell me my recent investment performance," the voice recognition system processes the command, and the server analyzes the investment performance, taking into account the user's emotional state and current market conditions, and reports it to the user's device.

[0831] Examples of prompts for the generating AI model include, "Tell me your recommended investment strategy when an investor is relaxed." In this way, flexible investment support tailored to the user's needs becomes possible through emotion-based interaction.

[0832] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0833] Step 1:

[0834] The server retrieves market data from financial APIs and news sources. Input is raw data from the APIs, and output is formatted data including price information and market trends. This data is organized by date and category for subsequent data analysis.

[0835] Step 2:

[0836] The server uses a machine learning model to analyze the acquired market data. The input is formatted market data, and the output is price fluctuation predictions and risk analysis results. The generative AI model performs predictive calculations from multiple data patterns to identify potential market fluctuations.

[0837] Step 3:

[0838] The device receives voice input from the user. The input is the user's voice data, and the output is text data. Google Cloud Speech-to-Text is used to convert the speech to text, preparing it to accurately understand the user's intent.

[0839] Step 4:

[0840] The device performs sentiment analysis on text obtained from audio data. The input is text data, and the output is the user's emotional state. Using Microsoft Azure's sentiment recognition API, it identifies emotions from the user's voice tone and speech content to determine their current psychological state.

[0841] Step 5:

[0842] The server generates personalized investment advice based on analyzed market data and the user's emotional state. The inputs are market analysis results and emotional analysis results, and the output is a personalized investment proposal. It dynamically adjusts investment strategies based on emotions, creating proposals adapted to the user's feelings.

[0843] Step 6:

[0844] The terminal delivers generated investment proposals to the user via voice. The input is investment proposals from the server, and the output is voice feedback. Using the terminal's speech synthesis function, the proposals are presented in a way that is easy for the user to understand, and detailed information and further interaction are provided as needed.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] The inside of the Emotion Map 400 represents what's in your mind, while the outside represents what you're doing. Therefore, the further you go out the 400-coordinate scale, the more visible your emotions become (the more they manifest in your actions).

[0852] 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.

[0853] 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."

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0866] The following is further disclosed regarding the embodiments described above.

[0867] (Claim 1)

[0868] Means of obtaining market information,

[0869] A means of analyzing acquired market information to predict price fluctuations,

[0870] Based on the analysis results, a means to automate the buying and selling of assets,

[0871] A means of generating personalized investment proposals through interaction with users,

[0872] A means of regularly reporting on the user's investment performance,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, further comprising means for converting audio data into text data.

[0876] (Claim 3)

[0877] The system according to claim 1, further comprising means for optimizing the timing of investments in real time based on the analysis results.

[0878] "Example 1"

[0879] (Claim 1)

[0880] Means of obtaining market information,

[0881] A means of analyzing acquired market information to predict price fluctuations,

[0882] Based on the analysis results, a means to automate the buying and selling of assets,

[0883] A means of converting user instructions into text data using speech recognition technology,

[0884] A means of generating personalized investment proposals through interaction with users,

[0885] A means of regularly reporting on the user's investment efficiency,

[0886] A means of notifying the user of the analysis results via voice and text,

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, further comprising means for updating and analyzing acquired market information on an hourly basis.

[0890] (Claim 3)

[0891] The system according to claim 1, further comprising means for generating buy / sell alerts based on real-time market fluctuation predictions from analysis results.

[0892] "Application Example 1"

[0893] (Claim 1)

[0894] Means of obtaining market information,

[0895] A means of analyzing acquired market information to predict price fluctuations,

[0896] Based on the analysis results, a means to automate the buying and selling of assets,

[0897] A means of generating personalized suggestions through interaction with the user,

[0898] A means of regularly reporting on the user's investment performance,

[0899] A means of proposing ways to optimize consumer behavior based on feedback on investment results,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, further comprising means for converting audio data into text data.

[0903] (Claim 3)

[0904] The system according to claim 1, further comprising means for optimizing the timing of consumption in real time, taking market information into consideration, based on the analysis results.

[0905] "Example 2 of combining an emotion engine"

[0906] (Claim 1)

[0907] Means of obtaining market data,

[0908] A method for analyzing acquired market data to predict numerical fluctuations,

[0909] Based on the analysis results, a means to automate asset trading,

[0910] A means of recognizing the emotional state of users and generating personalized investment proposals based on that information,

[0911] Through dialogue with users, a means of providing responses that respond to their emotions,

[0912] A means of regularly reporting on the investment results of users,

[0913] A system that includes this.

[0914] (Claim 2)

[0915] The system according to claim 1, further comprising means for converting audio information into text information.

[0916] (Claim 3)

[0917] The system according to claim 1, further comprising means for optimizing the timing of transactions in real time based on the analysis results.

[0918] "Application example 2 when combining with an emotional engine"

[0919] (Claim 1)

[0920] A device for acquiring market data,

[0921] A device that processes acquired market data to predict price fluctuations,

[0922] Based on the processing results, a device that automates asset trading,

[0923] A device that generates personalized investment advice through dialogue with the user,

[0924] A device that recognizes the user's emotions and adjusts the investment strategy based on their emotional state,

[0925] A device that periodically reports the user's investment results,

[0926] A device installed in a general-purpose machine for use in a home environment, including an emotion analysis module and a voice recognition system,

[0927] A system that includes this.

[0928] (Claim 2)

[0929] The system according to claim 1, further comprising a device for converting audio information into text information.

[0930] (Claim 3)

[0931] The system according to claim 1, further comprising a device for immediately optimizing the timing of an investment based on the results of a process. [Explanation of symbols]

[0932] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of obtaining market information, A means of analyzing acquired market information to predict price fluctuations, Based on the analysis results, a means to automate the buying and selling of assets, A means of generating personalized suggestions through interaction with the user, A means of regularly reporting on the user's investment performance, A means of proposing ways to optimize consumer behavior based on feedback on investment results, A system that includes this.

2. The system according to claim 1, further comprising means for converting audio data into text data.

3. The system according to claim 1, further comprising means for optimizing the timing of consumption in real time, taking market information into consideration, based on the analysis results.

Images