system

Abstract

We provide the system. [Solution] A means of analyzing voice input from users to identify their investment goals, risk tolerance, and investment amount, A method for analyzing market data collected in real time and predicting market trends using a predictive model, A means of automatically generating a portfolio optimized for the user's investment goals and providing an investment strategy, A means of automatically issuing buy and sell orders for assets based on the generated investment strategy, A means of notifying users of important market information and investment opportunities as alerts according to their schedule, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Individual investors have problems in that it is difficult to make optimal investment decisions due to insufficient market information and difficulty in quickly responding to market fluctuations. There are also risks such as the need for specialized investment knowledge and missing appropriate investment opportunities. Due to these problems, investment has become a high hurdle for beginners. Therefore, there is a need for a new method to support information acquisition, analysis, and decision-making so that individual investors can invest more effectively.

Means for Solving the Problems

[0005] This invention provides a technology that analyzes voice input from a user to identify investment goals, risk tolerance, and investment amount. It also analyzes real-time collected market data and predicts market trends using a predictive model. Furthermore, it includes means for automatically generating a portfolio optimized for the user's investment goals and providing an investment strategy based on it. This system can automatically issue buy and sell orders for assets based on the generated investment strategy and notifies the user of important market information and investment opportunities as alerts according to their schedule. This helps individual investors conduct investment activities more efficiently and effectively.

[0006] A "user" refers to an individual investor who uses the system to conduct investment activities.

[0007] "Voice input" is a means for users to communicate their investment wishes and commands to a system by speaking.

[0008] "Market data" refers to various numerical data in financial markets, such as stock prices, trading volume, and economic indicators.

[0009] A "predictive model" refers to a mathematical or statistical algorithm used to predict future market trends based on market data.

[0010] A "portfolio" refers to a combination of financial assets held by a user, and its purpose is to optimize risk and return.

[0011] An "investment strategy" refers to a plan that selects and allocates assets according to the user's objectives in order to maximize investment returns.

[0012] "Automated trading" refers to the process of buying and selling assets based on pre-set strategies and rules, without requiring user intervention.

[0013] An "alert" refers to a signal from a system that notifies users of important information that requires their attention, such as significant market fluctuations or investment opportunities. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0019] In the following embodiments, a 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, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is an AI-powered investment support system that enables users to make more effective investments by providing investment-related information through voice input. This system consists of three components: a server, a terminal, and a user.

[0036] Server functions:

[0037] The server obtains real-time market information from external market data providers via the internet. This market information includes stock prices, trading volume, and economic indicators. The server uses machine learning and statistical models to analyze the collected data. This allows it to predict future market trends and assess risks. This predictive data forms the basis for investment strategies generated for users.

[0038] Device features:

[0039] The user accesses the system through a device (e.g., a smartphone). The device receives the user's voice input and converts it into text data using speech recognition technology. This text data is sent to a server to analyze the user's investment goals and risk tolerance. The device then visually displays the investment strategies and market forecasts received from the server to the user.

[0040] User interaction:

[0041] The user inputs their preferences via voice, such as "I want to make long-term investments with minimal risk." The server receives the voice command and uses natural language processing to understand the user's investment intentions. Based on the conditions specified by the user, the server generates an optimal portfolio and provides an investment strategy accordingly.

[0042] Automated trading and alerts:

[0043] The server executes automated trades based on the generated investment strategy. It automatically buys and sells the user's assets through the brokerage's API, managing risk. In addition, in the event of significant market fluctuations, the server sends alerts to the user via the terminal to prompt a quick response.

[0044] This system automates investment activities, providing individual investors with an environment that makes it easier to adapt to market changes. By using the system, users can reduce the burden of market analysis and determining the timing of buy orders, thus supporting effective investment decision-making.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The user voice-inputs their investment preferences and commands into the terminal. The terminal uses speech recognition technology to convert this voice data into text data.

[0048] Step 2:

[0049] The terminal sends the converted text data to the server. The server uses natural language processing technology to analyze the text data and identify the user's investment goals, risk tolerance, and investment amount.

[0050] Step 3:

[0051] The server collects real-time market data from external market data providers. This data includes stock prices, trading volume, and economic indicators.

[0052] Step 4:

[0053] The server uses machine learning and statistical models to predict market trends based on collected market data. Based on these predictions, it automatically generates a portfolio that aligns with the user's investment goals.

[0054] Step 5:

[0055] The server sends the generated investment strategy and market forecast results to the terminal. The terminal displays them to the user in a visually easy-to-understand format (such as graphs and charts).

[0056] Step 6:

[0057] If the user has enabled the setting to perform automated trading based on their investment strategy, the server will execute buy and sell orders through the brokerage firm's API.

[0058] Step 7:

[0059] The server continuously monitors the market and, if it detects unusual market fluctuations, sends an alert to the user via the terminal. The user reviews the alert and re-evaluates their investment strategy as needed.

[0060] (Example 1)

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

[0062] There is a growing need to improve the accuracy of market trend predictions in investment, automatically generate strategies tailored to individual users' investment goals, and streamline asset management. Traditional manual market analysis and investment decisions struggle to respond quickly to market fluctuations, potentially leading to missed investment opportunities. Furthermore, there is a lack of personalized strategies to satisfy the preferences of individual investors.

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

[0064] In this invention, the server includes means for converting voice data into text data, means for identifying the user's investment goals and risk tolerance and generating an investment portfolio, and means for predicting market trends using machine learning. This enables the automatic generation of individual strategies tailored to the user's investment needs and flexible investment decisions that respond to real-time market changes.

[0065] A "user" is an entity that utilizes an investment support system and provides investment-related information and preferences via voice input.

[0066] "Voice input" is a method in which an electronic device recognizes the words spoken by the user and processes them as digital data.

[0067] "Voice data" refers to digital data generated when a user inputs voice commands into a system.

[0068] "Text data" refers to data in text format obtained by analyzing audio data.

[0069] "Market data" is a general term for data collected in real time, such as stock prices, trading volume, and economic indicators.

[0070] "Machine learning" is an artificial intelligence technology that allows computers to learn patterns and insights from large amounts of data, and is used to predict market trends.

[0071] A "predictive model" is a mathematical model used to estimate future market trends based on past data.

[0072] An "investment portfolio" is a combination of multiple financial products selected based on the user's investment goals and risk tolerance.

[0073] A "generative AI model" is a system that uses algorithms to automatically generate investment strategies optimized for the user.

[0074] "Automated trading" refers to a function in which a system automatically buys and sells financial products based on pre-set conditions.

[0075] An "alert" is a general term for warnings and notifications sent to users when important market information or investment opportunities arise.

[0076] This invention is a system that enables users to receive investment support using voice input. This system consists of three components: a server, a terminal, and a user.

[0077] The server acquires real-time market data through external market data provision services. This market data includes stock prices, trading volume, and economic indicators. The server analyzes the data using programming languages ​​such as Python and R, and leveraging pandas and NumPy. Furthermore, it predicts market trends using machine learning libraries such as scikit-learn and TENSORFLOW®.

[0078] A terminal refers to a smartphone or computer, and is the means by which a user accesses the system. The terminal receives the user's voice input and converts it into text data using Google® Speech Recognition API, etc. This data is sent to the server, where the user's investment objectives and risk tolerance are analyzed.

[0079] By using this system, users input their preferences, such as "I want to invest in environmentally conscious companies," via voice. Based on this input, the server analyzes the user's requests using natural language processing tools such as NLTK and spaCy, and generates an appropriate investment portfolio. The server then uses a generative AI model to automatically generate an efficient investment strategy based on prompts such as "Please propose an investment strategy that minimizes risk and aims for long-term profits."

[0080] This system executes automated trading through the brokerage firm's API, controlling the buying and selling of the user's assets in real time. Furthermore, if significant market fluctuations are detected, the server sends an alert to the user via their terminal.

[0081] This invention enables users to develop efficient investment strategies and manage assets without manually tracking the market, thereby maximizing the effectiveness of asset management.

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

[0083] Step 1:

[0084] The server retrieves real-time market data from external market data providers via the internet. This data includes stock prices, trading volume, and economic indicators. The entered market data is stored in a database, ensuring that the latest market information is always accessible.

[0085] Step 2:

[0086] The server processes acquired market data using Python's pandas and NumPy libraries for analysis. It utilizes machine learning libraries such as scikit-learn and TensorFlow to predict market trends. The input is real-time market data, and the output is an indicator for predicting future market trends. This enables accurate, data-driven predictions.

[0087] Step 3:

[0088] Users access the system through their devices and use voice input. Specifically, they use smartphones or computers to voice-input their preferences, such as "I want to invest in something that will yield stable returns." The input voice is converted into text data via the Google Speech Recognition API, and this data is sent to the server.

[0089] Step 4:

[0090] The server receives text data converted from voice input and analyzes the data using natural language processing tools such as NLTK and spaCy. The input is text data containing the user's wishes, and the output is information identifying the user's investment goals and risk tolerance.

[0091] Step 5:

[0092] The server uses a generative AI model to generate the optimal investment strategy based on the user's investment requests. Using the prompt "Propose an investment strategy that minimizes risk and aims for long-term profits," the AI ​​creates a proposed strategy. The input consists of investment conditions and market forecasts, and the output is the optimal investment strategy.

[0093] Step 6:

[0094] The server executes automated trades via the brokerage firm's API based on the generated investment strategy. The input is the generated investment strategy, and the output is the trading history and confirmation of successful trades.

[0095] Step 7:

[0096] The terminal visually presents investment strategies and market forecasts from the server to the user. Furthermore, if significant market fluctuations are detected, the terminal notifies the user of alerts sent from the server. This allows the user to respond quickly. Input is information from the server, and output is the display on the user interface.

[0097] (Application Example 1)

[0098] 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."

[0099] Traditional electronic payment services have faced challenges in providing immediate and personalized investment strategies to effectively support users' asset management. Furthermore, they lacked the means to respond quickly to market fluctuations, creating a risk that users' assets were exposed to unexpected volatility.

[0100] 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.

[0101] In this invention, the server includes means for analyzing voice input from the user to identify the user's goals, tolerance, and amount; means for analyzing data collected in real time and predicting trends using a model; and means for notifying electronic devices of warnings when market fluctuations occur and visualizing and displaying individual strategies. This allows users to receive recommended strategies based on their investment goals and risk tolerance, and enables them to respond quickly to rapid market changes.

[0102] "Voice input" is a method in which users provide instructions or information using their voice.

[0103] "Analysis" is the process of examining collected data to find its meaning and relationships.

[0104] "Goals" refer to the specific results or standards that users intend to achieve.

[0105] "Tolerance" refers to the range and degree of risk that a user is willing to accept.

[0106] "Amount" is a numerical value that indicates the amount of capital a user allocates to an investment.

[0107] "Data" is a collection of information that is expressed concretely using numbers or characters.

[0108] A "model" is a mathematical system used to mimic real-world phenomena and perform predictions and analyses.

[0109] "Trend" refers to a tendency that indicates the direction of change in events or situations.

[0110] A "warning" is a notification intended to inform people in advance of an anticipated crisis or problem.

[0111] An "electronic device" is a device that has the ability to process, transmit, and receive information.

[0112] "Visualization" is the process of representing data and information in shapes and diagrams that are easy for humans to understand.

[0113] "Display" refers to outputting information or data onto a screen or display and presenting it to the user.

[0114] "Strategy" is a general term for the means and methods that are systematically taken to achieve a goal.

[0115] An "asset" is property that has value and has the potential to bring profit or other benefits to its owner.

[0116] "Operation instructions" refer to specific commands or orders given to a system or device.

[0117] To realize this invention, the following system configuration is required. The server collects real-time market data from external data services via the internet. This includes information such as stock prices, trading volume, and economic indicators. This collected data is analyzed using libraries such as Python's Pandas, NumPy, and Scikit-learn. By using machine learning models such as Random Forest, market trends are predicted and investment strategies suitable for the user are generated. The server runs on an AWS® EC2 instance, and RDS is used for data storage.

[0118] Taking a smartphone as an example, the device uses voice recognition technology to receive voice input from the user and sends that data as text to the server. After analysis of the user's goals and risk tolerance, the generated investment strategy is visually displayed on the device. This display also includes a real-time alert function that responds to market fluctuations. For example, if a user voice-inputs, "I want to invest with the aim of long-term growth," a portfolio will be automatically generated according to that request.

[0119] An example of a prompt message that uses a generative AI model to support a user's investment decision-making might be, "Please advise me on how to grow my assets within five years with a low-risk portfolio." By using this system, users can respond quickly to market fluctuations and make more effective asset management and investment decisions.

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The terminal uses speech recognition technology to receive voice input from the user. This input includes the user's desired investment goals and risk tolerance. This voice data is converted into text data and sent to the server. This conversion makes the voice commands parseable.

[0123] Step 2:

[0124] The server receives text data from users and analyzes their investment goals and risk tolerance. The input data is in text format, and natural language processing is used to identify the user's intentions. This analysis clarifies the specific investment strategy the user desires.

[0125] Step 3:

[0126] The server retrieves market data from an external data service. This data includes stock prices, trading volume, and economic indicators. The retrieved data is preprocessed using Python's Pandas library, transformed using NumPy, and then a machine learning model is built using Scikit-learn. The output generates predicted market trends.

[0127] Step 4:

[0128] The server automatically generates a portfolio optimized for the user's investment goals based on the generated predictive data. In this process, it utilizes a pre-trained model to calculate the optimal asset allocation for the user. The output provides a specific investment strategy.

[0129] Step 5:

[0130] The server automatically issues buy and sell orders for assets based on the generated investment strategy. These orders are executed via the brokerage firm's API and are automatically adjusted to manage risks associated with market fluctuations.

[0131] Step 6:

[0132] Based on a schedule set by the user, the server notifies the terminal of important market information and investment opportunities as alerts. These alerts are sent via push notifications, especially during periods of significant market fluctuations, to help users respond quickly.

[0133] Step 7:

[0134] The terminal receives investment strategies and market information from the server and displays it visually to the user. As output, the user can check their asset status and market changes in real time. To broaden the user's knowledge, prompts generated using AI models are also utilized.

[0135] 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.

[0136] This invention is an AI investment support system incorporating an emotion engine, which supports the user's investment activities based on information acquired through the user's voice input. This system functions through three parties: a server, a terminal, and the user.

[0137] Server functions:

[0138] The server collects market data from external data providers and uses machine learning models and statistical methods to predict future market trends. In addition, it incorporates an emotion engine that analyzes user emotions from voice input. The information obtained from emotion analysis is used to adjust investment strategies.

[0139] Device features:

[0140] The terminal receives voice input from the user and converts it into text data using speech recognition technology. This text data is then transferred to a server, where emotional information is added by an emotion engine. The terminal displays investment strategies and market information received from the server and provides feedback to the user in a visually easy-to-understand format.

[0141] User interaction:

[0142] Users can communicate requests to their terminals via voice, such as "I want to invest more aggressively." The server then judges the user's emotions from their tone of voice and word choice. For example, if the user seems anxious, the server might suggest a strategy that minimizes risk.

[0143] Automated trading and alerts:

[0144] The server automatically issues buy and sell orders via the brokerage firm's API based on the generated investment strategy. Furthermore, it dynamically adjusts the investment strategy based on market data and the user's emotional state. If abnormal market fluctuations are detected, the server sends an alert via the terminal and suggests countermeasures tailored to the user's emotional state.

[0145] This system can mitigate investment biases based on emotions and provide users with a more stable investment environment. By incorporating an emotion engine, users can improve their investment experience and optimize their individual investment strategies.

[0146] The following describes the processing flow.

[0147] Step 1:

[0148] The user inputs their investment wishes and intentions by voice into the device. The device then uses speech recognition technology to convert this voice data into text.

[0149] Step 2:

[0150] The device sends text data, along with data used to determine the user's emotions from their voice, to the server. This emotion data is generated from tone analysis and word choice.

[0151] Step 3:

[0152] The server analyzes the received text data to identify the user's investment goals and risk tolerance. It also uses an emotion engine to analyze the transmitted emotion data and determine the user's emotional state.

[0153] Step 4:

[0154] The server acquires market data in real time from external data providers and uses machine learning models to predict market trends.

[0155] Step 5:

[0156] The server automatically generates an optimized portfolio and investment strategy for the user based on prediction results and the user's investment profile, while also considering their emotional state. Adjustments are made as needed to mitigate risk.

[0157] Step 6:

[0158] The server sends the generated investment strategy and market data analysis results to the terminal. The terminal displays this information graphically, presenting it in a format that is easy for the user to understand.

[0159] Step 7:

[0160] The server automatically executes trades via the brokerage firm's API based on predicted market trends and the user's emotional state. Furthermore, if abnormal market fluctuations are detected, it generates an alert based on the user's emotions and notifies the user via their device. The user receives the alert and readjusts their strategy as needed.

[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] Traditional investment systems often fail to adequately consider users' emotions and risk tolerance, instead relying solely on quantitative data to provide investment strategies. This makes it difficult to offer optimal investment advice tailored to individual users. Furthermore, they struggle to respond appropriately to sudden market fluctuations, requiring flexible strategic adjustments that take into account users' emotional states.

[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 analyzing voice information from the user to identify investment goals and risk tolerance, including emotions; means for analyzing market information in real time and adjusting the optimal investment strategy according to the user's emotional state; and means for detecting abnormal market fluctuations and quickly adjusting automated asset trading. This enables the provision of flexible and optimal investment strategies based on the user's individual emotions and risk preferences, and allows for appropriate responses to rapid market fluctuations.

[0166] "Voice information" refers to data provided by the user through voice, and includes input information such as the user's intentions and emotions.

[0167] "Emotional information" refers to the user's emotional state, analyzed from voice data, and is used to adjust investment strategies.

[0168] "Investment goals" refer to the specific objectives and results that a user hopes to achieve through their investment activities.

[0169] "Risk tolerance" refers to the range of risk a user can accept and is an important element in formulating an investment strategy.

[0170] "Market information" refers to data such as price fluctuations and trading volume in financial markets that are collected in real time.

[0171] An "investment strategy" is an asset management policy formulated based on the user's investment goals, risk tolerance, and market information.

[0172] "Automated asset trading" is a process that mechanically instructs and executes the buying and selling of assets based on predetermined conditions.

[0173] "Abnormal market fluctuations" refer to the phenomenon of price fluctuations that deviate significantly from normal market trends.

[0174] An "alert" refers to a warning message that notifies the user of important information or a situation that requires attention.

[0175] This invention is a system that analyzes information provided by users via voice and uses that information to support investment decisions. This system primarily functions between a server, a terminal, and the user.

[0176] Speech recognition and emotion analysis

[0177] The user inputs their investment intentions and feelings via voice into the terminal. The terminal receives this voice input and converts it into text data using speech recognition technology. Specifically, it utilizes a general-purpose speech recognition API as the speech recognition engine. This data is then sent directly to the server.

[0178] In addition, the device performs sentiment analysis to extract emotional information from the audio. This uses a library that incorporates sentiment analysis algorithms. For example, open-source libraries for Python or deep learning frameworks can be utilized.

[0179] Market data collection and forecasting

[0180] The server utilizes external information providers to collect market information in real time. This step requires selecting which platforms to use and what data to obtain. Based on this information, the server launches a predictive model to simulate future market trends. A predictive model using a common machine learning framework can be used here.

[0181] Investment strategy generation and automated trading

[0182] The server integrates the above data with sentiment information obtained from users to generate an optimal investment strategy for each user. This strategy automatically sends buy and sell instructions from the server via an API for securities trading. This allows users to execute appropriate asset management in real time.

[0183] Alerts and feedback

[0184] Furthermore, the server monitors unusual market fluctuations and notifies the user's device with appropriate alerts based on their emotional state. This allows users to stay informed about their investment situation and change their strategies if necessary.

[0185] Specific examples and prompt statements

[0186] As a concrete example, a user might voice-input, "Please tell me what investment opportunities you recommend in the current market conditions." This statement is converted into text data, which is then analyzed to determine if the user has any anxieties, and the strategy is adjusted on the server side. Another example of a prompt for the generated AI model could be a question like, "Please tell me about an investment strategy that minimizes risk."

[0187] This system allows users to receive high-quality investment strategies that comprehensively consider their own emotions and market trends.

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

[0189] Step 1:

[0190] The user inputs their investment intentions and questions via voice into the terminal. This voice input is recorded as data, including the user's specific requests and urgency. Upon receiving this voice input, the terminal uses a speech recognition API to convert it into text data. This process transforms the voice information into text format.

[0191] Step 2:

[0192] The terminal performs sentiment analysis using the converted text data. This involves using a sentiment analysis algorithm, which outputs sentiment data extracted from the text. Specifically, it analyzes the user's vocabulary and tone of voice, and identifies their emotional state based on the results. This data is then sent to the server for further processing.

[0193] Step 3:

[0194] The server collects real-time market information via APIs from external data providers. Inputs include securities information, trading information, etc. The server receives this data and uses machine learning models to predict future market trends. The predicted market trends are then output.

[0195] Step 4:

[0196] The server integrates user sentiment information and market forecast data to generate an optimal investment strategy. The inputs used are the user's emotional state and predicted market trends. The generated investment strategy is tailored to the user's risk tolerance and investment goals. The output is a specific investment strategy.

[0197] Step 5:

[0198] The server automatically sends buy and sell orders to the securities trading system's API based on the generated investment strategy. The input is the adjusted investment strategy, and the output is specific buy and sell orders. This process automatically manages the user's assets.

[0199] Step 6:

[0200] The server constantly monitors market anomalies and immediately sends an alert to the terminal when an anomaly is detected. The input used for this alert is the latest market data and user sentiment information. The output is an alert notification that takes user sentiment into consideration, and suggests appropriate countermeasures. This alert helps users respond quickly to sudden market fluctuations.

[0201] (Application Example 2)

[0202] 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".

[0203] In modern investment activities, investors face the risk that their emotions may bias their market judgments. Furthermore, making decisions based solely on market data without considering emotions can sometimes lead to inappropriate strategies. Moreover, in rapidly changing markets, there is a growing demand for real-time advice tailored to individual user needs. Under these circumstances, the need for investment support systems that take user emotions into account is particularly evident.

[0204] 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.

[0205] This invention includes a server that analyzes voice input from a user and identifies investment goals, risk tolerance, and investment amount based on the user's emotional state; a server that analyzes market information and predicts market trends using a predictive model; and a server that automatically generates a portfolio optimized for the user's emotional state and investment goals and provides an investment strategy. This enables the presentation and execution of flexible and optimal investment strategies that respond to the user's emotional state.

[0206] "User emotional state" refers to the psychological and emotional state of the user, analyzed from their voice input, and is a factor that influences investment decision-making.

[0207] "Investment goals" refer to the financial objectives that a user aims to achieve through asset management, specifically including goals such as increasing assets, diversifying risk, and preparing for specific future expenses.

[0208] "Risk tolerance" refers to the range of risk a user is willing to accept in asset management, and is primarily a measure of how much loss they can tolerate when the value of their assets fluctuates.

[0209] "Market information" refers to all data related to financial markets, including real-time collected stock prices, interest rates, and economic indicators.

[0210] A "portfolio" in investing refers to a collection of assets that combine different financial instruments, designed to optimize the balance between risk and return.

[0211] A "trading instruction" is an instruction issued in a financial market to buy or sell a specific asset, and its contents usually include the quantity and price conditions.

[0212] An "alert" is a system function that notifies users when predetermined conditions are met or when specific market fluctuations are confirmed, providing information to users through various channels.

[0213] To implement this invention, a system is required in which several key components work together. This system has the function of analyzing the user's voice, determining their emotional state, and providing an optimized investment strategy. The role of each component is described below.

[0214] server

[0215] The server collects market information from external data providers and uses machine learning models to predict market trends. Furthermore, it analyzes text data extracted from user voice input using an emotion engine to identify the user's emotional state. Based on this emotional state and market forecast data, it generates a portfolio tailored to the user and designs an investment strategy. Required hardware includes a general-purpose server computer, and the software uses natural language processing tools (e.g., IBM Watson®) and machine learning frameworks (e.g., TensorFlow).

[0216] terminal

[0217] The device receives voice input from the user and converts it into text data using speech recognition technology. At this stage, the voice data is processed using technologies such as the Google Speech-to-Text API. The converted data is sent to a server, where sentiment information is added. The device is equipped with interfaces such as a display and speaker to present the investment strategy returned from the server to the user in a visual and intuitive manner.

[0218] User

[0219] Users can communicate their requests via voice to their terminal, for example, "The market is volatile, how should I proceed with investing?" The server analyzes the user's emotions from their tone of voice and context, and presents the optimal investment strategy. The user then reviews the provided information and executes investment instructions as needed.

[0220] Specific examples and prompt statements

[0221] As a concrete example, a user might say to a robot at home, "The market is volatile today and I'm a little worried, so please tell me a safe investment approach." In this case, the system recognizes the user's anxiety and proposes a low-risk investment strategy. An example of a prompt to the generating AI model would be, "Consider the user's emotional state 'anxiety' and propose a low-risk investment strategy."

[0222] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0223] Step 1:

[0224] The device receives voice input from the user and sends that voice data to a speech recognition API (e.g., Google Speech-to-Text). The input is the user's voice data, and the output is generated as text data. In this process, the voice data is converted into text format and becomes the data that proceeds to the next processing step.

[0225] Step 2:

[0226] The terminal sends the converted text data to the server. This text data represents the user's statements, and the server uses an emotion engine to analyze the received text data. The input is text data, and the output is information indicating the emotional state.

[0227] Step 3:

[0228] The server uses an emotion engine (e.g., IBM Watson) to analyze the user's emotional state from text data. This process extracts emotions from linguistic features and context contained in the text. The input is text data, and the output is an analysis result indicating the user's emotional state.

[0229] Step 4:

[0230] The server collects market information from a database or external data service and uses a machine learning model to predict market trends. The input is market data, and the output is the predicted market trend. This prediction serves as the basis for generating the next strategy.

[0231] Step 5:

[0232] The server automatically generates portfolios and investment strategies by combining the user's emotional state with market forecasts. A generation AI model is used to adjust risk based on the user's emotions. The input is the emotional state and market forecasts, and the output is a customized investment strategy.

[0233] Step 6:

[0234] The terminal receives investment strategies transmitted from the server and provides information to the user visually and audibly. The strategy is displayed on the screen, and an overview is conveyed through the speaker. The output is investment strategy information provided in a user-understandable format.

[0235] Step 7:

[0236] The user reviews the presented investment strategy and makes a decision as needed. The terminal sends the user's decision to the server and, if triggered, initiates a trade instruction to the stock exchange. The output is either a trade instruction or a revised version.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] [Second Embodiment]

[0241] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0242] 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.

[0243] 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).

[0244] 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.

[0245] 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.

[0246] 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).

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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.

[0251] 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.

[0252] 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".

[0253] This invention is an AI-powered investment support system that enables users to make more effective investments by providing investment-related information through voice input. This system consists of three components: a server, a terminal, and a user.

[0254] Server functions:

[0255] The server obtains real-time market information from external market data providers via the internet. This market information includes stock prices, trading volume, and economic indicators. The server uses machine learning and statistical models to analyze the collected data. This allows it to predict future market trends and assess risks. This predictive data forms the basis for investment strategies generated for users.

[0256] Device features:

[0257] The user accesses the system through a device (e.g., a smartphone). The device receives the user's voice input and converts it into text data using speech recognition technology. This text data is sent to a server to analyze the user's investment goals and risk tolerance. The device then visually displays the investment strategies and market forecasts received from the server to the user.

[0258] User interaction:

[0259] The user inputs their preferences via voice, such as "I want to make long-term investments with minimal risk." The server receives the voice command and uses natural language processing to understand the user's investment intentions. Based on the conditions specified by the user, the server generates an optimal portfolio and provides an investment strategy accordingly.

[0260] Automated trading and alerts:

[0261] The server executes automated trades based on the generated investment strategy. It automatically buys and sells the user's assets through the brokerage's API, managing risk. In addition, in the event of significant market fluctuations, the server sends alerts to the user via the terminal to prompt a quick response.

[0262] This system automates investment activities, providing individual investors with an environment that makes it easier to adapt to market changes. By using the system, users can reduce the burden of market analysis and determining the timing of buy orders, thus supporting effective investment decision-making.

[0263] The following describes the processing flow.

[0264] Step 1:

[0265] The user voice-inputs their investment preferences and commands into the terminal. The terminal uses speech recognition technology to convert this voice data into text data.

[0266] Step 2:

[0267] The terminal sends the converted text data to the server. The server uses natural language processing technology to analyze the text data and identify the user's investment goals, risk tolerance, and investment amount.

[0268] Step 3:

[0269] The server collects real-time market data from external market data providers. This data includes stock prices, trading volume, and economic indicators.

[0270] Step 4:

[0271] The server uses machine learning and statistical models to predict market trends based on collected market data. Based on these predictions, it automatically generates a portfolio that aligns with the user's investment goals.

[0272] Step 5:

[0273] The server sends the generated investment strategy and market forecast results to the terminal. The terminal displays them to the user in a visually easy-to-understand format (such as graphs and charts).

[0274] Step 6:

[0275] If the user has enabled the setting to perform automated trading based on their investment strategy, the server will execute buy and sell orders through the brokerage firm's API.

[0276] Step 7:

[0277] The server continuously monitors the market and, if it detects unusual market fluctuations, sends an alert to the user via the terminal. The user reviews the alert and re-evaluates their investment strategy as needed.

[0278] (Example 1)

[0279] 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."

[0280] There is a growing need to improve the accuracy of market trend predictions in investment, automatically generate strategies tailored to individual users' investment goals, and streamline asset management. Traditional manual market analysis and investment decisions struggle to respond quickly to market fluctuations, potentially leading to missed investment opportunities. Furthermore, there is a lack of personalized strategies to satisfy the preferences of individual investors.

[0281] 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.

[0282] In this invention, the server includes means for converting voice data into text data, means for identifying the user's investment goals and risk tolerance and generating an investment portfolio, and means for predicting market trends using machine learning. This enables the automatic generation of individual strategies tailored to the user's investment needs and flexible investment decisions that respond to real-time market changes.

[0283] A "user" is an entity that utilizes an investment support system and provides investment-related information and preferences via voice input.

[0284] "Voice input" refers to a form in which an electronic device recognizes words uttered by a user and processes them as digital data.

[0285] "Voice data" refers to digital data generated when a user inputs voice to a system.

[0286] "Text data" refers to data in text format obtained by analyzing voice data.

[0287] "Market data" is a general term for data collected in real time, such as stock prices, trading volumes, and economic indicators.

[0288] "Machine learning" is an artificial intelligence technology that enables a computer to learn patterns and knowledge from a large amount of data, and is a technology used for predicting market trends.

[0289] "Prediction model" is a mathematical model used to estimate future market trends based on past data.

[0290] "Investment portfolio" is a combination of multiple financial products selected based on a user's investment goals and risk tolerance.

[0291] "Generative AI model" is a system that automatically generates an investment strategy optimized for a user using an algorithm.

[0292] "Automatic trading" is a function in which a system automatically conducts trading of financial products based on pre-set conditions.

[0293] "Alert" is a general term for warnings and notifications that are sent to a user when important market information or investment opportunities occur.

[0294] This invention is a system that enables a user to receive investment support using voice input. This system consists of three entities: a server, a terminal, and a user.

[0295] The server acquires real-time market data through external market data provision services. This market data includes stock prices, trading volume, and economic indicators. The server analyzes the data using programming languages ​​such as Python and R, and leveraging pandas and NumPy. Furthermore, it predicts market trends using machine learning libraries such as scikit-learn and TensorFlow.

[0296] A terminal refers to a smartphone or computer, and is the means by which a user accesses the system. The terminal receives the user's voice input and converts it into text data using APIs such as Google Speech Recognition. This data is sent to a server, where the user's investment objectives and risk tolerance are analyzed.

[0297] By using this system, users input their preferences, such as "I want to invest in environmentally conscious companies," via voice. Based on this input, the server analyzes the user's requests using natural language processing tools such as NLTK and spaCy, and generates an appropriate investment portfolio. The server then uses a generative AI model to automatically generate an efficient investment strategy based on prompts such as "Please propose an investment strategy that minimizes risk and aims for long-term profits."

[0298] This system executes automated trading through the brokerage firm's API, controlling the buying and selling of the user's assets in real time. Furthermore, if significant market fluctuations are detected, the server sends an alert to the user via their terminal.

[0299] This invention enables users to develop efficient investment strategies and manage assets without manually tracking the market, thereby maximizing the effectiveness of asset management.

[0300] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0301] Step 1:

[0302] The server obtains real-time market data from an external market data provider service via the Internet. This data includes stock prices, trading volumes, economic indicators, etc. The input market data is stored in a database, enabling access to the latest market information at all times.

[0303] Step 2:

[0304] The server processes the data using Python's pandas and NumPy to analyze the acquired market data. It utilizes machine learning libraries such as scikit-learn and TensorFlow to predict market trends. The input is real-time market data, and the output is an indicator for predicting future market movements, enabling accurate predictions based on the data.

[0305] Step 3:

[0306] The user accesses the system through a terminal and makes a voice input. Specifically, using a smartphone or a personal computer, the user inputs their desire, such as "want to invest for stable returns," in voice. The input voice is converted into text data via the Google Speech Recognition API, and this data is sent to the server.

[0307] Step 4:

[0308] The server receives the text data converted from the voice input and analyzes the data using natural language processing tools such as NLTK and spaCy. The input is the text data containing the user's desire, and the output is information identifying the user's investment goals and risk tolerance.

[0309] Step 5:

[0310] The server uses a generative AI model to generate the optimal investment strategy based on the user's investment requests. Using the prompt "Propose an investment strategy that minimizes risk and aims for long-term profits," the AI ​​creates a proposed strategy. The input consists of investment conditions and market forecasts, and the output is the optimal investment strategy.

[0311] Step 6:

[0312] The server executes automated trades via the brokerage firm's API based on the generated investment strategy. The input is the generated investment strategy, and the output is the trading history and confirmation of successful trades.

[0313] Step 7:

[0314] The terminal visually presents investment strategies and market forecasts from the server to the user. Furthermore, if significant market fluctuations are detected, the terminal notifies the user of alerts sent from the server. This allows the user to respond quickly. Input is information from the server, and output is the display on the user interface.

[0315] (Application Example 1)

[0316] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0317] Traditional electronic payment services have faced challenges in providing immediate and personalized investment strategies to effectively support users' asset management. Furthermore, they lacked the means to respond quickly to market fluctuations, creating a risk that users' assets were exposed to unexpected volatility.

[0318] 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.

[0319] In this invention, the server includes means for analyzing voice input from the user to identify the user's goals, tolerance, and amount; means for analyzing data collected in real time and predicting trends using a model; and means for notifying electronic devices of warnings when market fluctuations occur and visualizing and displaying individual strategies. This allows users to receive recommended strategies based on their investment goals and risk tolerance, and enables them to respond quickly to rapid market changes.

[0320] "Voice input" is a method in which users provide instructions or information using their voice.

[0321] "Analysis" is the process of examining collected data to find its meaning and relationships.

[0322] "Goals" refer to the specific results or standards that users intend to achieve.

[0323] "Tolerance" refers to the range and degree of risk that a user is willing to accept.

[0324] "Amount" is a numerical value that indicates the amount of capital a user allocates to an investment.

[0325] "Data" is a collection of information that is expressed concretely using numbers or characters.

[0326] A "model" is a mathematical system used to mimic real-world phenomena and perform predictions and analyses.

[0327] "Trend" refers to a tendency that indicates the direction of change in events or situations.

[0328] A "warning" is a notification intended to inform people in advance of an anticipated crisis or problem.

[0329] An "electronic device" is a device that has the ability to process, transmit, and receive information.

[0330] "Visualization" is the process of representing data and information in shapes and diagrams that are easy for humans to understand.

[0331] "Display" refers to outputting information or data onto a screen or display and presenting it to the user.

[0332] "Strategy" is a general term for the means and methods that are systematically taken to achieve a goal.

[0333] An "asset" is property that has value and has the potential to bring profit or other benefits to its owner.

[0334] "Operation instructions" refer to specific commands or orders given to a system or device.

[0335] To realize this invention, the following system configuration is required. The server collects real-time market data from external data services via the internet. This includes information such as stock prices, trading volume, and economic indicators. This collected data is analyzed using libraries such as Python's Pandas, NumPy, and Scikit-learn. By using machine learning models such as Random Forest, market trends are predicted and investment strategies suitable for the user are generated. The server runs on an AWS EC2 instance, and RDS is used for data storage.

[0336] Taking a smartphone as an example, the device uses voice recognition technology to receive voice input from the user and sends that data as text to the server. After analysis of the user's goals and risk tolerance, the generated investment strategy is visually displayed on the device. This display also includes a real-time alert function that responds to market fluctuations. For example, if a user voice-inputs, "I want to invest with the aim of long-term growth," a portfolio will be automatically generated according to that request.

[0337] An example of a prompt message that uses a generative AI model to support a user's investment decision-making might be, "Please advise me on how to grow my assets within five years with a low-risk portfolio." By using this system, users can respond quickly to market fluctuations and make more effective asset management and investment decisions.

[0338] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0339] Step 1:

[0340] The terminal uses speech recognition technology to receive voice input from the user. This input includes the user's desired investment goals and risk tolerance. This voice data is converted into text data and sent to the server. This conversion makes the voice commands parseable.

[0341] Step 2:

[0342] The server receives text data from users and analyzes their investment goals and risk tolerance. The input data is in text format, and natural language processing is used to identify the user's intentions. This analysis clarifies the specific investment strategy the user desires.

[0343] Step 3:

[0344] The server retrieves market data from an external data service. This data includes stock prices, trading volume, and economic indicators. The retrieved data is preprocessed using Python's Pandas library, transformed using NumPy, and then a machine learning model is built using Scikit-learn. The output generates predicted market trends.

[0345] Step 4:

[0346] The server automatically generates a portfolio optimized for the user's investment goals based on the generated predictive data. In this process, it utilizes a pre-trained model to calculate the optimal asset allocation for the user. The output provides a specific investment strategy.

[0347] Step 5:

[0348] The server automatically issues buy and sell orders for assets based on the generated investment strategy. These orders are executed via the brokerage firm's API and are automatically adjusted to manage risks associated with market fluctuations.

[0349] Step 6:

[0350] Based on a schedule set by the user, the server notifies the terminal of important market information and investment opportunities as alerts. These alerts are sent via push notifications, especially during periods of significant market fluctuations, to help users respond quickly.

[0351] Step 7:

[0352] The terminal receives investment strategies and market information from the server and displays it visually to the user. As output, the user can check their asset status and market changes in real time. To broaden the user's knowledge, prompts generated using AI models are also utilized.

[0353] 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.

[0354] This invention is an AI investment support system incorporating an emotion engine, which supports the user's investment activities based on information acquired through the user's voice input. This system functions through three parties: a server, a terminal, and the user.

[0355] Server functions:

[0356] The server collects market data from external data providers and uses machine learning models and statistical methods to predict future market trends. In addition, it incorporates an emotion engine that analyzes user emotions from voice input. The information obtained from emotion analysis is used to adjust investment strategies.

[0357] Device features:

[0358] The terminal receives voice input from the user and converts it into text data using speech recognition technology. This text data is then transferred to a server, where emotional information is added by an emotion engine. The terminal displays investment strategies and market information received from the server and provides feedback to the user in a visually easy-to-understand format.

[0359] User interaction:

[0360] Users can communicate requests to their terminals via voice, such as "I want to invest more aggressively." The server then judges the user's emotions from their tone of voice and word choice. For example, if the user seems anxious, the server might suggest a strategy that minimizes risk.

[0361] Automated trading and alerts:

[0362] The server automatically issues buy and sell orders via the brokerage firm's API based on the generated investment strategy. Furthermore, it dynamically adjusts the investment strategy based on market data and the user's emotional state. If abnormal market fluctuations are detected, the server sends an alert via the terminal and suggests countermeasures tailored to the user's emotional state.

[0363] This system can mitigate investment biases based on emotions and provide users with a more stable investment environment. By incorporating an emotion engine, users can improve their investment experience and optimize their individual investment strategies.

[0364] The following describes the processing flow.

[0365] Step 1:

[0366] The user inputs their investment wishes and intentions by voice into the device. The device then uses speech recognition technology to convert this voice data into text.

[0367] Step 2:

[0368] The device sends text data, along with data used to determine the user's emotions from their voice, to the server. This emotion data is generated from tone analysis and word choice.

[0369] Step 3:

[0370] The server analyzes the received text data to identify the user's investment goals and risk tolerance. It also uses an emotion engine to analyze the transmitted emotion data and determine the user's emotional state.

[0371] Step 4:

[0372] The server acquires market data in real time from external data providers and uses machine learning models to predict market trends.

[0373] Step 5:

[0374] The server automatically generates an optimized portfolio and investment strategy for the user based on prediction results and the user's investment profile, while also considering their emotional state. Adjustments are made as needed to mitigate risk.

[0375] Step 6:

[0376] The server sends the generated investment strategy and market data analysis results to the terminal. The terminal displays this information graphically, presenting it in a format that is easy for the user to understand.

[0377] Step 7:

[0378] The server automatically executes trades via the brokerage firm's API based on predicted market trends and the user's emotional state. Furthermore, if abnormal market fluctuations are detected, it generates an alert based on the user's emotions and notifies the user via their device. The user receives the alert and readjusts their strategy as needed.

[0379] (Example 2)

[0380] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0381] Traditional investment systems often fail to adequately consider users' emotions and risk tolerance, instead relying solely on quantitative data to provide investment strategies. This makes it difficult to offer optimal investment advice tailored to individual users. Furthermore, they struggle to respond appropriately to sudden market fluctuations, requiring flexible strategic adjustments that take into account users' emotional states.

[0382] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0383] In this invention, the server includes means for analyzing voice information from the user to identify investment goals and risk tolerance, including emotions; means for analyzing market information in real time and adjusting the optimal investment strategy according to the user's emotional state; and means for detecting abnormal market fluctuations and quickly adjusting automated asset trading. This enables the provision of flexible and optimal investment strategies based on the user's individual emotions and risk preferences, and allows for appropriate responses to rapid market fluctuations.

[0384] "Voice information" refers to data provided by the user through voice, and includes input information such as the user's intentions and emotions.

[0385] "Emotional information" refers to the user's emotional state, analyzed from voice data, and is used to adjust investment strategies.

[0386] "Investment goals" refer to the specific objectives and results that a user hopes to achieve through their investment activities.

[0387] "Risk tolerance" refers to the range of risk a user can accept and is an important element in formulating an investment strategy.

[0388] "Market information" refers to data such as price fluctuations and trading volume in financial markets that are collected in real time.

[0389] An "investment strategy" is an asset management policy formulated based on the user's investment goals, risk tolerance, and market information.

[0390] "Automated asset trading" is a process that mechanically instructs and executes the buying and selling of assets based on predetermined conditions.

[0391] "Abnormal market fluctuations" refer to the phenomenon of price fluctuations that deviate significantly from normal market trends.

[0392] An "alert" refers to a warning message that notifies the user of important information or a situation that requires attention.

[0393] This invention is a system that analyzes information provided by users via voice and uses that information to support investment decisions. This system primarily functions between a server, a terminal, and the user.

[0394] Speech recognition and emotion analysis

[0395] The user inputs their investment intentions and feelings via voice into the terminal. The terminal receives this voice input and converts it into text data using speech recognition technology. Specifically, it utilizes a general-purpose speech recognition API as the speech recognition engine. This data is then sent directly to the server.

[0396] In addition, the device performs sentiment analysis to extract emotional information from the audio. This uses a library that incorporates sentiment analysis algorithms. For example, open-source libraries for Python or deep learning frameworks can be utilized.

[0397] Market data collection and forecasting

[0398] The server utilizes external information providers to collect market information in real time. This step requires selecting which platforms to use and what data to obtain. Based on this information, the server launches a predictive model to simulate future market trends. A predictive model using a common machine learning framework can be used here.

[0399] Investment strategy generation and automated trading

[0400] The server integrates the above data with sentiment information obtained from users to generate an optimal investment strategy for each user. This strategy automatically sends buy and sell instructions from the server via an API for securities trading. This allows users to execute appropriate asset management in real time.

[0401] Alerts and feedback

[0402] Furthermore, the server monitors unusual market fluctuations and notifies the user's device with appropriate alerts based on their emotional state. This allows users to stay informed about their investment situation and change their strategies if necessary.

[0403] Specific examples and prompt statements

[0404] As a concrete example, a user might voice-input, "Please tell me what investment opportunities you recommend in the current market conditions." This statement is converted into text data, which is then analyzed to determine if the user has any anxieties, and the strategy is adjusted on the server side. Another example of a prompt for the generated AI model could be a question like, "Please tell me about an investment strategy that minimizes risk."

[0405] This system allows users to receive high-quality investment strategies that comprehensively consider their own emotions and market trends.

[0406] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0407] Step 1:

[0408] The user inputs their investment intentions and questions via voice into the terminal. This voice input is recorded as data, including the user's specific requests and urgency. Upon receiving this voice input, the terminal uses a speech recognition API to convert it into text data. This process transforms the voice information into text format.

[0409] Step 2:

[0410] The terminal performs sentiment analysis using the converted text data. This involves using a sentiment analysis algorithm, which outputs sentiment data extracted from the text. Specifically, it analyzes the user's vocabulary and tone of voice, and identifies their emotional state based on the results. This data is then sent to the server for further processing.

[0411] Step 3:

[0412] The server collects real-time market information via APIs from external data providers. Inputs include securities information, trading information, etc. The server receives this data and uses machine learning models to predict future market trends. The predicted market trends are then output.

[0413] Step 4:

[0414] The server integrates user sentiment information and market forecast data to generate an optimal investment strategy. The inputs used are the user's emotional state and predicted market trends. The generated investment strategy is tailored to the user's risk tolerance and investment goals. The output is a specific investment strategy.

[0415] Step 5:

[0416] The server automatically sends buy and sell orders to the securities trading system's API based on the generated investment strategy. The input is the adjusted investment strategy, and the output is specific buy and sell orders. This process automatically manages the user's assets.

[0417] Step 6:

[0418] The server constantly monitors market anomalies and immediately sends an alert to the terminal when an anomaly is detected. The input used for this alert is the latest market data and user sentiment information. The output is an alert notification that takes user sentiment into consideration, and suggests appropriate countermeasures. This alert helps users respond quickly to sudden market fluctuations.

[0419] (Application Example 2)

[0420] 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."

[0421] In modern investment activities, investors face the risk that their emotions may bias their market judgments. Furthermore, making decisions based solely on market data without considering emotions can sometimes lead to inappropriate strategies. Moreover, in rapidly changing markets, there is a growing demand for real-time advice tailored to individual user needs. Under these circumstances, the need for investment support systems that take user emotions into account is particularly evident.

[0422] 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.

[0423] This invention includes a server that analyzes voice input from a user and identifies investment goals, risk tolerance, and investment amount based on the user's emotional state; a server that analyzes market information and predicts market trends using a predictive model; and a server that automatically generates a portfolio optimized for the user's emotional state and investment goals and provides an investment strategy. This enables the presentation and execution of flexible and optimal investment strategies that respond to the user's emotional state.

[0424] "User emotional state" refers to the psychological and emotional state of the user, analyzed from their voice input, and is a factor that influences investment decision-making.

[0425] "Investment goals" refer to the financial objectives that a user aims to achieve through asset management, specifically including goals such as increasing assets, diversifying risk, and preparing for specific future expenses.

[0426] "Risk tolerance" refers to the range of risk a user is willing to accept in asset management, and is primarily a measure of how much loss they can tolerate when the value of their assets fluctuates.

[0427] "Market information" refers to all data related to financial markets, including real-time collected stock prices, interest rates, and economic indicators.

[0428] A "portfolio" in investing refers to a collection of assets that combine different financial instruments, designed to optimize the balance between risk and return.

[0429] A "trading instruction" is an instruction issued in a financial market to buy or sell a specific asset, and its contents usually include the quantity and price conditions.

[0430] An "alert" is a system function that notifies users when predetermined conditions are met or when specific market fluctuations are confirmed, providing information to users through various channels.

[0431] To implement this invention, a system is required in which several key components work together. This system has the function of analyzing the user's voice, determining their emotional state, and providing an optimized investment strategy. The role of each component is described below.

[0432] server

[0433] The server collects market information from external data providers and uses machine learning models to predict market trends. Furthermore, it analyzes text data extracted from user voice input using an emotion engine to identify the user's emotional state. Based on this emotional state and market forecast data, it generates a suitable portfolio for the user and designs an investment strategy. Required hardware includes a general-purpose server computer, and the software utilizes natural language processing tools (e.g., IBM Watson) and machine learning frameworks (e.g., TensorFlow).

[0434] terminal

[0435] The device receives voice input from the user and converts it into text data using speech recognition technology. At this stage, the voice data is processed using technologies such as the Google Speech-to-Text API. The converted data is sent to a server, where sentiment information is added. The device is equipped with interfaces such as a display and speaker to present the investment strategy returned from the server to the user in a visual and intuitive manner.

[0436] User

[0437] Users can communicate their requests via voice to their terminal, for example, "The market is volatile, how should I proceed with investing?" The server analyzes the user's emotions from their tone of voice and context, and presents the optimal investment strategy. The user then reviews the provided information and executes investment instructions as needed.

[0438] Specific examples and prompt statements

[0439] As a concrete example, a user might say to a robot at home, "The market is volatile today and I'm a little worried, so please tell me a safe investment approach." In this case, the system recognizes the user's anxiety and proposes a low-risk investment strategy. An example of a prompt to the generating AI model would be, "Consider the user's emotional state 'anxiety' and propose a low-risk investment strategy."

[0440] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0441] Step 1:

[0442] The device receives voice input from the user and sends that voice data to a speech recognition API (e.g., Google Speech-to-Text). The input is the user's voice data, and the output is generated as text data. In this process, the voice data is converted into text format and becomes the data that proceeds to the next processing step.

[0443] Step 2:

[0444] The terminal sends the converted text data to the server. This text data represents the user's statements, and the server uses an emotion engine to analyze the received text data. The input is text data, and the output is information indicating the emotional state.

[0445] Step 3:

[0446] The server uses an emotion engine (e.g., IBM Watson) to analyze the user's emotional state from text data. This process extracts emotions from linguistic features and context contained in the text. The input is text data, and the output is an analysis result indicating the user's emotional state.

[0447] Step 4:

[0448] The server collects market information from a database or external data service and uses a machine learning model to predict market trends. The input is market data, and the output is the predicted market trend. This prediction serves as the basis for generating the next strategy.

[0449] Step 5:

[0450] The server automatically generates portfolios and investment strategies by combining the user's emotional state with market forecasts. A generation AI model is used to adjust risk based on the user's emotions. The input is the emotional state and market forecasts, and the output is a customized investment strategy.

[0451] Step 6:

[0452] The terminal receives investment strategies transmitted from the server and provides information to the user visually and audibly. The strategy is displayed on the screen, and an overview is conveyed through the speaker. The output is investment strategy information provided in a user-understandable format.

[0453] Step 7:

[0454] The user reviews the presented investment strategy and makes a decision as needed. The terminal sends the user's decision to the server and, if triggered, initiates a trade instruction to the stock exchange. The output is either a trade instruction or a revised version.

[0455] 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.

[0456] 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.

[0457] 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.

[0458] [Third Embodiment]

[0459] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0460] 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.

[0461] 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).

[0462] 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.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] 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".

[0471] This invention is an AI-powered investment support system that enables users to make more effective investments by providing investment-related information through voice input. This system consists of three components: a server, a terminal, and a user.

[0472] Server functions:

[0473] The server obtains real-time market information from external market data providers via the internet. This market information includes stock prices, trading volume, and economic indicators. The server uses machine learning and statistical models to analyze the collected data. This allows it to predict future market trends and assess risks. This predictive data forms the basis for investment strategies generated for users.

[0474] Device features:

[0475] The user accesses the system through a device (e.g., a smartphone). The device receives the user's voice input and converts it into text data using speech recognition technology. This text data is sent to a server to analyze the user's investment goals and risk tolerance. The device then visually displays the investment strategies and market forecasts received from the server to the user.

[0476] User interaction:

[0477] The user inputs their preferences via voice, such as "I want to make long-term investments with minimal risk." The server receives the voice command and uses natural language processing to understand the user's investment intentions. Based on the conditions specified by the user, the server generates an optimal portfolio and provides an investment strategy accordingly.

[0478] Automated trading and alerts:

[0479] The server executes automated trades based on the generated investment strategy. It automatically buys and sells the user's assets through the brokerage's API, managing risk. In addition, in the event of significant market fluctuations, the server sends alerts to the user via the terminal to prompt a quick response.

[0480] This system automates investment activities, providing individual investors with an environment that makes it easier to adapt to market changes. By using the system, users can reduce the burden of market analysis and determining the timing of buy orders, thus supporting effective investment decision-making.

[0481] The following describes the processing flow.

[0482] Step 1:

[0483] The user voice-inputs their investment preferences and commands into the terminal. The terminal uses speech recognition technology to convert this voice data into text data.

[0484] Step 2:

[0485] The terminal sends the converted text data to the server. The server uses natural language processing technology to analyze the text data and identify the user's investment goals, risk tolerance, and investment amount.

[0486] Step 3:

[0487] The server collects real-time market data from external market data providers. This data includes stock prices, trading volume, and economic indicators.

[0488] Step 4:

[0489] The server uses machine learning and statistical models to predict market trends based on collected market data. Based on these predictions, it automatically generates a portfolio that aligns with the user's investment goals.

[0490] Step 5:

[0491] The server sends the generated investment strategy and market forecast results to the terminal. The terminal displays them to the user in a visually easy-to-understand format (such as graphs and charts).

[0492] Step 6:

[0493] If the user has enabled the setting to perform automated trading based on their investment strategy, the server will execute buy and sell orders through the brokerage firm's API.

[0494] Step 7:

[0495] The server continuously monitors the market and, if it detects unusual market fluctuations, sends an alert to the user via the terminal. The user reviews the alert and re-evaluates their investment strategy as needed.

[0496] (Example 1)

[0497] 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."

[0498] There is a growing need to improve the accuracy of market trend predictions in investment, automatically generate strategies tailored to individual users' investment goals, and streamline asset management. Traditional manual market analysis and investment decisions struggle to respond quickly to market fluctuations, potentially leading to missed investment opportunities. Furthermore, there is a lack of personalized strategies to satisfy the preferences of individual investors.

[0499] 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.

[0500] In this invention, the server includes means for converting voice data into text data, means for identifying the user's investment goals and risk tolerance and generating an investment portfolio, and means for predicting market trends using machine learning. This enables the automatic generation of individual strategies tailored to the user's investment needs and flexible investment decisions that respond to real-time market changes.

[0501] A "user" is an entity that utilizes an investment support system and provides investment-related information and preferences via voice input.

[0502] "Voice input" is a method in which an electronic device recognizes the words spoken by the user and processes them as digital data.

[0503] "Voice data" refers to digital data generated when a user inputs voice commands into a system.

[0504] "Text data" refers to data in text format obtained by analyzing audio data.

[0505] "Market data" is a general term for data collected in real time, such as stock prices, trading volume, and economic indicators.

[0506] "Machine learning" is an artificial intelligence technology that allows computers to learn patterns and insights from large amounts of data, and is used to predict market trends.

[0507] A "predictive model" is a mathematical model used to estimate future market trends based on past data.

[0508] An "investment portfolio" is a combination of multiple financial products selected based on the user's investment goals and risk tolerance.

[0509] A "generative AI model" is a system that uses algorithms to automatically generate investment strategies optimized for the user.

[0510] "Automated trading" refers to a function in which a system automatically buys and sells financial products based on pre-set conditions.

[0511] An "alert" is a general term for warnings and notifications sent to users when important market information or investment opportunities arise.

[0512] This invention is a system that enables users to receive investment support using voice input. This system consists of three components: a server, a terminal, and a user.

[0513] The server acquires real-time market data through external market data provision services. This market data includes stock prices, trading volume, and economic indicators. The server analyzes the data using programming languages ​​such as Python and R, and leveraging pandas and NumPy. Furthermore, it predicts market trends using machine learning libraries such as scikit-learn and TensorFlow.

[0514] A terminal refers to a smartphone or computer, and is the means by which a user accesses the system. The terminal receives the user's voice input and converts it into text data using APIs such as Google Speech Recognition. This data is sent to a server, where the user's investment objectives and risk tolerance are analyzed.

[0515] By using this system, users input their preferences, such as "I want to invest in environmentally conscious companies," via voice. Based on this input, the server analyzes the user's requests using natural language processing tools such as NLTK and spaCy, and generates an appropriate investment portfolio. The server then uses a generative AI model to automatically generate an efficient investment strategy based on prompts such as "Please propose an investment strategy that minimizes risk and aims for long-term profits."

[0516] This system executes automated trading through the brokerage firm's API, controlling the buying and selling of the user's assets in real time. Furthermore, if significant market fluctuations are detected, the server sends an alert to the user via their terminal.

[0517] This invention enables users to develop efficient investment strategies and manage assets without manually tracking the market, thereby maximizing the effectiveness of asset management.

[0518] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0519] Step 1:

[0520] The server retrieves real-time market data from external market data providers via the internet. This data includes stock prices, trading volume, and economic indicators. The entered market data is stored in a database, ensuring that the latest market information is always accessible.

[0521] Step 2:

[0522] The server processes acquired market data using Python's pandas and NumPy libraries for analysis. It utilizes machine learning libraries such as scikit-learn and TensorFlow to predict market trends. The input is real-time market data, and the output is an indicator for predicting future market trends. This enables accurate, data-driven predictions.

[0523] Step 3:

[0524] Users access the system through their devices and use voice input. Specifically, they use smartphones or computers to voice-input their preferences, such as "I want to invest in something that will yield stable returns." The input voice is converted into text data via the Google Speech Recognition API, and this data is sent to the server.

[0525] Step 4:

[0526] The server receives text data converted from voice input and analyzes the data using natural language processing tools such as NLTK and spaCy. The input is text data containing the user's wishes, and the output is information identifying the user's investment goals and risk tolerance.

[0527] Step 5:

[0528] The server uses a generative AI model to generate the optimal investment strategy based on the user's investment requests. Using the prompt "Propose an investment strategy that minimizes risk and aims for long-term profits," the AI ​​creates a proposed strategy. The input consists of investment conditions and market forecasts, and the output is the optimal investment strategy.

[0529] Step 6:

[0530] The server executes automated trades via the brokerage firm's API based on the generated investment strategy. The input is the generated investment strategy, and the output is the trading history and confirmation of successful trades.

[0531] Step 7:

[0532] The terminal visually presents investment strategies and market forecasts from the server to the user. Furthermore, if significant market fluctuations are detected, the terminal notifies the user of alerts sent from the server. This allows the user to respond quickly. Input is information from the server, and output is the display on the user interface.

[0533] (Application Example 1)

[0534] 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."

[0535] Traditional electronic payment services have faced challenges in providing immediate and personalized investment strategies to effectively support users' asset management. Furthermore, they lacked the means to respond quickly to market fluctuations, creating a risk that users' assets were exposed to unexpected volatility.

[0536] 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.

[0537] In this invention, the server includes means for analyzing voice input from the user to identify the user's goals, tolerance, and amount; means for analyzing data collected in real time and predicting trends using a model; and means for notifying electronic devices of warnings when market fluctuations occur and visualizing and displaying individual strategies. This allows users to receive recommended strategies based on their investment goals and risk tolerance, and enables them to respond quickly to rapid market changes.

[0538] "Voice input" is a method in which users provide instructions or information using their voice.

[0539] "Analysis" is the process of examining collected data to find its meaning and relationships.

[0540] "Goals" refer to the specific results or standards that users intend to achieve.

[0541] "Tolerance" refers to the range and degree of risk that a user is willing to accept.

[0542] "Amount" is a numerical value that indicates the amount of capital a user allocates to an investment.

[0543] "Data" is a collection of information that is expressed concretely using numbers or characters.

[0544] A "model" is a mathematical system used to mimic real-world phenomena and perform predictions and analyses.

[0545] "Trend" refers to a tendency that indicates the direction of change in events or situations.

[0546] A "warning" is a notification intended to inform people in advance of an anticipated crisis or problem.

[0547] An "electronic device" is a device that has the ability to process, transmit, and receive information.

[0548] "Visualization" is the process of representing data and information in shapes and diagrams that are easy for humans to understand.

[0549] "Display" refers to outputting information or data onto a screen or display and presenting it to the user.

[0550] "Strategy" is a general term for the means and methods that are systematically taken to achieve a goal.

[0551] An "asset" is property that has value and has the potential to bring profit or other benefits to its owner.

[0552] "Operation instructions" refer to specific commands or orders given to a system or device.

[0553] To realize this invention, the following system configuration is required. The server collects real-time market data from external data services via the internet. This includes information such as stock prices, trading volume, and economic indicators. This collected data is analyzed using libraries such as Python's Pandas, NumPy, and Scikit-learn. By using machine learning models such as Random Forest, market trends are predicted and investment strategies suitable for the user are generated. The server runs on an AWS EC2 instance, and RDS is used for data storage.

[0554] Taking a smartphone as an example, the device uses voice recognition technology to receive voice input from the user and sends that data as text to the server. After analysis of the user's goals and risk tolerance, the generated investment strategy is visually displayed on the device. This display also includes a real-time alert function that responds to market fluctuations. For example, if a user voice-inputs, "I want to invest with the aim of long-term growth," a portfolio will be automatically generated according to that request.

[0555] An example of a prompt message that uses a generative AI model to support a user's investment decision-making might be, "Please advise me on how to grow my assets within five years with a low-risk portfolio." By using this system, users can respond quickly to market fluctuations and make more effective asset management and investment decisions.

[0556] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0557] Step 1:

[0558] The terminal uses speech recognition technology to receive voice input from the user. This input includes the user's desired investment goals and risk tolerance. This voice data is converted into text data and sent to the server. This conversion makes the voice commands parseable.

[0559] Step 2:

[0560] The server receives text data from users and analyzes their investment goals and risk tolerance. The input data is in text format, and natural language processing is used to identify the user's intentions. This analysis clarifies the specific investment strategy the user desires.

[0561] Step 3:

[0562] The server retrieves market data from an external data service. This data includes stock prices, trading volume, and economic indicators. The retrieved data is preprocessed using Python's Pandas library, transformed using NumPy, and then a machine learning model is built using Scikit-learn. The output generates predicted market trends.

[0563] Step 4:

[0564] The server automatically generates a portfolio optimized for the user's investment goals based on the generated predictive data. In this process, it utilizes a pre-trained model to calculate the optimal asset allocation for the user. The output provides a specific investment strategy.

[0565] Step 5:

[0566] The server automatically issues buy and sell orders for assets based on the generated investment strategy. These orders are executed via the brokerage firm's API and are automatically adjusted to manage risks associated with market fluctuations.

[0567] Step 6:

[0568] Based on a schedule set by the user, the server notifies the terminal of important market information and investment opportunities as alerts. These alerts are sent via push notifications, especially during periods of significant market fluctuations, to help users respond quickly.

[0569] Step 7:

[0570] The terminal receives investment strategies and market information from the server and displays it visually to the user. As output, the user can check their asset status and market changes in real time. To broaden the user's knowledge, prompts generated using AI models are also utilized.

[0571] 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.

[0572] This invention is an AI investment support system incorporating an emotion engine, which supports the user's investment activities based on information acquired through the user's voice input. This system functions through three parties: a server, a terminal, and the user.

[0573] Server functions:

[0574] The server collects market data from external data providers and uses machine learning models and statistical methods to predict future market trends. In addition, it incorporates an emotion engine that analyzes user emotions from voice input. The information obtained from emotion analysis is used to adjust investment strategies.

[0575] Device features:

[0576] The terminal receives voice input from the user and converts it into text data using speech recognition technology. This text data is then transferred to a server, where emotional information is added by an emotion engine. The terminal displays investment strategies and market information received from the server and provides feedback to the user in a visually easy-to-understand format.

[0577] User interaction:

[0578] Users can communicate requests to their terminals via voice, such as "I want to invest more aggressively." The server then judges the user's emotions from their tone of voice and word choice. For example, if the user seems anxious, the server might suggest a strategy that minimizes risk.

[0579] Automated trading and alerts:

[0580] The server automatically issues buy and sell orders via the brokerage firm's API based on the generated investment strategy. Furthermore, it dynamically adjusts the investment strategy based on market data and the user's emotional state. If abnormal market fluctuations are detected, the server sends an alert via the terminal and suggests countermeasures tailored to the user's emotional state.

[0581] This system can mitigate investment biases based on emotions and provide users with a more stable investment environment. By incorporating an emotion engine, users can improve their investment experience and optimize their individual investment strategies.

[0582] The following describes the processing flow.

[0583] Step 1:

[0584] The user inputs their investment wishes and intentions by voice into the device. The device then uses speech recognition technology to convert this voice data into text.

[0585] Step 2:

[0586] The device sends text data, along with data used to determine the user's emotions from their voice, to the server. This emotion data is generated from tone analysis and word choice.

[0587] Step 3:

[0588] The server analyzes the received text data to identify the user's investment goals and risk tolerance. It also uses an emotion engine to analyze the transmitted emotion data and determine the user's emotional state.

[0589] Step 4:

[0590] The server acquires market data in real time from external data providers and uses machine learning models to predict market trends.

[0591] Step 5:

[0592] The server automatically generates an optimized portfolio and investment strategy for the user based on prediction results and the user's investment profile, while also considering their emotional state. Adjustments are made as needed to mitigate risk.

[0593] Step 6:

[0594] The server sends the generated investment strategy and market data analysis results to the terminal. The terminal displays this information graphically, presenting it in a format that is easy for the user to understand.

[0595] Step 7:

[0596] The server automatically executes trades via the brokerage firm's API based on predicted market trends and the user's emotional state. Furthermore, if abnormal market fluctuations are detected, it generates an alert based on the user's emotions and notifies the user via their device. The user receives the alert and readjusts their strategy as needed.

[0597] (Example 2)

[0598] 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."

[0599] Traditional investment systems often fail to adequately consider users' emotions and risk tolerance, instead relying solely on quantitative data to provide investment strategies. This makes it difficult to offer optimal investment advice tailored to individual users. Furthermore, they struggle to respond appropriately to sudden market fluctuations, requiring flexible strategic adjustments that take into account users' emotional states.

[0600] 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.

[0601] In this invention, the server includes means for analyzing voice information from the user to identify investment goals and risk tolerance, including emotions; means for analyzing market information in real time and adjusting the optimal investment strategy according to the user's emotional state; and means for detecting abnormal market fluctuations and quickly adjusting automated asset trading. This enables the provision of flexible and optimal investment strategies based on the user's individual emotions and risk preferences, and allows for appropriate responses to rapid market fluctuations.

[0602] "Voice information" refers to data provided by the user through voice, and includes input information such as the user's intentions and emotions.

[0603] "Emotional information" refers to the user's emotional state, analyzed from voice data, and is used to adjust investment strategies.

[0604] "Investment goals" refer to the specific objectives and results that a user hopes to achieve through their investment activities.

[0605] "Risk tolerance" refers to the range of risk a user can accept and is an important element in formulating an investment strategy.

[0606] "Market information" refers to data such as price fluctuations and trading volume in financial markets that are collected in real time.

[0607] An "investment strategy" is an asset management policy formulated based on the user's investment goals, risk tolerance, and market information.

[0608] "Automated asset trading" is a process that mechanically instructs and executes the buying and selling of assets based on predetermined conditions.

[0609] "Abnormal market fluctuations" refer to the phenomenon of price fluctuations that deviate significantly from normal market trends.

[0610] An "alert" refers to a warning message that notifies the user of important information or a situation that requires attention.

[0611] This invention is a system that analyzes information provided by users via voice and uses that information to support investment decisions. This system primarily functions between a server, a terminal, and the user.

[0612] Speech recognition and emotion analysis

[0613] The user inputs their investment intentions and feelings via voice into the terminal. The terminal receives this voice input and converts it into text data using speech recognition technology. Specifically, it utilizes a general-purpose speech recognition API as the speech recognition engine. This data is then sent directly to the server.

[0614] In addition, the device performs sentiment analysis to extract emotional information from the audio. This uses a library that incorporates sentiment analysis algorithms. For example, open-source libraries for Python or deep learning frameworks can be utilized.

[0615] Market data collection and forecasting

[0616] The server utilizes external information providers to collect market information in real time. This step requires selecting which platforms to use and what data to obtain. Based on this information, the server launches a predictive model to simulate future market trends. A predictive model using a common machine learning framework can be used here.

[0617] Investment strategy generation and automated trading

[0618] The server integrates the above data with sentiment information obtained from users to generate an optimal investment strategy for each user. This strategy automatically sends buy and sell instructions from the server via an API for securities trading. This allows users to execute appropriate asset management in real time.

[0619] Alerts and feedback

[0620] Furthermore, the server monitors unusual market fluctuations and notifies the user's device with appropriate alerts based on their emotional state. This allows users to stay informed about their investment situation and change their strategies if necessary.

[0621] Specific examples and prompt statements

[0622] As a concrete example, a user might voice-input, "Please tell me what investment opportunities you recommend in the current market conditions." This statement is converted into text data, which is then analyzed to determine if the user has any anxieties, and the strategy is adjusted on the server side. Another example of a prompt for the generated AI model could be a question like, "Please tell me about an investment strategy that minimizes risk."

[0623] This system allows users to receive high-quality investment strategies that comprehensively consider their own emotions and market trends.

[0624] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0625] Step 1:

[0626] The user inputs their investment intentions and questions via voice into the terminal. This voice input is recorded as data, including the user's specific requests and urgency. Upon receiving this voice input, the terminal uses a speech recognition API to convert it into text data. This process transforms the voice information into text format.

[0627] Step 2:

[0628] The terminal performs sentiment analysis using the converted text data. This involves using a sentiment analysis algorithm, which outputs sentiment data extracted from the text. Specifically, it analyzes the user's vocabulary and tone of voice, and identifies their emotional state based on the results. This data is then sent to the server for further processing.

[0629] Step 3:

[0630] The server collects real-time market information via APIs from external data providers. Inputs include securities information, trading information, etc. The server receives this data and uses machine learning models to predict future market trends. The predicted market trends are then output.

[0631] Step 4:

[0632] The server integrates user sentiment information and market forecast data to generate an optimal investment strategy. The inputs used are the user's emotional state and predicted market trends. The generated investment strategy is tailored to the user's risk tolerance and investment goals. The output is a specific investment strategy.

[0633] Step 5:

[0634] The server automatically sends buy and sell orders to the securities trading system's API based on the generated investment strategy. The input is the adjusted investment strategy, and the output is specific buy and sell orders. This process automatically manages the user's assets.

[0635] Step 6:

[0636] The server constantly monitors market anomalies and immediately sends an alert to the terminal when an anomaly is detected. The input used for this alert is the latest market data and user sentiment information. The output is an alert notification that takes user sentiment into consideration, and suggests appropriate countermeasures. This alert helps users respond quickly to sudden market fluctuations.

[0637] (Application Example 2)

[0638] 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."

[0639] In modern investment activities, investors face the risk that their emotions may bias their market judgments. Furthermore, making decisions based solely on market data without considering emotions can sometimes lead to inappropriate strategies. Moreover, in rapidly changing markets, there is a growing demand for real-time advice tailored to individual user needs. Under these circumstances, the need for investment support systems that take user emotions into account is particularly evident.

[0640] 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.

[0641] This invention includes a server that analyzes voice input from a user and identifies investment goals, risk tolerance, and investment amount based on the user's emotional state; a server that analyzes market information and predicts market trends using a predictive model; and a server that automatically generates a portfolio optimized for the user's emotional state and investment goals and provides an investment strategy. This enables the presentation and execution of flexible and optimal investment strategies that respond to the user's emotional state.

[0642] "User emotional state" refers to the psychological and emotional state of the user, analyzed from their voice input, and is a factor that influences investment decision-making.

[0643] "Investment goals" refer to the financial objectives that a user aims to achieve through asset management, specifically including goals such as increasing assets, diversifying risk, and preparing for specific future expenses.

[0644] "Risk tolerance" refers to the range of risk a user is willing to accept in asset management, and is primarily a measure of how much loss they can tolerate when the value of their assets fluctuates.

[0645] "Market information" refers to all data related to financial markets, including real-time collected stock prices, interest rates, and economic indicators.

[0646] A "portfolio" in investing refers to a collection of assets that combine different financial instruments, designed to optimize the balance between risk and return.

[0647] A "trading instruction" is an instruction issued in a financial market to buy or sell a specific asset, and its contents usually include the quantity and price conditions.

[0648] An "alert" is a system function that notifies users when predetermined conditions are met or when specific market fluctuations are confirmed, providing information to users through various channels.

[0649] To implement this invention, a system is required in which several key components work together. This system has the function of analyzing the user's voice, determining their emotional state, and providing an optimized investment strategy. The role of each component is described below.

[0650] server

[0651] The server collects market information from external data providers and uses machine learning models to predict market trends. Furthermore, it analyzes text data extracted from user voice input using an emotion engine to identify the user's emotional state. Based on this emotional state and market forecast data, it generates a suitable portfolio for the user and designs an investment strategy. Required hardware includes a general-purpose server computer, and the software utilizes natural language processing tools (e.g., IBM Watson) and machine learning frameworks (e.g., TensorFlow).

[0652] terminal

[0653] The device receives voice input from the user and converts it into text data using speech recognition technology. At this stage, the voice data is processed using technologies such as the Google Speech-to-Text API. The converted data is sent to a server, where sentiment information is added. The device is equipped with interfaces such as a display and speaker to present the investment strategy returned from the server to the user in a visual and intuitive manner.

[0654] User

[0655] Users can communicate their requests via voice to their terminal, for example, "The market is volatile, how should I proceed with investing?" The server analyzes the user's emotions from their tone of voice and context, and presents the optimal investment strategy. The user then reviews the provided information and executes investment instructions as needed.

[0656] Specific examples and prompt statements

[0657] As a concrete example, a user might say to a robot at home, "The market is volatile today and I'm a little worried, so please tell me a safe investment approach." In this case, the system recognizes the user's anxiety and proposes a low-risk investment strategy. An example of a prompt to the generating AI model would be, "Consider the user's emotional state 'anxiety' and propose a low-risk investment strategy."

[0658] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0659] Step 1:

[0660] The device receives voice input from the user and sends that voice data to a speech recognition API (e.g., Google Speech-to-Text). The input is the user's voice data, and the output is generated as text data. In this process, the voice data is converted into text format and becomes the data that proceeds to the next processing step.

[0661] Step 2:

[0662] The terminal sends the converted text data to the server. This text data represents the user's statements, and the server uses an emotion engine to analyze the received text data. The input is text data, and the output is information indicating the emotional state.

[0663] Step 3:

[0664] The server uses an emotion engine (e.g., IBM Watson) to analyze the user's emotional state from text data. This process extracts emotions from linguistic features and context contained in the text. The input is text data, and the output is an analysis result indicating the user's emotional state.

[0665] Step 4:

[0666] The server collects market information from a database or external data service and uses a machine learning model to predict market trends. The input is market data, and the output is the predicted market trend. This prediction serves as the basis for generating the next strategy.

[0667] Step 5:

[0668] The server automatically generates portfolios and investment strategies by combining the user's emotional state with market forecasts. A generation AI model is used to adjust risk based on the user's emotions. The input is the emotional state and market forecasts, and the output is a customized investment strategy.

[0669] Step 6:

[0670] The terminal receives investment strategies transmitted from the server and provides information to the user visually and audibly. The strategy is displayed on the screen, and an overview is conveyed through the speaker. The output is investment strategy information provided in a user-understandable format.

[0671] Step 7:

[0672] The user reviews the presented investment strategy and makes a decision as needed. The terminal sends the user's decision to the server and, if triggered, initiates a trade instruction to the stock exchange. The output is either a trade instruction or a revised version.

[0673] 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.

[0674] 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.

[0675] 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.

[0676] [Fourth Embodiment]

[0677] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0678] 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.

[0679] 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).

[0680] 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.

[0681] 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.

[0682] 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).

[0683] 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.

[0684] 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.

[0685] 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.

[0686] 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.

[0687] 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.

[0688] 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.

[0689] 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".

[0690] This invention is an AI-powered investment support system that enables users to make more effective investments by providing investment-related information through voice input. This system consists of three components: a server, a terminal, and a user.

[0691] Server functions:

[0692] The server obtains real-time market information from external market data providers via the internet. This market information includes stock prices, trading volume, and economic indicators. The server uses machine learning and statistical models to analyze the collected data. This allows it to predict future market trends and assess risks. This predictive data forms the basis for investment strategies generated for users.

[0693] Device features:

[0694] The user accesses the system through a device (e.g., a smartphone). The device receives the user's voice input and converts it into text data using speech recognition technology. This text data is sent to a server to analyze the user's investment goals and risk tolerance. The device then visually displays the investment strategies and market forecasts received from the server to the user.

[0695] User interaction:

[0696] The user inputs their preferences via voice, such as "I want to make long-term investments with minimal risk." The server receives the voice command and uses natural language processing to understand the user's investment intentions. Based on the conditions specified by the user, the server generates an optimal portfolio and provides an investment strategy accordingly.

[0697] Automated trading and alerts:

[0698] The server executes automated trades based on the generated investment strategy. It automatically buys and sells the user's assets through the brokerage's API, managing risk. In addition, in the event of significant market fluctuations, the server sends alerts to the user via the terminal to prompt a quick response.

[0699] This system automates investment activities, providing individual investors with an environment that makes it easier to adapt to market changes. By using the system, users can reduce the burden of market analysis and determining the timing of buy orders, thus supporting effective investment decision-making.

[0700] The following describes the processing flow.

[0701] Step 1:

[0702] The user voice-inputs their investment preferences and commands into the terminal. The terminal uses speech recognition technology to convert this voice data into text data.

[0703] Step 2:

[0704] The terminal sends the converted text data to the server. The server uses natural language processing technology to analyze the text data and identify the user's investment goals, risk tolerance, and investment amount.

[0705] Step 3:

[0706] The server collects real-time market data from external market data providers. This data includes stock prices, trading volume, and economic indicators.

[0707] Step 4:

[0708] The server uses machine learning and statistical models to predict market trends based on collected market data. Based on these predictions, it automatically generates a portfolio that aligns with the user's investment goals.

[0709] Step 5:

[0710] The server sends the generated investment strategy and market forecast results to the terminal. The terminal displays them to the user in a visually easy-to-understand format (such as graphs and charts).

[0711] Step 6:

[0712] If the user has enabled the setting to perform automated trading based on their investment strategy, the server will execute buy and sell orders through the brokerage firm's API.

[0713] Step 7:

[0714] The server continuously monitors the market and, if it detects unusual market fluctuations, sends an alert to the user via the terminal. The user reviews the alert and re-evaluates their investment strategy as needed.

[0715] (Example 1)

[0716] 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".

[0717] There is a growing need to improve the accuracy of market trend predictions in investment, automatically generate strategies tailored to individual users' investment goals, and streamline asset management. Traditional manual market analysis and investment decisions struggle to respond quickly to market fluctuations, potentially leading to missed investment opportunities. Furthermore, there is a lack of personalized strategies to satisfy the preferences of individual investors.

[0718] 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.

[0719] In this invention, the server includes means for converting voice data into text data, means for identifying the user's investment goals and risk tolerance and generating an investment portfolio, and means for predicting market trends using machine learning. This enables the automatic generation of individual strategies tailored to the user's investment needs and flexible investment decisions that respond to real-time market changes.

[0720] A "user" is an entity that utilizes an investment support system and provides investment-related information and preferences via voice input.

[0721] "Voice input" is a method in which an electronic device recognizes the words spoken by the user and processes them as digital data.

[0722] "Voice data" refers to digital data generated when a user inputs voice commands into a system.

[0723] "Text data" refers to data in text format obtained by analyzing audio data.

[0724] "Market data" is a general term for data collected in real time, such as stock prices, trading volume, and economic indicators.

[0725] "Machine learning" is an artificial intelligence technology that allows computers to learn patterns and insights from large amounts of data, and is used to predict market trends.

[0726] A "predictive model" is a mathematical model used to estimate future market trends based on past data.

[0727] An "investment portfolio" is a combination of multiple financial products selected based on the user's investment goals and risk tolerance.

[0728] A "generative AI model" is a system that uses algorithms to automatically generate investment strategies optimized for the user.

[0729] "Automated trading" refers to a function in which a system automatically buys and sells financial products based on pre-set conditions.

[0730] An "alert" is a general term for warnings and notifications sent to users when important market information or investment opportunities arise.

[0731] This invention is a system that enables users to receive investment support using voice input. This system consists of three components: a server, a terminal, and a user.

[0732] The server acquires real-time market data through external market data provision services. This market data includes stock prices, trading volume, and economic indicators. The server analyzes the data using programming languages ​​such as Python and R, and leveraging pandas and NumPy. Furthermore, it predicts market trends using machine learning libraries such as scikit-learn and TensorFlow.

[0733] A terminal refers to a smartphone or computer, and is the means by which a user accesses the system. The terminal receives the user's voice input and converts it into text data using APIs such as Google Speech Recognition. This data is sent to a server, where the user's investment objectives and risk tolerance are analyzed.

[0734] By using this system, users input their preferences, such as "I want to invest in environmentally conscious companies," via voice. Based on this input, the server analyzes the user's requests using natural language processing tools such as NLTK and spaCy, and generates an appropriate investment portfolio. The server then uses a generative AI model to automatically generate an efficient investment strategy based on prompts such as "Please propose an investment strategy that minimizes risk and aims for long-term profits."

[0735] This system executes automated trading through the brokerage firm's API, controlling the buying and selling of the user's assets in real time. Furthermore, if significant market fluctuations are detected, the server sends an alert to the user via their terminal.

[0736] This invention enables users to develop efficient investment strategies and manage assets without manually tracking the market, thereby maximizing the effectiveness of asset management.

[0737] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0738] Step 1:

[0739] The server retrieves real-time market data from external market data providers via the internet. This data includes stock prices, trading volume, and economic indicators. The entered market data is stored in a database, ensuring that the latest market information is always accessible.

[0740] Step 2:

[0741] The server processes acquired market data using Python's pandas and NumPy libraries for analysis. It utilizes machine learning libraries such as scikit-learn and TensorFlow to predict market trends. The input is real-time market data, and the output is an indicator for predicting future market trends. This enables accurate, data-driven predictions.

[0742] Step 3:

[0743] Users access the system through their devices and use voice input. Specifically, they use smartphones or computers to voice-input their preferences, such as "I want to invest in something that will yield stable returns." The input voice is converted into text data via the Google Speech Recognition API, and this data is sent to the server.

[0744] Step 4:

[0745] The server receives text data converted from voice input and analyzes the data using natural language processing tools such as NLTK and spaCy. The input is text data containing the user's wishes, and the output is information identifying the user's investment goals and risk tolerance.

[0746] Step 5:

[0747] The server uses a generative AI model to generate the optimal investment strategy based on the user's investment requests. Using the prompt "Propose an investment strategy that minimizes risk and aims for long-term profits," the AI ​​creates a proposed strategy. The input consists of investment conditions and market forecasts, and the output is the optimal investment strategy.

[0748] Step 6:

[0749] The server executes automated trades via the brokerage firm's API based on the generated investment strategy. The input is the generated investment strategy, and the output is the trading history and confirmation of successful trades.

[0750] Step 7:

[0751] The terminal visually presents investment strategies and market forecasts from the server to the user. Furthermore, if significant market fluctuations are detected, the terminal notifies the user of alerts sent from the server. This allows the user to respond quickly. Input is information from the server, and output is the display on the user interface.

[0752] (Application Example 1)

[0753] 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".

[0754] Traditional electronic payment services have faced challenges in providing immediate and personalized investment strategies to effectively support users' asset management. Furthermore, they lacked the means to respond quickly to market fluctuations, creating a risk that users' assets were exposed to unexpected volatility.

[0755] 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.

[0756] In this invention, the server includes means for analyzing voice input from the user to identify the user's goals, tolerance, and amount; means for analyzing data collected in real time and predicting trends using a model; and means for notifying electronic devices of warnings when market fluctuations occur and visualizing and displaying individual strategies. This allows users to receive recommended strategies based on their investment goals and risk tolerance, and enables them to respond quickly to rapid market changes.

[0757] "Voice input" is a method in which users provide instructions or information using their voice.

[0758] "Analysis" is the process of examining collected data to find its meaning and relationships.

[0759] "Goals" refer to the specific results or standards that users intend to achieve.

[0760] "Tolerance" refers to the range and degree of risk that a user is willing to accept.

[0761] "Amount" is a numerical value that indicates the amount of capital a user allocates to an investment.

[0762] "Data" is a collection of information that is expressed concretely using numbers or characters.

[0763] A "model" is a mathematical system used to mimic real-world phenomena and perform predictions and analyses.

[0764] "Trend" refers to a tendency that indicates the direction of change in events or situations.

[0765] A "warning" is a notification intended to inform people in advance of an anticipated crisis or problem.

[0766] An "electronic device" is a device that has the ability to process, transmit, and receive information.

[0767] "Visualization" is the process of representing data and information in shapes and diagrams that are easy for humans to understand.

[0768] "Display" refers to outputting information or data onto a screen or display and presenting it to the user.

[0769] "Strategy" is a general term for the means and methods that are systematically taken to achieve a goal.

[0770] An "asset" is property that has value and has the potential to bring profit or other benefits to its owner.

[0771] "Operation instructions" refer to specific commands or orders given to a system or device.

[0772] To realize this invention, the following system configuration is required. The server collects real-time market data from external data services via the internet. This includes information such as stock prices, trading volume, and economic indicators. This collected data is analyzed using libraries such as Python's Pandas, NumPy, and Scikit-learn. By using machine learning models such as Random Forest, market trends are predicted and investment strategies suitable for the user are generated. The server runs on an AWS EC2 instance, and RDS is used for data storage.

[0773] Taking a smartphone as an example, the device uses voice recognition technology to receive voice input from the user and sends that data as text to the server. After analysis of the user's goals and risk tolerance, the generated investment strategy is visually displayed on the device. This display also includes a real-time alert function that responds to market fluctuations. For example, if a user voice-inputs, "I want to invest with the aim of long-term growth," a portfolio will be automatically generated according to that request.

[0774] An example of a prompt message that uses a generative AI model to support a user's investment decision-making might be, "Please advise me on how to grow my assets within five years with a low-risk portfolio." By using this system, users can respond quickly to market fluctuations and make more effective asset management and investment decisions.

[0775] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0776] Step 1:

[0777] The terminal uses speech recognition technology to receive voice input from the user. This input includes the user's desired investment goals and risk tolerance. This voice data is converted into text data and sent to the server. This conversion makes the voice commands parseable.

[0778] Step 2:

[0779] The server receives text data from users and analyzes their investment goals and risk tolerance. The input data is in text format, and natural language processing is used to identify the user's intentions. This analysis clarifies the specific investment strategy the user desires.

[0780] Step 3:

[0781] The server retrieves market data from an external data service. This data includes stock prices, trading volume, and economic indicators. The retrieved data is preprocessed using Python's Pandas library, transformed using NumPy, and then a machine learning model is built using Scikit-learn. The output generates predicted market trends.

[0782] Step 4:

[0783] The server automatically generates a portfolio optimized for the user's investment goals based on the generated predictive data. In this process, it utilizes a pre-trained model to calculate the optimal asset allocation for the user. The output provides a specific investment strategy.

[0784] Step 5:

[0785] The server automatically issues buy and sell orders for assets based on the generated investment strategy. These orders are executed via the brokerage firm's API and are automatically adjusted to manage risks associated with market fluctuations.

[0786] Step 6:

[0787] Based on a schedule set by the user, the server notifies the terminal of important market information and investment opportunities as alerts. These alerts are sent via push notifications, especially during periods of significant market fluctuations, to help users respond quickly.

[0788] Step 7:

[0789] The terminal receives investment strategies and market information from the server and displays it visually to the user. As output, the user can check their asset status and market changes in real time. To broaden the user's knowledge, prompts generated using AI models are also utilized.

[0790] 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.

[0791] This invention is an AI investment support system incorporating an emotion engine, which supports the user's investment activities based on information acquired through the user's voice input. This system functions through three parties: a server, a terminal, and the user.

[0792] Server functions:

[0793] The server collects market data from external data providers and uses machine learning models and statistical methods to predict future market trends. In addition, it incorporates an emotion engine that analyzes user emotions from voice input. The information obtained from emotion analysis is used to adjust investment strategies.

[0794] Device features:

[0795] The terminal receives voice input from the user and converts it into text data using speech recognition technology. This text data is then transferred to a server, where emotional information is added by an emotion engine. The terminal displays investment strategies and market information received from the server and provides feedback to the user in a visually easy-to-understand format.

[0796] User interaction:

[0797] Users can communicate requests to their terminals via voice, such as "I want to invest more aggressively." The server then judges the user's emotions from their tone of voice and word choice. For example, if the user seems anxious, the server might suggest a strategy that minimizes risk.

[0798] Automated trading and alerts:

[0799] The server automatically issues buy and sell orders via the brokerage firm's API based on the generated investment strategy. Furthermore, it dynamically adjusts the investment strategy based on market data and the user's emotional state. If abnormal market fluctuations are detected, the server sends an alert via the terminal and suggests countermeasures tailored to the user's emotional state.

[0800] This system can mitigate investment biases based on emotions and provide users with a more stable investment environment. By incorporating an emotion engine, users can improve their investment experience and optimize their individual investment strategies.

[0801] The following describes the processing flow.

[0802] Step 1:

[0803] The user inputs their investment wishes and intentions by voice into the device. The device then uses speech recognition technology to convert this voice data into text.

[0804] Step 2:

[0805] The device sends text data, along with data used to determine the user's emotions from their voice, to the server. This emotion data is generated from tone analysis and word choice.

[0806] Step 3:

[0807] The server analyzes the received text data to identify the user's investment goals and risk tolerance. It also uses an emotion engine to analyze the transmitted emotion data and determine the user's emotional state.

[0808] Step 4:

[0809] The server acquires market data in real time from external data providers and uses machine learning models to predict market trends.

[0810] Step 5:

[0811] The server automatically generates an optimized portfolio and investment strategy for the user based on prediction results and the user's investment profile, while also considering their emotional state. Adjustments are made as needed to mitigate risk.

[0812] Step 6:

[0813] The server sends the generated investment strategy and market data analysis results to the terminal. The terminal displays this information graphically, presenting it in a format that is easy for the user to understand.

[0814] Step 7:

[0815] The server automatically executes trades via the brokerage firm's API based on predicted market trends and the user's emotional state. Furthermore, if abnormal market fluctuations are detected, it generates an alert based on the user's emotions and notifies the user via their device. The user receives the alert and readjusts their strategy as needed.

[0816] (Example 2)

[0817] 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".

[0818] Traditional investment systems often fail to adequately consider users' emotions and risk tolerance, instead relying solely on quantitative data to provide investment strategies. This makes it difficult to offer optimal investment advice tailored to individual users. Furthermore, they struggle to respond appropriately to sudden market fluctuations, requiring flexible strategic adjustments that take into account users' emotional states.

[0819] 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.

[0820] In this invention, the server includes means for analyzing voice information from the user to identify investment goals and risk tolerance, including emotions; means for analyzing market information in real time and adjusting the optimal investment strategy according to the user's emotional state; and means for detecting abnormal market fluctuations and quickly adjusting automated asset trading. This enables the provision of flexible and optimal investment strategies based on the user's individual emotions and risk preferences, and allows for appropriate responses to rapid market fluctuations.

[0821] "Voice information" refers to data provided by the user through voice, and includes input information such as the user's intentions and emotions.

[0822] "Emotional information" refers to the user's emotional state, analyzed from voice data, and is used to adjust investment strategies.

[0823] "Investment goals" refer to the specific objectives and results that a user hopes to achieve through their investment activities.

[0824] "Risk tolerance" refers to the range of risk a user can accept and is an important element in formulating an investment strategy.

[0825] "Market information" refers to data such as price fluctuations and trading volume in financial markets that are collected in real time.

[0826] An "investment strategy" is an asset management policy formulated based on the user's investment goals, risk tolerance, and market information.

[0827] "Automated asset trading" is a process that mechanically instructs and executes the buying and selling of assets based on predetermined conditions.

[0828] "Abnormal market fluctuations" refer to the phenomenon of price fluctuations that deviate significantly from normal market trends.

[0829] An "alert" refers to a warning message that notifies the user of important information or a situation that requires attention.

[0830] This invention is a system that analyzes information provided by users via voice and uses that information to support investment decisions. This system primarily functions between a server, a terminal, and the user.

[0831] Speech recognition and emotion analysis

[0832] The user inputs their investment intentions and feelings via voice into the terminal. The terminal receives this voice input and converts it into text data using speech recognition technology. Specifically, it utilizes a general-purpose speech recognition API as the speech recognition engine. This data is then sent directly to the server.

[0833] In addition, the device performs sentiment analysis to extract emotional information from the audio. This uses a library that incorporates sentiment analysis algorithms. For example, open-source libraries for Python or deep learning frameworks can be utilized.

[0834] Market data collection and forecasting

[0835] The server utilizes external information providers to collect market information in real time. This step requires selecting which platforms to use and what data to obtain. Based on this information, the server launches a predictive model to simulate future market trends. A predictive model using a common machine learning framework can be used here.

[0836] Investment strategy generation and automated trading

[0837] The server integrates the above data with sentiment information obtained from users to generate an optimal investment strategy for each user. This strategy automatically sends buy and sell instructions from the server via an API for securities trading. This allows users to execute appropriate asset management in real time.

[0838] Alerts and feedback

[0839] Furthermore, the server monitors unusual market fluctuations and notifies the user's device with appropriate alerts based on their emotional state. This allows users to stay informed about their investment situation and change their strategies if necessary.

[0840] Specific examples and prompt statements

[0841] As a concrete example, a user might voice-input, "Please tell me what investment opportunities you recommend in the current market conditions." This statement is converted into text data, which is then analyzed to determine if the user has any anxieties, and the strategy is adjusted on the server side. Another example of a prompt for the generated AI model could be a question like, "Please tell me about an investment strategy that minimizes risk."

[0842] This system allows users to receive high-quality investment strategies that comprehensively consider their own emotions and market trends.

[0843] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0844] Step 1:

[0845] The user inputs their investment intentions and questions via voice into the terminal. This voice input is recorded as data, including the user's specific requests and urgency. Upon receiving this voice input, the terminal uses a speech recognition API to convert it into text data. This process transforms the voice information into text format.

[0846] Step 2:

[0847] The terminal performs sentiment analysis using the converted text data. This involves using a sentiment analysis algorithm, which outputs sentiment data extracted from the text. Specifically, it analyzes the user's vocabulary and tone of voice, and identifies their emotional state based on the results. This data is then sent to the server for further processing.

[0848] Step 3:

[0849] The server collects real-time market information via APIs from external data providers. Inputs include securities information, trading information, etc. The server receives this data and uses machine learning models to predict future market trends. The predicted market trends are then output.

[0850] Step 4:

[0851] The server integrates user sentiment information and market forecast data to generate an optimal investment strategy. The inputs used are the user's emotional state and predicted market trends. The generated investment strategy is tailored to the user's risk tolerance and investment goals. The output is a specific investment strategy.

[0852] Step 5:

[0853] The server automatically sends buy and sell orders to the securities trading system's API based on the generated investment strategy. The input is the adjusted investment strategy, and the output is specific buy and sell orders. This process automatically manages the user's assets.

[0854] Step 6:

[0855] The server constantly monitors market anomalies and immediately sends an alert to the terminal when an anomaly is detected. The input used for this alert is the latest market data and user sentiment information. The output is an alert notification that takes user sentiment into consideration, and suggests appropriate countermeasures. This alert helps users respond quickly to sudden market fluctuations.

[0856] (Application Example 2)

[0857] 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".

[0858] In modern investment activities, investors face the risk that their emotions may bias their market judgments. Furthermore, making decisions based solely on market data without considering emotions can sometimes lead to inappropriate strategies. Moreover, in rapidly changing markets, there is a growing demand for real-time advice tailored to individual user needs. Under these circumstances, the need for investment support systems that take user emotions into account is particularly evident.

[0859] 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.

[0860] This invention includes a server that analyzes voice input from a user and identifies investment goals, risk tolerance, and investment amount based on the user's emotional state; a server that analyzes market information and predicts market trends using a predictive model; and a server that automatically generates a portfolio optimized for the user's emotional state and investment goals and provides an investment strategy. This enables the presentation and execution of flexible and optimal investment strategies that respond to the user's emotional state.

[0861] "User emotional state" refers to the psychological and emotional state of the user, analyzed from their voice input, and is a factor that influences investment decision-making.

[0862] "Investment goals" refer to the financial objectives that a user aims to achieve through asset management, specifically including goals such as increasing assets, diversifying risk, and preparing for specific future expenses.

[0863] "Risk tolerance" refers to the range of risk a user is willing to accept in asset management, and is primarily a measure of how much loss they can tolerate when the value of their assets fluctuates.

[0864] "Market information" refers to all data related to financial markets, including real-time collected stock prices, interest rates, and economic indicators.

[0865] A "portfolio" in investing refers to a collection of assets that combine different financial instruments, designed to optimize the balance between risk and return.

[0866] A "trading instruction" is an instruction issued in a financial market to buy or sell a specific asset, and its contents usually include the quantity and price conditions.

[0867] An "alert" is a system function that notifies users when predetermined conditions are met or when specific market fluctuations are confirmed, providing information to users through various channels.

[0868] To implement this invention, a system is required in which several key components work together. This system has the function of analyzing the user's voice, determining their emotional state, and providing an optimized investment strategy. The role of each component is described below.

[0869] server

[0870] The server collects market information from external data providers and uses machine learning models to predict market trends. Furthermore, it analyzes text data extracted from user voice input using an emotion engine to identify the user's emotional state. Based on this emotional state and market forecast data, it generates a suitable portfolio for the user and designs an investment strategy. Required hardware includes a general-purpose server computer, and the software utilizes natural language processing tools (e.g., IBM Watson) and machine learning frameworks (e.g., TensorFlow).

[0871] terminal

[0872] The device receives voice input from the user and converts it into text data using speech recognition technology. At this stage, the voice data is processed using technologies such as the Google Speech-to-Text API. The converted data is sent to a server, where sentiment information is added. The device is equipped with interfaces such as a display and speaker to present the investment strategy returned from the server to the user in a visual and intuitive manner.

[0873] User

[0874] Users can communicate their requests via voice to their terminal, for example, "The market is volatile, how should I proceed with investing?" The server analyzes the user's emotions from their tone of voice and context, and presents the optimal investment strategy. The user then reviews the provided information and executes investment instructions as needed.

[0875] Specific examples and prompt statements

[0876] As a concrete example, a user might say to a robot at home, "The market is volatile today and I'm a little worried, so please tell me a safe investment approach." In this case, the system recognizes the user's anxiety and proposes a low-risk investment strategy. An example of a prompt to the generating AI model would be, "Consider the user's emotional state 'anxiety' and propose a low-risk investment strategy."

[0877] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0878] Step 1:

[0879] The device receives voice input from the user and sends that voice data to a speech recognition API (e.g., Google Speech-to-Text). The input is the user's voice data, and the output is generated as text data. In this process, the voice data is converted into text format and becomes the data that proceeds to the next processing step.

[0880] Step 2:

[0881] The terminal sends the converted text data to the server. This text data represents the user's statements, and the server uses an emotion engine to analyze the received text data. The input is text data, and the output is information indicating the emotional state.

[0882] Step 3:

[0883] The server uses an emotion engine (e.g., IBM Watson) to analyze the user's emotional state from text data. This process extracts emotions from linguistic features and context contained in the text. The input is text data, and the output is an analysis result indicating the user's emotional state.

[0884] Step 4:

[0885] The server collects market information from a database or external data service and uses a machine learning model to predict market trends. The input is market data, and the output is the predicted market trend. This prediction serves as the basis for generating the next strategy.

[0886] Step 5:

[0887] The server automatically generates portfolios and investment strategies by combining the user's emotional state with market forecasts. A generation AI model is used to adjust risk based on the user's emotions. The input is the emotional state and market forecasts, and the output is a customized investment strategy.

[0888] Step 6:

[0889] The terminal receives investment strategies transmitted from the server and provides information to the user visually and audibly. The strategy is displayed on the screen, and an overview is conveyed through the speaker. The output is investment strategy information provided in a user-understandable format.

[0890] Step 7:

[0891] The user reviews the presented investment strategy and makes a decision as needed. The terminal sends the user's decision to the server and, if triggered, initiates a trade instruction to the stock exchange. The output is either a trade instruction or a revised version.

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0899] 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.

[0900] 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."

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] 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.

[0913] The following is further disclosed regarding the embodiments described above.

[0914] (Claim 1)

[0915] A means of analyzing voice input from users to identify their investment goals, risk tolerance, and investment amount,

[0916] A method for analyzing market data collected in real time and predicting market trends using a predictive model,

[0917] A means of automatically generating a portfolio optimized for the user's investment goals and providing an investment strategy,

[0918] A means of automatically issuing buy and sell orders for assets based on the generated investment strategy,

[0919] A means of notifying users of important market information and investment opportunities as alerts according to their schedule,

[0920] A system that includes this.

[0921] (Claim 2)

[0922] The system according to claim 1, further comprising means for converting a user's voice input into text data and analyzing the text data to understand the user's investment preferences.

[0923] (Claim 3)

[0924] The system according to claim 1, further comprising means for detecting abnormal market fluctuations based on predicted market trends, promptly notifying the system in such cases, and adjusting automated trading of the relevant assets.

[0925] "Example 1"

[0926] (Claim 1)

[0927] A means for analyzing voice input from a user and converting the voice data into text data,

[0928] A means of identifying a user's investment goals and risk tolerance by analyzing textual data, and generating an investment portfolio.

[0929] A method for analyzing market data collected in real time and predicting market trends using machine learning,

[0930] A means of automatically generating investment strategies optimized for the user's investment goals using a generative AI model,

[0931] A means of conducting automated trading of financial products based on a generated investment strategy,

[0932] A means of notifying users of important market information and investment opportunities according to the time and conditions they specify,

[0933] A system that includes this.

[0934] (Claim 2)

[0935] The system according to claim 1, further comprising means for analyzing user investment preference settings on a server and constructing an appropriate portfolio.

[0936] (Claim 3)

[0937] The system according to claim 1, further comprising means for automatically detecting abnormal market fluctuations and quickly modifying investment strategies and buying / selling assets in response to those fluctuations.

[0938] "Application Example 1"

[0939] (Claim 1)

[0940] A means of analyzing voice input from users to identify their goals, tolerance levels, and budgets,

[0941] A method for analyzing data collected in real time and predicting trends using a model,

[0942] A means of automatically generating a configuration optimized for the user's goals and providing a strategy,

[0943] A means of automatically issuing asset operation instructions based on the generated strategy,

[0944] A means of notifying users of important information and opportunities as alerts according to their schedule,

[0945] A means of notifying electronic devices of warnings during market fluctuations and visualizing and displaying individual strategies,

[0946] A system that includes this.

[0947] (Claim 2)

[0948] The system according to claim 1, further comprising means for converting voice-input requests into data and analyzing that data to understand investment preferences.

[0949] (Claim 3)

[0950] The system according to claim 1, further comprising means for detecting abnormal fluctuations based on predicted trends, promptly notifying in such cases, and adjusting the automated operation of the relevant asset.

[0951] "Example 2 of combining an emotion engine"

[0952] (Claim 1)

[0953] A means of analyzing voice information from users to identify their investment goals, risk tolerance, and investment amount,

[0954] A method for analyzing market information collected in real time and predicting market trends using a predictive model,

[0955] A means of analyzing emotional information based on voice data and adjusting investment strategies according to the user's emotional state,

[0956] A means of automatically generating asset groups optimized for the user's investment goals and providing investment strategies,

[0957] A means of automatically issuing buy and sell instructions based on the generated investment strategy,

[0958] A means of notifying users of investment opportunities as alerts based on market information and their emotional state,

[0959] A system that includes this.

[0960] (Claim 2)

[0961] The system according to claim 1, further comprising means for converting audio information into text data and analyzing the text data to understand the user's investment preferences.

[0962] (Claim 3)

[0963] The system according to claim 1, further comprising means for detecting abnormal market fluctuations based on predicted market trends and sentiment information, promptly notifying the system in such cases, and adjusting automated trading of the relevant assets.

[0964] "Application example 2 of combining emotional engines"

[0965] (Claim 1)

[0966] A means of analyzing voice input from users to identify investment goals, risk tolerance, and investment amounts based on the user's emotional state,

[0967] A method for analyzing market information collected in real time and predicting market trends using a predictive model,

[0968] A means of automatically generating a portfolio optimized for the user's emotional state and investment goals, and providing an investment strategy,

[0969] A means of automatically issuing trading instructions for assets based on the generated investment strategy,

[0970] A means of notifying users of important market information and investment opportunities as alerts based on their emotional state,

[0971] A system that includes this.

[0972] (Claim 2)

[0973] The system according to claim 1, further comprising means for converting a user's voice input into text data and understanding the user's investment preferences based on the text data and sentiment analysis results.

[0974] (Claim 3)

[0975] The system according to claim 1, further comprising means for detecting abnormal market fluctuations based on predicted market trends, promptly notifying the user in such cases, and adjusting automated trading with countermeasures that take into account the user's emotional state. [Explanation of Symbols]

[0976] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analyzing voice input from users to identify their investment goals, risk tolerance, and investment amount, A method for analyzing market data collected in real time and predicting market trends using a predictive model, A means of automatically generating a portfolio optimized for the user's investment goals and providing an investment strategy, A means of automatically issuing buy and sell orders for assets based on the generated investment strategy, A means of notifying users of important market information and investment opportunities as alerts according to their schedule, A system that includes this.

2. The system according to claim 1, further comprising means for converting a user's voice input into text data and analyzing the text data to understand the user's investment preferences.

3. The system according to claim 1, further comprising means for detecting abnormal market fluctuations based on predicted market trends, promptly notifying the system in such cases, and adjusting automated trading of the relevant assets.

Images