system

Abstract

We provide the system. [Solution] Means for collecting market data, A means for generating investment decisions based on news data analyzed using natural language processing technology, Based on the aforementioned investment decision, a means of automatically executing buy and sell orders via the trading platform API, A display means for reporting the results of the aforementioned trades to the user, A means to improve the accuracy of investment decisions by analyzing past investment results and updating generative models, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In diverse financial markets, in order for individual investors to invest effectively, advanced market analysis capabilities and timely information collection are required, but there is a problem that it is not always easy to perform these. Also, in regions where there are many inexperienced investors, the uneasiness regarding asset management and the complexity of the market are raising the barriers to entry into investment. As a result, there is a problem not only of missing opportunities for efficient asset management but also of increasing potential loss risks.

Means for Solving the Problems

[0005] According to the present invention, a means is provided for automatically generating investment decisions by collecting market data in real time and analyzing news data using natural language processing technology. Based on these investment decisions, automated trading is performed using a trading platform API, and the system is equipped with a means for reporting trading results to the user in an easy-to-understand manner, thereby improving the user's investment experience. Furthermore, by periodically updating the generation model based on past investment results and improving the accuracy of the decisions, the system provides a means to promote safe and efficient investment activities for investors, including new entrants.

[0006] "Market data" refers to data such as price information, transaction information, and economic indicators obtained from financial markets, and is fundamental information necessary for investment decisions.

[0007] "Natural language processing technology" is a technology that allows computers to understand, analyze, and utilize human language, and is particularly used for analyzing text data such as news articles.

[0008] "Investment decisions" refer to the decision-making process for determining whether to buy, sell, or hold assets, based on market conditions and economic trends.

[0009] A "trading platform API" is an interface that allows external programs to access the trading systems of exchanges and securities companies and place buy and sell orders.

[0010] "Automated trading" is a process in which a computer executes trades based on pre-set rules and algorithms without human intervention.

[0011] "Display means" refers to methods and technologies for visually presenting data and information to users using computer screens, devices, etc.

[0012] A "generative model" refers to an AI algorithm or mathematical method created for a specific purpose, which performs learning and prediction based on a specific dataset.

[0013] "Risk tolerance" refers to the range and degree of risk that an investor is willing to accept, and is a factor that influences an individual investor's asset management strategy. [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, etc.

[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-driven system that enables individual investors to efficiently conduct investment activities in diverse financial markets. The system is server-centric, and users can manage their investment portfolios by accessing the system via terminals.

[0036] The server first collects market data. This includes stock, bond, and foreign exchange data, which is regularly gathered from financial data providers and news sources on the internet. The server analyzes this data using natural language processing technology to predict future market trends and make investment-related decisions.

[0037] For example, if the server detects news that "stock prices in a particular technology sector are expected to fall due to disruptions in global supply chains," the system can refer to similar past cases and recommend selling the stocks. The system can adjust this decision according to the user's risk tolerance, advising low-risk users to sell some stocks and suggesting high-risk users continue holding their stocks to weather short-term market volatility.

[0038] After an investment decision is made, the server executes automated trades via the trading platform API. This eliminates the need for users to constantly monitor market conditions, as the system automatically buys and sells at the optimal time. Furthermore, after each trade is executed, the server reports a performance summary to the terminal, supporting efficient investment management.

[0039] This system also allows for continuous model updates. By analyzing past investment results, the AI ​​model improves the accuracy of investment decisions and provides better predictions for future decisions. As a result, users can respond quickly and effectively to market changes and maximize investment returns without having to perform complex market analysis.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server accesses market data providers to collect real-time data such as stock prices, bond yields, and foreign exchange rates. The collected data is stored in a database and used for subsequent analysis.

[0043] Step 2:

[0044] The server retrieves the latest financial news from internet news sources. The retrieved news is analyzed using natural language processing technology, and its potential impact on the market is evaluated. For example, the server identifies important keywords in the text and scores their potential impact on the market based on historical data.

[0045] Step 3:

[0046] The server generates investment decisions based on the data it analyzes. This process considers a combination of news analysis results and market data to determine buy and sell actions. These decisions are adjusted according to the user's risk tolerance.

[0047] Step 4:

[0048] The server executes automated trades via the trading platform API. Trading orders are generated by the server and sent through the API. This automatically buys and sells the specified financial instruments.

[0049] Step 5:

[0050] The terminal receives information sent from the server and displays the latest investment performance to the user. The information can be visually viewed on the dashboard, allowing the user to understand the status of their portfolio.

[0051] Step 6:

[0052] The server analyzes past trading data and updates the AI ​​model. This improves the accuracy of future investment decisions. The model is continuously improved through this feedback loop.

[0053] (Example 1)

[0054] 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."

[0055] For individual investors to invest efficiently and effectively in diverse financial markets, they need to analyze vast amounts of market data and continuously make accurate investment decisions. However, performing these tasks manually is extremely labor-intensive and requires specialized knowledge and quick decision-making skills, making it difficult for individuals to handle. Therefore, there is a need to provide a system that automates everything from market data collection and analysis to investment decisions and execution, and that can adjust decisions according to the risk tolerance of individual investors.

[0056] 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.

[0057] In this invention, the server includes means for collecting information, means for generating decisions based on information data analyzed using language processing technology, and means for automatically executing operations via a communication interface based on the decisions. This makes it possible for individual investors to efficiently perform everything from collecting and analyzing market data to executing automated trading.

[0058] "Information" refers to data obtained from markets and other sources, as well as text data such as news articles.

[0059] "Means of collection" refers to the components responsible for the process of obtaining information from external data providers and news sources.

[0060] "Language processing technology" refers to the technology of applying natural language analysis to information data and extracting the necessary meaning.

[0061] "Means of generating judgments" refers to the process of deriving the next course of action or decision based on analyzed information data.

[0062] A "communication interface" refers to the interface through which a server exchanges information with external systems and services.

[0063] "Means of executing operations" refers to a mechanism that carries out specific actions, such as buying and selling, based on the generated judgment.

[0064] "Display means" refers to a function that shows the results of an operation or notifications from the system in a way that is recognizable to the user.

[0065] "Methods for updating a model" refers to the process of adjusting the algorithms and parameters of a generative model based on past results to improve prediction accuracy.

[0066] "Tolerance" refers to the range or level of risk that a user can accept, and it serves as a criterion for adjusting investment decisions.

[0067] This invention provides a system that allows individual investors to automatically manage their investments in accordance with market trends. The server first collects market information from data providers on the internet. This information is provided in JSON format, and the server periodically retrieves the data using HTTP requests. The retrieved information is then analyzed as text data using natural language processing techniques. In this process, Python libraries such as NLTK and Spacy are utilized to extract important keywords and context from the information.

[0068] Based on the analysis, the server utilizes a generated AI model to produce investment decisions. This AI model proposes individual investment strategies based on the user's risk tolerance, while comparing them with historical market data. For example, a prompt message such as "Considering this week's market trends, please propose an investment strategy related to Apple's new product announcement" is generated, and the AI ​​provides recommendations accordingly.

[0069] Based on this generated investment decision, the server directly executes automated trades via the trading platform's communication interface (e.g., API). Once the trade is complete, the result is notified to the user's terminal. Specifically, a message such as "Your purchase of 100 shares of Apple was successful" is displayed on the terminal.

[0070] Furthermore, by analyzing past trading results, the server updates its generative model, improving the accuracy of investment decisions. This enables users to make efficient and strategic investments without having to closely monitor the market.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The server collects market information from data providers on the internet. Specifically, it uses APIs to issue HTTP requests and retrieve data provided in JSON format. This data includes information on stocks, bonds, foreign exchange, etc. The input is the API endpoint, and the output is the raw data stored on the server.

[0074] Step 2:

[0075] The server analyzes the collected market information using natural language processing techniques. Specifically, it uses Python's NLTK and Spacy libraries to extract important keywords and context from news articles and market information. The input is market data in JSON format, and the output is text data of the analyzed information.

[0076] Step 3:

[0077] The server utilizes a generated AI model based on the analyzed information to generate investment decisions. In this process, it references the user's risk tolerance and historical market data to create a highly probable investment strategy. The generated prompt statements are used to query the AI ​​model. The input is the analyzed data and the user's risk tolerance, and the output is a specific investment strategy.

[0078] Step 4:

[0079] The server automatically executes trades via the trading platform's API based on the generated investment decisions. Specifically, it sends appropriate buy and sell instructions to the platform API and checks the results. The input is the investment strategy, and the output is the success or failure of the trade.

[0080] Step 5:

[0081] The server notifies the user's terminal of the trading results. For example, it might send a message to the terminal saying, "Your purchase of 100 shares of Apple was successful," allowing the user to check the transaction status. The input is the trading result, and the output is the notification information sent to the user.

[0082] Step 6:

[0083] The server analyzes past trading results and updates the generated AI model. Specifically, it retrains the model using historical investment performance data to prepare for improved accuracy in future decisions. The input is historical trading data, and the output is the updated AI model.

[0084] (Application Example 1)

[0085] 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."

[0086] Individual investors need to analyze vast amounts of market and news information daily to make quick and accurate financial decisions, but this is a very time-consuming and specialized task, and many investors find this process difficult. Furthermore, security and efficiency are required in the settlement of asset buying and selling transactions, but current manual processes struggle to meet these requirements. The present invention aims to solve these problems and enable more investors to engage in efficient and safe investment activities.

[0087] 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.

[0088] In this invention, the server includes means for collecting market information, means for generating financial decisions based on news information analyzed using natural language processing technology, and means for automatically executing asset trades via an information exchange platform API. This enables investors to make optimal investment decisions and asset trades efficiently and safely without having to manually analyze market information.

[0089] "Market information" refers to all data related to financial markets, such as stocks, bonds, and foreign exchange.

[0090] "Natural language processing technology" is a technique for analyzing text data into a format that computers can understand and grasping its meaning.

[0091] "News information" refers to market and economic information contained in news articles and other materials that may influence investment decisions.

[0092] "Financial decision-making" refers to the act of deciding whether to buy, sell, or hold assets in the course of investment activities, as well as the results thereof.

[0093] An "information exchange platform API" is an application programming interface for direct communication with a platform used for asset trading.

[0094] "Asset trading" refers to the act of selling or buying stocks or other financial products.

[0095] "Approval" refers to the payment processing involved in the completion of a transaction and the transfer of assets.

[0096] "Financial optimization" is the process of optimizing the allocation of financial assets according to an individual's investment objectives and risk tolerance.

[0097] A "user profile" refers to individual information, including records of an person's investments, risk tolerance, and financial objectives.

[0098] To implement this invention, a platform centered around an AI-driven automated trading system will be constructed. The server will first periodically collect market information. Specifically, it will obtain data on stocks, bonds, foreign exchange, etc., from internet data providers and store it in a database.

[0099] The server then analyzes the collected news information using Python and natural language processing libraries. Natural language processing techniques are used to extract information from news and articles that could potentially influence investment decisions, and a generative AI model is used to make financial decisions. TENSORFLOW® is used to train the AI ​​model, and Scikit-learn is used in conjunction with it for data analysis.

[0100] Through an information exchange platform API, the server automatically executes asset trades. This process integrates with electronic payment services such as Stripe, enabling secure and rapid settlement of each transaction. Furthermore, the server notifies users of the transaction results and provides this information through mobile apps and desktop clients.

[0101] On the user's device, information is received through an application built with React Native, and financial optimization is performed based on the user profile. For example, as a result of an AI analysis, an alert such as "Emerging markets are performing well, and we recommend purchasing related stocks" is sent to the user's device, and based on the user's decision, the purchase process is automatically carried out on the server side.

[0102] An example of a prompt message is to give the AI ​​model an instruction such as, "Based on new market data, have the AI ​​model predict which assets to recommend purchasing," and the AI ​​model will then analyze market trends.

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The server periodically collects market information such as stocks, bonds, and foreign exchange from market data providers and stores it in a database. The input is real-time market information from external data sources, and the output is structured database entries. This data is used for subsequent analysis.

[0106] Step 2:

[0107] The server analyzes news information using natural language processing technology. News information is provided as input, and a generative AI model extracts information from the document that influences investment decisions. The output is elemental information identified by the server for making investment decisions. This makes it possible to understand news trends and their impact on the market.

[0108] Step 3:

[0109] The server uses an AI model to make financial decisions based on the analysis data from the previous step. The input is the result of natural language processing, which the predictive model uses to forecast fluctuations in the financial market. The output is a proposal for specific investment actions. TensorFlow is used throughout this process, and the model is continuously trained to improve prediction accuracy.

[0110] Step 4:

[0111] Through an information exchange platform API, the server automatically executes buy and sell transactions for recommended assets. The input is investment recommendations from an AI model, and the output is buy and sell orders sent to the trading platform. This enables instant trading without human intervention.

[0112] Step 5:

[0113] The system notifies the user terminal of the transaction results. Input is a notification of the transaction's success or failure, and output is a user-facing report containing detailed information. It informs users of market trends in real time, helping them to take the next action.

[0114] Step 6:

[0115] The server analyzes transaction history and uses this data to update the generated AI model. The input is past transaction data and results, and the output is an improved predictive model. This process acts as a feedback loop to improve the accuracy of the user's investment decisions.

[0116] 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.

[0117] This invention provides a system that recognizes user emotions and reflects them in investment decisions, thereby offering more personalized investment support. The system comprises a server, terminals, and an emotion engine.

[0118] First, the server collects market data and relevant news, and performs data analysis using natural language processing technology. During this process, generative AI is used to generate investment decisions to predict market trends. These generated investment decisions are then adjusted based on the user's risk tolerance.

[0119] Next, the emotion engine works to recognize the user's emotions through the user's device. This analyzes the current emotional state using biometric information (e.g., heart rate, facial expressions, etc.) and information entered by the user. For example, if the emotion engine detects that the user is feeling stressed, it will adjust investment decisions conservatively. This emotion-based adjustment allows the user to invest safely while reducing psychological burden.

[0120] The server also has the ability to execute automated trades via the trading platform API and report the trading results to the user. The terminal is equipped with a dashboard that displays performance data to the user in real time, allowing the user to see how their investment status and emotions are influencing their investment decisions.

[0121] Furthermore, the server analyzes past investment results and sentiment data to update the model. This improves the accuracy of future investment decisions and allows for the provision of more user-friendly investment advice. By utilizing sentiment data in this way, it becomes possible to provide sophisticated investment support that is not merely data-driven, but also takes into account the user's emotional state.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The server retrieves real-time financial data from market data providers. This includes stock prices, bond yields, and foreign exchange rates, and the retrieved data is stored in a database. The server also collects the latest market-related news via a news API.

[0125] Step 2:

[0126] The server analyzes collected news data using natural language processing technology. A generating AI analyzes news articles, assesses their potential impact on the market, and calculates specific indicators to make investment decisions. Based on this assessment, it determines specific buy or sell actions.

[0127] Step 3:

[0128] The device analyzes the user's emotional state through an emotion engine. It acquires the user's biometric information using sensors and other means to identify their current emotional state (e.g., relaxed, stressed). Users can also directly input their emotions.

[0129] Step 4:

[0130] The server adjusts investment decisions based on emotional information obtained from the emotion engine. For example, if a user is experiencing stress, the investment portfolio is readjusted to reduce risk. This adjustment is then compiled into the final investment decision.

[0131] Step 5:

[0132] The server executes automated trades via the trading platform API. The system sends determined buy and sell instructions to the trading platform, and the sale or purchase of selected financial instruments is executed.

[0133] Step 6:

[0134] The terminal receives information from the server and displays the latest investment status and trading results to the user on a dashboard. Through this information, the user can check the performance of their portfolio and the impact of their emotions.

[0135] Step 7:

[0136] The server analyzes past investment performance and sentiment data to update the AI ​​model. This makes future investment decisions more accurate. The analysis results are shared within the system as feedback and presented to the user as improvement suggestions.

[0137] (Example 2)

[0138] 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".

[0139] Conventional investment support systems make investment decisions based on market trends, but they do not take into account the user's emotions or psychological state, making it difficult to provide investment strategies optimized for individual users. Furthermore, there were challenges in improving the accuracy of automated investment decisions and establishing a user-friendly interface.

[0140] 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.

[0141] In this invention, the server includes a device for collecting market information, a device for generating investment decisions based on information data analyzed using natural language processing technology, and a device for automatically executing trades via a management system API. This enables individually optimized investment support by recognizing the user's emotional state and providing investment decisions adjusted accordingly.

[0142] "Market information" refers to data and information related to financial markets, including, for example, stock prices, exchange rates, economic indicators, and news articles.

[0143] "Analyzed information data" refers to data such as news and market information that has been analyzed using natural language processing technology, and is a fundamental element for investment decisions.

[0144] A "management system API" is an application programming interface that enables automated trading and data access, and is a means of communicating with external systems and software.

[0145] A "display device" is a device or interface that provides information to a user visually, and typically includes computer monitors and smartphone screens.

[0146] A "generative model" is a data processing algorithm that learns from past data and information to make future investment decisions, and typically uses machine learning techniques.

[0147] "User emotional state" refers to the actual emotional state analyzed from biometric information such as heart rate and facial expressions, and is used to fine-tune investment decisions.

[0148] "Investment decisions" are judgments and policies that guide the timing and strategies for buying and selling assets, generated based on market information and the emotional state of the user.

[0149] This invention provides a system that offers individually optimized investment support that takes into account the user's emotional data. This system mainly consists of a server, terminals, and an emotional engine.

[0150] First, the server collects market information and stores it in a database. Market information is obtained from financial market news and various economic data through web scraping techniques and publicly available APIs. Specific data sources typically include financial news websites and economic data provision services.

[0151] Next, the server analyzes the collected information using natural language processing techniques. This analysis utilizes generative AI models, such as sentiment analysis of news articles and prediction of market trends. For this purpose, generative AI models like BERT and the GPT series are used. An example of a prompt might be, "Predict important trends from today's market news."

[0152] The server generates investment decisions based on these analysis results and automatically executes trades via the management system API. These trades are automated and can buy and sell stocks and other financial instruments based on specific conditions.

[0153] Meanwhile, the device collects the user's biometric information and transmits it to the emotion engine. The device acquires biometric information such as heart rate from the wearable device and also analyzes facial expressions through the camera. This analysis estimates the user's emotional state in real time.

[0154] The emotion engine uses this emotional data to adjust investment decisions generated on the server according to the user's risk tolerance. For example, if a user is experiencing high levels of stress, the system will adjust to select a more conservative investment strategy.

[0155] Finally, the server sends the updated investment decision results to the terminal and displays them to the user. This allows the user to visualize how their emotional state is influencing their investment decisions.

[0156] By integrating the entire system in this way, it becomes possible to provide sophisticated investment support that utilizes sentiment data, not just decisions based on market data.

[0157] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0158] Step 1:

[0159] The server collects market information. Input is raw market data obtained through web scraping techniques and APIs, while output is organized market information stored in a database. The server performs this regularly, covering financial news and economic indicators.

[0160] Step 2:

[0161] The server performs natural language processing based on the collected market information. The input is the market information obtained in step 1, and the output is the analyzed data. Specifically, a generative AI model is used, with the prompt "Perform market trend and sentiment analysis" as input, and trends are extracted from the data.

[0162] Step 3:

[0163] The server generates investment decisions using naturally language processed data. The input is the analyzed data obtained in step 2, and the output is a specific investment strategy indicator. The generated investment decisions provide concrete examples, such as "you should focus on buying technology stocks in the next week." This clarifies the guidance for automated trading systems.

[0164] Step 4:

[0165] The device collects biometric information to measure the user's emotional state. Input is biometric information obtained from wearable devices or cameras (e.g., heart rate, facial expression data), and output is analyzed emotional data sent to an emotion engine. By tracking the user's emotional state in real time, the system aims to identify potential influences on investment decisions.

[0166] Step 5:

[0167] The emotion engine adjusts investment decisions based on the user's emotional data. The input is the emotional data obtained in step 4 and the investment decision in step 3, and the output is the adjusted investment strategy. For example, it might make a decision such as, "The user is currently feeling stressed, so adopt a conservative strategy."

[0168] Step 6:

[0169] The server executes the adjusted investment strategy and reports the results to the terminal in real time. The input is the adjusted investment strategy generated in step 5, and the output is the result of the trades executed based on that strategy. The user can view this from the terminal and evaluate their investment performance in real time.

[0170] (Application Example 2)

[0171] 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".

[0172] In recent years, individual investors have been required to make investment decisions based on diverse market information and trends. However, general automated trading systems cannot adequately consider the emotions and subjective risk tolerance of individual investors. As a result, this can lead to psychological burden and unnecessary depletion of assets due to taking excessive risks. Therefore, there is a need for a system that can make investment decisions based on the emotional state and risk tolerance of individual investors, thereby optimizing asset management while reducing mental stress.

[0173] 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.

[0174] In this invention, the server includes means for collecting market information, means for generating investment decisions based on article information analyzed using natural language processing technology, means for automatically executing buy and sell orders via a trading system API, means for analyzing the user's biometric information and adjusting investment policies based on their emotional state, and means for adjusting the user's spending and savings strategies in real time. This enables investment decisions and asset management that comprehensively consider the user's emotional state and market trends.

[0175] "Market information" refers to all data in financial markets, including price fluctuations, trading volume, and trends.

[0176] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and specifically to methods for extracting information from text data.

[0177] "Article information" refers to published written information such as news articles and reports, and is data that should be analyzed for investment decisions.

[0178] "Investment decisions" refer to plans and decisions made to buy or sell assets based on market conditions and the user's risk tolerance.

[0179] A "trading system API" is an interface used for automated trading and refers to a protocol for communicating with external trading platforms.

[0180] "User biometric information" refers to data obtained by measuring the user's physical condition, such as heart rate and facial expressions.

[0181] "Emotional state" refers to the user's mental state, such as stress or relaxation.

[0182] "Investment policy" refers to the basic direction and strategy used when making investment decisions.

[0183] "Spending and savings strategies" refer to plans for how users spend and save their assets, aiming to improve their economic activity.

[0184] The system that realizes this invention consists of three main elements: a server, a terminal, and a user. The server first collects market information from financial markets. Specifically, this includes general market data such as price fluctuations and trading volume. The server then uses natural language processing technology to analyze the collected article information. Here, a generative AI model using Google's TensorFlow is used to generate investment decisions from various articles.

[0185] The generated investment decisions are automatically executed on the terminal via the trading system API. The terminal collects biometric information from the user, such as heart rate and facial expressions, and sends it to the server. At that time, the user's biometric information is analyzed by dedicated emotion recognition software, and the user's emotional state is estimated based on this. The server takes this emotional state into consideration and adjusts investment decisions and investment strategies accordingly.

[0186] The server also adjusts spending and savings strategies in real time to support users' economic activities. For example, if a user is feeling stressed, the server will suggest ways to reduce spending or increase savings. In this way, investment decisions and asset management are made by comprehensively considering each user's emotional state and market trends.

[0187] For example, if an increase in heart rate is detected when a user is about to purchase an expensive item, the server will notify the user to re-evaluate their spending. An example of a prompt message supporting this process is, "Please provide advice to help the user avoid overspending based on their recent spending history and current emotional state."

[0188] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0189] Step 1:

[0190] The server collects market information from financial markets. This input includes price fluctuations and trading volume, which are then stored in a database. Data processing involves normalization and time-series transformation, and conversion to a unified format.

[0191] Step 2:

[0192] The server retrieves article information and analyzes it using natural language processing techniques. The input is text data, and the output generates information for investment decisions. Data calculations include topic modeling and sentiment analysis.

[0193] Step 3:

[0194] The server uses a generative AI model to generate investment decisions from collected market and article information. The input data consists of market information and article analysis results, and the output is specific buy / sell instructions.

[0195] Step 4:

[0196] The device collects the user's biometric information, including heart rate and facial expression data, which is then analyzed by emotion recognition software. The input is sensor data, and the output is the analyzed emotional state.

[0197] Step 5:

[0198] The server integrates the received emotional state with the generated investment decisions to determine a refined investment policy. This process adjusts the risk profile based on the emotional state and determines specific investment actions.

[0199] Step 6:

[0200] The terminal executes automated trades based on investment policies adjusted via the trading system API. Using the API, the input is buy / sell instructions, and the output is the execution result.

[0201] Step 7:

[0202] The server reports all activity results to the user and presents performance status in real time. Visualized information is provided through a dashboard as output.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] [Second Embodiment]

[0207] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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".

[0219] This invention is an AI-driven system that enables individual investors to efficiently conduct investment activities in diverse financial markets. The system is server-centric, and users can manage their investment portfolios by accessing the system via terminals.

[0220] The server first collects market data. This includes stock, bond, and foreign exchange data, which is regularly gathered from financial data providers and news sources on the internet. The server analyzes this data using natural language processing technology to predict future market trends and make investment-related decisions.

[0221] For example, if the server detects news that "stock prices in a particular technology sector are expected to fall due to disruptions in global supply chains," the system can refer to similar past cases and recommend selling the stocks. The system can adjust this decision according to the user's risk tolerance, advising low-risk users to sell some stocks and suggesting high-risk users continue holding their stocks to weather short-term market volatility.

[0222] After an investment decision is made, the server executes automated trades via the trading platform API. This eliminates the need for users to constantly monitor market conditions, as the system automatically buys and sells at the optimal time. Furthermore, after each trade is executed, the server reports a performance summary to the terminal, supporting efficient investment management.

[0223] This system also allows for continuous model updates. By analyzing past investment results, the AI ​​model improves the accuracy of investment decisions and provides better predictions for future decisions. As a result, users can respond quickly and effectively to market changes and maximize investment returns without having to perform complex market analysis.

[0224] The following describes the processing flow.

[0225] Step 1:

[0226] The server accesses market data providers to collect real-time data such as stock prices, bond yields, and foreign exchange rates. The collected data is stored in a database and used for subsequent analysis.

[0227] Step 2:

[0228] The server retrieves the latest financial news from internet news sources. The retrieved news is analyzed using natural language processing technology, and its potential impact on the market is evaluated. For example, the server identifies important keywords in the text and scores their potential impact on the market based on historical data.

[0229] Step 3:

[0230] The server generates investment decisions based on the data it analyzes. This process considers a combination of news analysis results and market data to determine buy and sell actions. These decisions are adjusted according to the user's risk tolerance.

[0231] Step 4:

[0232] The server executes automated trades via the trading platform API. Trading orders are generated by the server and sent through the API. This automatically buys and sells the specified financial instruments.

[0233] Step 5:

[0234] The terminal receives information sent from the server and displays the latest investment performance to the user. The information can be visually viewed on the dashboard, allowing the user to understand the status of their portfolio.

[0235] Step 6:

[0236] The server analyzes past trading data and updates the AI ​​model. This improves the accuracy of future investment decisions. The model is continuously improved through this feedback loop.

[0237] (Example 1)

[0238] 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."

[0239] For individual investors to invest efficiently and effectively in diverse financial markets, they need to analyze vast amounts of market data and continuously make accurate investment decisions. However, performing these tasks manually is extremely labor-intensive and requires specialized knowledge and quick decision-making skills, making it difficult for individuals to handle. Therefore, there is a need to provide a system that automates everything from market data collection and analysis to investment decisions and execution, and that can adjust decisions according to the risk tolerance of individual investors.

[0240] 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.

[0241] In this invention, the server includes means for collecting information, means for generating decisions based on information data analyzed using language processing technology, and means for automatically executing operations via a communication interface based on the decisions. This makes it possible for individual investors to efficiently perform everything from collecting and analyzing market data to executing automated trading.

[0242] "Information" refers to data obtained from markets and other sources, as well as text data such as news articles.

[0243] "Means of collection" refers to the components responsible for the process of obtaining information from external data providers and news sources.

[0244] "Language processing technology" refers to the technology of applying natural language analysis to information data and extracting the necessary meaning.

[0245] "Means of generating judgments" refers to the process of deriving the next course of action or decision based on analyzed information data.

[0246] A "communication interface" refers to the interface through which a server exchanges information with external systems and services.

[0247] "Means of executing operations" refers to a mechanism that carries out specific actions, such as buying and selling, based on the generated judgment.

[0248] "Display means" refers to a function that shows the results of an operation or notifications from the system in a way that is recognizable to the user.

[0249] "Methods for updating a model" refers to the process of adjusting the algorithms and parameters of a generative model based on past results to improve prediction accuracy.

[0250] "Tolerance" refers to the range or level of risk that a user can accept, and it serves as a criterion for adjusting investment decisions.

[0251] This invention provides a system that allows individual investors to automatically manage their investments in accordance with market trends. The server first collects market information from data providers on the internet. This information is provided in JSON format, and the server periodically retrieves the data using HTTP requests. The retrieved information is then analyzed as text data using natural language processing techniques. In this process, Python libraries such as NLTK and Spacy are utilized to extract important keywords and context from the information.

[0252] Based on the analysis, the server utilizes a generated AI model to produce investment decisions. This AI model proposes individual investment strategies based on the user's risk tolerance, while comparing them with historical market data. For example, a prompt message such as "Considering this week's market trends, please propose an investment strategy related to Apple's new product announcement" is generated, and the AI ​​provides recommendations accordingly.

[0253] Based on this generated investment decision, the server directly executes automated trades via the trading platform's communication interface (e.g., API). Once the trade is complete, the result is notified to the user's terminal. Specifically, a message such as "Your purchase of 100 shares of Apple was successful" is displayed on the terminal.

[0254] Furthermore, by analyzing past trading results, the server updates its generative model, improving the accuracy of investment decisions. This enables users to make efficient and strategic investments without having to closely monitor the market.

[0255] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0256] Step 1:

[0257] The server collects market information from data providers on the internet. Specifically, it uses APIs to issue HTTP requests and retrieve data provided in JSON format. This data includes information on stocks, bonds, foreign exchange, etc. The input is the API endpoint, and the output is the raw data stored on the server.

[0258] Step 2:

[0259] The server analyzes the collected market information using natural language processing techniques. Specifically, it uses Python's NLTK and Spacy libraries to extract important keywords and context from news articles and market information. The input is market data in JSON format, and the output is text data of the analyzed information.

[0260] Step 3:

[0261] The server utilizes a generated AI model based on the analyzed information to generate investment decisions. In this process, it references the user's risk tolerance and historical market data to create a highly probable investment strategy. The generated prompt statements are used to query the AI ​​model. The input is the analyzed data and the user's risk tolerance, and the output is a specific investment strategy.

[0262] Step 4:

[0263] The server automatically executes trades via the trading platform's API based on the generated investment decisions. Specifically, it sends appropriate buy and sell instructions to the platform API and checks the results. The input is the investment strategy, and the output is the success or failure of the trade.

[0264] Step 5:

[0265] The server notifies the user's terminal of the trading results. For example, it might send a message to the terminal saying, "Your purchase of 100 shares of Apple was successful," allowing the user to check the transaction status. The input is the trading result, and the output is the notification information sent to the user.

[0266] Step 6:

[0267] The server analyzes past trading results and updates the generated AI model. Specifically, it retrains the model using historical investment performance data to prepare for improved accuracy in future decisions. The input is historical trading data, and the output is the updated AI model.

[0268] (Application Example 1)

[0269] 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."

[0270] Individual investors need to analyze vast amounts of market and news information daily to make quick and accurate financial decisions, but this is a very time-consuming and specialized task, and many investors find this process difficult. Furthermore, security and efficiency are required in the settlement of asset buying and selling transactions, but current manual processes struggle to meet these requirements. The present invention aims to solve these problems and enable more investors to engage in efficient and safe investment activities.

[0271] 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.

[0272] In this invention, the server includes means for collecting market information, means for generating financial decisions based on news information analyzed using natural language processing technology, and means for automatically executing asset trades via an information exchange platform API. This enables investors to make optimal investment decisions and asset trades efficiently and safely without having to manually analyze market information.

[0273] "Market information" refers to all data related to financial markets, such as stocks, bonds, and foreign exchange.

[0274] "Natural language processing technology" is a technique for analyzing text data into a format that computers can understand and grasping its meaning.

[0275] "News information" refers to market and economic information contained in news articles and other materials that may influence investment decisions.

[0276] "Financial decision-making" refers to the act of deciding whether to buy, sell, or hold assets in the course of investment activities, as well as the results thereof.

[0277] An "information exchange platform API" is an application programming interface for direct communication with a platform used for asset trading.

[0278] "Asset trading" refers to the act of selling or buying stocks or other financial products.

[0279] "Approval" refers to the payment processing involved in the completion of a transaction and the transfer of assets.

[0280] "Financial optimization" is the process of optimizing the allocation of financial assets according to an individual's investment objectives and risk tolerance.

[0281] The "user profile" refers to individual information including records related to personal investments, risk tolerance, financial objectives, etc.

[0282] To implement this invention, a platform centered around an AI-driven automated trading system is constructed. The server first periodically collects market information. Specifically, it obtains data such as stocks, bonds, and foreign exchange from data providers on the Internet and stores it in a database.

[0283] The server then analyzes the collected news information using Python and a natural language analysis library. Through natural language analysis technology, information that may affect investment decisions is extracted from news and articles, and an AI model is utilized to make financial decisions. TensorFlow is used for the training of the AI model, and Scikit-learn is used in combination for data analysis.

[0284] Through the information exchange platform API, the server automatically conducts asset trading. In this process, it can cooperate with electronic payment services such as Stripe to approve each transaction safely and quickly. Furthermore, the server notifies the user of the results after the transaction and provides this information through a mobile app or a desktop client.

[0285] On the user terminal, information is received through an application built with React Native, and financial optimization is performed based on the user profile. As a specific example, an alert such as "The emerging market is booming, and it is recommended to purchase related stocks" is sent to the user terminal as a result of certain AI analysis. Based on the user's decision, the purchase process automatically proceeds on the server side.

[0286] As an example of a prompt sentence, an instruction such as "Based on the new market data, predict which assets the AI model recommends for purchase." is given to the AI model, and an analysis of market trends is conducted.

[0287] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0288] Step 1:

[0289] The server periodically collects market information such as stocks, bonds, and foreign exchange from market data providers and stores it in a database. The input is real-time market information from external data sources, and the output is structured database entries. This data is used for subsequent analysis.

[0290] Step 2:

[0291] The server analyzes news information using natural language processing technology. News information is provided as input, and a generative AI model extracts information from the document that influences investment decisions. The output is elemental information identified by the server for making investment decisions. This makes it possible to understand news trends and their impact on the market.

[0292] Step 3:

[0293] The server uses an AI model to make financial decisions based on the analysis data from the previous step. The input is the result of natural language processing, which the predictive model uses to forecast fluctuations in the financial market. The output is a proposal for specific investment actions. TensorFlow is used throughout this process, and the model is continuously trained to improve prediction accuracy.

[0294] Step 4:

[0295] Through an information exchange platform API, the server automatically executes buy and sell transactions for recommended assets. The input is investment recommendations from an AI model, and the output is buy and sell orders sent to the trading platform. This enables instant trading without human intervention.

[0296] Step 5:

[0297] The system notifies the user terminal of the transaction results. Input is a notification of the transaction's success or failure, and output is a user-facing report containing detailed information. It informs users of market trends in real time, helping them to take the next action.

[0298] Step 6:

[0299] The server analyzes transaction history and uses this data to update the generated AI model. The input is past transaction data and results, and the output is an improved predictive model. This process acts as a feedback loop to improve the accuracy of the user's investment decisions.

[0300] 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.

[0301] This invention provides a system that recognizes user emotions and reflects them in investment decisions, thereby offering more personalized investment support. The system comprises a server, terminals, and an emotion engine.

[0302] First, the server collects market data and relevant news, and performs data analysis using natural language processing technology. During this process, generative AI is used to generate investment decisions to predict market trends. These generated investment decisions are then adjusted based on the user's risk tolerance.

[0303] Next, the emotion engine works to recognize the user's emotions through the user's device. This analyzes the current emotional state using biometric information (e.g., heart rate, facial expressions, etc.) and information entered by the user. For example, if the emotion engine detects that the user is feeling stressed, it will adjust investment decisions conservatively. This emotion-based adjustment allows the user to invest safely while reducing psychological burden.

[0304] The server also has the function of conducting automated trading via the trading platform API and reporting the trading results to the user. The terminal is equipped with a dashboard that displays performance data to the user in real time, allowing the user to check how their investment situation and emotions affect their investment decisions.

[0305] Furthermore, the server analyzes past investment results and emotion data to update the model. This improves the accuracy in the next investment decision and enables the provision of more user - suitable investment advice. By utilizing emotion data in this way, it becomes possible to provide advanced investment support that takes into account the user's emotional state, rather than just being data - driven.

[0306] The following describes the process flow.

[0307] Step 1:

[0308] The server obtains real - time financial data from the market data provider. This includes stock prices, bond yields, foreign exchange rates, etc., and the acquired data is stored in the database. Also, the server collects the latest news related to the market via the news API.

[0309] Step 2:

[0310] The server analyzes the news data it has collected using natural language processing technology. The generative AI analyzes the news articles, evaluates the potential impact on the market, calculates specific indicators, and makes investment decisions. Based on this evaluation, specific actions such as buying or selling are determined.

[0311] Step 3:

[0312] The terminal analyzes the user's emotional state through the emotion engine. It obtains the user's biometric information using sensors etc. to identify the current emotional state (e.g., relaxed, stressed). It is also possible for the user to directly input their emotions.

[0313] Step 4:

[0314] The server adjusts investment decisions based on emotional information obtained from the emotion engine. For example, if a user is experiencing stress, the investment portfolio is readjusted to reduce risk. This adjustment is then compiled into the final investment decision.

[0315] Step 5:

[0316] The server executes automated trades via the trading platform API. The system sends determined buy and sell instructions to the trading platform, and the sale or purchase of selected financial instruments is executed.

[0317] Step 6:

[0318] The terminal receives information from the server and displays the latest investment status and trading results to the user on a dashboard. Through this information, the user can check the performance of their portfolio and the impact of their emotions.

[0319] Step 7:

[0320] The server analyzes past investment performance and sentiment data to update the AI ​​model. This makes future investment decisions more accurate. The analysis results are shared within the system as feedback and presented to the user as improvement suggestions.

[0321] (Example 2)

[0322] 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".

[0323] Conventional investment support systems make investment decisions based on market trends, but they do not take into account the user's emotions or psychological state, making it difficult to provide investment strategies optimized for individual users. Furthermore, there were challenges in improving the accuracy of automated investment decisions and establishing a user-friendly interface.

[0324] 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.

[0325] In this invention, the server includes a device for collecting market information, a device for generating investment decisions based on information data analyzed using natural language processing technology, and a device for automatically executing trades via a management system API. This enables individually optimized investment support by recognizing the user's emotional state and providing investment decisions adjusted accordingly.

[0326] "Market information" refers to data and information related to financial markets, including, for example, stock prices, exchange rates, economic indicators, and news articles.

[0327] "Analyzed information data" refers to data such as news and market information that has been analyzed using natural language processing technology, and is a fundamental element for investment decisions.

[0328] A "management system API" is an application programming interface that enables automated trading and data access, and is a means of communicating with external systems and software.

[0329] A "display device" is a device or interface that provides information to a user visually, and typically includes computer monitors and smartphone screens.

[0330] A "generative model" is a data processing algorithm that learns from past data and information to make future investment decisions, and typically uses machine learning techniques.

[0331] "User emotional state" refers to the actual emotional state analyzed from biometric information such as heart rate and facial expressions, and is used to fine-tune investment decisions.

[0332] "Investment decisions" are judgments and policies that guide the timing and strategies for buying and selling assets, generated based on market information and the emotional state of the user.

[0333] This invention provides a system that offers individually optimized investment support that takes into account the user's emotional data. This system mainly consists of a server, terminals, and an emotional engine.

[0334] First, the server collects market information and stores it in a database. Market information is obtained from financial market news and various economic data through web scraping techniques and publicly available APIs. Specific data sources typically include financial news websites and economic data provision services.

[0335] Next, the server analyzes the collected information using natural language processing techniques. This analysis utilizes generative AI models, such as sentiment analysis of news articles and prediction of market trends. For this purpose, generative AI models like BERT and the GPT series are used. An example of a prompt might be, "Predict important trends from today's market news."

[0336] The server generates investment decisions based on these analysis results and automatically executes trades via the management system API. These trades are automated and can buy and sell stocks and other financial instruments based on specific conditions.

[0337] Meanwhile, the device collects the user's biometric information and transmits it to the emotion engine. The device acquires biometric information such as heart rate from the wearable device and also analyzes facial expressions through the camera. This analysis estimates the user's emotional state in real time.

[0338] The emotion engine uses this emotional data to adjust investment decisions generated on the server according to the user's risk tolerance. For example, if a user is experiencing high levels of stress, the system will adjust to select a more conservative investment strategy.

[0339] Finally, the server sends the updated investment decision results to the terminal and displays them to the user. This allows the user to visualize how their emotional state is influencing their investment decisions.

[0340] By integrating the entire system in this way, it becomes possible to provide sophisticated investment support that utilizes sentiment data, not just decisions based on market data.

[0341] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0342] Step 1:

[0343] The server collects market information. Input is raw market data obtained through web scraping techniques and APIs, while output is organized market information stored in a database. The server performs this regularly, covering financial news and economic indicators.

[0344] Step 2:

[0345] The server performs natural language processing based on the collected market information. The input is the market information obtained in step 1, and the output is the analyzed data. Specifically, a generative AI model is used, with the prompt "Perform market trend and sentiment analysis" as input, and trends are extracted from the data.

[0346] Step 3:

[0347] The server generates investment decisions using naturally language processed data. The input is the analyzed data obtained in step 2, and the output is a specific investment strategy indicator. The generated investment decisions provide concrete examples, such as "you should focus on buying technology stocks in the next week." This clarifies the guidance for automated trading systems.

[0348] Step 4:

[0349] The device collects biometric information to measure the user's emotional state. Input is biometric information obtained from wearable devices or cameras (e.g., heart rate, facial expression data), and output is analyzed emotional data sent to an emotion engine. By tracking the user's emotional state in real time, the system aims to identify potential influences on investment decisions.

[0350] Step 5:

[0351] The emotion engine adjusts investment decisions based on the user's emotional data. The input is the emotional data obtained in step 4 and the investment decision in step 3, and the output is the adjusted investment strategy. For example, it might make a decision such as, "The user is currently feeling stressed, so adopt a conservative strategy."

[0352] Step 6:

[0353] The server executes the adjusted investment strategy and reports the results to the terminal in real time. The input is the adjusted investment strategy generated in step 5, and the output is the result of the trades executed based on that strategy. The user can view this from the terminal and evaluate their investment performance in real time.

[0354] (Application Example 2)

[0355] 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."

[0356] In recent years, individual investors have been required to make investment decisions based on diverse market information and trends. However, general automated trading systems cannot adequately consider the emotions and subjective risk tolerance of individual investors. As a result, this can lead to psychological burden and unnecessary depletion of assets due to taking excessive risks. Therefore, there is a need for a system that can make investment decisions based on the emotional state and risk tolerance of individual investors, thereby optimizing asset management while reducing mental stress.

[0357] 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.

[0358] In this invention, the server includes means for collecting market information, means for generating investment decisions based on article information analyzed using natural language processing technology, means for automatically executing buy and sell orders via a trading system API, means for analyzing the user's biometric information and adjusting investment policies based on their emotional state, and means for adjusting the user's spending and savings strategies in real time. This enables investment decisions and asset management that comprehensively consider the user's emotional state and market trends.

[0359] "Market information" refers to all data in financial markets, including price fluctuations, trading volume, and trends.

[0360] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and specifically to methods for extracting information from text data.

[0361] "Article information" refers to published written information such as news articles and reports, and is data that should be analyzed for investment decisions.

[0362] "Investment decisions" refer to plans and decisions made to buy or sell assets based on market conditions and the user's risk tolerance.

[0363] A "trading system API" is an interface used for automated trading and refers to a protocol for communicating with external trading platforms.

[0364] "User biometric information" refers to data obtained by measuring the user's physical condition, such as heart rate and facial expressions.

[0365] "Emotional state" refers to the user's mental state, such as stress or relaxation.

[0366] "Investment policy" refers to the basic direction and strategy used when making investment decisions.

[0367] "Spending and savings strategies" refer to plans for how users spend and save their assets, aiming to improve their economic activity.

[0368] The system that realizes this invention consists of three main elements: a server, a terminal, and a user. The server first collects market information from financial markets. Specifically, this includes general market data such as price fluctuations and trading volume. The server then uses natural language processing technology to analyze the collected article information. Here, a generative AI model using Google's TensorFlow is used to generate investment decisions from various articles.

[0369] The generated investment decisions are automatically executed on the terminal via the trading system API. The terminal collects biometric information from the user, such as heart rate and facial expressions, and sends it to the server. At that time, the user's biometric information is analyzed by dedicated emotion recognition software, and the user's emotional state is estimated based on this. The server takes this emotional state into consideration and adjusts investment decisions and investment strategies accordingly.

[0370] The server also adjusts spending and savings strategies in real time to support users' economic activities. For example, if a user is feeling stressed, the server will suggest ways to reduce spending or increase savings. In this way, investment decisions and asset management are made by comprehensively considering each user's emotional state and market trends.

[0371] For example, if an increase in heart rate is detected when a user is about to purchase an expensive item, the server will notify the user to re-evaluate their spending. An example of a prompt message supporting this process is, "Please provide advice to help the user avoid overspending based on their recent spending history and current emotional state."

[0372] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0373] Step 1:

[0374] The server collects market information from financial markets. This input includes price fluctuations and trading volume, which are then stored in a database. Data processing involves normalization and time-series transformation, and conversion to a unified format.

[0375] Step 2:

[0376] The server retrieves article information and analyzes it using natural language processing techniques. The input is text data, and the output generates information for investment decisions. Data calculations include topic modeling and sentiment analysis.

[0377] Step 3:

[0378] The server uses a generative AI model to generate investment decisions from collected market and article information. The input data consists of market information and article analysis results, and the output is specific buy / sell instructions.

[0379] Step 4:

[0380] The device collects the user's biometric information, including heart rate and facial expression data, which is then analyzed by emotion recognition software. The input is sensor data, and the output is the analyzed emotional state.

[0381] Step 5:

[0382] The server integrates the received emotional state with the generated investment decisions to determine a refined investment policy. This process adjusts the risk profile based on the emotional state and determines specific investment actions.

[0383] Step 6:

[0384] The terminal executes automated trades based on investment policies adjusted via the trading system API. Using the API, the input is buy / sell instructions, and the output is the execution result.

[0385] Step 7:

[0386] The server reports all activity results to the user and presents performance status in real time. Visualized information is provided through a dashboard as output.

[0387] 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.

[0388] 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.

[0389] 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.

[0390] [Third Embodiment]

[0391] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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".

[0403] This invention is an AI-driven system that enables individual investors to efficiently conduct investment activities in diverse financial markets. The system is server-centric, and users can manage their investment portfolios by accessing the system via terminals.

[0404] The server first collects market data. This includes stock, bond, and foreign exchange data, which is regularly gathered from financial data providers and news sources on the internet. The server analyzes this data using natural language processing technology to predict future market trends and make investment-related decisions.

[0405] For example, if the server detects news that "stock prices in a particular technology sector are expected to fall due to disruptions in global supply chains," the system can refer to similar past cases and recommend selling the stocks. The system can adjust this decision according to the user's risk tolerance, advising low-risk users to sell some stocks and suggesting high-risk users continue holding their stocks to weather short-term market volatility.

[0406] After an investment decision is made, the server executes automated trades via the trading platform API. This eliminates the need for users to constantly monitor market conditions, as the system automatically buys and sells at the optimal time. Furthermore, after each trade is executed, the server reports a performance summary to the terminal, supporting efficient investment management.

[0407] This system also allows for continuous model updates. By analyzing past investment results, the AI ​​model improves the accuracy of investment decisions and provides better predictions for future decisions. As a result, users can respond quickly and effectively to market changes and maximize investment returns without having to perform complex market analysis.

[0408] The following describes the processing flow.

[0409] Step 1:

[0410] The server accesses market data providers to collect real-time data such as stock prices, bond yields, and foreign exchange rates. The collected data is stored in a database and used for subsequent analysis.

[0411] Step 2:

[0412] The server retrieves the latest financial news from internet news sources. The retrieved news is analyzed using natural language processing technology, and its potential impact on the market is evaluated. For example, the server identifies important keywords in the text and scores their potential impact on the market based on historical data.

[0413] Step 3:

[0414] The server generates investment decisions based on the data it analyzes. This process considers a combination of news analysis results and market data to determine buy and sell actions. These decisions are adjusted according to the user's risk tolerance.

[0415] Step 4:

[0416] The server executes automated trades via the trading platform API. Trading orders are generated by the server and sent through the API. This automatically buys and sells the specified financial instruments.

[0417] Step 5:

[0418] The terminal receives information sent from the server and displays the latest investment performance to the user. The information can be visually viewed on the dashboard, allowing the user to understand the status of their portfolio.

[0419] Step 6:

[0420] The server analyzes past trading data and updates the AI ​​model. This improves the accuracy of future investment decisions. The model is continuously improved through this feedback loop.

[0421] (Example 1)

[0422] 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."

[0423] For individual investors to invest efficiently and effectively in diverse financial markets, they need to analyze vast amounts of market data and continuously make accurate investment decisions. However, performing these tasks manually is extremely labor-intensive and requires specialized knowledge and quick decision-making skills, making it difficult for individuals to handle. Therefore, there is a need to provide a system that automates everything from market data collection and analysis to investment decisions and execution, and that can adjust decisions according to the risk tolerance of individual investors.

[0424] 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.

[0425] In this invention, the server includes means for collecting information, means for generating decisions based on information data analyzed using language processing technology, and means for automatically executing operations via a communication interface based on the decisions. This makes it possible for individual investors to efficiently perform everything from collecting and analyzing market data to executing automated trading.

[0426] "Information" refers to data obtained from markets and other sources, as well as text data such as news articles.

[0427] "Means of collection" refers to the components responsible for the process of obtaining information from external data providers and news sources.

[0428] "Language processing technology" refers to the technology of applying natural language analysis to information data and extracting the necessary meaning.

[0429] "Means of generating judgments" refers to the process of deriving the next course of action or decision based on analyzed information data.

[0430] A "communication interface" refers to the interface through which a server exchanges information with external systems and services.

[0431] "Means of executing operations" refers to a mechanism that carries out specific actions, such as buying and selling, based on the generated judgment.

[0432] "Display means" refers to a function that shows the results of an operation or notifications from the system in a way that is recognizable to the user.

[0433] "Methods for updating a model" refers to the process of adjusting the algorithms and parameters of a generative model based on past results to improve prediction accuracy.

[0434] "Tolerance" refers to the range or level of risk that a user can accept, and it serves as a criterion for adjusting investment decisions.

[0435] This invention provides a system that allows individual investors to automatically manage their investments in accordance with market trends. The server first collects market information from data providers on the internet. This information is provided in JSON format, and the server periodically retrieves the data using HTTP requests. The retrieved information is then analyzed as text data using natural language processing techniques. In this process, Python libraries such as NLTK and Spacy are utilized to extract important keywords and context from the information.

[0436] Based on the analysis, the server utilizes a generated AI model to produce investment decisions. This AI model proposes individual investment strategies based on the user's risk tolerance, while comparing them with historical market data. For example, a prompt message such as "Considering this week's market trends, please propose an investment strategy related to Apple's new product announcement" is generated, and the AI ​​provides recommendations accordingly.

[0437] Based on this generated investment decision, the server directly executes automated trades via the trading platform's communication interface (e.g., API). Once the trade is complete, the result is notified to the user's terminal. Specifically, a message such as "Your purchase of 100 shares of Apple was successful" is displayed on the terminal.

[0438] Furthermore, by analyzing past trading results, the server updates its generative model, improving the accuracy of investment decisions. This enables users to make efficient and strategic investments without having to closely monitor the market.

[0439] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0440] Step 1:

[0441] The server collects market information from data providers on the internet. Specifically, it uses APIs to issue HTTP requests and retrieve data provided in JSON format. This data includes information on stocks, bonds, foreign exchange, etc. The input is the API endpoint, and the output is the raw data stored on the server.

[0442] Step 2:

[0443] The server analyzes the collected market information using natural language processing techniques. Specifically, it uses Python's NLTK and Spacy libraries to extract important keywords and context from news articles and market information. The input is market data in JSON format, and the output is text data of the analyzed information.

[0444] Step 3:

[0445] The server utilizes a generated AI model based on the analyzed information to generate investment decisions. In this process, it references the user's risk tolerance and historical market data to create a highly probable investment strategy. The generated prompt statements are used to query the AI ​​model. The input is the analyzed data and the user's risk tolerance, and the output is a specific investment strategy.

[0446] Step 4:

[0447] The server automatically executes trades via the trading platform's API based on the generated investment decisions. Specifically, it sends appropriate buy and sell instructions to the platform API and checks the results. The input is the investment strategy, and the output is the success or failure of the trade.

[0448] Step 5:

[0449] The server notifies the user's terminal of the trading results. For example, it might send a message to the terminal saying, "Your purchase of 100 shares of Apple was successful," allowing the user to check the transaction status. The input is the trading result, and the output is the notification information sent to the user.

[0450] Step 6:

[0451] The server analyzes past trading results and updates the generated AI model. Specifically, it retrains the model using historical investment performance data to prepare for improved accuracy in future decisions. The input is historical trading data, and the output is the updated AI model.

[0452] (Application Example 1)

[0453] 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."

[0454] Individual investors need to analyze vast amounts of market and news information daily to make quick and accurate financial decisions, but this is a very time-consuming and specialized task, and many investors find this process difficult. Furthermore, security and efficiency are required in the settlement of asset buying and selling transactions, but current manual processes struggle to meet these requirements. The present invention aims to solve these problems and enable more investors to engage in efficient and safe investment activities.

[0455] 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.

[0456] In this invention, the server includes means for collecting market information, means for generating financial decisions based on news information analyzed using natural language processing technology, and means for automatically executing asset trades via an information exchange platform API. This enables investors to make optimal investment decisions and asset trades efficiently and safely without having to manually analyze market information.

[0457] "Market information" refers to all data related to financial markets, such as stocks, bonds, and foreign exchange.

[0458] "Natural language processing technology" is a technique for analyzing text data into a format that computers can understand and grasping its meaning.

[0459] "News information" refers to market and economic information contained in news articles and other materials that may influence investment decisions.

[0460] "Financial decision-making" refers to the act of deciding whether to buy, sell, or hold assets in the course of investment activities, as well as the results thereof.

[0461] An "information exchange platform API" is an application programming interface for direct communication with a platform used for asset trading.

[0462] "Asset trading" refers to the act of selling or buying stocks or other financial products.

[0463] "Approval" refers to the payment processing involved in the completion of a transaction and the transfer of assets.

[0464] "Financial optimization" is the process of optimizing the allocation of financial assets according to an individual's investment objectives and risk tolerance.

[0465] A "user profile" refers to individual information, including records of an person's investments, risk tolerance, and financial objectives.

[0466] To implement this invention, a platform centered around an AI-driven automated trading system will be constructed. The server will first periodically collect market information. Specifically, it will obtain data on stocks, bonds, foreign exchange, etc., from internet data providers and store it in a database.

[0467] The server then analyzes the collected news information using Python and natural language processing libraries. Using natural language processing techniques, it extracts information from news and articles that could potentially influence investment decisions, and then leverages a generative AI model to make financial decisions. TensorFlow is used to train the AI ​​model, and Scikit-learn is used in conjunction with it for data analysis.

[0468] Through an information exchange platform API, the server automatically executes asset trades. This process integrates with electronic payment services such as Stripe, enabling secure and rapid settlement of each transaction. Furthermore, the server notifies users of the transaction results and provides this information through mobile apps and desktop clients.

[0469] On the user's device, information is received through an application built with React Native, and financial optimization is performed based on the user profile. For example, as a result of an AI analysis, an alert such as "Emerging markets are performing well, and we recommend purchasing related stocks" is sent to the user's device, and based on the user's decision, the purchase process is automatically carried out on the server side.

[0470] An example of a prompt message is to give the AI ​​model an instruction such as, "Based on new market data, have the AI ​​model predict which assets to recommend purchasing," and the AI ​​model will then analyze market trends.

[0471] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0472] Step 1:

[0473] The server periodically collects market information such as stocks, bonds, and foreign exchange from market data providers and stores it in a database. The input is real-time market information from external data sources, and the output is structured database entries. This data is used for subsequent analysis.

[0474] Step 2:

[0475] The server analyzes news information using natural language processing technology. News information is provided as input, and a generative AI model extracts information from the document that influences investment decisions. The output is elemental information identified by the server for making investment decisions. This makes it possible to understand news trends and their impact on the market.

[0476] Step 3:

[0477] The server uses an AI model to make financial decisions based on the analysis data from the previous step. The input is the result of natural language processing, which the predictive model uses to forecast fluctuations in the financial market. The output is a proposal for specific investment actions. TensorFlow is used throughout this process, and the model is continuously trained to improve prediction accuracy.

[0478] Step 4:

[0479] Through an information exchange platform API, the server automatically executes buy and sell transactions for recommended assets. The input is investment recommendations from an AI model, and the output is buy and sell orders sent to the trading platform. This enables instant trading without human intervention.

[0480] Step 5:

[0481] The system notifies the user terminal of the transaction results. Input is a notification of the transaction's success or failure, and output is a user-facing report containing detailed information. It informs users of market trends in real time, helping them to take the next action.

[0482] Step 6:

[0483] The server analyzes transaction history and uses this data to update the generated AI model. The input is past transaction data and results, and the output is an improved predictive model. This process acts as a feedback loop to improve the accuracy of the user's investment decisions.

[0484] 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.

[0485] This invention provides a system that recognizes user emotions and reflects them in investment decisions, thereby offering more personalized investment support. The system comprises a server, terminals, and an emotion engine.

[0486] First, the server collects market data and relevant news, and performs data analysis using natural language processing technology. During this process, generative AI is used to generate investment decisions to predict market trends. These generated investment decisions are then adjusted based on the user's risk tolerance.

[0487] Next, the emotion engine works to recognize the user's emotions through the user's device. This analyzes the current emotional state using biometric information (e.g., heart rate, facial expressions, etc.) and information entered by the user. For example, if the emotion engine detects that the user is feeling stressed, it will adjust investment decisions conservatively. This emotion-based adjustment allows the user to invest safely while reducing psychological burden.

[0488] The server also has the ability to execute automated trades via the trading platform API and report the trading results to the user. The terminal is equipped with a dashboard that displays performance data to the user in real time, allowing the user to see how their investment status and emotions are influencing their investment decisions.

[0489] Furthermore, the server analyzes past investment results and sentiment data to update the model. This improves the accuracy of future investment decisions and allows for the provision of more user-friendly investment advice. By utilizing sentiment data in this way, it becomes possible to provide sophisticated investment support that is not merely data-driven, but also takes into account the user's emotional state.

[0490] The following describes the processing flow.

[0491] Step 1:

[0492] The server retrieves real-time financial data from market data providers. This includes stock prices, bond yields, and foreign exchange rates, and the retrieved data is stored in a database. The server also collects the latest market-related news via a news API.

[0493] Step 2:

[0494] The server analyzes collected news data using natural language processing technology. A generating AI analyzes news articles, assesses their potential impact on the market, and calculates specific indicators to make investment decisions. Based on this assessment, it determines specific buy or sell actions.

[0495] Step 3:

[0496] The device analyzes the user's emotional state through an emotion engine. It acquires the user's biometric information using sensors and other means to identify their current emotional state (e.g., relaxed, stressed). Users can also directly input their emotions.

[0497] Step 4:

[0498] The server adjusts investment decisions based on emotional information obtained from the emotion engine. For example, if a user is experiencing stress, the investment portfolio is readjusted to reduce risk. This adjustment is then compiled into the final investment decision.

[0499] Step 5:

[0500] The server executes automated trades via the trading platform API. The system sends determined buy and sell instructions to the trading platform, and the sale or purchase of selected financial instruments is executed.

[0501] Step 6:

[0502] The terminal receives information from the server and displays the latest investment status and trading results to the user on a dashboard. Through this information, the user can check the performance of their portfolio and the impact of their emotions.

[0503] Step 7:

[0504] The server analyzes past investment performance and sentiment data to update the AI ​​model. This makes future investment decisions more accurate. The analysis results are shared within the system as feedback and presented to the user as improvement suggestions.

[0505] (Example 2)

[0506] 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."

[0507] Conventional investment support systems make investment decisions based on market trends, but they do not take into account the user's emotions or psychological state, making it difficult to provide investment strategies optimized for individual users. Furthermore, there were challenges in improving the accuracy of automated investment decisions and establishing a user-friendly interface.

[0508] 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.

[0509] In this invention, the server includes a device for collecting market information, a device for generating investment decisions based on information data analyzed using natural language processing technology, and a device for automatically executing trades via a management system API. This enables individually optimized investment support by recognizing the user's emotional state and providing investment decisions adjusted accordingly.

[0510] "Market information" refers to data and information related to financial markets, including, for example, stock prices, exchange rates, economic indicators, and news articles.

[0511] "Analyzed information data" refers to data such as news and market information that has been analyzed using natural language processing technology, and is a fundamental element for investment decisions.

[0512] A "management system API" is an application programming interface that enables automated trading and data access, and is a means of communicating with external systems and software.

[0513] A "display device" is a device or interface that provides information to a user visually, and typically includes computer monitors and smartphone screens.

[0514] A "generative model" is a data processing algorithm that learns from past data and information to make future investment decisions, and typically uses machine learning techniques.

[0515] "User emotional state" refers to the actual emotional state analyzed from biometric information such as heart rate and facial expressions, and is used to fine-tune investment decisions.

[0516] "Investment decisions" are judgments and policies that guide the timing and strategies for buying and selling assets, generated based on market information and the emotional state of the user.

[0517] This invention provides a system that offers individually optimized investment support that takes into account the user's emotional data. This system mainly consists of a server, terminals, and an emotional engine.

[0518] First, the server collects market information and stores it in a database. Market information is obtained from financial market news and various economic data through web scraping techniques and publicly available APIs. Specific data sources typically include financial news websites and economic data provision services.

[0519] Next, the server analyzes the collected information using natural language processing techniques. This analysis utilizes generative AI models, such as sentiment analysis of news articles and prediction of market trends. For this purpose, generative AI models like BERT and the GPT series are used. An example of a prompt might be, "Predict important trends from today's market news."

[0520] The server generates investment decisions based on these analysis results and automatically executes trades via the management system API. These trades are automated and can buy and sell stocks and other financial instruments based on specific conditions.

[0521] Meanwhile, the device collects the user's biometric information and transmits it to the emotion engine. The device acquires biometric information such as heart rate from the wearable device and also analyzes facial expressions through the camera. This analysis estimates the user's emotional state in real time.

[0522] The emotion engine uses this emotional data to adjust investment decisions generated on the server according to the user's risk tolerance. For example, if a user is experiencing high levels of stress, the system will adjust to select a more conservative investment strategy.

[0523] Finally, the server sends the updated investment decision results to the terminal and displays them to the user. This allows the user to visualize how their emotional state is influencing their investment decisions.

[0524] By integrating the entire system in this way, it becomes possible to provide sophisticated investment support that utilizes sentiment data, not just decisions based on market data.

[0525] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0526] Step 1:

[0527] The server collects market information. Input is raw market data obtained through web scraping techniques and APIs, while output is organized market information stored in a database. The server performs this regularly, covering financial news and economic indicators.

[0528] Step 2:

[0529] The server performs natural language processing based on the collected market information. The input is the market information obtained in step 1, and the output is the analyzed data. Specifically, a generative AI model is used, with the prompt "Perform market trend and sentiment analysis" as input, and trends are extracted from the data.

[0530] Step 3:

[0531] The server generates investment decisions using naturally language processed data. The input is the analyzed data obtained in step 2, and the output is a specific investment strategy indicator. The generated investment decisions provide concrete examples, such as "you should focus on buying technology stocks in the next week." This clarifies the guidance for automated trading systems.

[0532] Step 4:

[0533] The device collects biometric information to measure the user's emotional state. Input is biometric information obtained from wearable devices or cameras (e.g., heart rate, facial expression data), and output is analyzed emotional data sent to an emotion engine. By tracking the user's emotional state in real time, the system aims to identify potential influences on investment decisions.

[0534] Step 5:

[0535] The emotion engine adjusts investment decisions based on the user's emotional data. The input is the emotional data obtained in step 4 and the investment decision in step 3, and the output is the adjusted investment strategy. For example, it might make a decision such as, "The user is currently feeling stressed, so adopt a conservative strategy."

[0536] Step 6:

[0537] The server executes the adjusted investment strategy and reports the results to the terminal in real time. The input is the adjusted investment strategy generated in step 5, and the output is the result of the trades executed based on that strategy. The user can view this from the terminal and evaluate their investment performance in real time.

[0538] (Application Example 2)

[0539] 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."

[0540] In recent years, individual investors have been required to make investment decisions based on diverse market information and trends. However, general automated trading systems cannot adequately consider the emotions and subjective risk tolerance of individual investors. As a result, this can lead to psychological burden and unnecessary depletion of assets due to taking excessive risks. Therefore, there is a need for a system that can make investment decisions based on the emotional state and risk tolerance of individual investors, thereby optimizing asset management while reducing mental stress.

[0541] 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.

[0542] In this invention, the server includes means for collecting market information, means for generating investment decisions based on article information analyzed using natural language processing technology, means for automatically executing buy and sell orders via a trading system API, means for analyzing the user's biometric information and adjusting investment policies based on their emotional state, and means for adjusting the user's spending and savings strategies in real time. This enables investment decisions and asset management that comprehensively consider the user's emotional state and market trends.

[0543] "Market information" refers to all data in financial markets, including price fluctuations, trading volume, and trends.

[0544] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and specifically to methods for extracting information from text data.

[0545] "Article information" refers to published written information such as news articles and reports, and is data that should be analyzed for investment decisions.

[0546] "Investment decisions" refer to plans and decisions made to buy or sell assets based on market conditions and the user's risk tolerance.

[0547] A "trading system API" is an interface used for automated trading and refers to a protocol for communicating with external trading platforms.

[0548] "User biometric information" refers to data obtained by measuring the user's physical condition, such as heart rate and facial expressions.

[0549] "Emotional state" refers to the user's mental state, such as stress or relaxation.

[0550] "Investment policy" refers to the basic direction and strategy used when making investment decisions.

[0551] "Spending and savings strategies" refer to plans for how users spend and save their assets, aiming to improve their economic activity.

[0552] The system that realizes this invention consists of three main elements: a server, a terminal, and a user. The server first collects market information from financial markets. Specifically, this includes general market data such as price fluctuations and trading volume. The server then uses natural language processing technology to analyze the collected article information. Here, a generative AI model using Google's TensorFlow is used to generate investment decisions from various articles.

[0553] The generated investment decisions are automatically executed on the terminal via the trading system API. The terminal collects biometric information from the user, such as heart rate and facial expressions, and sends it to the server. At that time, the user's biometric information is analyzed by dedicated emotion recognition software, and the user's emotional state is estimated based on this. The server takes this emotional state into consideration and adjusts investment decisions and investment strategies accordingly.

[0554] The server also adjusts spending and savings strategies in real time to support users' economic activities. For example, if a user is feeling stressed, the server will suggest ways to reduce spending or increase savings. In this way, investment decisions and asset management are made by comprehensively considering each user's emotional state and market trends.

[0555] For example, if an increase in heart rate is detected when a user is about to purchase an expensive item, the server will notify the user to re-evaluate their spending. An example of a prompt message supporting this process is, "Please provide advice to help the user avoid overspending based on their recent spending history and current emotional state."

[0556] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0557] Step 1:

[0558] The server collects market information from financial markets. This input includes price fluctuations and trading volume, which are then stored in a database. Data processing involves normalization and time-series transformation, and conversion to a unified format.

[0559] Step 2:

[0560] The server retrieves article information and analyzes it using natural language processing techniques. The input is text data, and the output generates information for investment decisions. Data calculations include topic modeling and sentiment analysis.

[0561] Step 3:

[0562] The server uses a generative AI model to generate investment decisions from collected market and article information. The input data consists of market information and article analysis results, and the output is specific buy / sell instructions.

[0563] Step 4:

[0564] The device collects the user's biometric information, including heart rate and facial expression data, which is then analyzed by emotion recognition software. The input is sensor data, and the output is the analyzed emotional state.

[0565] Step 5:

[0566] The server integrates the received emotional state with the generated investment decisions to determine a refined investment policy. This process adjusts the risk profile based on the emotional state and determines specific investment actions.

[0567] Step 6:

[0568] The terminal executes automated trades based on investment policies adjusted via the trading system API. Using the API, the input is buy / sell instructions, and the output is the execution result.

[0569] Step 7:

[0570] The server reports all activity results to the user and presents performance status in real time. Visualized information is provided through a dashboard as output.

[0571] 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.

[0572] 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.

[0573] 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.

[0574] [Fourth Embodiment]

[0575] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0576] 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.

[0577] 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).

[0578] 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.

[0579] 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.

[0580] 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).

[0581] 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.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] 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.

[0586] 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.

[0587] 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".

[0588] This invention is an AI-driven system that enables individual investors to efficiently conduct investment activities in diverse financial markets. The system is server-centric, and users can manage their investment portfolios by accessing the system via terminals.

[0589] The server first collects market data. This includes stock, bond, and foreign exchange data, which is regularly gathered from financial data providers and news sources on the internet. The server analyzes this data using natural language processing technology to predict future market trends and make investment-related decisions.

[0590] For example, if the server detects news that "stock prices in a particular technology sector are expected to fall due to disruptions in global supply chains," the system can refer to similar past cases and recommend selling the stocks. The system can adjust this decision according to the user's risk tolerance, advising low-risk users to sell some stocks and suggesting high-risk users continue holding their stocks to weather short-term market volatility.

[0591] After an investment decision is made, the server executes automated trades via the trading platform API. This eliminates the need for users to constantly monitor market conditions, as the system automatically buys and sells at the optimal time. Furthermore, after each trade is executed, the server reports a performance summary to the terminal, supporting efficient investment management.

[0592] This system also allows for continuous model updates. By analyzing past investment results, the AI ​​model improves the accuracy of investment decisions and provides better predictions for future decisions. As a result, users can respond quickly and effectively to market changes and maximize investment returns without having to perform complex market analysis.

[0593] The following describes the processing flow.

[0594] Step 1:

[0595] The server accesses market data providers to collect real-time data such as stock prices, bond yields, and foreign exchange rates. The collected data is stored in a database and used for subsequent analysis.

[0596] Step 2:

[0597] The server retrieves the latest financial news from internet news sources. The retrieved news is analyzed using natural language processing technology, and its potential impact on the market is evaluated. For example, the server identifies important keywords in the text and scores their potential impact on the market based on historical data.

[0598] Step 3:

[0599] The server generates investment decisions based on the data it analyzes. This process considers a combination of news analysis results and market data to determine buy and sell actions. These decisions are adjusted according to the user's risk tolerance.

[0600] Step 4:

[0601] The server executes automated trades via the trading platform API. Trading orders are generated by the server and sent through the API. This automatically buys and sells the specified financial instruments.

[0602] Step 5:

[0603] The terminal receives information sent from the server and displays the latest investment performance to the user. The information can be visually viewed on the dashboard, allowing the user to understand the status of their portfolio.

[0604] Step 6:

[0605] The server analyzes past trading data and updates the AI ​​model. This improves the accuracy of future investment decisions. The model is continuously improved through this feedback loop.

[0606] (Example 1)

[0607] 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".

[0608] For individual investors to invest efficiently and effectively in diverse financial markets, they need to analyze vast amounts of market data and continuously make accurate investment decisions. However, performing these tasks manually is extremely labor-intensive and requires specialized knowledge and quick decision-making skills, making it difficult for individuals to handle. Therefore, there is a need to provide a system that automates everything from market data collection and analysis to investment decisions and execution, and that can adjust decisions according to the risk tolerance of individual investors.

[0609] 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.

[0610] In this invention, the server includes means for collecting information, means for generating decisions based on information data analyzed using language processing technology, and means for automatically executing operations via a communication interface based on the decisions. This makes it possible for individual investors to efficiently perform everything from collecting and analyzing market data to executing automated trading.

[0611] "Information" refers to data obtained from markets and other sources, as well as text data such as news articles.

[0612] "Means of collection" refers to the components responsible for the process of obtaining information from external data providers and news sources.

[0613] "Language processing technology" refers to the technology of applying natural language analysis to information data and extracting the necessary meaning.

[0614] "Means of generating judgments" refers to the process of deriving the next course of action or decision based on analyzed information data.

[0615] A "communication interface" refers to the interface through which a server exchanges information with external systems and services.

[0616] "Means of executing operations" refers to a mechanism that carries out specific actions, such as buying and selling, based on the generated judgment.

[0617] "Display means" refers to a function that shows the results of an operation or notifications from the system in a way that is recognizable to the user.

[0618] "Methods for updating a model" refers to the process of adjusting the algorithms and parameters of a generative model based on past results to improve prediction accuracy.

[0619] "Tolerance" refers to the range or level of risk that a user can accept, and it serves as a criterion for adjusting investment decisions.

[0620] This invention provides a system that allows individual investors to automatically manage their investments in accordance with market trends. The server first collects market information from data providers on the internet. This information is provided in JSON format, and the server periodically retrieves the data using HTTP requests. The retrieved information is then analyzed as text data using natural language processing techniques. In this process, Python libraries such as NLTK and Spacy are utilized to extract important keywords and context from the information.

[0621] Based on the analysis, the server utilizes a generated AI model to produce investment decisions. This AI model proposes individual investment strategies based on the user's risk tolerance, while comparing them with historical market data. For example, a prompt message such as "Considering this week's market trends, please propose an investment strategy related to Apple's new product announcement" is generated, and the AI ​​provides recommendations accordingly.

[0622] Based on this generated investment decision, the server directly executes automated trades via the trading platform's communication interface (e.g., API). Once the trade is complete, the result is notified to the user's terminal. Specifically, a message such as "Your purchase of 100 shares of Apple was successful" is displayed on the terminal.

[0623] Furthermore, by analyzing past trading results, the server updates its generative model, improving the accuracy of investment decisions. This enables users to make efficient and strategic investments without having to closely monitor the market.

[0624] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0625] Step 1:

[0626] The server collects market information from data providers on the internet. Specifically, it uses APIs to issue HTTP requests and retrieve data provided in JSON format. This data includes information on stocks, bonds, foreign exchange, etc. The input is the API endpoint, and the output is the raw data stored on the server.

[0627] Step 2:

[0628] The server analyzes the collected market information using natural language processing techniques. Specifically, it uses Python's NLTK and Spacy libraries to extract important keywords and context from news articles and market information. The input is market data in JSON format, and the output is text data of the analyzed information.

[0629] Step 3:

[0630] The server utilizes a generated AI model based on the analyzed information to generate investment decisions. In this process, it references the user's risk tolerance and historical market data to create a highly probable investment strategy. The generated prompt statements are used to query the AI ​​model. The input is the analyzed data and the user's risk tolerance, and the output is a specific investment strategy.

[0631] Step 4:

[0632] The server automatically executes trades via the trading platform's API based on the generated investment decisions. Specifically, it sends appropriate buy and sell instructions to the platform API and checks the results. The input is the investment strategy, and the output is the success or failure of the trade.

[0633] Step 5:

[0634] The server notifies the user's terminal of the trading results. For example, it might send a message to the terminal saying, "Your purchase of 100 shares of Apple was successful," allowing the user to check the transaction status. The input is the trading result, and the output is the notification information sent to the user.

[0635] Step 6:

[0636] The server analyzes past trading results and updates the generated AI model. Specifically, it retrains the model using historical investment performance data to prepare for improved accuracy in future decisions. The input is historical trading data, and the output is the updated AI model.

[0637] (Application Example 1)

[0638] 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".

[0639] Individual investors need to analyze vast amounts of market and news information daily to make quick and accurate financial decisions, but this is a very time-consuming and specialized task, and many investors find this process difficult. Furthermore, security and efficiency are required in the settlement of asset buying and selling transactions, but current manual processes struggle to meet these requirements. The present invention aims to solve these problems and enable more investors to engage in efficient and safe investment activities.

[0640] 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.

[0641] In this invention, the server includes means for collecting market information, means for generating financial decisions based on news information analyzed using natural language processing technology, and means for automatically executing asset trades via an information exchange platform API. This enables investors to make optimal investment decisions and asset trades efficiently and safely without having to manually analyze market information.

[0642] "Market information" refers to all data related to financial markets, such as stocks, bonds, and foreign exchange.

[0643] "Natural language processing technology" is a technique for analyzing text data into a format that computers can understand and grasping its meaning.

[0644] "News information" refers to market and economic information contained in news articles and other materials that may influence investment decisions.

[0645] "Financial decision-making" refers to the act of deciding whether to buy, sell, or hold assets in the course of investment activities, as well as the results thereof.

[0646] An "information exchange platform API" is an application programming interface for direct communication with a platform used for asset trading.

[0647] "Asset trading" refers to the act of selling or buying stocks or other financial products.

[0648] "Approval" refers to the payment processing involved in the completion of a transaction and the transfer of assets.

[0649] "Financial optimization" is the process of optimizing the allocation of financial assets according to an individual's investment objectives and risk tolerance.

[0650] A "user profile" refers to individual information, including records of an person's investments, risk tolerance, and financial objectives.

[0651] To implement this invention, a platform centered around an AI-driven automated trading system will be constructed. The server will first periodically collect market information. Specifically, it will obtain data on stocks, bonds, foreign exchange, etc., from internet data providers and store it in a database.

[0652] The server then analyzes the collected news information using Python and natural language processing libraries. Using natural language processing techniques, it extracts information from news and articles that could potentially influence investment decisions, and then leverages a generative AI model to make financial decisions. TensorFlow is used to train the AI ​​model, and Scikit-learn is used in conjunction with it for data analysis.

[0653] Through an information exchange platform API, the server automatically executes asset trades. This process integrates with electronic payment services such as Stripe, enabling secure and rapid settlement of each transaction. Furthermore, the server notifies users of the transaction results and provides this information through mobile apps and desktop clients.

[0654] On the user's device, information is received through an application built with React Native, and financial optimization is performed based on the user profile. For example, as a result of an AI analysis, an alert such as "Emerging markets are performing well, and we recommend purchasing related stocks" is sent to the user's device, and based on the user's decision, the purchase process is automatically carried out on the server side.

[0655] An example of a prompt message is to give the AI ​​model an instruction such as, "Based on new market data, have the AI ​​model predict which assets to recommend purchasing," and the AI ​​model will then analyze market trends.

[0656] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0657] Step 1:

[0658] The server periodically collects market information such as stocks, bonds, and foreign exchange from market data providers and stores it in a database. The input is real-time market information from external data sources, and the output is structured database entries. This data is used for subsequent analysis.

[0659] Step 2:

[0660] The server analyzes news information using natural language processing technology. News information is provided as input, and a generative AI model extracts information from the document that influences investment decisions. The output is elemental information identified by the server for making investment decisions. This makes it possible to understand news trends and their impact on the market.

[0661] Step 3:

[0662] The server uses an AI model to make financial decisions based on the analysis data from the previous step. The input is the result of natural language processing, which the predictive model uses to forecast fluctuations in the financial market. The output is a proposal for specific investment actions. TensorFlow is used throughout this process, and the model is continuously trained to improve prediction accuracy.

[0663] Step 4:

[0664] Through an information exchange platform API, the server automatically executes buy and sell transactions for recommended assets. The input is investment recommendations from an AI model, and the output is buy and sell orders sent to the trading platform. This enables instant trading without human intervention.

[0665] Step 5:

[0666] The system notifies the user terminal of the transaction results. Input is a notification of the transaction's success or failure, and output is a user-facing report containing detailed information. It informs users of market trends in real time, helping them to take the next action.

[0667] Step 6:

[0668] The server analyzes transaction history and uses this data to update the generated AI model. The input is past transaction data and results, and the output is an improved predictive model. This process acts as a feedback loop to improve the accuracy of the user's investment decisions.

[0669] 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.

[0670] This invention provides a system that recognizes user emotions and reflects them in investment decisions, thereby offering more personalized investment support. The system comprises a server, terminals, and an emotion engine.

[0671] First, the server collects market data and relevant news, and performs data analysis using natural language processing technology. During this process, generative AI is used to generate investment decisions to predict market trends. These generated investment decisions are then adjusted based on the user's risk tolerance.

[0672] Next, the emotion engine works to recognize the user's emotions through the user's device. This analyzes the current emotional state using biometric information (e.g., heart rate, facial expressions, etc.) and information entered by the user. For example, if the emotion engine detects that the user is feeling stressed, it will adjust investment decisions conservatively. This emotion-based adjustment allows the user to invest safely while reducing psychological burden.

[0673] The server also has the ability to execute automated trades via the trading platform API and report the trading results to the user. The terminal is equipped with a dashboard that displays performance data to the user in real time, allowing the user to see how their investment status and emotions are influencing their investment decisions.

[0674] Furthermore, the server analyzes past investment results and sentiment data to update the model. This improves the accuracy of future investment decisions and allows for the provision of more user-friendly investment advice. By utilizing sentiment data in this way, it becomes possible to provide sophisticated investment support that is not merely data-driven, but also takes into account the user's emotional state.

[0675] The following describes the processing flow.

[0676] Step 1:

[0677] The server retrieves real-time financial data from market data providers. This includes stock prices, bond yields, and foreign exchange rates, and the retrieved data is stored in a database. The server also collects the latest market-related news via a news API.

[0678] Step 2:

[0679] The server analyzes collected news data using natural language processing technology. A generating AI analyzes news articles, assesses their potential impact on the market, and calculates specific indicators to make investment decisions. Based on this assessment, it determines specific buy or sell actions.

[0680] Step 3:

[0681] The device analyzes the user's emotional state through an emotion engine. It acquires the user's biometric information using sensors and other means to identify their current emotional state (e.g., relaxed, stressed). Users can also directly input their emotions.

[0682] Step 4:

[0683] The server adjusts investment decisions based on emotional information obtained from the emotion engine. For example, if a user is experiencing stress, the investment portfolio is readjusted to reduce risk. This adjustment is then compiled into the final investment decision.

[0684] Step 5:

[0685] The server executes automated trades via the trading platform API. The system sends determined buy and sell instructions to the trading platform, and the sale or purchase of selected financial instruments is executed.

[0686] Step 6:

[0687] The terminal receives information from the server and displays the latest investment status and trading results to the user on a dashboard. Through this information, the user can check the performance of their portfolio and the impact of their emotions.

[0688] Step 7:

[0689] The server analyzes past investment performance and sentiment data to update the AI ​​model. This makes future investment decisions more accurate. The analysis results are shared within the system as feedback and presented to the user as improvement suggestions.

[0690] (Example 2)

[0691] 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".

[0692] Conventional investment support systems make investment decisions based on market trends, but they do not take into account the user's emotions or psychological state, making it difficult to provide investment strategies optimized for individual users. Furthermore, there were challenges in improving the accuracy of automated investment decisions and establishing a user-friendly interface.

[0693] 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.

[0694] In this invention, the server includes a device for collecting market information, a device for generating investment decisions based on information data analyzed using natural language processing technology, and a device for automatically executing trades via a management system API. This enables individually optimized investment support by recognizing the user's emotional state and providing investment decisions adjusted accordingly.

[0695] "Market information" refers to data and information related to financial markets, including, for example, stock prices, exchange rates, economic indicators, and news articles.

[0696] "Analyzed information data" refers to data such as news and market information that has been analyzed using natural language processing technology, and is a fundamental element for investment decisions.

[0697] A "management system API" is an application programming interface that enables automated trading and data access, and is a means of communicating with external systems and software.

[0698] A "display device" is a device or interface that provides information to a user visually, and typically includes computer monitors and smartphone screens.

[0699] A "generative model" is a data processing algorithm that learns from past data and information to make future investment decisions, and typically uses machine learning techniques.

[0700] "User emotional state" refers to the actual emotional state analyzed from biometric information such as heart rate and facial expressions, and is used to fine-tune investment decisions.

[0701] "Investment decisions" are judgments and policies that guide the timing and strategies for buying and selling assets, generated based on market information and the emotional state of the user.

[0702] This invention provides a system that offers individually optimized investment support that takes into account the user's emotional data. This system mainly consists of a server, terminals, and an emotional engine.

[0703] First, the server collects market information and stores it in a database. Market information is obtained from financial market news and various economic data through web scraping techniques and publicly available APIs. Specific data sources typically include financial news websites and economic data provision services.

[0704] Next, the server analyzes the collected information using natural language processing techniques. This analysis utilizes generative AI models, such as sentiment analysis of news articles and prediction of market trends. For this purpose, generative AI models like BERT and the GPT series are used. An example of a prompt might be, "Predict important trends from today's market news."

[0705] The server generates investment decisions based on these analysis results and automatically executes trades via the management system API. These trades are automated and can buy and sell stocks and other financial instruments based on specific conditions.

[0706] Meanwhile, the device collects the user's biometric information and transmits it to the emotion engine. The device acquires biometric information such as heart rate from the wearable device and also analyzes facial expressions through the camera. This analysis estimates the user's emotional state in real time.

[0707] The emotion engine uses this emotional data to adjust investment decisions generated on the server according to the user's risk tolerance. For example, if a user is experiencing high levels of stress, the system will adjust to select a more conservative investment strategy.

[0708] Finally, the server sends the updated investment decision results to the terminal and displays them to the user. This allows the user to visualize how their emotional state is influencing their investment decisions.

[0709] By integrating the entire system in this way, it becomes possible to provide sophisticated investment support that utilizes sentiment data, not just decisions based on market data.

[0710] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0711] Step 1:

[0712] The server collects market information. Input is raw market data obtained through web scraping techniques and APIs, while output is organized market information stored in a database. The server performs this regularly, covering financial news and economic indicators.

[0713] Step 2:

[0714] The server performs natural language processing based on the collected market information. The input is the market information obtained in step 1, and the output is the analyzed data. Specifically, a generative AI model is used, with the prompt "Perform market trend and sentiment analysis" as input, and trends are extracted from the data.

[0715] Step 3:

[0716] The server generates investment decisions using naturally language processed data. The input is the analyzed data obtained in step 2, and the output is a specific investment strategy indicator. The generated investment decisions provide concrete examples, such as "you should focus on buying technology stocks in the next week." This clarifies the guidance for automated trading systems.

[0717] Step 4:

[0718] The device collects biometric information to measure the user's emotional state. Input is biometric information obtained from wearable devices or cameras (e.g., heart rate, facial expression data), and output is analyzed emotional data sent to an emotion engine. By tracking the user's emotional state in real time, the system aims to identify potential influences on investment decisions.

[0719] Step 5:

[0720] The emotion engine adjusts investment decisions based on the user's emotional data. The input is the emotional data obtained in step 4 and the investment decision in step 3, and the output is the adjusted investment strategy. For example, it might make a decision such as, "The user is currently feeling stressed, so adopt a conservative strategy."

[0721] Step 6:

[0722] The server executes the adjusted investment strategy and reports the results to the terminal in real time. The input is the adjusted investment strategy generated in step 5, and the output is the result of the trades executed based on that strategy. The user can view this from the terminal and evaluate their investment performance in real time.

[0723] (Application Example 2)

[0724] 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".

[0725] In recent years, individual investors have been required to make investment decisions based on diverse market information and trends. However, general automated trading systems cannot adequately consider the emotions and subjective risk tolerance of individual investors. As a result, this can lead to psychological burden and unnecessary depletion of assets due to taking excessive risks. Therefore, there is a need for a system that can make investment decisions based on the emotional state and risk tolerance of individual investors, thereby optimizing asset management while reducing mental stress.

[0726] 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.

[0727] In this invention, the server includes means for collecting market information, means for generating investment decisions based on article information analyzed using natural language processing technology, means for automatically executing buy and sell orders via a trading system API, means for analyzing the user's biometric information and adjusting investment policies based on their emotional state, and means for adjusting the user's spending and savings strategies in real time. This enables investment decisions and asset management that comprehensively consider the user's emotional state and market trends.

[0728] "Market information" refers to all data in financial markets, including price fluctuations, trading volume, and trends.

[0729] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and specifically to methods for extracting information from text data.

[0730] "Article information" refers to published written information such as news articles and reports, and is data that should be analyzed for investment decisions.

[0731] "Investment decisions" refer to plans and decisions made to buy or sell assets based on market conditions and the user's risk tolerance.

[0732] A "trading system API" is an interface used for automated trading and refers to a protocol for communicating with external trading platforms.

[0733] "User biometric information" refers to data obtained by measuring the user's physical condition, such as heart rate and facial expressions.

[0734] "Emotional state" refers to the user's mental state, such as stress or relaxation.

[0735] "Investment policy" refers to the basic direction and strategy used when making investment decisions.

[0736] "Spending and savings strategies" refer to plans for how users spend and save their assets, aiming to improve their economic activity.

[0737] The system that realizes this invention consists of three main elements: a server, a terminal, and a user. The server first collects market information from financial markets. Specifically, this includes general market data such as price fluctuations and trading volume. The server then uses natural language processing technology to analyze the collected article information. Here, a generative AI model using Google's TensorFlow is used to generate investment decisions from various articles.

[0738] The generated investment decisions are automatically executed on the terminal via the trading system API. The terminal collects biometric information from the user, such as heart rate and facial expressions, and sends it to the server. At that time, the user's biometric information is analyzed by dedicated emotion recognition software, and the user's emotional state is estimated based on this. The server takes this emotional state into consideration and adjusts investment decisions and investment strategies accordingly.

[0739] The server also adjusts spending and savings strategies in real time to support users' economic activities. For example, if a user is feeling stressed, the server will suggest ways to reduce spending or increase savings. In this way, investment decisions and asset management are made by comprehensively considering each user's emotional state and market trends.

[0740] For example, if an increase in heart rate is detected when a user is about to purchase an expensive item, the server will notify the user to re-evaluate their spending. An example of a prompt message supporting this process is, "Please provide advice to help the user avoid overspending based on their recent spending history and current emotional state."

[0741] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0742] Step 1:

[0743] The server collects market information from financial markets. This input includes price fluctuations and trading volume, which are then stored in a database. Data processing involves normalization and time-series transformation, and conversion to a unified format.

[0744] Step 2:

[0745] The server retrieves article information and analyzes it using natural language processing techniques. The input is text data, and the output generates information for investment decisions. Data calculations include topic modeling and sentiment analysis.

[0746] Step 3:

[0747] The server uses a generative AI model to generate investment decisions from collected market and article information. The input data consists of market information and article analysis results, and the output is specific buy / sell instructions.

[0748] Step 4:

[0749] The device collects the user's biometric information, including heart rate and facial expression data, which is then analyzed by emotion recognition software. The input is sensor data, and the output is the analyzed emotional state.

[0750] Step 5:

[0751] The server integrates the received emotional state with the generated investment decisions to determine a refined investment policy. This process adjusts the risk profile based on the emotional state and determines specific investment actions.

[0752] Step 6:

[0753] The terminal executes automated trades based on investment policies adjusted via the trading system API. Using the API, the input is buy / sell instructions, and the output is the execution result.

[0754] Step 7:

[0755] The server reports all activity results to the user and presents performance status in real time. Visualized information is provided through a dashboard as output.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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."

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] The following is further disclosed regarding the embodiments described above.

[0778] (Claim 1)

[0779] Means for collecting market data,

[0780] A means for generating investment decisions based on news data analyzed using natural language processing technology,

[0781] Based on the aforementioned investment decision, a means of automatically executing buy and sell orders via the trading platform API,

[0782] A display means for reporting the results of the aforementioned trades to the user,

[0783] A means to improve the accuracy of investment decisions by analyzing past investment results and updating generative models,

[0784] A system that includes this.

[0785] (Claim 2)

[0786] The system according to claim 1, wherein the natural language processing technology uses generative AI.

[0787] (Claim 3)

[0788] The system according to claim 1, further comprising means for adjusting investment decisions according to the user's risk tolerance.

[0789] "Example 1"

[0790] (Claim 1)

[0791] Means for collecting information,

[0792] A means for generating judgments based on information data analyzed using language processing technology,

[0793] Based on the above determination, means for automatically performing operations via a communication interface,

[0794] A display means for reporting the results of the above operation to the user,

[0795] A means to improve the accuracy of decisions by analyzing past results and updating the generative model,

[0796] A means for adjusting the generated judgment according to the user's tolerance level,

[0797] A system that includes this.

[0798] (Claim 2)

[0799] The system according to claim 1, wherein the language processing technology uses generative artificial intelligence.

[0800] (Claim 3)

[0801] The system according to claim 1, further comprising means for referring to past data patterns when making the aforementioned determination.

[0802] "Application Example 1"

[0803] (Claim 1)

[0804] Means for gathering market information,

[0805] A means of generating financial decision-making based on news information analyzed using natural language processing technology,

[0806] A means for automatically executing asset trading via an information exchange platform API based on the aforementioned financial decision,

[0807] A means for reporting the results of the aforementioned transactions to the user,

[0808] A means to improve the accuracy of financial decision-making by analyzing past financial results and updating generative models,

[0809] A means of securely settling transactions by linking with electronic payment services,

[0810] A means of optimizing finances based on user profiles and market information,

[0811] A system that includes this.

[0812] (Claim 2)

[0813] The system according to claim 1, wherein the natural language processing technology uses generative AI.

[0814] (Claim 3)

[0815] The system according to claim 1, further comprising means for adjusting financial decision-making in accordance with the user's risk tolerance.

[0816] "Example 2 of combining an emotion engine"

[0817] (Claim 1)

[0818] A device for collecting market information,

[0819] A device that generates investment decisions based on information data analyzed using natural language processing technology,

[0820] Based on the aforementioned investment decision, a device that automatically executes transactions via a management system API,

[0821] A display device for reporting the results of the aforementioned transaction to the user,

[0822] A device for updating generative models by analyzing past investment results and improving the accuracy of investment decisions,

[0823] A device that recognizes the emotional state of the user and adjusts investment decisions based on that state,

[0824] A system that includes this.

[0825] (Claim 2)

[0826] The system according to claim 1, wherein the natural language processing technology uses generative AI.

[0827] (Claim 3)

[0828] The system according to claim 1, further comprising a device that analyzes the user's biometric information and adjusts investment decisions based on their emotional state.

[0829] "Application example 2 when combining with an emotional engine"

[0830] (Claim 1)

[0831] Means for gathering market information,

[0832] A means for generating investment decisions based on article information analyzed using natural language processing technology,

[0833] Based on the aforementioned investment decision, a means of automatically executing buy and sell orders via the trading system API,

[0834] A means for presenting the results of the aforementioned transaction to the user,

[0835] A means to improve the accuracy of investment decisions by analyzing past investment results and updating generative models,

[0836] A means of analyzing users' biometric information and adjusting investment policies based on their emotional state,

[0837] A means to adjust users' spending and savings strategies in real time,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, wherein the natural language processing technology uses generative AI.

[0841] (Claim 3)

[0842] The system according to claim 1, further comprising means for adjusting investment decisions in accordance with the user's risk tolerance and emotional state. [Explanation of Symbols]

[0843] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting market data, A means for generating investment decisions based on news data analyzed using natural language processing technology, Based on the aforementioned investment decision, a means of automatically executing buy and sell orders via the trading platform API, A display means for reporting the results of the aforementioned trades to the user, A means to improve the accuracy of investment decisions by analyzing past investment results and updating generative models, A system that includes this.

2. The system according to claim 1, wherein the natural language processing technology uses generative AI.

3. The system according to claim 1, further comprising means for adjusting investment decisions according to the user's risk tolerance.

Images