system

Abstract

Provide a system. [Solution] A means of obtaining positive information, market conditions, speculation information, technical data, and fundamental data from various sources; A means of analyzing the acquired data, extracting necessary information, and storing it in a database; A means for performing analysis to assess the value of stocks based on the stored data; A means for generating investment decision information based on the analysis results; means for transmitting the generated investment decision information to a user's terminal; A system including:

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In today's stock market, investors are required to quickly analyze large amounts of information and make accurate investment decisions. However, it is difficult to integrate and analyze the various data provided individually, including positive factors, market sentiment, speculation information, technical analysis, and fundamental analysis, to obtain information useful for investment decisions. Conventional methods evaluate each element separately, making it difficult to make investment decisions from a comprehensive perspective and requiring a great deal of time and effort. There is a need to build a system that can solve these problems and provide efficient and accurate information for investment decisions. [Means for solving the problem]

[0005] The present invention provides a system that employs means for acquiring positive factors, market conditions, stock manipulation information, technical data, and fundamental data from various information sources, analyzes the acquired data, extracts necessary information, and stores it in a database. Based on the stored data, a means for performing analysis to evaluate stock value performs scoring of positive factors, market conditions evaluation, detection of stock manipulation information, technical analysis, and fundamental analysis. Furthermore, a system is constructed that includes means for generating investment decision information (probability of increase, recommended stocks, risk assessment) based on the analysis results, and means for transmitting the generated investment decision information to the user's terminal, thereby providing an integrated and efficient system for providing investment decision information. This system enables users to make investment decisions quickly and accurately.

[0006] "Positive news" refers to news or events that have a positive impact on a company or the market as a whole.

[0007] "Market conditions" refers to an indicator that shows the investment environment and trend conditions in the market as a whole or in a specific sector.

[0008] "Speculation information" refers to information regarding stock trading by large investors and trading activity on specific stocks.

[0009] "Technical data" refers to data used in technical analysis based on past stock price movements and trading volume patterns.

[0010] "Fundamental data" refers to basic data based on a company's financial condition, performance, and management analysis.

[0011] A "database" refers to a system that stores collected information and data in an organized manner and makes them available for efficient search and use.

[0012] "Analysis" refers to the process of evaluating collected data and drawing conclusions or predictions for a specific purpose.

[0013] "Investment decision information" refers to information to support decisions regarding the buying and selling of stocks, and specifically includes information such as the probability of an increase, recommended stocks, and risk assessment.

[0014] A "terminal" is a device that a user uses to receive and display information, such as a smartphone or PC.

[0015] "Natural language processing algorithm" refers to computer programming technology for analyzing and understanding human language.

[0016] A "chart pattern" refers to a visual pattern of stock price movement that can be used to predict future price direction.

[0017] An "indicator" is an index calculated based on stock price and trading volume data and used to determine the timing of buying and selling.

[0018] An "overall score" is an evaluation index generated by integrating the results of various analyses, and is used to comprehensively evaluate the investment value of the target stock. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a 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.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0033] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention is a system that collects and analyzes information related to stock investment from various sources and provides users with investment decision information. This system consists of three elements: a server, a terminal, and a user.

[0041] Data collection

[0042] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest news about a company and obtains market data such as stock prices and trading volume from the API of a financial data provider.

[0043] Data organization

[0044] The server then applies a natural language processing algorithm to the acquired data to extract and organize information such as company names, events, and information that influences stock prices. For example, information such as "Company A has announced a new product" can be extracted from a news article and stored in a database.

[0045] Analytical Processing

[0046] The server performs various analyses based on the information stored in the database.

[0047] Positive Factor Analysis: Information useful to a company is extracted from news and social media posts and scored. For example, the impact of "Company A's new product announcement" on the stock price is evaluated.

[0048] Market sentiment analysis: Analyze the overall market trend and the situation of each sector to assess the market sentiment. For example, "The overall market is in an uptrend."

[0049] Analysis of stock manipulation information: Analyzes the movements of large investors in specific stocks and detects them as stock manipulation information. For example, it provides information such as "Large buy orders are concentrated on Company A."

[0050] Technical analysis: Predicts stock price trends using chart patterns and trend indicators. For example, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0051] Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts. For example, it provides information such as "Company A's EPS forecast is increasing by 20% compared to the same period last year."

[0052] result generation

[0053] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." It also generates a recommended stock list and risk assessment based on the overall score.

[0054] Information provision

[0055] The server sends the generated investment decision information to the terminal. The terminal formats the received data and displays it to the user via a user interface. For example, the user can open the application and check information such as "Company A has a 70% chance of increasing, and its risk assessment is medium."

[0056] Specific examples

[0057] At 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, it extracts information such as "Company A announces a new product, which could lead to an increase in stock price" and stores it in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine the probability of a stock price increase as 70%. The server then adds Company A to the recommended stock list with a 70% increase probability and a "medium" risk assessment, generating a result. At 9:00 AM, the user opens the app and confirms that Company A is included in the recommended stock list. The increase probability and risk assessment are also displayed.

[0058] As described above, this system works in cooperation with three elements - server, terminal, and user - to provide important stock information every day, allowing users to make investment decisions quickly and accurately.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The server sends API requests to each information source to retrieve the latest data. Specifically, it retrieves corporate news from news sites, market data such as stock prices and trading volume from financial data providers, and collects related post data from social media.

[0062] Step 2:

[0063] The server analyzes the acquired data, extracts necessary information, and stores it in a database. For example, it extracts keywords that affect company names and stock prices from news articles, analyzes the tone of social media posts, and assigns positive or negative ratings.

[0064] Step 3:

[0065] The server analyzes positive factors. Specifically, it scores information that has a positive impact on the company from news and social media posts and evaluates the importance of that information. For example, it may evaluate "Company A's new product announcement: importance 85%."

[0066] Step 4:

[0067] The server analyzes the market conditions. It evaluates the overall market trend and the situation of each sector, and evaluates the current trend of the market. For example, it may evaluate the overall market as "Strong upward trend."

[0068] Step 5:

[0069] The server analyzes the stock manipulation information, tracking the movements of large investors and detecting large trades for specific stocks. For example, it extracts information such as "large buy orders are concentrated on Company A."

[0070] Step 6:

[0071] The server performs technical analysis. It analyzes stock price trends using chart patterns and trend indicators and predicts future stock prices. For example, it may evaluate that "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0072] Step 7:

[0073] The server performs fundamental analysis, assessing the future value of a company based on its financial data and performance forecasts. For example, it might say, "Company A's EPS forecast is up 20% compared to the same period last year."

[0074] Step 8:

[0075] The server aggregates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." Based on the overall score, it creates a recommended stock list and risk assessment.

[0076] Step 9:

[0077] The server transmits the generated investment decision information to the terminal, which formats the received data and displays it to the user via a user interface.

[0078] Step 10:

[0079] Users can open the application and see a list of recommended stocks and detailed analysis results, such as "Company A has a 70% chance of rising and is rated medium risk."

[0080] In this way, the server, terminals, and users work together to operate a system that provides daily important stock information.

[0081] Example 1

[0082] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0083] Conventional stock investment systems often have limited sources of information, making it difficult to provide up-to-date, comprehensive information for investment decisions. Furthermore, when analyzing data and generating investment decision information, they are limited to evaluating individual factors, lacking detailed trend analysis of the overall market or individual companies. This creates the problem of investors not being provided with enough information to make quick and accurate investment decisions, resulting in increased investment risk.

[0084] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0085] In this invention, the server includes means for acquiring accurate data, economic environment, trading information, technical indicators, and fundamental data from various information sources, means for analyzing the acquired data, extracting necessary information, and storing it in a database, and means for performing analysis to evaluate stock values ​​based on the stored data, thereby enabling the rapid provision of comprehensive and up-to-date investment decision information.

[0086] The server further includes means for performing the following analytical processes:

[0087] A method for extracting and scoring information useful to companies from news and social media posts

[0088] A means of analyzing overall market trends and sectoral conditions to assess market conditions

[0089] A method for analyzing the movements of large investors in specific stocks and detecting speculative information

[0090] A means of predicting stock price movements using chart patterns and trend indicators

[0091] A method for evaluating a company's value based on its financial data and performance forecasts

[0092] The system further includes a means for transmitting the generated investment decision information to the user's terminal, thereby enabling the user to make quick investment decisions based on the latest and most accurate information, thereby reducing investment risks.

[0093] "Accurate data" means data related to stock investments that is obtained from up-to-date and reliable sources.

[0094] The "economic environment" refers to macroeconomic conditions that affect the stock market, such as national economic policies, interest rates, exchange rates, and economic indicators.

[0095] "Trading information" refers to information such as trading data, order status, volume, and price fluctuations for the entire market or specific stocks.

[0096] "Technical indicators" are indicators or groups of indicators used in technical analysis, such as chart patterns, trend indicators, moving averages, RSI, and MACD.

[0097] "Basic data" refers to data used to evaluate a company's fundamental value, such as financial data, performance forecasts, and business plans.

[0098] "Necessary information" refers to information that can be used as the basis for reliable investment decisions, such as company names, events, and factors that affect stock prices, which are important factors in stock investment decisions.

[0099] A "database" is a system for storing acquired, analyzed, and structured data.

[0100] "Means for performing analysis" refers to the ability to evaluate stock values ​​and market trends using specific analytical algorithms and models based on stored data.

[0101] "News and social media posts" refers to information about the stock market or specific companies posted on online news sites or social media.

[0102] "Scoring" is the process of quantifying information that is useful to a company and quantitatively evaluating the extent to which it will affect the stock price.

[0103] "Market sentiment" refers to the trends and mood of the stock market as a whole or a specific sector, and is a concept that generally reflects trading trends and investor sentiment.

[0104] "Large investors" usually refer to institutional or individual investors who buy and sell large amounts of stocks, and their actions often have a major impact on the market.

[0105] A "chart pattern" is a visualization of historical price data, and is a method of predicting future price trends by analyzing specific shapes and patterns.

[0106] "Trend indicators" are indicators that show the direction of a market or a particular stock, and include moving averages and trend lines.

[0107] "Investment decision information" is information that integrates the results of various analyses and supports investment decisions, including the recommendation level and risk assessment of specific stocks, expected stock price fluctuations, etc.

[0108] "User terminal" refers to a device for receiving and displaying investment decision information, such as a smartphone, tablet, or PC.

[0109] MODE FOR CARRYING OUT THE INVENTION

[0110] This invention is a system that collects and analyzes information related to stock investment from various sources and provides users with investment decision information. This system consists of three elements: a server, a terminal, and a user.

[0111] Data collection

[0112] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest corporate news and obtains market data such as stock prices and trading volume from the financial data provider's API. Specifically, it uses NewsAPI as the news API and Alpha Vantage as the financial data provider.

[0113] Data organization

[0114] The server runs the acquired data through a natural language processing algorithm to extract and organize information that influences company names, events, and stock prices. For example, information such as "Company A has announced a new product" is extracted from a news article and stored in a database. SpaCy and NLTK are used as natural language processing algorithms, and MySQL (registered trademark) or MongoDB are used as databases.

[0115] Analytical Processing

[0116] The server performs various analyses based on the information stored in the database, including:

[0117] 1. Analysis of positive factors: Extracting information useful to a company from news and social media posts and scoring it. For example, assessing the impact of Company A's "new product announcement" on its stock price.

[0118] 2. Market Condition Analysis: Analyze the overall market trend and evaluate the situation of each sector. For example, you might say, "The overall market is in an uptrend."

[0119] 3. Analysis of stock manipulation information: Analyzes the movements of large investors in specific stocks and detects them as stock manipulation information. For example, it generates information such as "Large buy orders are concentrated on Company A."

[0120] 4. Technical analysis: Predict stock price movements using chart patterns and trend indicators. For example, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0121] 5. Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts. For example, providing information such as "Company A's EPS forecast is increasing by 20% compared to the same period last year."

[0122] result generation

[0123] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." It also generates a list of recommended stocks and a risk assessment based on the overall score. Specifically, it generates information such as "Risk assessment: Medium, Probability of Company A's Upturn: 70%."

[0124] Information provision

[0125] The server sends the generated investment decision information to the terminal. The terminal formats the received data and displays it to the user via a user interface (mobile app or web application). For example, the user can open the application and check information such as "Company A has a 70% chance of increasing, and its risk assessment is medium."

[0126] Specific examples

[0127] At 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, it extracts information such as "Company A announces a new product, which could lead to an increase in stock price" and stores it in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine the probability of a stock price increase as 70%. The server then adds Company A to the recommended stock list with a 70% increase probability and a "medium" risk assessment, generating a result. At 9:00 AM, the user opens the app and confirms that Company A is included in the recommended stock list. The increase probability and risk assessment are also displayed.

[0128] Examples of prompt statements

[0129] "Collect the latest news about Company A and assess its impact on the stock price."

[0130] "Analyze overall market trends and assess the situation in each sector."

[0131] "Analyze the probability of a stock price increase based on Company A's past stock price data and new product announcements."

[0132] By using this system, users can make quick investment decisions based on the latest and most accurate information, thereby reducing investment risk.

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] Step 1: Data collection

[0135] The server accesses various information sources, such as news sites, financial data providers, and social media.

[0136] Input: API information from news sites, financial data providers, and social media.

[0137] How it works: Collects corporate news using a news API (e.g., NewsAPI) and obtains market data such as stock prices from financial data providers (e.g., Alpha Vantage).

[0138] Output: Latest company news, stock prices, trading volume, and other data.

[0139] Step 2: Data organization

[0140] The server analyzes the collected data and runs it through natural language processing algorithms to extract information.

[0141] Input: News articles, stock price data, and social media posts obtained in Step 1.

[0142] How it works: It uses natural language processing algorithms (e.g. SpaCy, NLTK) to extract and structure company names, events, and stock price impact information.

[0143] Output: A database containing extracted company names, events, and stock price impact information.

[0144] Step 3: Analyze the positives

[0145] The server extracts information useful to companies from news and social media posts and performs scoring.

[0146] Input: News articles and social media posts formatted in Step 2.

[0147] How it works: Uses keyword extraction and scoring algorithms to evaluate useful information such as "new product launches."

[0148] Output: Positive material score for each company.

[0149] Step 4: Analyze the formation

[0150] The server analyzes the overall market and sectoral conditions to assess market sentiment.

[0151] Inputs: Market-wide and sector-specific trend data obtained in Step 1.

[0152] How it works: Uses market trend analysis algorithms to assess the sentiment of each sector.

[0153] Output: Trend assessment results for the overall market and each sector.

[0154] Step 5: Analyze the information

[0155] The server analyzes the movements of large investors in specific stocks and provides information on stock manipulation.

[0156] Input: Trade data for a specific stock obtained in Step 1.

[0157] How it works: Analyzes trading patterns of large investors to detect anomalous trading activity.

[0158] Output: Detected speculation information.

[0159] Step 6: Technical analysis

[0160] The server predicts stock price trends using chart patterns and trend indicators.

[0161] Input: Stock price data and technical indicator data obtained in Step 1.

[0162] What it does: Calculates technical indicators (e.g. RSI, MACD) and analyzes chart patterns.

[0163] Output: Stock price prediction results and technical indicator evaluation results.

[0164] Step 7: Fundamental analysis

[0165] The server evaluates the company's value based on the company's financial data and performance forecasts.

[0166] Input: Company financial data, performance forecast data.

[0167] What it does: Analyzes financial data and evaluates performance forecasts to calculate company value.

[0168] Output: Company value assessment results.

[0169] Step 8: Result Generation

[0170] The server integrates the results of the various analyses and calculates an overall score.

[0171] Input: Analysis results from steps 3 to 7.

[0172] How it works: An algorithm combines the results of each analysis to calculate an overall score.

[0173] Output: Overall score and recommended stock list.

[0174] Step 9: Provide information

[0175] The server transmits the generated investment decision information to the terminal.

[0176] Input: The overall score and recommended stock list generated in Step 8.

[0177] What it does: Formats data and converts it into a form that can be displayed through a user interface.

[0178] Output: Formatted data for displaying investment decision information.

[0179] Step 10: Display Information

[0180] The terminal displays information to the user via a user interface.

[0181] Input: Formatted data sent in step 9.

[0182] What it does: Display information to the user using an application or web interface.

[0183] Output: Displayed investment decision information.

[0184] (Application example 1)

[0185] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0186] Providing fast and accurate information for investment decisions is important in stock investment, but conventional systems are limited in the collection and analysis of information, making it difficult to comprehensively evaluate information from multiple sources. Furthermore, in the food delivery industry, evaluations based on customer reviews and sales data are not adequately conducted, and customer satisfaction and market trends are not properly reflected. To solve these problems, a system is needed that efficiently collects and analyzes data from a wide range of sources and provides accurate evaluation information.

[0187] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0188] In this invention, the server includes: means for acquiring positive factors, market conditions, speculation information, technical data, and fundamental data from various sources; means for analyzing the acquired data, extracting necessary information, and storing it in a database; and means for performing analysis to evaluate stock values ​​based on the stored data. It also includes means for collecting and analyzing customer reviews, sales data, and market trends, and means for extracting positive evaluations from customer word-of-mouth and social media. It also includes means for calculating evaluation scores and generating ranking lists based on the extracted and analyzed data. This enables information from multiple sources to be integrated, enabling accurate and prompt evaluations and recommendation information to be provided.

[0189] "Positive information" is information that has a positive impact on a company's stock price in the market.

[0190] "Market conditions" refers to information that indicates the overall market trend and the situation in each sector.

[0191] "Stock manipulation information" is information that shows the trading trends of large investors and institutional investors in specific stocks.

[0192] "Technical data" refers to analytical data based on stock price chart patterns and technical indicators.

[0193] "Fundamental data" refers to basic information based on a company's financial data and performance forecasts.

[0194] "Customer reviews" are ratings and comments from customers about restaurants and products.

[0195] "Sales data" is information that indicates the quantity and amount of sales of a restaurant or product during a specific period.

[0196] "Market trends" are data that show trends in consumer preferences and purchasing behavior.

[0197] "Social media" refers to a medium through which users share information on digital platforms such as social networking services (SNS).

[0198] A "positive rating" is information that gives a positive opinion or high rating to the subject of the rating in customer reviews or social media mentions.

[0199] The "evaluation score" is a comprehensive evaluation value calculated based on the analyzed data.

[0200] A "ranking list" is a list ranked based on evaluation scores.

[0201] The system that realizes this invention consists of three elements: a server, a terminal, and a user. Through the operation of the entire system, a wide range of data related to stock investments is collected and analyzed, as well as customer reviews and sales data in the food delivery industry.

[0202] Data collection

[0203] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest news about a company and obtains market data such as stock prices and trading volume from a financial data provider's API. For food delivery data, it obtains customer reviews from a review site API and collects mentions on social media using APIs such as Twitter.

[0204] Data organization

[0205] The server runs the collected data through natural language processing algorithms to extract and organize information that influences company names, events, and stock prices. For example, information such as "A company announced a new product" can be extracted from a news article and stored in a database. Similarly, evaluations such as "The restaurant's pizza is delicious" can be extracted from customer reviews.

[0206] Analytical Processing

[0207] The server performs various analyses based on the information stored in the database. For example, in stock investment, it analyzes positive factors, market conditions, speculation information, technical analysis, and fundamental analysis. In food delivery, it analyzes best-selling menu items based on sales data and scores items by extracting positive evaluations from customer reviews.

[0208] result generation

[0209] The server integrates the results of various analyses and calculates an overall score. Based on the overall score, it generates a list of recommended stocks and a risk assessment. In the case of food delivery, it generates a ranking list of restaurants and menus based on the assessment score.

[0210] Information provision

[0211] The server then sends the generated investment decision information and food delivery evaluation information to the device. The device then formats the received data and displays it to the user via a user interface. For example, a user can open a smartphone app to check the stock price forecast for a specific company or the evaluation score of a specific restaurant.

[0212] Hardware and software used

[0213] Hardware:

[0214] Server: High-performance server (e.g. Amazon EC2)

[0215] User device: smartphone, smart glasses (e.g., Google® Glass®)

[0216] software:

[0217] Data Collection: API (e.g. Twitter API, Google Maps API)

[0218] Natural Language Processing: Python's NLTK library, spaCy

[0219] Database: MySQL, MongoDB

[0220] Results display: iOS / ANDROID (registered trademark) app, AR interface

[0221] Specific examples

[0222] For example, at 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. At the same time, the latest restaurant reviews are collected. Based on this data, the server calculates the probability that the company's stock price will rise and the restaurant's rating score. When a user opens the app at 9:00 AM, the company's stock price prediction and restaurant rankings are displayed.

[0223] Prompt Sentence Examples

[0224] "Describe a process for using the Twitter API to gather the latest tweets about a restaurant and then using NLP to extract positive reviews. Also show how you can use this data to calculate a restaurant rating score."

[0225] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0226] Step 1:

[0227] The server collects data related to stock investments from news sites, financial data providers, and social media. For example, it uses APIs to retrieve news articles about new product launches and stock market data for specific companies. For food delivery, it uses review site APIs and Twitter APIs to retrieve the latest customer reviews and social media mentions for specific restaurants.

[0228] Input: Data from news sites, financial data providers, social media, and review sites

[0229] Output: A set of raw data

[0230] Step 2:

[0231] The server runs the acquired raw data through a natural language processing algorithm to extract information such as company names, events, and positive reviews, and then organizes and stores it in a database. For stock investments, key points such as company names and new product announcements are extracted, and for food delivery, positive reviews of food and service are extracted from customer reviews.

[0232] Input: Raw data

[0233] Output: Extracted element data (company name, event, evaluation comment)

[0234] Step 3:

[0235] The server performs various analyses based on the element data stored in the database. In stock investment, it evaluates information by analyzing positive factors, market conditions, detecting stock manipulation information, technical analysis, and fundamental analysis. In food delivery, it scores positive ratings based on sales data and customer reviews, and calculates evaluation scores for restaurants and menus.

[0236] Input: Element data

[0237] Output: Analysis results (evaluation score, various analysis results)

[0238] Step 4:

[0239] The server integrates the results of each analysis and generates an overall evaluation score. For stock investment, it calculates the overall score and generates a list of recommended stocks and a risk assessment. For food delivery, it generates a ranking list of restaurants and menus based on the evaluation score.

[0240] Input: Analysis results

[0241] Output: Overall evaluation score, ranking list

[0242] Step 5:

[0243] The server sends the generated rating scores and ranking list to the device. The device formats the received data and displays it to the user via a user interface. The user can check stock price predictions and restaurant rating scores on their own device using a smartphone app or smart glasses.

[0244] Input: Evaluation score, ranking list

[0245] Output: Information displayed on the user's device (stock price forecast, restaurant rating score)

[0246] Prompt Sentence Examples

[0247] "Describe a process for using the Twitter API to gather the latest tweets about a restaurant and then using NLP to extract positive reviews. Also show how you can use this data to calculate a restaurant rating score."

[0248] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0249] This invention is a system that collects and analyzes information related to stock investment from various sources, recognizes the user's emotions, and provides investment decision information. This system is composed of three elements: a server, a terminal, and a user, and is characterized by the incorporation of an emotion engine.

[0250] Data collection

[0251] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investment. For example, it uses a news API to collect the latest news about a company, market data such as stock prices and trading volume from the API of a financial data provider, and related post data from social media.

[0252] Data organization

[0253] The server then applies a natural language processing algorithm to the acquired data to extract and organize information such as company names, events, and information that influences stock prices. For example, information such as "Company A has announced a new product" can be extracted from a news article and stored in a database.

[0254] Analytical Processing

[0255] The server performs various analyses based on the information stored in the database.

[0256] Positive Factor Analysis: Information from news and social media posts that has a positive impact on a company is scored and the importance of that information is evaluated. For example, an evaluation such as "Company A's new product announcement: importance 85%" is made.

[0257] Market analysis: Analyze the overall market trend and the situation of each sector to evaluate the current trend of the market. For example, evaluate the overall market upward trend as "Strong."

[0258] Analysis of stock manipulation information: Analyzes the movements of large investors in specific stocks and detects them as stock manipulation information. For example, it provides information such as "large buy orders are concentrated on Company A."

[0259] Technical analysis: Analyzes stock price trends using chart patterns and trend indicators to predict future stock prices. For example, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0260] Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts. For example, it provides information such as "Company A's EPS forecast is increasing by 20% compared to the same period last year."

[0261] result generation

[0262] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." It also generates a recommended stock list and risk assessment based on the overall score.

[0263] Emotion Engine Functions

[0264] The device is equipped with an emotion engine that recognizes the user's emotional state. The engine analyzes the user's text and voice input to recognize positive, negative, and neutral emotions. For example, if a user types, "What will the market be like today?", the tone of the text is analyzed to assess the user's emotional state.

[0265] Information provision

[0266] The server transmits the generated investment decision information to the terminal. The terminal adjusts the content of the investment decision information provided based on the user's emotional state evaluated by the emotion engine. For example, if the user is in a negative emotional state, the terminal provides detailed risk assessments and displays more reassuring information. On the other hand, if the user is in a positive emotional state, the terminal emphasizes positive investment suggestions.

[0267] Specific examples

[0268] At 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, information such as "Company A announces a new product, which could lead to an increase in stock price" is extracted and stored in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine a 70% probability of stock price increase. The server then generates a result with a 70% probability of Company A increasing, adds Company A to a recommended stock list, and assigns a "medium" risk assessment. At 9:00 AM, the user opens the app, and the device's emotion engine recognizes the user's emotional state as "positive." As a result, investment decision information is adjusted according to the user's emotions, emphasizing aggressive investment suggestions. Information such as "Company A has a 70% chance of increasing, and its risk assessment is medium" is displayed.

[0269] As described above, this system works in conjunction with three elements - the server, the terminal, and the user - and combines the functions of the emotion engine to provide daily important stock information, allowing users to make quick and accurate investment decisions.

[0270] The processing flow will be explained below.

[0271] Step 1:

[0272] The server sends API requests to various information sources such as news sites, financial data providers, and social media to obtain the latest data. Specifically, it obtains corporate news using a news API, market data such as stock prices and trading volume from the financial data provider's API, and related post data from the social media API.

[0273] Step 2:

[0274] The server analyzes the acquired data, extracts necessary information, and stores it in a database. For example, it extracts keywords related to company names, events, and stock price impacts from news articles, analyzes the tone of social media posts, and stores positive and negative evaluations.

[0275] Step 3:

[0276] The server analyzes positive factors, scoring information from news and social media posts that has a positive impact on the company and assessing its importance. For example, it might assess "Company A's new product announcement: importance 85%."

[0277] Step 4:

[0278] The server analyzes the market conditions. It evaluates the overall market trend and the situation of each sector and evaluates the market conditions. For example, it evaluates the market condition as "Strong upward trend of the overall market."

[0279] Step 5:

[0280] The server analyzes the information on stock manipulation. It analyzes the movements of large investors and detects large transactions for specific stocks. For example, it provides information such as "large buy orders are concentrated on Company A."

[0281] Step 6:

[0282] The server performs technical analysis. It analyzes stock price trends using chart patterns and trend indicators and predicts future stock prices. For example, it may evaluate that "Company A's RSI is above 70, so there is a high possibility of overbuying."

[0283] Step 7:

[0284] The server performs fundamental analysis, evaluating the company's value based on the company's financial data and performance forecasts. For example, it may evaluate that "Company A's EPS forecast is up 20% compared to the same period last year."

[0285] Step 8:

[0286] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." Based on the overall score, it generates a list of recommended stocks and a risk assessment.

[0287] Step 9:

[0288] The server uses an emotion engine to recognize the user's emotional state. The device analyzes the user's text and voice input to determine positive, negative, or neutral emotions. For example, if a user types, "What will the market be like today?", the tone of the text is analyzed to assess the user's emotion.

[0289] Step 10:

[0290] The server transmits the generated investment decision information to the terminal, which formats the received data and displays it to the user via a user interface.

[0291] Step 11:

[0292] The device adjusts the content of investment decision information provided based on the user's emotional state. For example, if the user is in a negative emotional state, it provides detailed risk assessments and displays more reassuring information. On the other hand, if the user is in a positive emotional state, it emphasizes positive investment suggestions.

[0293] Step 12:

[0294] Users can open the application and see a list of recommended stocks and detailed analysis results, such as "Company A has a 70% chance of rising and is rated medium risk."

[0295] In this way, the server, terminals, and users work together, combining the functions of the emotion engine to provide daily important stock information, allowing users to make investment decisions quickly and accurately.

[0296] Example 2

[0297] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0298] In recent years, information in the stock market has changed very rapidly, and investors need to be able to quickly extract useful information from the vast amount of information available and make investment decisions. However, conventional systems lack the ability to provide information that takes emotional factors into account, making it difficult for investors to make rational investment decisions without being influenced by their emotions. Furthermore, there is a need for an efficient method that can automatically extract important elements such as company names and events from news articles and social media posts, and provide users with information that is appropriate for them based on the analysis results.

[0299] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring positive information, the overall market state, large-scale investment information, technical indicator data, and fundamental data from various information sources; means for analyzing the acquired information, extracting necessary information, and storing it in a database; means for performing analysis to evaluate the value of financial products based on the stored information; means for analyzing the emotional state of the user using an emotion engine; and means for transmitting the generated investment decision information to the user's terminal and adjusting the content of the information provided in accordance with the emotional state. This makes it possible to provide investment decision information that takes emotions into consideration, allowing users to make quick and rational investment decisions.

[0300] "Positive information" is information that has a positive impact on a company or the market.

[0301] "Overall market conditions" refers to information that represents the overall trends of a particular stock market and the situation of each sector.

[0302] "Large-scale investment information" is information that shows the investment trends of large investors in specific stocks.

[0303] "Technical indicator data" refers to data used to analyze stock price fluctuations using chart patterns, trend indicators, etc.

[0304] "Basic data" refers to fundamental data used to evaluate a company's value, such as a company's financial data and earnings forecasts.

[0305] An "emotion engine" is a system that analyzes a user's text and voice input and recognizes emotions such as positive, negative, and neutral.

[0306] A "natural language processing algorithm" is a technology that analyzes text data to understand human language and extract key points about company names, events, and stock price impacts.

[0307] A "database" is a collection of information that collects and stores data in an organized manner so that it can be accessed and queried efficiently at a later time.

[0308] This invention is a system that collects and analyzes information related to stock investment from various sources, recognizes the user's emotions, and provides investment decision information. This system is composed of three elements: a server, a terminal, and a user, and also has an emotion engine.

[0309] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest news about a company, obtains market data such as stock prices and trading volume from a financial data provider's API, and collects related post data from social media. This allows the server to obtain a wide range of information in real time.

[0310] The server then runs the acquired data through a natural language processing algorithm to extract and organize information that influences company names, events, and stock prices. This process uses a natural language processing library such as NLTK. For example, information such as "Company A has announced a new product" can be extracted from a news article and stored in a database. This allows for structuring and efficient storage of data.

[0311] The server then performs various analyses based on the information stored in the database. These include analysis of positive factors, analysis of the overall market state, analysis of large-scale investment information, technical analysis using technical indicators, and fundamental analysis based on basic data. For example, a Python library can be used to analyze stock price trends using chart patterns and trend indicators and predict future stock prices. An assessment could be made such as, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0312] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85" and generate a list of recommended stocks and a risk assessment. This allows users to see comprehensive information at a glance to make investment decisions.

[0313] The device is equipped with an emotion engine that recognizes the user's emotional state. This engine analyzes the user's text and voice input and recognizes emotions such as positive, negative, and neutral. For example, using Python's TextBlob library, the engine analyzes the input text "What will the market be like today?" and recognizes the user's emotional state as "negative."

[0314] The server transmits the generated investment decision information to the terminal. The terminal adjusts the content of the investment decision information provided based on the user's emotional state evaluated by the emotion engine. For example, if the user is in a negative emotional state, the terminal provides detailed risk assessments and displays more reassuring information. On the other hand, if the user is in a positive emotional state, the terminal emphasizes positive investment suggestions.

[0315] As a specific example, at 8:00 AM, a server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, information such as "Company A's new product announcement may lead to a rise in stock price" is extracted and stored in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine the probability of a stock price rise as 70%. The server then adds Company A to the recommended stocks list with a 70% probability of an increase and a "medium" risk assessment, generating a result.

[0316] At 9:00 a.m., the user opens the app, and the device's emotion engine recognizes the user's emotional state as "positive." Therefore, investment decision information is adjusted to reflect the user's emotions, emphasizing positive investment recommendations. Information such as "Company A has a 70% chance of growth and a medium risk assessment" is displayed.

[0317] As described above, this system works in conjunction with three elements - the server, the terminal, and the user - and combines the functions of the emotion engine to provide daily stock investment information, allowing users to make quick and accurate investment decisions.

[0318] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0319] Step 1: Data collection

[0320] The server accesses various information sources such as news sites, financial data providers, and social media to obtain the latest stock investment-related data. Specifically, the server calls a news API (e.g., NewsAPI) to obtain the latest news about a company. It also uses the financial data provider's API (e.g., Alpha Vantage or Yahoo Finance API) to obtain market data such as stock prices and trading volume. It also obtains related post data from social media APIs (e.g., Twitter API). The input is the API endpoint, and the output is the obtained raw data.

[0321] Step 2: Data organization

[0322] The server runs the acquired raw data through natural language processing algorithms to organize the information. Specifically, the server uses Python's NLTK library to extract company names, events, and key points that affect stock prices from news articles and social media posts. For example, it extracts information from a news article that "Company A has announced a new product." The input is the acquired raw data, and the output is structured information (company names, event information, etc.). This information is stored in a database.

[0323] Step 3: Save data

[0324] The server stores the organized data in a database, for example using a relational database system such as MySQL. The input is structured information and the output is the stored data in the database.

[0325] Step 4: Analyze the positives

[0326] The server scores positive information based on the information stored in the database. Specifically, the server evaluates positive news and social media posts and quantifies their importance. For example, it may evaluate "Company A's new product announcement: importance 85%." The input is the data stored in the database, and the output is scored positive information.

[0327] Step 5: Analyze the formation

[0328] The server analyzes the overall market condition. Specifically, it evaluates the overall market trend and the situation of each sector. For example, it makes an evaluation such as "Overall market uptrend: strong." The input is market data, and the output is an evaluation result that indicates the overall market condition.

[0329] Step 6: Analyze the information

[0330] The server analyzes the trends of large investors in specific stocks. For example, it provides information such as "large buy orders are concentrated on Company A." The input is stock price and trading volume data, and the output is information on the trends of large investors.

[0331] Step 7: Technical analysis

[0332] The server analyzes stock price trends using chart patterns and trend indicators to predict future stock prices. For example, it may evaluate that "Company A's RSI is above 70, so there is a high possibility of overbuying." The input is stock price data and technical indicator data, and the output is the technical analysis results.

[0333] Step 8: Fundamental analysis

[0334] The server evaluates a company's value based on its financial data and performance forecast. For example, it provides information such as "Company A's EPS forecast is up 20% compared to the same period last year." The input is the company's financial data, and the output is the results of fundamental analysis.

[0335] Step 9: Result integration and generation

[0336] The server integrates the results of various analyses and calculates an overall score. For example, it evaluates "Company A has an overall score of 85" and generates a list of recommended stocks and a risk assessment. The input is the results of various analyses, and the output is integrated investment decision information.

[0337] Step 10: Emotion Recognition

[0338] The device analyzes the user's text and voice input to recognize their emotional state. Specifically, the device uses Python's TextBlob library to classify the emotion of the input text as "positive," "negative," or "neutral." The input is the user's text or voice data, and the output is the user's emotional state.

[0339] Step 11: Provide information

[0340] The server sends the generated investment decision information to the terminal, and the terminal adjusts the content of the information provided based on the user's emotional state. For example, if the user is in a negative emotional state, detailed risk assessments are provided and more information that gives a sense of security is displayed. If the user is in a positive emotional state, positive investment suggestions are emphasized. The input is the generated investment decision information and the user's emotional state, and the output is the optimized information content provided.

[0341] (Application example 2)

[0342] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0343] In today's world, users are required to make important decisions based on large amounts of data provided by many sources. However, making appropriate decisions can be difficult because a user's emotional state significantly influences how they interpret the data. In particular, food and delivery services require appropriate suggestions based on the user's emotions, but existing systems are unable to fully meet this need.

[0344] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0345] In this invention, the server includes means for acquiring positive factors, market conditions, speculation information, technical data, and fundamental data from various information sources, means for analyzing the acquired data, extracting necessary information, and storing it in a database, means for performing analysis for evaluation based on the stored data, means for transmitting the generated judgment information to the user's terminal, means for analyzing the user's emotions, and means for adjusting the content of the offer based on the emotion analysis results. This makes it possible to provide proposals optimized for the user's emotional state.

[0346] "Various information sources" are external sources that provide various types of information, such as news sites, data providers, and social media.

[0347] "Positive factors" are elements or information that have a positive influence on the evaluation of the event or object in question.

[0348] "Condition" refers to the overall market environment or economic situation, or a means of assessing such conditions.

[0349] "Stock manipulation information" is information about the trends and transactions of large investors in specific stocks in the market.

[0350] "Technical data" refers to data collected using technical methods, such as stock prices, trading volume, and trend indicators.

[0351] "Fundamental data" refers to data used for basic analysis, such as a company's financial information, performance, and economic indicators.

[0352] "Analysis" is the process of analyzing collected data and extracting and understanding the necessary information.

[0353] A "database" is a system or structure for systematically storing and managing information.

[0354] "Evaluation" is the act of measuring the value and quality of an object based on collected information and data.

[0355] "Judgment information" is information provided based on evaluation results to support decision-making.

[0356] "Emotion analysis" is the process of detecting a user's emotional state and analyzing that information.

[0357] "Adjusting the content provided" refers to the act of optimizing the information and suggestions displayed to users based on the analysis results.

[0358] A "terminal" is a device through which a user receives information, and examples include smartphones and tablets.

[0359] This invention is a system that provides suggestions optimized for the user's emotional state. This system consists of three elements: a server, a terminal, and a user. In addition, by combining it with an emotion engine, it is possible to analyze the user's emotions.

[0360] Hardware and software used

[0361] 1. Hardware: Smartphones, smart glasses, head-mounted displays (HMDs)

[0362] 2. Software: Facial expression recognition API (Amazon Rekognition, etc.), voice emotion analysis API (IBM Watson (registered trademark) Tone Analyzer), natural language processing algorithms (SpaCy, NLTK), machine learning frameworks (TENSORFLOW (registered trademark), Keras)

[0363] Data collection

[0364] The server accesses various information sources such as news sites, data providers, and social media to obtain the latest relevant data. For example, it may collect the latest articles using a news API, obtain market data from a data provider's API, and collect relevant post data from social media.

[0365] Data organization

[0366] The server runs the acquired data through natural language processing algorithms (SpaCy or NLTK) to extract and organize company names, events, and impact information. For example, it extracts information from a news article such as "A certain company has announced a new product" and stores it in a database.

[0367] Analytical Processing

[0368] The server performs various analyses based on the information stored in the database. Examples of the main analysis processes are shown below.

[0369] Positive information analysis: Scores information that has a positive impact from news and social media posts and evaluates the importance of that information.

[0370] Market Analysis: Analyze overall market trends and assess the current state of the market.

[0371] Analysis of stock manipulation information: Analyze the movements of large investors in specific stocks.

[0372] Technical analysis: Analyzing stock price trends using chart patterns and trend indicators.

[0373] Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts.

[0374] Emotion analysis

[0375] The device is equipped with an emotion engine that recognizes the user's emotional state. This engine analyzes the user's facial expressions and voice to recognize positive, negative, and neutral emotions. For example, the device captures the user's facial expressions using a smartphone or HMD camera and analyzes emotions using the Amazon Rekognition API. The device uses the IBM Watson Tone Analyzer API for voice tone analysis.

[0376] Information provision

[0377] The server sends the generated judgment information to the device, and the device adjusts the information provided based on the user's emotional state analyzed by the emotion engine. For example, if the user is in a negative emotional state, detailed risk assessment information is provided and more information that gives a sense of security is displayed. If the user is in a positive emotional state, positive suggestions are emphasized.

[0378] Specific examples

[0379] Consider an example where a user launches the app at 8:00 AM and performs sentiment analysis using the device's camera. In this example, a smartphone is used. The server collects the latest articles from news sites and extracts information about specific companies using natural language processing. For example, based on the information that "a certain company has announced a new product," the probability of a stock price increase is analyzed and assessed as 70%. The generated information is sent to the device, and if the sentiment engine recognizes it as "positive," information such as "70% chance of increase due to new product announcement, risk assessment is medium" is displayed.

[0380] Prompt Sentence Examples

[0381] 1. Sentiment Analysis Prompt:

[0382] Capture facial expressions and analyze emotions.

[0383] Input image: {user's face image}

[0384] Output: Happiness, sadness, surprise, anger, etc. scores

[0385] 2. Data Collection Prompt:

[0386] Get the latest menu information from our partner data providers.

[0387] Output: Restaurant name, menu name, price, user rating, etc.

[0388] 3. Analytical Processing Prompt:

[0389] Generate optimal meal suggestions based on user sentiment data and past ordering history.

[0390] Input: Happiness score, past order history

[0391] Output: Recommended restaurant name, menu name, reason

[0392] As described above, the present invention makes it possible to provide suggestions optimized for the emotional state of the user.

[0393] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0394] Step 1: Data collection

[0395] The server accesses information sources such as news sites, data providers, and social media to obtain relevant data. It uses news APIs to obtain the latest articles, obtains market data from data provider APIs, and collects relevant post data from social media.

[0396] Input: News API, data provider API, SNS data

[0397] Output: Raw data collected

[0398] Step 2: Data organization

[0399] The server runs the collected data through natural language processing algorithms (SpaCy or NLTK) to extract company names, event information, etc., and stores them in a database. For example, this includes extracting information such as "a company has announced a new product" from a news article.

[0400] Input: Raw data collected

[0401] Output: Organized data, data stored in a database

[0402] Step 3: Emotion analysis (facial expressions)

[0403] The device captures the user's facial expressions using the smartphone or HMD camera and analyzes their emotions using the Amazon Rekognition API, generating scores such as happiness, sadness, surprise, and anger.

[0404] Input: User's face image

[0405] Output: Emotion score (happiness, sadness, surprise, anger, etc.)

[0406] Step 4: Sentiment Analysis (Audio)

[0407] The device captures the user's voice using the smartphone or HMD microphone and analyzes the voice tone using the IBM Watson Tone Analyzer API, generating a voice-based emotion score in the process.

[0408] Input: User's voice data

[0409] Output: Emotion score based on audio tone

[0410] Step 5: Data analysis

[0411] The server performs various analyses based on the information stored in the database and sentiment scores, such as positive analysis, market sentiment analysis, speculation analysis, technical analysis, and fundamental analysis, and generates related evaluations for each.

[0412] Input: Data in the database, sentiment scores

[0413] Output: Evaluation information (positive factors, market conditions, speculation information, technical analysis results, fundamental analysis results)

[0414] Step 6: Information Generation

[0415] The server integrates the results of various analyses to generate comprehensive judgment information, which is adjusted based on the results of sentiment analysis and provided in an optimized format.

[0416] Input: Evaluation information

[0417] Output: Judgment information (total score, recommendation list, risk assessment)

[0418] Step 7: Provide information

[0419] The server sends the generated judgment information to the device, which then displays the information in an appropriate format to the user. For example, if the positive emotion score is high, proactive suggestions are displayed.

[0420] Input: Judgment information

[0421] Output: Information displayed in the user interface (recommended menu, risk assessment)

[0422] Examples:

[0423] An example of a prompt sentence is the following emotion analysis prompt: "Capture an image of the user's facial expression and analyze their emotions. Input image: {user's facial image} Output: scores such as happiness, sadness, surprise, and anger."

[0424] Other examples include a data collection prompt: "Get the latest menu information from our partner data providers. Output: Restaurant name, menu name, price, user rating, etc."

[0425] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0426] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0427] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0428] [Second embodiment]

[0429] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0430] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0431] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0432] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0433] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0434] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0435] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0436] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0437] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0438] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0439] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0440] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0441] This invention is a system that collects and analyzes information related to stock investment from various sources and provides users with investment decision information. This system consists of three elements: a server, a terminal, and a user.

[0442] Data collection

[0443] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest news about a company and obtains market data such as stock prices and trading volume from the API of a financial data provider.

[0444] Data organization

[0445] The server then applies a natural language processing algorithm to the acquired data to extract and organize information such as company names, events, and information that influences stock prices. For example, information such as "Company A has announced a new product" can be extracted from a news article and stored in a database.

[0446] Analytical Processing

[0447] The server performs various analyses based on the information stored in the database.

[0448] Positive Factor Analysis: Information useful to a company is extracted from news and social media posts and scored. For example, the impact of "Company A's new product announcement" on the stock price is evaluated.

[0449] Market sentiment analysis: Analyze the overall market trend and the situation of each sector to assess the market sentiment. For example, "The overall market is in an uptrend."

[0450] Analysis of stock manipulation information: Analyzes the movements of large investors in specific stocks and detects them as stock manipulation information. For example, it provides information such as "Large buy orders are concentrated on Company A."

[0451] Technical analysis: Predicts stock price trends using chart patterns and trend indicators. For example, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0452] Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts. For example, it provides information such as "Company A's EPS forecast is increasing by 20% compared to the same period last year."

[0453] result generation

[0454] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." It also generates a recommended stock list and risk assessment based on the overall score.

[0455] Information provision

[0456] The server sends the generated investment decision information to the terminal. The terminal formats the received data and displays it to the user via a user interface. For example, the user can open the application and check information such as "Company A has a 70% chance of increasing, and its risk assessment is medium."

[0457] Specific examples

[0458] At 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, it extracts information such as "Company A announces a new product, which could lead to an increase in stock price" and stores it in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine the probability of a stock price increase as 70%. The server then adds Company A to the recommended stock list with a 70% increase probability and a "medium" risk assessment, generating a result. At 9:00 AM, the user opens the app and confirms that Company A is included in the recommended stock list. The increase probability and risk assessment are also displayed.

[0459] As described above, this system works in cooperation with three elements - server, terminal, and user - to provide important stock information every day, allowing users to make investment decisions quickly and accurately.

[0460] The processing flow will be explained below.

[0461] Step 1:

[0462] The server sends API requests to each information source to retrieve the latest data. Specifically, it retrieves corporate news from news sites, market data such as stock prices and trading volume from financial data providers, and collects related post data from social media.

[0463] Step 2:

[0464] The server analyzes the acquired data, extracts necessary information, and stores it in a database. For example, it extracts keywords that affect company names and stock prices from news articles, analyzes the tone of social media posts, and assigns positive or negative ratings.

[0465] Step 3:

[0466] The server analyzes positive factors. Specifically, it scores information that has a positive impact on the company from news and social media posts and evaluates the importance of that information. For example, it may evaluate "Company A's new product announcement: importance 85%."

[0467] Step 4:

[0468] The server analyzes the market conditions. It evaluates the overall market trend and the situation of each sector, and evaluates the current trend of the market. For example, it may evaluate the overall market as "Strong upward trend."

[0469] Step 5:

[0470] The server analyzes the stock manipulation information, tracking the movements of large investors and detecting large trades for specific stocks. For example, it extracts information such as "large buy orders are concentrated on Company A."

[0471] Step 6:

[0472] The server performs technical analysis. It analyzes stock price trends using chart patterns and trend indicators and predicts future stock prices. For example, it may evaluate that "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0473] Step 7:

[0474] The server performs fundamental analysis, assessing the future value of a company based on its financial data and performance forecasts. For example, it might say, "Company A's EPS forecast is up 20% compared to the same period last year."

[0475] Step 8:

[0476] The server aggregates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." Based on the overall score, it creates a recommended stock list and risk assessment.

[0477] Step 9:

[0478] The server transmits the generated investment decision information to the terminal, which formats the received data and displays it to the user via a user interface.

[0479] Step 10:

[0480] Users can open the application and see a list of recommended stocks and detailed analysis results, such as "Company A has a 70% chance of rising and is rated medium risk."

[0481] In this way, the server, terminals, and users work together to operate a system that provides daily important stock information.

[0482] Example 1

[0483] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0484] Conventional stock investment systems often have limited sources of information, making it difficult to provide up-to-date, comprehensive information for investment decisions. Furthermore, when analyzing data and generating investment decision information, they are limited to evaluating individual factors, lacking detailed trend analysis of the overall market or individual companies. This creates the problem of investors not being provided with enough information to make quick and accurate investment decisions, resulting in increased investment risk.

[0485] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0486] In this invention, the server includes means for acquiring accurate data, economic environment, trading information, technical indicators, and fundamental data from various information sources, means for analyzing the acquired data, extracting necessary information, and storing it in a database, and means for performing analysis to evaluate stock values ​​based on the stored data, thereby enabling the rapid provision of comprehensive and up-to-date investment decision information.

[0487] The server further includes means for performing the following analytical processes:

[0488] A method for extracting and scoring information useful to companies from news and social media posts

[0489] A means of analyzing overall market trends and sectoral conditions to assess market conditions

[0490] A method for analyzing the movements of large investors in specific stocks and detecting speculative information

[0491] A means of predicting stock price movements using chart patterns and trend indicators

[0492] A method for evaluating a company's value based on its financial data and performance forecasts

[0493] The system further includes a means for transmitting the generated investment decision information to the user's terminal, thereby enabling the user to make quick investment decisions based on the latest and most accurate information, thereby reducing investment risks.

[0494] "Accurate data" means data related to stock investments that is obtained from up-to-date and reliable sources.

[0495] The "economic environment" refers to macroeconomic conditions that affect the stock market, such as national economic policies, interest rates, exchange rates, and economic indicators.

[0496] "Trading information" refers to information such as trading data, order status, volume, and price fluctuations for the entire market or specific stocks.

[0497] "Technical indicators" are indicators or groups of indicators used in technical analysis, such as chart patterns, trend indicators, moving averages, RSI, and MACD.

[0498] "Basic data" refers to data used to evaluate a company's fundamental value, such as financial data, performance forecasts, and business plans.

[0499] "Necessary information" refers to information that can be used as the basis for reliable investment decisions, such as company names, events, and factors that affect stock prices, which are important factors in stock investment decisions.

[0500] A "database" is a system for storing acquired, analyzed, and structured data.

[0501] "Means for performing analysis" refers to the ability to evaluate stock values ​​and market trends using specific analytical algorithms and models based on stored data.

[0502] "News and social media posts" refers to information about the stock market or specific companies posted on online news sites or social media.

[0503] "Scoring" is the process of quantifying information that is useful to a company and quantitatively evaluating the extent to which it will affect the stock price.

[0504] "Market sentiment" refers to the trends and mood of the stock market as a whole or a specific sector, and is a concept that generally reflects trading trends and investor sentiment.

[0505] "Large investors" usually refer to institutional or individual investors who buy and sell large amounts of stocks, and their actions often have a major impact on the market.

[0506] A "chart pattern" is a visualization of historical price data, and is a method of predicting future price trends by analyzing specific shapes and patterns.

[0507] "Trend indicators" are indicators that show the direction of a market or a particular stock, and include moving averages and trend lines.

[0508] "Investment decision information" is information that integrates the results of various analyses and supports investment decisions, including the recommendation level and risk assessment of specific stocks, expected stock price fluctuations, etc.

[0509] "User terminal" refers to a device for receiving and displaying investment decision information, such as a smartphone, tablet, or PC.

[0510] MODE FOR CARRYING OUT THE INVENTION

[0511] This invention is a system that collects and analyzes information related to stock investment from various sources and provides users with investment decision information. This system consists of three elements: a server, a terminal, and a user.

[0512] Data collection

[0513] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest corporate news and obtains market data such as stock prices and trading volume from the financial data provider's API. Specifically, it uses NewsAPI as the news API and Alpha Vantage as the financial data provider.

[0514] Data organization

[0515] The server runs the acquired data through a natural language processing algorithm to extract and organize company names, events, and information that influences stock prices. For example, information such as "Company A has announced a new product" is extracted from a news article and stored in a database. SpaCy and NLTK are used as natural language processing algorithms, and MySQL or MongoDB are used as databases.

[0516] Analytical Processing

[0517] The server performs various analyses based on the information stored in the database, including:

[0518] 1. Analysis of positive factors: Extracting information useful to a company from news and social media posts and scoring it. For example, assessing the impact of Company A's "new product announcement" on its stock price.

[0519] 2. Market Condition Analysis: Analyze the overall market trend and evaluate the situation of each sector. For example, you might say, "The overall market is in an uptrend."

[0520] 3. Analysis of stock manipulation information: Analyzes the movements of large investors in specific stocks and detects them as stock manipulation information. For example, it generates information such as "Large buy orders are concentrated on Company A."

[0521] 4. Technical analysis: Predict stock price movements using chart patterns and trend indicators. For example, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0522] 5. Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts. For example, providing information such as "Company A's EPS forecast is increasing by 20% compared to the same period last year."

[0523] result generation

[0524] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." It also generates a list of recommended stocks and a risk assessment based on the overall score. Specifically, it generates information such as "Risk assessment: Medium, Probability of Company A's Upturn: 70%."

[0525] Information provision

[0526] The server sends the generated investment decision information to the terminal. The terminal formats the received data and displays it to the user via a user interface (mobile app or web application). For example, the user can open the application and check information such as "Company A has a 70% chance of increasing, and its risk assessment is medium."

[0527] Specific examples

[0528] At 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, it extracts information such as "Company A announces a new product, which could lead to an increase in stock price" and stores it in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine the probability of a stock price increase as 70%. The server then adds Company A to the recommended stock list with a 70% increase probability and a "medium" risk assessment, generating a result. At 9:00 AM, the user opens the app and confirms that Company A is included in the recommended stock list. The increase probability and risk assessment are also displayed.

[0529] Examples of prompt statements

[0530] "Collect the latest news about Company A and assess its impact on the stock price."

[0531] "Analyze overall market trends and assess the situation in each sector."

[0532] "Analyze the probability of a stock price increase based on Company A's past stock price data and new product announcements."

[0533] By using this system, users can make quick investment decisions based on the latest and most accurate information, thereby reducing investment risk.

[0534] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0535] Step 1: Data collection

[0536] The server accesses various information sources, such as news sites, financial data providers, and social media.

[0537] Input: API information from news sites, financial data providers, and social media.

[0538] How it works: Collects corporate news using a news API (e.g., NewsAPI) and obtains market data such as stock prices from financial data providers (e.g., Alpha Vantage).

[0539] Output: Latest company news, stock prices, trading volume, and other data.

[0540] Step 2: Data organization

[0541] The server analyzes the collected data and runs it through natural language processing algorithms to extract information.

[0542] Input: News articles, stock price data, and social media posts obtained in Step 1.

[0543] How it works: It uses natural language processing algorithms (e.g. SpaCy, NLTK) to extract and structure company names, events, and stock price impact information.

[0544] Output: A database containing extracted company names, events, and stock price impact information.

[0545] Step 3: Analyze the positives

[0546] The server extracts information useful to companies from news and social media posts and performs scoring.

[0547] Input: News articles and social media posts formatted in Step 2.

[0548] How it works: Uses keyword extraction and scoring algorithms to evaluate useful information such as "new product launches."

[0549] Output: Positive material score for each company.

[0550] Step 4: Analyze the formation

[0551] The server analyzes the overall market and sectoral conditions to assess market sentiment.

[0552] Inputs: Market-wide and sector-specific trend data obtained in Step 1.

[0553] How it works: Uses market trend analysis algorithms to assess the sentiment of each sector.

[0554] Output: Trend assessment results for the overall market and each sector.

[0555] Step 5: Analyze the information

[0556] The server analyzes the movements of large investors in specific stocks and provides information on stock manipulation.

[0557] Input: Trade data for a specific stock obtained in Step 1.

[0558] How it works: Analyzes trading patterns of large investors to detect anomalous trading activity.

[0559] Output: Detected speculation information.

[0560] Step 6: Technical analysis

[0561] The server predicts stock price trends using chart patterns and trend indicators.

[0562] Input: Stock price data and technical indicator data obtained in Step 1.

[0563] What it does: Calculates technical indicators (e.g. RSI, MACD) and analyzes chart patterns.

[0564] Output: Stock price prediction results and technical indicator evaluation results.

[0565] Step 7: Fundamental analysis

[0566] The server evaluates the company's value based on the company's financial data and performance forecasts.

[0567] Input: Company financial data, performance forecast data.

[0568] What it does: Analyzes financial data and evaluates performance forecasts to calculate company value.

[0569] Output: Company value assessment results.

[0570] Step 8: Result Generation

[0571] The server integrates the results of the various analyses and calculates an overall score.

[0572] Input: Analysis results from steps 3 to 7.

[0573] How it works: An algorithm combines the results of each analysis to calculate an overall score.

[0574] Output: Overall score and recommended stock list.

[0575] Step 9: Provide information

[0576] The server transmits the generated investment decision information to the terminal.

[0577] Input: The overall score and recommended stock list generated in Step 8.

[0578] What it does: Formats data and converts it into a form that can be displayed through a user interface.

[0579] Output: Formatted data for displaying investment decision information.

[0580] Step 10: Display Information

[0581] The terminal displays information to the user via a user interface.

[0582] Input: Formatted data sent in step 9.

[0583] What it does: Display information to the user using an application or web interface.

[0584] Output: Displayed investment decision information.

[0585] (Application example 1)

[0586] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0587] Providing fast and accurate information for investment decisions is important in stock investment, but conventional systems are limited in the collection and analysis of information, making it difficult to comprehensively evaluate information from multiple sources. Furthermore, in the food delivery industry, evaluations based on customer reviews and sales data are not adequately conducted, and customer satisfaction and market trends are not properly reflected. To solve these problems, a system is needed that efficiently collects and analyzes data from a wide range of sources and provides accurate evaluation information.

[0588] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0589] In this invention, the server includes: means for acquiring positive factors, market conditions, speculation information, technical data, and fundamental data from various sources; means for analyzing the acquired data, extracting necessary information, and storing it in a database; and means for performing analysis to evaluate stock values ​​based on the stored data. It also includes means for collecting and analyzing customer reviews, sales data, and market trends, and means for extracting positive evaluations from customer word-of-mouth and social media. It also includes means for calculating evaluation scores and generating ranking lists based on the extracted and analyzed data. This enables information from multiple sources to be integrated, enabling accurate and prompt evaluations and recommendation information to be provided.

[0590] "Positive information" is information that has a positive impact on a company's stock price in the market.

[0591] "Market conditions" refers to information that indicates the overall market trend and the situation in each sector.

[0592] "Stock manipulation information" is information that shows the trading trends of large investors and institutional investors in specific stocks.

[0593] "Technical data" refers to analytical data based on stock price chart patterns and technical indicators.

[0594] "Fundamental data" refers to basic information based on a company's financial data and performance forecasts.

[0595] "Customer reviews" are ratings and comments from customers about restaurants and products.

[0596] "Sales data" is information that indicates the quantity and amount of sales of a restaurant or product during a specific period.

[0597] "Market trends" are data that show trends in consumer preferences and purchasing behavior.

[0598] "Social media" refers to a medium through which users share information on digital platforms such as social networking services (SNS).

[0599] A "positive rating" is information that gives a positive opinion or high rating to the subject of the rating in customer reviews or social media mentions.

[0600] The "evaluation score" is a comprehensive evaluation value calculated based on the analyzed data.

[0601] A "ranking list" is a list ranked based on evaluation scores.

[0602] The system that realizes this invention consists of three elements: a server, a terminal, and a user. Through the operation of the entire system, a wide range of data related to stock investments is collected and analyzed, as well as customer reviews and sales data in the food delivery industry.

[0603] Data collection

[0604] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest news about a company and obtains market data such as stock prices and trading volume from a financial data provider's API. For food delivery data, it obtains customer reviews from a review site API and collects mentions on social media using APIs such as Twitter.

[0605] Data organization

[0606] The server runs the collected data through natural language processing algorithms to extract and organize information that influences company names, events, and stock prices. For example, information such as "A company announced a new product" can be extracted from a news article and stored in a database. Similarly, evaluations such as "The restaurant's pizza is delicious" can be extracted from customer reviews.

[0607] Analytical Processing

[0608] The server performs various analyses based on the information stored in the database. For example, in stock investment, it analyzes positive factors, market conditions, speculation information, technical analysis, and fundamental analysis. In food delivery, it analyzes best-selling menu items based on sales data and scores items by extracting positive evaluations from customer reviews.

[0609] result generation

[0610] The server integrates the results of various analyses and calculates an overall score. Based on the overall score, it generates a list of recommended stocks and a risk assessment. In the case of food delivery, it generates a ranking list of restaurants and menus based on the assessment score.

[0611] Information provision

[0612] The server then sends the generated investment decision information and food delivery evaluation information to the device. The device then formats the received data and displays it to the user via a user interface. For example, a user can open a smartphone app to check the stock price forecast for a specific company or the evaluation score of a specific restaurant.

[0613] Hardware and software used

[0614] Hardware:

[0615] Server: High-performance server (e.g. Amazon EC2)

[0616] User devices: smartphones, smart glasses (e.g., Google Glass)

[0617] software:

[0618] Data Collection: API (e.g. Twitter API, Google Maps API)

[0619] Natural Language Processing: Python's NLTK library, spaCy

[0620] Database: MySQL, MongoDB

[0621] Results display: iOS / Android app, AR interface

[0622] Specific examples

[0623] For example, at 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. At the same time, the latest restaurant reviews are collected. Based on this data, the server calculates the probability that the company's stock price will rise and the restaurant's rating score. When a user opens the app at 9:00 AM, the company's stock price prediction and restaurant rankings are displayed.

[0624] Prompt Sentence Examples

[0625] "Describe a process for using the Twitter API to gather the latest tweets about a restaurant and then using NLP to extract positive reviews. Also show how you can use this data to calculate a restaurant rating score."

[0626] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0627] Step 1:

[0628] The server collects data related to stock investments from news sites, financial data providers, and social media. For example, it uses APIs to retrieve news articles about new product launches and stock market data for specific companies. For food delivery, it uses review site APIs and Twitter APIs to retrieve the latest customer reviews and social media mentions for specific restaurants.

[0629] Input: Data from news sites, financial data providers, social media, and review sites

[0630] Output: A set of raw data

[0631] Step 2:

[0632] The server runs the acquired raw data through a natural language processing algorithm to extract information such as company names, events, and positive reviews, and then organizes and stores it in a database. For stock investments, key points such as company names and new product announcements are extracted, and for food delivery, positive reviews of food and service are extracted from customer reviews.

[0633] Input: Raw data

[0634] Output: Extracted element data (company name, event, evaluation comment)

[0635] Step 3:

[0636] The server performs various analyses based on the element data stored in the database. In stock investment, it evaluates information by analyzing positive factors, market conditions, detecting stock manipulation information, technical analysis, and fundamental analysis. In food delivery, it scores positive ratings based on sales data and customer reviews, and calculates evaluation scores for restaurants and menus.

[0637] Input: Element data

[0638] Output: Analysis results (evaluation score, various analysis results)

[0639] Step 4:

[0640] The server integrates the results of each analysis and generates an overall evaluation score. For stock investment, it calculates the overall score and generates a list of recommended stocks and a risk assessment. For food delivery, it generates a ranking list of restaurants and menus based on the evaluation score.

[0641] Input: Analysis results

[0642] Output: Overall evaluation score, ranking list

[0643] Step 5:

[0644] The server sends the generated rating scores and ranking list to the device. The device formats the received data and displays it to the user via a user interface. The user can check stock price predictions and restaurant rating scores on their own device using a smartphone app or smart glasses.

[0645] Input: Evaluation score, ranking list

[0646] Output: Information displayed on the user's device (stock price forecast, restaurant rating score)

[0647] Prompt Sentence Examples

[0648] "Describe a process for using the Twitter API to gather the latest tweets about a restaurant and then using NLP to extract positive reviews. Also show how you can use this data to calculate a restaurant rating score."

[0649] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0650] This invention is a system that collects and analyzes information related to stock investment from various sources, recognizes the user's emotions, and provides investment decision information. This system is composed of three elements: a server, a terminal, and a user, and is characterized by the incorporation of an emotion engine.

[0651] Data collection

[0652] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investment. For example, it uses a news API to collect the latest news about a company, market data such as stock prices and trading volume from the API of a financial data provider, and related post data from social media.

[0653] Data organization

[0654] The server then applies a natural language processing algorithm to the acquired data to extract and organize information such as company names, events, and information that influences stock prices. For example, information such as "Company A has announced a new product" can be extracted from a news article and stored in a database.

[0655] Analytical Processing

[0656] The server performs various analyses based on the information stored in the database.

[0657] Positive Factor Analysis: Information from news and social media posts that has a positive impact on a company is scored and the importance of that information is evaluated. For example, an evaluation such as "Company A's new product announcement: importance 85%" is made.

[0658] Market analysis: Analyze the overall market trend and the situation of each sector to evaluate the current trend of the market. For example, evaluate the overall market upward trend as "Strong."

[0659] Analysis of stock manipulation information: Analyzes the movements of large investors in specific stocks and detects them as stock manipulation information. For example, it provides information such as "large buy orders are concentrated on Company A."

[0660] Technical analysis: Analyzes stock price trends using chart patterns and trend indicators to predict future stock prices. For example, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0661] Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts. For example, it provides information such as "Company A's EPS forecast is increasing by 20% compared to the same period last year."

[0662] result generation

[0663] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." It also generates a recommended stock list and risk assessment based on the overall score.

[0664] Emotion Engine Functions

[0665] The device is equipped with an emotion engine that recognizes the user's emotional state. The engine analyzes the user's text and voice input to recognize positive, negative, and neutral emotions. For example, if a user types, "What will the market be like today?", the tone of the text is analyzed to assess the user's emotional state.

[0666] Information provision

[0667] The server transmits the generated investment decision information to the terminal. The terminal adjusts the content of the investment decision information provided based on the user's emotional state evaluated by the emotion engine. For example, if the user is in a negative emotional state, the terminal provides detailed risk assessments and displays more reassuring information. On the other hand, if the user is in a positive emotional state, the terminal emphasizes positive investment suggestions.

[0668] Specific examples

[0669] At 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, information such as "Company A announces a new product, which could lead to an increase in stock price" is extracted and stored in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine a 70% probability of stock price increase. The server then generates a result with a 70% probability of Company A increasing, adds Company A to a recommended stock list, and assigns a "medium" risk assessment. At 9:00 AM, the user opens the app, and the device's emotion engine recognizes the user's emotional state as "positive." As a result, investment decision information is adjusted according to the user's emotions, emphasizing aggressive investment suggestions. Information such as "Company A has a 70% chance of increasing, and its risk assessment is medium" is displayed.

[0670] As described above, this system works in conjunction with three elements - the server, the terminal, and the user - and combines the functions of the emotion engine to provide daily important stock information, allowing users to make quick and accurate investment decisions.

[0671] The processing flow will be explained below.

[0672] Step 1:

[0673] The server sends API requests to various information sources such as news sites, financial data providers, and social media to obtain the latest data. Specifically, it obtains corporate news using a news API, market data such as stock prices and trading volume from the financial data provider's API, and related post data from the social media API.

[0674] Step 2:

[0675] The server analyzes the acquired data, extracts necessary information, and stores it in a database. For example, it extracts keywords related to company names, events, and stock price impacts from news articles, analyzes the tone of social media posts, and stores positive and negative evaluations.

[0676] Step 3:

[0677] The server analyzes positive factors, scoring information from news and social media posts that has a positive impact on the company and assessing its importance. For example, it might assess "Company A's new product announcement: importance 85%."

[0678] Step 4:

[0679] The server analyzes the market conditions. It evaluates the overall market trend and the situation of each sector and evaluates the market conditions. For example, it evaluates the market condition as "Strong upward trend of the overall market."

[0680] Step 5:

[0681] The server analyzes the information on stock manipulation. It analyzes the movements of large investors and detects large transactions for specific stocks. For example, it provides information such as "large buy orders are concentrated on Company A."

[0682] Step 6:

[0683] The server performs technical analysis. It analyzes stock price trends using chart patterns and trend indicators and predicts future stock prices. For example, it may evaluate that "Company A's RSI is above 70, so there is a high possibility of overbuying."

[0684] Step 7:

[0685] The server performs fundamental analysis, evaluating the company's value based on the company's financial data and performance forecasts. For example, it may evaluate that "Company A's EPS forecast is up 20% compared to the same period last year."

[0686] Step 8:

[0687] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." Based on the overall score, it generates a list of recommended stocks and a risk assessment.

[0688] Step 9:

[0689] The server uses an emotion engine to recognize the user's emotional state. The device analyzes the user's text and voice input to determine positive, negative, or neutral emotions. For example, if a user types, "What will the market be like today?", the tone of the text is analyzed to assess the user's emotion.

[0690] Step 10:

[0691] The server transmits the generated investment decision information to the terminal, which formats the received data and displays it to the user via a user interface.

[0692] Step 11:

[0693] The device adjusts the content of investment decision information provided based on the user's emotional state. For example, if the user is in a negative emotional state, it provides detailed risk assessments and displays more reassuring information. On the other hand, if the user is in a positive emotional state, it emphasizes positive investment suggestions.

[0694] Step 12:

[0695] Users can open the application and see a list of recommended stocks and detailed analysis results, such as "Company A has a 70% chance of rising and is rated medium risk."

[0696] In this way, the server, terminals, and users work together, combining the functions of the emotion engine to provide daily important stock information, allowing users to make investment decisions quickly and accurately.

[0697] Example 2

[0698] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0699] In recent years, information in the stock market has changed very rapidly, and investors need to be able to quickly extract useful information from the vast amount of information available and make investment decisions. However, conventional systems lack the ability to provide information that takes emotional factors into account, making it difficult for investors to make rational investment decisions without being influenced by their emotions. Furthermore, there is a need for an efficient method that can automatically extract important elements such as company names and events from news articles and social media posts, and provide users with information that is appropriate for them based on the analysis results.

[0700] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring positive information, the overall market state, large-scale investment information, technical indicator data, and fundamental data from various information sources; means for analyzing the acquired information, extracting necessary information, and storing it in a database; means for performing analysis to evaluate the value of financial products based on the stored information; means for analyzing the emotional state of the user using an emotion engine; and means for transmitting the generated investment decision information to the user's terminal and adjusting the content of the information provided in accordance with the emotional state. This makes it possible to provide investment decision information that takes emotions into consideration, allowing users to make quick and rational investment decisions.

[0701] "Positive information" is information that has a positive impact on a company or the market.

[0702] "Overall market conditions" refers to information that represents the overall trends of a particular stock market and the situation of each sector.

[0703] "Large-scale investment information" is information that shows the investment trends of large investors in specific stocks.

[0704] "Technical indicator data" refers to data used to analyze stock price fluctuations using chart patterns, trend indicators, etc.

[0705] "Basic data" refers to fundamental data used to evaluate a company's value, such as a company's financial data and earnings forecasts.

[0706] An "emotion engine" is a system that analyzes a user's text and voice input and recognizes emotions such as positive, negative, and neutral.

[0707] A "natural language processing algorithm" is a technology that analyzes text data to understand human language and extract key points about company names, events, and stock price impacts.

[0708] A "database" is a collection of information that collects and stores data in an organized manner so that it can be accessed and queried efficiently at a later time.

[0709] This invention is a system that collects and analyzes information related to stock investment from various sources, recognizes the user's emotions, and provides investment decision information. This system is composed of three elements: a server, a terminal, and a user, and also has an emotion engine.

[0710] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest news about a company, obtains market data such as stock prices and trading volume from a financial data provider's API, and collects related post data from social media. This allows the server to obtain a wide range of information in real time.

[0711] The server then runs the acquired data through a natural language processing algorithm to extract and organize information that influences company names, events, and stock prices. This process uses a natural language processing library such as NLTK. For example, information such as "Company A has announced a new product" can be extracted from a news article and stored in a database. This allows for structuring and efficient storage of data.

[0712] The server then performs various analyses based on the information stored in the database. These include analysis of positive factors, analysis of the overall market state, analysis of large-scale investment information, technical analysis using technical indicators, and fundamental analysis based on basic data. For example, a Python library can be used to analyze stock price trends using chart patterns and trend indicators and predict future stock prices. An assessment could be made such as, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0713] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85" and generate a list of recommended stocks and a risk assessment. This allows users to see comprehensive information at a glance to make investment decisions.

[0714] The device is equipped with an emotion engine that recognizes the user's emotional state. This engine analyzes the user's text and voice input and recognizes emotions such as positive, negative, and neutral. For example, using Python's TextBlob library, the engine analyzes the input text "What will the market be like today?" and recognizes the user's emotional state as "negative."

[0715] The server transmits the generated investment decision information to the terminal. The terminal adjusts the content of the investment decision information provided based on the user's emotional state evaluated by the emotion engine. For example, if the user is in a negative emotional state, the terminal provides detailed risk assessments and displays more reassuring information. On the other hand, if the user is in a positive emotional state, the terminal emphasizes positive investment suggestions.

[0716] As a specific example, at 8:00 AM, a server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, information such as "Company A's new product announcement may lead to a rise in stock price" is extracted and stored in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine the probability of a stock price rise as 70%. The server then adds Company A to the recommended stocks list with a 70% probability of an increase and a "medium" risk assessment, generating a result.

[0717] At 9:00 a.m., the user opens the app, and the device's emotion engine recognizes the user's emotional state as "positive." Therefore, investment decision information is adjusted to reflect the user's emotions, emphasizing positive investment recommendations. Information such as "Company A has a 70% chance of growth and a medium risk assessment" is displayed.

[0718] As described above, this system works in conjunction with three elements - the server, the terminal, and the user - and combines the functions of the emotion engine to provide daily stock investment information, allowing users to make quick and accurate investment decisions.

[0719] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0720] Step 1: Data collection

[0721] The server accesses various information sources such as news sites, financial data providers, and social media to obtain the latest stock investment-related data. Specifically, the server calls a news API (e.g., NewsAPI) to obtain the latest news about a company. It also uses the financial data provider's API (e.g., Alpha Vantage or Yahoo Finance API) to obtain market data such as stock prices and trading volume. It also obtains related post data from social media APIs (e.g., Twitter API). The input is the API endpoint, and the output is the obtained raw data.

[0722] Step 2: Data organization

[0723] The server runs the acquired raw data through natural language processing algorithms to organize the information. Specifically, the server uses Python's NLTK library to extract company names, events, and key points that affect stock prices from news articles and social media posts. For example, it extracts information from a news article that "Company A has announced a new product." The input is the acquired raw data, and the output is structured information (company names, event information, etc.). This information is stored in a database.

[0724] Step 3: Save data

[0725] The server stores the organized data in a database, for example using a relational database system such as MySQL. The input is structured information and the output is the stored data in the database.

[0726] Step 4: Analyze the positives

[0727] The server scores positive information based on the information stored in the database. Specifically, the server evaluates positive news and social media posts and quantifies their importance. For example, it may evaluate "Company A's new product announcement: importance 85%." The input is the data stored in the database, and the output is scored positive information.

[0728] Step 5: Analyze the formation

[0729] The server analyzes the overall market condition. Specifically, it evaluates the overall market trend and the situation of each sector. For example, it makes an evaluation such as "Overall market uptrend: strong." The input is market data, and the output is an evaluation result that indicates the overall market condition.

[0730] Step 6: Analyze the information

[0731] The server analyzes the trends of large investors in specific stocks. For example, it provides information such as "large buy orders are concentrated on Company A." The input is stock price and trading volume data, and the output is information on the trends of large investors.

[0732] Step 7: Technical analysis

[0733] The server analyzes stock price trends using chart patterns and trend indicators to predict future stock prices. For example, it may evaluate that "Company A's RSI is above 70, so there is a high possibility of overbuying." The input is stock price data and technical indicator data, and the output is the technical analysis results.

[0734] Step 8: Fundamental analysis

[0735] The server evaluates a company's value based on its financial data and performance forecast. For example, it provides information such as "Company A's EPS forecast is up 20% compared to the same period last year." The input is the company's financial data, and the output is the results of fundamental analysis.

[0736] Step 9: Result integration and generation

[0737] The server integrates the results of various analyses and calculates an overall score. For example, it evaluates "Company A has an overall score of 85" and generates a list of recommended stocks and a risk assessment. The input is the results of various analyses, and the output is integrated investment decision information.

[0738] Step 10: Emotion Recognition

[0739] The device analyzes the user's text and voice input to recognize their emotional state. Specifically, the device uses Python's TextBlob library to classify the emotion of the input text as "positive," "negative," or "neutral." The input is the user's text or voice data, and the output is the user's emotional state.

[0740] Step 11: Provide information

[0741] The server sends the generated investment decision information to the terminal, and the terminal adjusts the content of the information provided based on the user's emotional state. For example, if the user is in a negative emotional state, detailed risk assessments are provided and more information that gives a sense of security is displayed. If the user is in a positive emotional state, positive investment suggestions are emphasized. The input is the generated investment decision information and the user's emotional state, and the output is the optimized information content provided.

[0742] (Application example 2)

[0743] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0744] In today's world, users are required to make important decisions based on large amounts of data provided by many sources. However, making appropriate decisions can be difficult because a user's emotional state significantly influences how they interpret the data. In particular, food and delivery services require appropriate suggestions based on the user's emotions, but existing systems are unable to fully meet this need.

[0745] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0746] In this invention, the server includes means for acquiring positive factors, market conditions, speculation information, technical data, and fundamental data from various information sources, means for analyzing the acquired data, extracting necessary information, and storing it in a database, means for performing analysis for evaluation based on the stored data, means for transmitting the generated judgment information to the user's terminal, means for analyzing the user's emotions, and means for adjusting the content of the offer based on the emotion analysis results. This makes it possible to provide proposals optimized for the user's emotional state.

[0747] "Various information sources" are external sources that provide various types of information, such as news sites, data providers, and social media.

[0748] "Positive factors" are elements or information that have a positive influence on the evaluation of the event or object in question.

[0749] "Condition" refers to the overall market environment or economic situation, or a means of assessing such conditions.

[0750] "Stock manipulation information" is information about the trends and transactions of large investors in specific stocks in the market.

[0751] "Technical data" refers to data collected using technical methods, such as stock prices, trading volume, and trend indicators.

[0752] "Fundamental data" refers to data used for basic analysis, such as a company's financial information, performance, and economic indicators.

[0753] "Analysis" is the process of analyzing collected data and extracting and understanding the necessary information.

[0754] A "database" is a system or structure for systematically storing and managing information.

[0755] "Evaluation" is the act of measuring the value and quality of an object based on collected information and data.

[0756] "Judgment information" is information provided based on evaluation results to support decision-making.

[0757] "Emotion analysis" is the process of detecting a user's emotional state and analyzing that information.

[0758] "Adjusting the content provided" refers to the act of optimizing the information and suggestions displayed to users based on the analysis results.

[0759] A "terminal" is a device through which a user receives information, and examples include smartphones and tablets.

[0760] This invention is a system that provides suggestions optimized for the user's emotional state. This system consists of three elements: a server, a terminal, and a user. In addition, by combining it with an emotion engine, it is possible to analyze the user's emotions.

[0761] Hardware and software used

[0762] 1. Hardware: Smartphones, smart glasses, head-mounted displays (HMDs)

[0763] 2. Software: Facial expression recognition API (Amazon Rekognition, etc.), voice emotion analysis API (IBM Watson Tone Analyzer), natural language processing algorithms (SpaCy, NLTK), machine learning frameworks (TensorFlow, Keras)

[0764] Data collection

[0765] The server accesses various information sources such as news sites, data providers, and social media to obtain the latest relevant data. For example, it may collect the latest articles using a news API, obtain market data from a data provider's API, and collect relevant post data from social media.

[0766] Data organization

[0767] The server runs the acquired data through natural language processing algorithms (SpaCy or NLTK) to extract and organize company names, events, and impact information. For example, it extracts information from a news article such as "A certain company has announced a new product" and stores it in a database.

[0768] Analytical Processing

[0769] The server performs various analyses based on the information stored in the database. Examples of the main analysis processes are shown below.

[0770] Positive information analysis: Scores information that has a positive impact from news and social media posts and evaluates the importance of that information.

[0771] Market Analysis: Analyze overall market trends and assess the current state of the market.

[0772] Analysis of stock manipulation information: Analyze the movements of large investors in specific stocks.

[0773] Technical analysis: Analyzing stock price trends using chart patterns and trend indicators.

[0774] Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts.

[0775] Emotion analysis

[0776] The device is equipped with an emotion engine that recognizes the user's emotional state. This engine analyzes the user's facial expressions and voice to recognize positive, negative, and neutral emotions. For example, the device captures the user's facial expressions using a smartphone or HMD camera and analyzes emotions using the Amazon Rekognition API. The device uses the IBM Watson Tone Analyzer API for voice tone analysis.

[0777] Information provision

[0778] The server sends the generated judgment information to the device, and the device adjusts the information provided based on the user's emotional state analyzed by the emotion engine. For example, if the user is in a negative emotional state, detailed risk assessment information is provided and more information that gives a sense of security is displayed. If the user is in a positive emotional state, positive suggestions are emphasized.

[0779] Specific examples

[0780] Consider an example where a user launches the app at 8:00 AM and performs sentiment analysis using the device's camera. In this example, a smartphone is used. The server collects the latest articles from news sites and extracts information about specific companies using natural language processing. For example, based on the information that "a certain company has announced a new product," the probability of a stock price increase is analyzed and assessed as 70%. The generated information is sent to the device, and if the sentiment engine recognizes it as "positive," information such as "70% chance of increase due to new product announcement, risk assessment is medium" is displayed.

[0781] Prompt Sentence Examples

[0782] 1. Sentiment Analysis Prompt:

[0783] Capture facial expressions and analyze emotions.

[0784] Input image: {user's face image}

[0785] Output: Happiness, sadness, surprise, anger, etc. scores

[0786] 2. Data Collection Prompt:

[0787] Get the latest menu information from our partner data providers.

[0788] Output: Restaurant name, menu name, price, user rating, etc.

[0789] 3. Analytical Processing Prompt:

[0790] Generate optimal meal suggestions based on user sentiment data and past ordering history.

[0791] Input: Happiness score, past order history

[0792] Output: Recommended restaurant name, menu name, reason

[0793] As described above, the present invention makes it possible to provide suggestions optimized for the emotional state of the user.

[0794] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0795] Step 1: Data collection

[0796] The server accesses information sources such as news sites, data providers, and social media to obtain relevant data. It uses news APIs to obtain the latest articles, obtains market data from data provider APIs, and collects relevant post data from social media.

[0797] Input: News API, data provider API, SNS data

[0798] Output: Raw data collected

[0799] Step 2: Data organization

[0800] The server runs the collected data through natural language processing algorithms (SpaCy or NLTK) to extract company names, event information, etc., and stores them in a database. For example, this includes extracting information such as "a company has announced a new product" from a news article.

[0801] Input: Raw data collected

[0802] Output: Organized data, data stored in a database

[0803] Step 3: Emotion analysis (facial expressions)

[0804] The device captures the user's facial expressions using the smartphone or HMD camera and analyzes their emotions using the Amazon Rekognition API, generating scores such as happiness, sadness, surprise, and anger.

[0805] Input: User's face image

[0806] Output: Emotion score (happiness, sadness, surprise, anger, etc.)

[0807] Step 4: Sentiment Analysis (Audio)

[0808] The device captures the user's voice using the smartphone or HMD microphone and analyzes the voice tone using the IBM Watson Tone Analyzer API, generating a voice-based emotion score in the process.

[0809] Input: User's voice data

[0810] Output: Emotion score based on audio tone

[0811] Step 5: Data analysis

[0812] The server performs various analyses based on the information stored in the database and sentiment scores, such as positive analysis, market sentiment analysis, speculation analysis, technical analysis, and fundamental analysis, and generates related evaluations for each.

[0813] Input: Data in the database, sentiment scores

[0814] Output: Evaluation information (positive factors, market conditions, speculation information, technical analysis results, fundamental analysis results)

[0815] Step 6: Information Generation

[0816] The server integrates the results of various analyses to generate comprehensive judgment information, which is adjusted based on the results of sentiment analysis and provided in an optimized format.

[0817] Input: Evaluation information

[0818] Output: Judgment information (total score, recommendation list, risk assessment)

[0819] Step 7: Provide information

[0820] The server sends the generated judgment information to the device, which then displays the information in an appropriate format to the user. For example, if the positive emotion score is high, proactive suggestions are displayed.

[0821] Input: Judgment information

[0822] Output: Information displayed in the user interface (recommended menu, risk assessment)

[0823] Examples:

[0824] An example of a prompt sentence is the following emotion analysis prompt: "Capture an image of the user's facial expression and analyze their emotions. Input image: {user's facial image} Output: scores such as happiness, sadness, surprise, and anger."

[0825] Other examples include a data collection prompt: "Get the latest menu information from our partner data providers. Output: Restaurant name, menu name, price, user rating, etc."

[0826] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0827] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0828] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0829] [Third embodiment]

[0830] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0831] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0832] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0833] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0834] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0835] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0836] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0837] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0838] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0839] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0840] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0841] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0842] This invention is a system that collects and analyzes information related to stock investment from various sources and provides users with investment decision information. This system consists of three elements: a server, a terminal, and a user.

[0843] Data collection

[0844] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest news about a company and obtains market data such as stock prices and trading volume from the API of a financial data provider.

[0845] Data organization

[0846] The server then applies a natural language processing algorithm to the acquired data to extract and organize information such as company names, events, and information that influences stock prices. For example, information such as "Company A has announced a new product" can be extracted from a news article and stored in a database.

[0847] Analytical Processing

[0848] The server performs various analyses based on the information stored in the database.

[0849] Positive Factor Analysis: Information useful to a company is extracted from news and social media posts and scored. For example, the impact of "Company A's new product announcement" on the stock price is evaluated.

[0850] Market sentiment analysis: Analyze the overall market trend and the situation of each sector to assess the market sentiment. For example, "The overall market is in an uptrend."

[0851] Analysis of stock manipulation information: Analyzes the movements of large investors in specific stocks and detects them as stock manipulation information. For example, it provides information such as "Large buy orders are concentrated on Company A."

[0852] Technical analysis: Predicts stock price trends using chart patterns and trend indicators. For example, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0853] Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts. For example, it provides information such as "Company A's EPS forecast is increasing by 20% compared to the same period last year."

[0854] result generation

[0855] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." It also generates a recommended stock list and risk assessment based on the overall score.

[0856] Information provision

[0857] The server sends the generated investment decision information to the terminal. The terminal formats the received data and displays it to the user via a user interface. For example, the user can open the application and check information such as "Company A has a 70% chance of increasing, and its risk assessment is medium."

[0858] Specific examples

[0859] At 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, it extracts information such as "Company A announces a new product, which could lead to an increase in stock price" and stores it in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine the probability of a stock price increase as 70%. The server then adds Company A to the recommended stock list with a 70% increase probability and a "medium" risk assessment, generating a result. At 9:00 AM, the user opens the app and confirms that Company A is included in the recommended stock list. The increase probability and risk assessment are also displayed.

[0860] As described above, this system works in cooperation with three elements - server, terminal, and user - to provide important stock information every day, allowing users to make investment decisions quickly and accurately.

[0861] The processing flow will be explained below.

[0862] Step 1:

[0863] The server sends API requests to each information source to retrieve the latest data. Specifically, it retrieves corporate news from news sites, market data such as stock prices and trading volume from financial data providers, and collects related post data from social media.

[0864] Step 2:

[0865] The server analyzes the acquired data, extracts necessary information, and stores it in a database. For example, it extracts keywords that affect company names and stock prices from news articles, analyzes the tone of social media posts, and assigns positive or negative ratings.

[0866] Step 3:

[0867] The server analyzes positive factors. Specifically, it scores information that has a positive impact on the company from news and social media posts and evaluates the importance of that information. For example, it may evaluate "Company A's new product announcement: importance 85%."

[0868] Step 4:

[0869] The server analyzes the market conditions. It evaluates the overall market trend and the situation of each sector, and evaluates the current trend of the market. For example, it may evaluate the overall market as "Strong upward trend."

[0870] Step 5:

[0871] The server analyzes the stock manipulation information, tracking the movements of large investors and detecting large trades for specific stocks. For example, it extracts information such as "large buy orders are concentrated on Company A."

[0872] Step 6:

[0873] The server performs technical analysis. It analyzes stock price trends using chart patterns and trend indicators and predicts future stock prices. For example, it may evaluate that "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0874] Step 7:

[0875] The server performs fundamental analysis, assessing the future value of a company based on its financial data and performance forecasts. For example, it might say, "Company A's EPS forecast is up 20% compared to the same period last year."

[0876] Step 8:

[0877] The server aggregates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." Based on the overall score, it creates a recommended stock list and risk assessment.

[0878] Step 9:

[0879] The server transmits the generated investment decision information to the terminal, which formats the received data and displays it to the user via a user interface.

[0880] Step 10:

[0881] Users can open the application and see a list of recommended stocks and detailed analysis results, such as "Company A has a 70% chance of rising and is rated medium risk."

[0882] In this way, the server, terminals, and users work together to operate a system that provides daily important stock information.

[0883] Example 1

[0884] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0885] Conventional stock investment systems often have limited sources of information, making it difficult to provide up-to-date, comprehensive information for investment decisions. Furthermore, when analyzing data and generating investment decision information, they are limited to evaluating individual factors, lacking detailed trend analysis of the overall market or individual companies. This creates the problem of investors not being provided with enough information to make quick and accurate investment decisions, resulting in increased investment risk.

[0886] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0887] In this invention, the server includes means for acquiring accurate data, economic environment, trading information, technical indicators, and fundamental data from various information sources, means for analyzing the acquired data, extracting necessary information, and storing it in a database, and means for performing analysis to evaluate stock values ​​based on the stored data, thereby enabling the rapid provision of comprehensive and up-to-date investment decision information.

[0888] The server further includes means for performing the following analytical processes:

[0889] A method for extracting and scoring information useful to companies from news and social media posts

[0890] A means of analyzing overall market trends and sectoral conditions to assess market conditions

[0891] A method for analyzing the movements of large investors in specific stocks and detecting speculative information

[0892] A means of predicting stock price movements using chart patterns and trend indicators

[0893] A method for evaluating a company's value based on its financial data and performance forecasts

[0894] The system further includes a means for transmitting the generated investment decision information to the user's terminal, thereby enabling the user to make quick investment decisions based on the latest and most accurate information, thereby reducing investment risks.

[0895] "Accurate data" means data related to stock investments that is obtained from up-to-date and reliable sources.

[0896] The "economic environment" refers to macroeconomic conditions that affect the stock market, such as national economic policies, interest rates, exchange rates, and economic indicators.

[0897] "Trading information" refers to information such as trading data, order status, volume, and price fluctuations for the entire market or specific stocks.

[0898] "Technical indicators" are indicators or groups of indicators used in technical analysis, such as chart patterns, trend indicators, moving averages, RSI, and MACD.

[0899] "Basic data" refers to data used to evaluate a company's fundamental value, such as financial data, performance forecasts, and business plans.

[0900] "Necessary information" refers to information that can be used as the basis for reliable investment decisions, such as company names, events, and factors that affect stock prices, which are important factors in stock investment decisions.

[0901] A "database" is a system for storing acquired, analyzed, and structured data.

[0902] "Means for performing analysis" refers to the ability to evaluate stock values ​​and market trends using specific analytical algorithms and models based on stored data.

[0903] "News and social media posts" refers to information about the stock market or specific companies posted on online news sites or social media.

[0904] "Scoring" is the process of quantifying information that is useful to a company and quantitatively evaluating the extent to which it will affect the stock price.

[0905] "Market sentiment" refers to the trends and mood of the stock market as a whole or a specific sector, and is a concept that generally reflects trading trends and investor sentiment.

[0906] "Large investors" usually refer to institutional or individual investors who buy and sell large amounts of stocks, and their actions often have a major impact on the market.

[0907] A "chart pattern" is a visualization of historical price data, and is a method of predicting future price trends by analyzing specific shapes and patterns.

[0908] "Trend indicators" are indicators that show the direction of a market or a particular stock, and include moving averages and trend lines.

[0909] "Investment decision information" is information that integrates the results of various analyses and supports investment decisions, including the recommendation level and risk assessment of specific stocks, expected stock price fluctuations, etc.

[0910] "User terminal" refers to a device for receiving and displaying investment decision information, such as a smartphone, tablet, or PC.

[0911] MODE FOR CARRYING OUT THE INVENTION

[0912] This invention is a system that collects and analyzes information related to stock investment from various sources and provides users with investment decision information. This system consists of three elements: a server, a terminal, and a user.

[0913] Data collection

[0914] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest corporate news and obtains market data such as stock prices and trading volume from the financial data provider's API. Specifically, it uses NewsAPI as the news API and Alpha Vantage as the financial data provider.

[0915] Data organization

[0916] The server runs the acquired data through a natural language processing algorithm to extract and organize company names, events, and information that influences stock prices. For example, information such as "Company A has announced a new product" is extracted from a news article and stored in a database. SpaCy and NLTK are used as natural language processing algorithms, and MySQL or MongoDB are used as databases.

[0917] Analytical Processing

[0918] The server performs various analyses based on the information stored in the database, including:

[0919] 1. Analysis of positive factors: Extracting information useful to a company from news and social media posts and scoring it. For example, assessing the impact of Company A's "new product announcement" on its stock price.

[0920] 2. Market Condition Analysis: Analyze the overall market trend and evaluate the situation of each sector. For example, you might say, "The overall market is in an uptrend."

[0921] 3. Analysis of stock manipulation information: Analyzes the movements of large investors in specific stocks and detects them as stock manipulation information. For example, it generates information such as "Large buy orders are concentrated on Company A."

[0922] 4. Technical analysis: Predict stock price movements using chart patterns and trend indicators. For example, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[0923] 5. Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts. For example, providing information such as "Company A's EPS forecast is increasing by 20% compared to the same period last year."

[0924] result generation

[0925] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." It also generates a list of recommended stocks and a risk assessment based on the overall score. Specifically, it generates information such as "Risk assessment: Medium, Probability of Company A's Upturn: 70%."

[0926] Information provision

[0927] The server sends the generated investment decision information to the terminal. The terminal formats the received data and displays it to the user via a user interface (mobile app or web application). For example, the user can open the application and check information such as "Company A has a 70% chance of increasing, and its risk assessment is medium."

[0928] Specific examples

[0929] At 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, it extracts information such as "Company A announces a new product, which could lead to an increase in stock price" and stores it in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine the probability of a stock price increase as 70%. The server then adds Company A to the recommended stock list with a 70% increase probability and a "medium" risk assessment, generating a result. At 9:00 AM, the user opens the app and confirms that Company A is included in the recommended stock list. The increase probability and risk assessment are also displayed.

[0930] Examples of prompt statements

[0931] "Collect the latest news about Company A and assess its impact on the stock price."

[0932] "Analyze overall market trends and assess the situation in each sector."

[0933] "Analyze the probability of a stock price increase based on Company A's past stock price data and new product announcements."

[0934] By using this system, users can make quick investment decisions based on the latest and most accurate information, thereby reducing investment risk.

[0935] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0936] Step 1: Data collection

[0937] The server accesses various information sources, such as news sites, financial data providers, and social media.

[0938] Input: API information from news sites, financial data providers, and social media.

[0939] How it works: Collects corporate news using a news API (e.g., NewsAPI) and obtains market data such as stock prices from financial data providers (e.g., Alpha Vantage).

[0940] Output: Latest company news, stock prices, trading volume, and other data.

[0941] Step 2: Data organization

[0942] The server analyzes the collected data and runs it through natural language processing algorithms to extract information.

[0943] Input: News articles, stock price data, and social media posts obtained in Step 1.

[0944] How it works: It uses natural language processing algorithms (e.g. SpaCy, NLTK) to extract and structure company names, events, and stock price impact information.

[0945] Output: A database containing extracted company names, events, and stock price impact information.

[0946] Step 3: Analyze the positives

[0947] The server extracts information useful to companies from news and social media posts and performs scoring.

[0948] Input: News articles and social media posts formatted in Step 2.

[0949] How it works: Uses keyword extraction and scoring algorithms to evaluate useful information such as "new product launches."

[0950] Output: Positive material score for each company.

[0951] Step 4: Analyze the formation

[0952] The server analyzes the overall market and sectoral conditions to assess market sentiment.

[0953] Inputs: Market-wide and sector-specific trend data obtained in Step 1.

[0954] How it works: Uses market trend analysis algorithms to assess the sentiment of each sector.

[0955] Output: Trend assessment results for the overall market and each sector.

[0956] Step 5: Analyze the information

[0957] The server analyzes the movements of large investors in specific stocks and provides information on stock manipulation.

[0958] Input: Trade data for a specific stock obtained in Step 1.

[0959] How it works: Analyzes trading patterns of large investors to detect anomalous trading activity.

[0960] Output: Detected speculation information.

[0961] Step 6: Technical analysis

[0962] The server predicts stock price trends using chart patterns and trend indicators.

[0963] Input: Stock price data and technical indicator data obtained in Step 1.

[0964] What it does: Calculates technical indicators (e.g. RSI, MACD) and analyzes chart patterns.

[0965] Output: Stock price prediction results and technical indicator evaluation results.

[0966] Step 7: Fundamental analysis

[0967] The server evaluates the company's value based on the company's financial data and performance forecasts.

[0968] Input: Company financial data, performance forecast data.

[0969] What it does: Analyzes financial data and evaluates performance forecasts to calculate company value.

[0970] Output: Company value assessment results.

[0971] Step 8: Result Generation

[0972] The server integrates the results of the various analyses and calculates an overall score.

[0973] Input: Analysis results from steps 3 to 7.

[0974] How it works: An algorithm combines the results of each analysis to calculate an overall score.

[0975] Output: Overall score and recommended stock list.

[0976] Step 9: Provide information

[0977] The server transmits the generated investment decision information to the terminal.

[0978] Input: The overall score and recommended stock list generated in Step 8.

[0979] What it does: Formats data and converts it into a form that can be displayed through a user interface.

[0980] Output: Formatted data for displaying investment decision information.

[0981] Step 10: Display Information

[0982] The terminal displays information to the user via a user interface.

[0983] Input: Formatted data sent in step 9.

[0984] What it does: Display information to the user using an application or web interface.

[0985] Output: Displayed investment decision information.

[0986] (Application example 1)

[0987] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0988] Providing fast and accurate information for investment decisions is important in stock investment, but conventional systems are limited in the collection and analysis of information, making it difficult to comprehensively evaluate information from multiple sources. Furthermore, in the food delivery industry, evaluations based on customer reviews and sales data are not adequately conducted, and customer satisfaction and market trends are not properly reflected. To solve these problems, a system is needed that efficiently collects and analyzes data from a wide range of sources and provides accurate evaluation information.

[0989] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0990] In this invention, the server includes: means for acquiring positive factors, market conditions, speculation information, technical data, and fundamental data from various sources; means for analyzing the acquired data, extracting necessary information, and storing it in a database; and means for performing analysis to evaluate stock values ​​based on the stored data. It also includes means for collecting and analyzing customer reviews, sales data, and market trends, and means for extracting positive evaluations from customer word-of-mouth and social media. It also includes means for calculating evaluation scores and generating ranking lists based on the extracted and analyzed data. This enables information from multiple sources to be integrated, enabling accurate and prompt evaluations and recommendation information to be provided.

[0991] "Positive information" is information that has a positive impact on a company's stock price in the market.

[0992] "Market conditions" refers to information that indicates the overall market trend and the situation in each sector.

[0993] "Stock manipulation information" is information that shows the trading trends of large investors and institutional investors in specific stocks.

[0994] "Technical data" refers to analytical data based on stock price chart patterns and technical indicators.

[0995] "Fundamental data" refers to basic information based on a company's financial data and performance forecasts.

[0996] "Customer reviews" are ratings and comments from customers about restaurants and products.

[0997] "Sales data" is information that indicates the quantity and amount of sales of a restaurant or product during a specific period.

[0998] "Market trends" are data that show trends in consumer preferences and purchasing behavior.

[0999] "Social media" refers to a medium through which users share information on digital platforms such as social networking services (SNS).

[1000] A "positive rating" is information that gives a positive opinion or high rating to the subject of the rating in customer reviews or social media mentions.

[1001] The "evaluation score" is a comprehensive evaluation value calculated based on the analyzed data.

[1002] A "ranking list" is a list ranked based on evaluation scores.

[1003] The system that realizes this invention consists of three elements: a server, a terminal, and a user. Through the operation of the entire system, a wide range of data related to stock investments is collected and analyzed, as well as customer reviews and sales data in the food delivery industry.

[1004] Data collection

[1005] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest news about a company and obtains market data such as stock prices and trading volume from a financial data provider's API. For food delivery data, it obtains customer reviews from a review site API and collects mentions on social media using APIs such as Twitter.

[1006] Data organization

[1007] The server runs the collected data through natural language processing algorithms to extract and organize information that influences company names, events, and stock prices. For example, information such as "A company announced a new product" can be extracted from a news article and stored in a database. Similarly, evaluations such as "The restaurant's pizza is delicious" can be extracted from customer reviews.

[1008] Analytical Processing

[1009] The server performs various analyses based on the information stored in the database. For example, in stock investment, it analyzes positive factors, market conditions, speculation information, technical analysis, and fundamental analysis. In food delivery, it analyzes best-selling menu items based on sales data and scores items by extracting positive evaluations from customer reviews.

[1010] result generation

[1011] The server integrates the results of various analyses and calculates an overall score. Based on the overall score, it generates a list of recommended stocks and a risk assessment. In the case of food delivery, it generates a ranking list of restaurants and menus based on the assessment score.

[1012] Information provision

[1013] The server then sends the generated investment decision information and food delivery evaluation information to the device. The device then formats the received data and displays it to the user via a user interface. For example, a user can open a smartphone app to check the stock price forecast for a specific company or the evaluation score of a specific restaurant.

[1014] Hardware and software used

[1015] Hardware:

[1016] Server: High-performance server (e.g. Amazon EC2)

[1017] User devices: smartphones, smart glasses (e.g., Google Glass)

[1018] software:

[1019] Data Collection: API (e.g. Twitter API, Google Maps API)

[1020] Natural Language Processing: Python's NLTK library, spaCy

[1021] Database: MySQL, MongoDB

[1022] Results display: iOS / Android app, AR interface

[1023] Specific examples

[1024] For example, at 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. At the same time, the latest restaurant reviews are collected. Based on this data, the server calculates the probability that the company's stock price will rise and the restaurant's rating score. When a user opens the app at 9:00 AM, the company's stock price prediction and restaurant rankings are displayed.

[1025] Prompt Sentence Examples

[1026] "Describe a process for using the Twitter API to gather the latest tweets about a restaurant and then using NLP to extract positive reviews. Also show how you can use this data to calculate a restaurant rating score."

[1027] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1028] Step 1:

[1029] The server collects data related to stock investments from news sites, financial data providers, and social media. For example, it uses APIs to retrieve news articles about new product launches and stock market data for specific companies. For food delivery, it uses review site APIs and Twitter APIs to retrieve the latest customer reviews and social media mentions for specific restaurants.

[1030] Input: Data from news sites, financial data providers, social media, and review sites

[1031] Output: A set of raw data

[1032] Step 2:

[1033] The server runs the acquired raw data through a natural language processing algorithm to extract information such as company names, events, and positive reviews, and then organizes and stores it in a database. For stock investments, key points such as company names and new product announcements are extracted, and for food delivery, positive reviews of food and service are extracted from customer reviews.

[1034] Input: Raw data

[1035] Output: Extracted element data (company name, event, evaluation comment)

[1036] Step 3:

[1037] The server performs various analyses based on the element data stored in the database. In stock investment, it evaluates information by analyzing positive factors, market conditions, detecting stock manipulation information, technical analysis, and fundamental analysis. In food delivery, it scores positive ratings based on sales data and customer reviews, and calculates evaluation scores for restaurants and menus.

[1038] Input: Element data

[1039] Output: Analysis results (evaluation score, various analysis results)

[1040] Step 4:

[1041] The server integrates the results of each analysis and generates an overall evaluation score. For stock investment, it calculates the overall score and generates a list of recommended stocks and a risk assessment. For food delivery, it generates a ranking list of restaurants and menus based on the evaluation score.

[1042] Input: Analysis results

[1043] Output: Overall evaluation score, ranking list

[1044] Step 5:

[1045] The server sends the generated rating scores and ranking list to the device. The device formats the received data and displays it to the user via a user interface. The user can check stock price predictions and restaurant rating scores on their own device using a smartphone app or smart glasses.

[1046] Input: Evaluation score, ranking list

[1047] Output: Information displayed on the user's device (stock price forecast, restaurant rating score)

[1048] Prompt Sentence Examples

[1049] "Describe a process for using the Twitter API to gather the latest tweets about a restaurant and then using NLP to extract positive reviews. Also show how you can use this data to calculate a restaurant rating score."

[1050] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1051] This invention is a system that collects and analyzes information related to stock investment from various sources, recognizes the user's emotions, and provides investment decision information. This system is composed of three elements: a server, a terminal, and a user, and is characterized by the incorporation of an emotion engine.

[1052] Data collection

[1053] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investment. For example, it uses a news API to collect the latest news about a company, market data such as stock prices and trading volume from the API of a financial data provider, and related post data from social media.

[1054] Data organization

[1055] The server then applies a natural language processing algorithm to the acquired data to extract and organize information such as company names, events, and information that influences stock prices. For example, information such as "Company A has announced a new product" can be extracted from a news article and stored in a database.

[1056] Analytical Processing

[1057] The server performs various analyses based on the information stored in the database.

[1058] Positive Factor Analysis: Information from news and social media posts that has a positive impact on a company is scored and the importance of that information is evaluated. For example, an evaluation such as "Company A's new product announcement: importance 85%" is made.

[1059] Market analysis: Analyze the overall market trend and the situation of each sector to evaluate the current trend of the market. For example, evaluate the overall market upward trend as "Strong."

[1060] Analysis of stock manipulation information: Analyzes the movements of large investors in specific stocks and detects them as stock manipulation information. For example, it provides information such as "large buy orders are concentrated on Company A."

[1061] Technical analysis: Analyzes stock price trends using chart patterns and trend indicators to predict future stock prices. For example, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[1062] Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts. For example, it provides information such as "Company A's EPS forecast is increasing by 20% compared to the same period last year."

[1063] result generation

[1064] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." It also generates a recommended stock list and risk assessment based on the overall score.

[1065] Emotion Engine Functions

[1066] The device is equipped with an emotion engine that recognizes the user's emotional state. The engine analyzes the user's text and voice input to recognize positive, negative, and neutral emotions. For example, if a user types, "What will the market be like today?", the tone of the text is analyzed to assess the user's emotional state.

[1067] Information provision

[1068] The server transmits the generated investment decision information to the terminal. The terminal adjusts the content of the investment decision information provided based on the user's emotional state evaluated by the emotion engine. For example, if the user is in a negative emotional state, the terminal provides detailed risk assessments and displays more reassuring information. On the other hand, if the user is in a positive emotional state, the terminal emphasizes positive investment suggestions.

[1069] Specific examples

[1070] At 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, information such as "Company A announces a new product, which could lead to an increase in stock price" is extracted and stored in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine a 70% probability of stock price increase. The server then generates a result with a 70% probability of Company A increasing, adds Company A to a recommended stock list, and assigns a "medium" risk assessment. At 9:00 AM, the user opens the app, and the device's emotion engine recognizes the user's emotional state as "positive." As a result, investment decision information is adjusted according to the user's emotions, emphasizing aggressive investment suggestions. Information such as "Company A has a 70% chance of increasing, and its risk assessment is medium" is displayed.

[1071] As described above, this system works in conjunction with three elements - the server, the terminal, and the user - and combines the functions of the emotion engine to provide daily important stock information, allowing users to make quick and accurate investment decisions.

[1072] The processing flow will be explained below.

[1073] Step 1:

[1074] The server sends API requests to various information sources such as news sites, financial data providers, and social media to obtain the latest data. Specifically, it obtains corporate news using a news API, market data such as stock prices and trading volume from the financial data provider's API, and related post data from the social media API.

[1075] Step 2:

[1076] The server analyzes the acquired data, extracts necessary information, and stores it in a database. For example, it extracts keywords related to company names, events, and stock price impacts from news articles, analyzes the tone of social media posts, and stores positive and negative evaluations.

[1077] Step 3:

[1078] The server analyzes positive factors, scoring information from news and social media posts that has a positive impact on the company and assessing its importance. For example, it might assess "Company A's new product announcement: importance 85%."

[1079] Step 4:

[1080] The server analyzes the market conditions. It evaluates the overall market trend and the situation of each sector and evaluates the market conditions. For example, it evaluates the market condition as "Strong upward trend of the overall market."

[1081] Step 5:

[1082] The server analyzes the information on stock manipulation. It analyzes the movements of large investors and detects large transactions for specific stocks. For example, it provides information such as "large buy orders are concentrated on Company A."

[1083] Step 6:

[1084] The server performs technical analysis. It analyzes stock price trends using chart patterns and trend indicators and predicts future stock prices. For example, it may evaluate that "Company A's RSI is above 70, so there is a high possibility of overbuying."

[1085] Step 7:

[1086] The server performs fundamental analysis, evaluating the company's value based on the company's financial data and performance forecasts. For example, it may evaluate that "Company A's EPS forecast is up 20% compared to the same period last year."

[1087] Step 8:

[1088] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." Based on the overall score, it generates a list of recommended stocks and a risk assessment.

[1089] Step 9:

[1090] The server uses an emotion engine to recognize the user's emotional state. The device analyzes the user's text and voice input to determine positive, negative, or neutral emotions. For example, if a user types, "What will the market be like today?", the tone of the text is analyzed to assess the user's emotion.

[1091] Step 10:

[1092] The server transmits the generated investment decision information to the terminal, which formats the received data and displays it to the user via a user interface.

[1093] Step 11:

[1094] The device adjusts the content of investment decision information provided based on the user's emotional state. For example, if the user is in a negative emotional state, it provides detailed risk assessments and displays more reassuring information. On the other hand, if the user is in a positive emotional state, it emphasizes positive investment suggestions.

[1095] Step 12:

[1096] Users can open the application and see a list of recommended stocks and detailed analysis results, such as "Company A has a 70% chance of rising and is rated medium risk."

[1097] In this way, the server, terminals, and users work together, combining the functions of the emotion engine to provide daily important stock information, allowing users to make investment decisions quickly and accurately.

[1098] Example 2

[1099] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1100] In recent years, information in the stock market has changed very rapidly, and investors need to be able to quickly extract useful information from the vast amount of information available and make investment decisions. However, conventional systems lack the ability to provide information that takes emotional factors into account, making it difficult for investors to make rational investment decisions without being influenced by their emotions. Furthermore, there is a need for an efficient method that can automatically extract important elements such as company names and events from news articles and social media posts, and provide users with information that is appropriate for them based on the analysis results.

[1101] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring positive information, the overall market state, large-scale investment information, technical indicator data, and fundamental data from various information sources; means for analyzing the acquired information, extracting necessary information, and storing it in a database; means for performing analysis to evaluate the value of financial products based on the stored information; means for analyzing the emotional state of the user using an emotion engine; and means for transmitting the generated investment decision information to the user's terminal and adjusting the content of the information provided in accordance with the emotional state. This makes it possible to provide investment decision information that takes emotions into consideration, allowing users to make quick and rational investment decisions.

[1102] "Positive information" is information that has a positive impact on a company or the market.

[1103] "Overall market conditions" refers to information that represents the overall trends of a particular stock market and the situation of each sector.

[1104] "Large-scale investment information" is information that shows the investment trends of large investors in specific stocks.

[1105] "Technical indicator data" refers to data used to analyze stock price fluctuations using chart patterns, trend indicators, etc.

[1106] "Basic data" refers to fundamental data used to evaluate a company's value, such as a company's financial data and earnings forecasts.

[1107] An "emotion engine" is a system that analyzes a user's text and voice input and recognizes emotions such as positive, negative, and neutral.

[1108] A "natural language processing algorithm" is a technology that analyzes text data to understand human language and extract key points about company names, events, and stock price impacts.

[1109] A "database" is a collection of information that collects and stores data in an organized manner so that it can be accessed and queried efficiently at a later time.

[1110] This invention is a system that collects and analyzes information related to stock investment from various sources, recognizes the user's emotions, and provides investment decision information. This system is composed of three elements: a server, a terminal, and a user, and also has an emotion engine.

[1111] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest news about a company, obtains market data such as stock prices and trading volume from a financial data provider's API, and collects related post data from social media. This allows the server to obtain a wide range of information in real time.

[1112] The server then runs the acquired data through a natural language processing algorithm to extract and organize information that influences company names, events, and stock prices. This process uses a natural language processing library such as NLTK. For example, information such as "Company A has announced a new product" can be extracted from a news article and stored in a database. This allows for structuring and efficient storage of data.

[1113] The server then performs various analyses based on the information stored in the database. These include analysis of positive factors, analysis of the overall market state, analysis of large-scale investment information, technical analysis using technical indicators, and fundamental analysis based on basic data. For example, a Python library can be used to analyze stock price trends using chart patterns and trend indicators and predict future stock prices. An assessment could be made such as, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[1114] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85" and generate a list of recommended stocks and a risk assessment. This allows users to see comprehensive information at a glance to make investment decisions.

[1115] The device is equipped with an emotion engine that recognizes the user's emotional state. This engine analyzes the user's text and voice input and recognizes emotions such as positive, negative, and neutral. For example, using Python's TextBlob library, the engine analyzes the input text "What will the market be like today?" and recognizes the user's emotional state as "negative."

[1116] The server transmits the generated investment decision information to the terminal. The terminal adjusts the content of the investment decision information provided based on the user's emotional state evaluated by the emotion engine. For example, if the user is in a negative emotional state, the terminal provides detailed risk assessments and displays more reassuring information. On the other hand, if the user is in a positive emotional state, the terminal emphasizes positive investment suggestions.

[1117] As a specific example, at 8:00 AM, a server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, information such as "Company A's new product announcement may lead to a rise in stock price" is extracted and stored in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine the probability of a stock price rise as 70%. The server then adds Company A to the recommended stocks list with a 70% probability of an increase and a "medium" risk assessment, generating a result.

[1118] At 9:00 a.m., the user opens the app, and the device's emotion engine recognizes the user's emotional state as "positive." Therefore, investment decision information is adjusted to reflect the user's emotions, emphasizing positive investment recommendations. Information such as "Company A has a 70% chance of growth and a medium risk assessment" is displayed.

[1119] As described above, this system works in conjunction with three elements - the server, the terminal, and the user - and combines the functions of the emotion engine to provide daily stock investment information, allowing users to make quick and accurate investment decisions.

[1120] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1121] Step 1: Data collection

[1122] The server accesses various information sources such as news sites, financial data providers, and social media to obtain the latest stock investment-related data. Specifically, the server calls a news API (e.g., NewsAPI) to obtain the latest news about a company. It also uses the financial data provider's API (e.g., Alpha Vantage or Yahoo Finance API) to obtain market data such as stock prices and trading volume. It also obtains related post data from social media APIs (e.g., Twitter API). The input is the API endpoint, and the output is the obtained raw data.

[1123] Step 2: Data organization

[1124] The server runs the acquired raw data through natural language processing algorithms to organize the information. Specifically, the server uses Python's NLTK library to extract company names, events, and key points that affect stock prices from news articles and social media posts. For example, it extracts information from a news article that "Company A has announced a new product." The input is the acquired raw data, and the output is structured information (company names, event information, etc.). This information is stored in a database.

[1125] Step 3: Save data

[1126] The server stores the organized data in a database, for example using a relational database system such as MySQL. The input is structured information and the output is the stored data in the database.

[1127] Step 4: Analyze the positives

[1128] The server scores positive information based on the information stored in the database. Specifically, the server evaluates positive news and social media posts and quantifies their importance. For example, it may evaluate "Company A's new product announcement: importance 85%." The input is the data stored in the database, and the output is scored positive information.

[1129] Step 5: Analyze the formation

[1130] The server analyzes the overall market condition. Specifically, it evaluates the overall market trend and the situation of each sector. For example, it makes an evaluation such as "Overall market uptrend: strong." The input is market data, and the output is an evaluation result that indicates the overall market condition.

[1131] Step 6: Analyze the information

[1132] The server analyzes the trends of large investors in specific stocks. For example, it provides information such as "large buy orders are concentrated on Company A." The input is stock price and trading volume data, and the output is information on the trends of large investors.

[1133] Step 7: Technical analysis

[1134] The server analyzes stock price trends using chart patterns and trend indicators to predict future stock prices. For example, it may evaluate that "Company A's RSI is above 70, so there is a high possibility of overbuying." The input is stock price data and technical indicator data, and the output is the technical analysis results.

[1135] Step 8: Fundamental analysis

[1136] The server evaluates a company's value based on its financial data and performance forecast. For example, it provides information such as "Company A's EPS forecast is up 20% compared to the same period last year." The input is the company's financial data, and the output is the results of fundamental analysis.

[1137] Step 9: Result integration and generation

[1138] The server integrates the results of various analyses and calculates an overall score. For example, it evaluates "Company A has an overall score of 85" and generates a list of recommended stocks and a risk assessment. The input is the results of various analyses, and the output is integrated investment decision information.

[1139] Step 10: Emotion Recognition

[1140] The device analyzes the user's text and voice input to recognize their emotional state. Specifically, the device uses Python's TextBlob library to classify the emotion of the input text as "positive," "negative," or "neutral." The input is the user's text or voice data, and the output is the user's emotional state.

[1141] Step 11: Provide information

[1142] The server sends the generated investment decision information to the terminal, and the terminal adjusts the content of the information provided based on the user's emotional state. For example, if the user is in a negative emotional state, detailed risk assessments are provided and more information that gives a sense of security is displayed. If the user is in a positive emotional state, positive investment suggestions are emphasized. The input is the generated investment decision information and the user's emotional state, and the output is the optimized information content provided.

[1143] (Application example 2)

[1144] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1145] In today's world, users are required to make important decisions based on large amounts of data provided by many sources. However, making appropriate decisions can be difficult because a user's emotional state significantly influences how they interpret the data. In particular, food and delivery services require appropriate suggestions based on the user's emotions, but existing systems are unable to fully meet this need.

[1146] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1147] In this invention, the server includes means for acquiring positive factors, market conditions, speculation information, technical data, and fundamental data from various information sources, means for analyzing the acquired data, extracting necessary information, and storing it in a database, means for performing analysis for evaluation based on the stored data, means for transmitting the generated judgment information to the user's terminal, means for analyzing the user's emotions, and means for adjusting the content of the offer based on the emotion analysis results. This makes it possible to provide proposals optimized for the user's emotional state.

[1148] "Various information sources" are external sources that provide various types of information, such as news sites, data providers, and social media.

[1149] "Positive factors" are elements or information that have a positive influence on the evaluation of the event or object in question.

[1150] "Condition" refers to the overall market environment or economic situation, or a means of assessing such conditions.

[1151] "Stock manipulation information" is information about the trends and transactions of large investors in specific stocks in the market.

[1152] "Technical data" refers to data collected using technical methods, such as stock prices, trading volume, and trend indicators.

[1153] "Fundamental data" refers to data used for basic analysis, such as a company's financial information, performance, and economic indicators.

[1154] "Analysis" is the process of analyzing collected data and extracting and understanding the necessary information.

[1155] A "database" is a system or structure for systematically storing and managing information.

[1156] "Evaluation" is the act of measuring the value and quality of an object based on collected information and data.

[1157] "Judgment information" is information provided based on evaluation results to support decision-making.

[1158] "Emotion analysis" is the process of detecting a user's emotional state and analyzing that information.

[1159] "Adjusting the content provided" refers to the act of optimizing the information and suggestions displayed to users based on the analysis results.

[1160] A "terminal" is a device through which a user receives information, and examples include smartphones and tablets.

[1161] This invention is a system that provides suggestions optimized for the user's emotional state. This system consists of three elements: a server, a terminal, and a user. In addition, by combining it with an emotion engine, it is possible to analyze the user's emotions.

[1162] Hardware and software used

[1163] 1. Hardware: Smartphones, smart glasses, head-mounted displays (HMDs)

[1164] 2. Software: Facial expression recognition API (Amazon Rekognition, etc.), voice emotion analysis API (IBM Watson Tone Analyzer), natural language processing algorithms (SpaCy, NLTK), machine learning frameworks (TensorFlow, Keras)

[1165] Data collection

[1166] The server accesses various information sources such as news sites, data providers, and social media to obtain the latest relevant data. For example, it may collect the latest articles using a news API, obtain market data from a data provider's API, and collect relevant post data from social media.

[1167] Data organization

[1168] The server runs the acquired data through natural language processing algorithms (SpaCy or NLTK) to extract and organize company names, events, and impact information. For example, it extracts information from a news article such as "A certain company has announced a new product" and stores it in a database.

[1169] Analytical Processing

[1170] The server performs various analyses based on the information stored in the database. Examples of the main analysis processes are shown below.

[1171] Positive information analysis: Scores information that has a positive impact from news and social media posts and evaluates the importance of that information.

[1172] Market Analysis: Analyze overall market trends and assess the current state of the market.

[1173] Analysis of stock manipulation information: Analyze the movements of large investors in specific stocks.

[1174] Technical analysis: Analyzing stock price trends using chart patterns and trend indicators.

[1175] Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts.

[1176] Emotion analysis

[1177] The device is equipped with an emotion engine that recognizes the user's emotional state. This engine analyzes the user's facial expressions and voice to recognize positive, negative, and neutral emotions. For example, the device captures the user's facial expressions using a smartphone or HMD camera and analyzes emotions using the Amazon Rekognition API. The device uses the IBM Watson Tone Analyzer API for voice tone analysis.

[1178] Information provision

[1179] The server sends the generated judgment information to the device, and the device adjusts the information provided based on the user's emotional state analyzed by the emotion engine. For example, if the user is in a negative emotional state, detailed risk assessment information is provided and more information that gives a sense of security is displayed. If the user is in a positive emotional state, positive suggestions are emphasized.

[1180] Specific examples

[1181] Consider an example where a user launches the app at 8:00 AM and performs sentiment analysis using the device's camera. In this example, a smartphone is used. The server collects the latest articles from news sites and extracts information about specific companies using natural language processing. For example, based on the information that "a certain company has announced a new product," the probability of a stock price increase is analyzed and assessed as 70%. The generated information is sent to the device, and if the sentiment engine recognizes it as "positive," information such as "70% chance of increase due to new product announcement, risk assessment is medium" is displayed.

[1182] Prompt Sentence Examples

[1183] 1. Sentiment Analysis Prompt:

[1184] Capture facial expressions and analyze emotions.

[1185] Input image: {user's face image}

[1186] Output: Happiness, sadness, surprise, anger, etc. scores

[1187] 2. Data Collection Prompt:

[1188] Get the latest menu information from our partner data providers.

[1189] Output: Restaurant name, menu name, price, user rating, etc.

[1190] 3. Analytical Processing Prompt:

[1191] Generate optimal meal suggestions based on user sentiment data and past ordering history.

[1192] Input: Happiness score, past order history

[1193] Output: Recommended restaurant name, menu name, reason

[1194] As described above, the present invention makes it possible to provide suggestions optimized for the emotional state of the user.

[1195] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1196] Step 1: Data collection

[1197] The server accesses information sources such as news sites, data providers, and social media to obtain relevant data. It uses news APIs to obtain the latest articles, obtains market data from data provider APIs, and collects relevant post data from social media.

[1198] Input: News API, data provider API, SNS data

[1199] Output: Raw data collected

[1200] Step 2: Data organization

[1201] The server runs the collected data through natural language processing algorithms (SpaCy or NLTK) to extract company names, event information, etc., and stores them in a database. For example, this includes extracting information such as "a company has announced a new product" from a news article.

[1202] Input: Raw data collected

[1203] Output: Organized data, data stored in a database

[1204] Step 3: Emotion analysis (facial expressions)

[1205] The device captures the user's facial expressions using the smartphone or HMD camera and analyzes their emotions using the Amazon Rekognition API, generating scores such as happiness, sadness, surprise, and anger.

[1206] Input: User's face image

[1207] Output: Emotion score (happiness, sadness, surprise, anger, etc.)

[1208] Step 4: Sentiment Analysis (Audio)

[1209] The device captures the user's voice using the smartphone or HMD microphone and analyzes the voice tone using the IBM Watson Tone Analyzer API, generating a voice-based emotion score in the process.

[1210] Input: User's voice data

[1211] Output: Emotion score based on audio tone

[1212] Step 5: Data analysis

[1213] The server performs various analyses based on the information stored in the database and sentiment scores, such as positive analysis, market sentiment analysis, speculation analysis, technical analysis, and fundamental analysis, and generates related evaluations for each.

[1214] Input: Data in the database, sentiment scores

[1215] Output: Evaluation information (positive factors, market conditions, speculation information, technical analysis results, fundamental analysis results)

[1216] Step 6: Information Generation

[1217] The server integrates the results of various analyses to generate comprehensive judgment information, which is adjusted based on the results of sentiment analysis and provided in an optimized format.

[1218] Input: Evaluation information

[1219] Output: Judgment information (total score, recommendation list, risk assessment)

[1220] Step 7: Provide information

[1221] The server sends the generated judgment information to the device, which then displays the information in an appropriate format to the user. For example, if the positive emotion score is high, proactive suggestions are displayed.

[1222] Input: Judgment information

[1223] Output: Information displayed in the user interface (recommended menu, risk assessment)

[1224] Examples:

[1225] An example of a prompt sentence is the following emotion analysis prompt: "Capture an image of the user's facial expression and analyze their emotions. Input image: {user's facial image} Output: scores such as happiness, sadness, surprise, and anger."

[1226] Other examples include a data collection prompt: "Get the latest menu information from our partner data providers. Output: Restaurant name, menu name, price, user rating, etc."

[1227] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1228] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1229] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1230] [Fourth embodiment]

[1231] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1232] 7, a 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.

[1233] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1234] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1235] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1236] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1237] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1238] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1239] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1240] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1241] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1242] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1243] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1244] This invention is a system that collects and analyzes information related to stock investment from various sources and provides users with investment decision information. This system consists of three elements: a server, a terminal, and a user.

[1245] Data collection

[1246] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest news about a company and obtains market data such as stock prices and trading volume from the API of a financial data provider.

[1247] Data organization

[1248] The server then applies a natural language processing algorithm to the acquired data to extract and organize information such as company names, events, and information that influences stock prices. For example, information such as "Company A has announced a new product" can be extracted from a news article and stored in a database.

[1249] Analytical Processing

[1250] The server performs various analyses based on the information stored in the database.

[1251] Positive Factor Analysis: Information useful to a company is extracted from news and social media posts and scored. For example, the impact of "Company A's new product announcement" on the stock price is evaluated.

[1252] Market sentiment analysis: Analyze the overall market trend and the situation of each sector to assess the market sentiment. For example, "The overall market is in an uptrend."

[1253] Analysis of stock manipulation information: Analyzes the movements of large investors in specific stocks and detects them as stock manipulation information. For example, it provides information such as "Large buy orders are concentrated on Company A."

[1254] Technical analysis: Predicts stock price trends using chart patterns and trend indicators. For example, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[1255] Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts. For example, it provides information such as "Company A's EPS forecast is increasing by 20% compared to the same period last year."

[1256] result generation

[1257] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." It also generates a recommended stock list and risk assessment based on the overall score.

[1258] Information provision

[1259] The server sends the generated investment decision information to the terminal. The terminal formats the received data and displays it to the user via a user interface. For example, the user can open the application and check information such as "Company A has a 70% chance of increasing, and its risk assessment is medium."

[1260] Specific examples

[1261] At 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, it extracts information such as "Company A announces a new product, which could lead to an increase in stock price" and stores it in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine the probability of a stock price increase as 70%. The server then adds Company A to the recommended stock list with a 70% increase probability and a "medium" risk assessment, generating a result. At 9:00 AM, the user opens the app and confirms that Company A is included in the recommended stock list. The increase probability and risk assessment are also displayed.

[1262] As described above, this system works in cooperation with three elements - server, terminal, and user - to provide important stock information every day, allowing users to make investment decisions quickly and accurately.

[1263] The processing flow will be explained below.

[1264] Step 1:

[1265] The server sends API requests to each information source to retrieve the latest data. Specifically, it retrieves corporate news from news sites, market data such as stock prices and trading volume from financial data providers, and collects related post data from social media.

[1266] Step 2:

[1267] The server analyzes the acquired data, extracts necessary information, and stores it in a database. For example, it extracts keywords that affect company names and stock prices from news articles, analyzes the tone of social media posts, and assigns positive or negative ratings.

[1268] Step 3:

[1269] The server analyzes positive factors. Specifically, it scores information that has a positive impact on the company from news and social media posts and evaluates the importance of that information. For example, it may evaluate "Company A's new product announcement: importance 85%."

[1270] Step 4:

[1271] The server analyzes the market conditions. It evaluates the overall market trend and the situation of each sector, and evaluates the current trend of the market. For example, it may evaluate the overall market as "Strong upward trend."

[1272] Step 5:

[1273] The server analyzes the stock manipulation information, tracking the movements of large investors and detecting large trades for specific stocks. For example, it extracts information such as "large buy orders are concentrated on Company A."

[1274] Step 6:

[1275] The server performs technical analysis. It analyzes stock price trends using chart patterns and trend indicators and predicts future stock prices. For example, it may evaluate that "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[1276] Step 7:

[1277] The server performs fundamental analysis, assessing the future value of a company based on its financial data and performance forecasts. For example, it might say, "Company A's EPS forecast is up 20% compared to the same period last year."

[1278] Step 8:

[1279] The server aggregates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." Based on the overall score, it creates a recommended stock list and risk assessment.

[1280] Step 9:

[1281] The server transmits the generated investment decision information to the terminal, which formats the received data and displays it to the user via a user interface.

[1282] Step 10:

[1283] Users can open the application and see a list of recommended stocks and detailed analysis results, such as "Company A has a 70% chance of rising and is rated medium risk."

[1284] In this way, the server, terminals, and users work together to operate a system that provides daily important stock information.

[1285] Example 1

[1286] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1287] Conventional stock investment systems often have limited sources of information, making it difficult to provide up-to-date, comprehensive information for investment decisions. Furthermore, when analyzing data and generating investment decision information, they are limited to evaluating individual factors, lacking detailed trend analysis of the overall market or individual companies. This creates the problem of investors not being provided with enough information to make quick and accurate investment decisions, resulting in increased investment risk.

[1288] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1289] In this invention, the server includes means for acquiring accurate data, economic environment, trading information, technical indicators, and fundamental data from various information sources, means for analyzing the acquired data, extracting necessary information, and storing it in a database, and means for performing analysis to evaluate stock values ​​based on the stored data, thereby enabling the rapid provision of comprehensive and up-to-date investment decision information.

[1290] The server further includes means for performing the following analytical processes:

[1291] A method for extracting and scoring information useful to companies from news and social media posts

[1292] A means of analyzing overall market trends and sectoral conditions to assess market conditions

[1293] A method for analyzing the movements of large investors in specific stocks and detecting speculative information

[1294] A means of predicting stock price movements using chart patterns and trend indicators

[1295] A method for evaluating a company's value based on its financial data and performance forecasts

[1296] The system further includes a means for transmitting the generated investment decision information to the user's terminal, thereby enabling the user to make quick investment decisions based on the latest and most accurate information, thereby reducing investment risks.

[1297] "Accurate data" means data related to stock investments that is obtained from up-to-date and reliable sources.

[1298] The "economic environment" refers to macroeconomic conditions that affect the stock market, such as national economic policies, interest rates, exchange rates, and economic indicators.

[1299] "Trading information" refers to information such as trading data, order status, volume, and price fluctuations for the entire market or specific stocks.

[1300] "Technical indicators" are indicators or groups of indicators used in technical analysis, such as chart patterns, trend indicators, moving averages, RSI, and MACD.

[1301] "Basic data" refers to data used to evaluate a company's fundamental value, such as financial data, performance forecasts, and business plans.

[1302] "Necessary information" refers to information that can be used as the basis for reliable investment decisions, such as company names, events, and factors that affect stock prices, which are important factors in stock investment decisions.

[1303] A "database" is a system for storing acquired, analyzed, and structured data.

[1304] "Means for performing analysis" refers to the ability to evaluate stock values ​​and market trends using specific analytical algorithms and models based on stored data.

[1305] "News and social media posts" refers to information about the stock market or specific companies posted on online news sites or social media.

[1306] "Scoring" is the process of quantifying information that is useful to a company and quantitatively evaluating the extent to which it will affect the stock price.

[1307] "Market sentiment" refers to the trends and mood of the stock market as a whole or a specific sector, and is a concept that generally reflects trading trends and investor sentiment.

[1308] "Large investors" usually refer to institutional or individual investors who buy and sell large amounts of stocks, and their actions often have a major impact on the market.

[1309] A "chart pattern" is a visualization of historical price data, and is a method of predicting future price trends by analyzing specific shapes and patterns.

[1310] "Trend indicators" are indicators that show the direction of a market or a particular stock, and include moving averages and trend lines.

[1311] "Investment decision information" is information that integrates the results of various analyses and supports investment decisions, including the recommendation level and risk assessment of specific stocks, expected stock price fluctuations, etc.

[1312] "User terminal" refers to a device for receiving and displaying investment decision information, such as a smartphone, tablet, or PC.

[1313] MODE FOR CARRYING OUT THE INVENTION

[1314] This invention is a system that collects and analyzes information related to stock investment from various sources and provides users with investment decision information. This system consists of three elements: a server, a terminal, and a user.

[1315] Data collection

[1316] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest corporate news and obtains market data such as stock prices and trading volume from the financial data provider's API. Specifically, it uses NewsAPI as the news API and Alpha Vantage as the financial data provider.

[1317] Data organization

[1318] The server runs the acquired data through a natural language processing algorithm to extract and organize company names, events, and information that influences stock prices. For example, information such as "Company A has announced a new product" is extracted from a news article and stored in a database. SpaCy and NLTK are used as natural language processing algorithms, and MySQL or MongoDB are used as databases.

[1319] Analytical Processing

[1320] The server performs various analyses based on the information stored in the database, including:

[1321] 1. Analysis of positive factors: Extracting information useful to a company from news and social media posts and scoring it. For example, assessing the impact of Company A's "new product announcement" on its stock price.

[1322] 2. Market Condition Analysis: Analyze the overall market trend and evaluate the situation of each sector. For example, you might say, "The overall market is in an uptrend."

[1323] 3. Analysis of stock manipulation information: Analyzes the movements of large investors in specific stocks and detects them as stock manipulation information. For example, it generates information such as "Large buy orders are concentrated on Company A."

[1324] 4. Technical analysis: Predict stock price movements using chart patterns and trend indicators. For example, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[1325] 5. Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts. For example, providing information such as "Company A's EPS forecast is increasing by 20% compared to the same period last year."

[1326] result generation

[1327] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." It also generates a list of recommended stocks and a risk assessment based on the overall score. Specifically, it generates information such as "Risk assessment: Medium, Probability of Company A's Upturn: 70%."

[1328] Information provision

[1329] The server sends the generated investment decision information to the terminal. The terminal formats the received data and displays it to the user via a user interface (mobile app or web application). For example, the user can open the application and check information such as "Company A has a 70% chance of increasing, and its risk assessment is medium."

[1330] Specific examples

[1331] At 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, it extracts information such as "Company A announces a new product, which could lead to an increase in stock price" and stores it in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine the probability of a stock price increase as 70%. The server then adds Company A to the recommended stock list with a 70% increase probability and a "medium" risk assessment, generating a result. At 9:00 AM, the user opens the app and confirms that Company A is included in the recommended stock list. The increase probability and risk assessment are also displayed.

[1332] Examples of prompt statements

[1333] "Collect the latest news about Company A and assess its impact on the stock price."

[1334] "Analyze overall market trends and assess the situation in each sector."

[1335] "Analyze the probability of a stock price increase based on Company A's past stock price data and new product announcements."

[1336] By using this system, users can make quick investment decisions based on the latest and most accurate information, thereby reducing investment risk.

[1337] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1338] Step 1: Data collection

[1339] The server accesses various information sources, such as news sites, financial data providers, and social media.

[1340] Input: API information from news sites, financial data providers, and social media.

[1341] How it works: Collects corporate news using a news API (e.g., NewsAPI) and obtains market data such as stock prices from financial data providers (e.g., Alpha Vantage).

[1342] Output: Latest company news, stock prices, trading volume, and other data.

[1343] Step 2: Data organization

[1344] The server analyzes the collected data and runs it through natural language processing algorithms to extract information.

[1345] Input: News articles, stock price data, and social media posts obtained in Step 1.

[1346] How it works: It uses natural language processing algorithms (e.g. SpaCy, NLTK) to extract and structure company names, events, and stock price impact information.

[1347] Output: A database containing extracted company names, events, and stock price impact information.

[1348] Step 3: Analyze the positives

[1349] The server extracts information useful to companies from news and social media posts and performs scoring.

[1350] Input: News articles and social media posts formatted in Step 2.

[1351] How it works: Uses keyword extraction and scoring algorithms to evaluate useful information such as "new product launches."

[1352] Output: Positive material score for each company.

[1353] Step 4: Analyze the formation

[1354] The server analyzes the overall market and sectoral conditions to assess market sentiment.

[1355] Inputs: Market-wide and sector-specific trend data obtained in Step 1.

[1356] How it works: Uses market trend analysis algorithms to assess the sentiment of each sector.

[1357] Output: Trend assessment results for the overall market and each sector.

[1358] Step 5: Analyze the information

[1359] The server analyzes the movements of large investors in specific stocks and provides information on stock manipulation.

[1360] Input: Trade data for a specific stock obtained in Step 1.

[1361] How it works: Analyzes trading patterns of large investors to detect anomalous trading activity.

[1362] Output: Detected speculation information.

[1363] Step 6: Technical analysis

[1364] The server predicts stock price trends using chart patterns and trend indicators.

[1365] Input: Stock price data and technical indicator data obtained in Step 1.

[1366] What it does: Calculates technical indicators (e.g. RSI, MACD) and analyzes chart patterns.

[1367] Output: Stock price prediction results and technical indicator evaluation results.

[1368] Step 7: Fundamental analysis

[1369] The server evaluates the company's value based on the company's financial data and performance forecasts.

[1370] Input: Company financial data, performance forecast data.

[1371] What it does: Analyzes financial data and evaluates performance forecasts to calculate company value.

[1372] Output: Company value assessment results.

[1373] Step 8: Result Generation

[1374] The server integrates the results of the various analyses and calculates an overall score.

[1375] Input: Analysis results from steps 3 to 7.

[1376] How it works: An algorithm combines the results of each analysis to calculate an overall score.

[1377] Output: Overall score and recommended stock list.

[1378] Step 9: Provide information

[1379] The server transmits the generated investment decision information to the terminal.

[1380] Input: The overall score and recommended stock list generated in Step 8.

[1381] What it does: Formats data and converts it into a form that can be displayed through a user interface.

[1382] Output: Formatted data for displaying investment decision information.

[1383] Step 10: Display Information

[1384] The terminal displays information to the user via a user interface.

[1385] Input: Formatted data sent in step 9.

[1386] What it does: Display information to the user using an application or web interface.

[1387] Output: Displayed investment decision information.

[1388] (Application example 1)

[1389] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1390] Providing fast and accurate information for investment decisions is important in stock investment, but conventional systems are limited in the collection and analysis of information, making it difficult to comprehensively evaluate information from multiple sources. Furthermore, in the food delivery industry, evaluations based on customer reviews and sales data are not adequately conducted, and customer satisfaction and market trends are not properly reflected. To solve these problems, a system is needed that efficiently collects and analyzes data from a wide range of sources and provides accurate evaluation information.

[1391] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1392] In this invention, the server includes: means for acquiring positive factors, market conditions, speculation information, technical data, and fundamental data from various sources; means for analyzing the acquired data, extracting necessary information, and storing it in a database; and means for performing analysis to evaluate stock values ​​based on the stored data. It also includes means for collecting and analyzing customer reviews, sales data, and market trends, and means for extracting positive evaluations from customer word-of-mouth and social media. It also includes means for calculating evaluation scores and generating ranking lists based on the extracted and analyzed data. This enables information from multiple sources to be integrated, enabling accurate and prompt evaluations and recommendation information to be provided.

[1393] "Positive information" is information that has a positive impact on a company's stock price in the market.

[1394] "Market conditions" refers to information that indicates the overall market trend and the situation in each sector.

[1395] "Stock manipulation information" is information that shows the trading trends of large investors and institutional investors in specific stocks.

[1396] "Technical data" refers to analytical data based on stock price chart patterns and technical indicators.

[1397] "Fundamental data" refers to basic information based on a company's financial data and performance forecasts.

[1398] "Customer reviews" are ratings and comments from customers about restaurants and products.

[1399] "Sales data" is information that indicates the quantity and amount of sales of a restaurant or product during a specific period.

[1400] "Market trends" are data that show trends in consumer preferences and purchasing behavior.

[1401] "Social media" refers to a medium through which users share information on digital platforms such as social networking services (SNS).

[1402] A "positive rating" is information that gives a positive opinion or high rating to the subject of the rating in customer reviews or social media mentions.

[1403] The "evaluation score" is a comprehensive evaluation value calculated based on the analyzed data.

[1404] A "ranking list" is a list ranked based on evaluation scores.

[1405] The system that realizes this invention consists of three elements: a server, a terminal, and a user. Through the operation of the entire system, a wide range of data related to stock investments is collected and analyzed, as well as customer reviews and sales data in the food delivery industry.

[1406] Data collection

[1407] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest news about a company and obtains market data such as stock prices and trading volume from a financial data provider's API. For food delivery data, it obtains customer reviews from a review site API and collects mentions on social media using APIs such as Twitter.

[1408] Data organization

[1409] The server runs the collected data through natural language processing algorithms to extract and organize information that influences company names, events, and stock prices. For example, information such as "A company announced a new product" can be extracted from a news article and stored in a database. Similarly, evaluations such as "The restaurant's pizza is delicious" can be extracted from customer reviews.

[1410] Analytical Processing

[1411] The server performs various analyses based on the information stored in the database. For example, in stock investment, it analyzes positive factors, market conditions, speculation information, technical analysis, and fundamental analysis. In food delivery, it analyzes best-selling menu items based on sales data and scores items by extracting positive evaluations from customer reviews.

[1412] result generation

[1413] The server integrates the results of various analyses and calculates an overall score. Based on the overall score, it generates a list of recommended stocks and a risk assessment. In the case of food delivery, it generates a ranking list of restaurants and menus based on the assessment score.

[1414] Information provision

[1415] The server then sends the generated investment decision information and food delivery evaluation information to the device. The device then formats the received data and displays it to the user via a user interface. For example, a user can open a smartphone app to check the stock price forecast for a specific company or the evaluation score of a specific restaurant.

[1416] Hardware and software used

[1417] Hardware:

[1418] Server: High-performance server (e.g. Amazon EC2)

[1419] User devices: smartphones, smart glasses (e.g., Google Glass)

[1420] software:

[1421] Data Collection: API (e.g. Twitter API, Google Maps API)

[1422] Natural Language Processing: Python's NLTK library, spaCy

[1423] Database: MySQL, MongoDB

[1424] Results display: iOS / Android app, AR interface

[1425] Specific examples

[1426] For example, at 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. At the same time, the latest restaurant reviews are collected. Based on this data, the server calculates the probability that the company's stock price will rise and the restaurant's rating score. When a user opens the app at 9:00 AM, the company's stock price prediction and restaurant rankings are displayed.

[1427] Prompt Sentence Examples

[1428] "Describe a process for using the Twitter API to gather the latest tweets about a restaurant and then using NLP to extract positive reviews. Also show how you can use this data to calculate a restaurant rating score."

[1429] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1430] Step 1:

[1431] The server collects data related to stock investments from news sites, financial data providers, and social media. For example, it uses APIs to retrieve news articles about new product launches and stock market data for specific companies. For food delivery, it uses review site APIs and Twitter APIs to retrieve the latest customer reviews and social media mentions for specific restaurants.

[1432] Input: Data from news sites, financial data providers, social media, and review sites

[1433] Output: A set of raw data

[1434] Step 2:

[1435] The server runs the acquired raw data through a natural language processing algorithm to extract information such as company names, events, and positive reviews, and then organizes and stores it in a database. For stock investments, key points such as company names and new product announcements are extracted, and for food delivery, positive reviews of food and service are extracted from customer reviews.

[1436] Input: Raw data

[1437] Output: Extracted element data (company name, event, evaluation comment)

[1438] Step 3:

[1439] The server performs various analyses based on the element data stored in the database. In stock investment, it evaluates information by analyzing positive factors, market conditions, detecting stock manipulation information, technical analysis, and fundamental analysis. In food delivery, it scores positive ratings based on sales data and customer reviews, and calculates evaluation scores for restaurants and menus.

[1440] Input: Element data

[1441] Output: Analysis results (evaluation score, various analysis results)

[1442] Step 4:

[1443] The server integrates the results of each analysis and generates an overall evaluation score. For stock investment, it calculates the overall score and generates a list of recommended stocks and a risk assessment. For food delivery, it generates a ranking list of restaurants and menus based on the evaluation score.

[1444] Input: Analysis results

[1445] Output: Overall evaluation score, ranking list

[1446] Step 5:

[1447] The server sends the generated rating scores and ranking list to the device. The device formats the received data and displays it to the user via a user interface. The user can check stock price predictions and restaurant rating scores on their own device using a smartphone app or smart glasses.

[1448] Input: Evaluation score, ranking list

[1449] Output: Information displayed on the user's device (stock price forecast, restaurant rating score)

[1450] Prompt Sentence Examples

[1451] "Describe a process for using the Twitter API to gather the latest tweets about a restaurant and then using NLP to extract positive reviews. Also show how you can use this data to calculate a restaurant rating score."

[1452] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1453] This invention is a system that collects and analyzes information related to stock investment from various sources, recognizes the user's emotions, and provides investment decision information. This system is composed of three elements: a server, a terminal, and a user, and is characterized by the incorporation of an emotion engine.

[1454] Data collection

[1455] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investment. For example, it uses a news API to collect the latest news about a company, market data such as stock prices and trading volume from the API of a financial data provider, and related post data from social media.

[1456] Data organization

[1457] The server then applies a natural language processing algorithm to the acquired data to extract and organize information such as company names, events, and information that influences stock prices. For example, information such as "Company A has announced a new product" can be extracted from a news article and stored in a database.

[1458] Analytical Processing

[1459] The server performs various analyses based on the information stored in the database.

[1460] Positive Factor Analysis: Information from news and social media posts that has a positive impact on a company is scored and the importance of that information is evaluated. For example, an evaluation such as "Company A's new product announcement: importance 85%" is made.

[1461] Market analysis: Analyze the overall market trend and the situation of each sector to evaluate the current trend of the market. For example, evaluate the overall market upward trend as "Strong."

[1462] Analysis of stock manipulation information: Analyzes the movements of large investors in specific stocks and detects them as stock manipulation information. For example, it provides information such as "large buy orders are concentrated on Company A."

[1463] Technical analysis: Analyzes stock price trends using chart patterns and trend indicators to predict future stock prices. For example, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[1464] Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts. For example, it provides information such as "Company A's EPS forecast is increasing by 20% compared to the same period last year."

[1465] result generation

[1466] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." It also generates a recommended stock list and risk assessment based on the overall score.

[1467] Emotion Engine Functions

[1468] The device is equipped with an emotion engine that recognizes the user's emotional state. The engine analyzes the user's text and voice input to recognize positive, negative, and neutral emotions. For example, if a user types, "What will the market be like today?", the tone of the text is analyzed to assess the user's emotional state.

[1469] Information provision

[1470] The server transmits the generated investment decision information to the terminal. The terminal adjusts the content of the investment decision information provided based on the user's emotional state evaluated by the emotion engine. For example, if the user is in a negative emotional state, the terminal provides detailed risk assessments and displays more reassuring information. On the other hand, if the user is in a positive emotional state, the terminal emphasizes positive investment suggestions.

[1471] Specific examples

[1472] At 8:00 AM, the server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, information such as "Company A announces a new product, which could lead to an increase in stock price" is extracted and stored in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine a 70% probability of stock price increase. The server then generates a result with a 70% probability of Company A increasing, adds Company A to a recommended stock list, and assigns a "medium" risk assessment. At 9:00 AM, the user opens the app, and the device's emotion engine recognizes the user's emotional state as "positive." As a result, investment decision information is adjusted according to the user's emotions, emphasizing aggressive investment suggestions. Information such as "Company A has a 70% chance of increasing, and its risk assessment is medium" is displayed.

[1473] As described above, this system works in conjunction with three elements - the server, the terminal, and the user - and combines the functions of the emotion engine to provide daily important stock information, allowing users to make quick and accurate investment decisions.

[1474] The processing flow will be explained below.

[1475] Step 1:

[1476] The server sends API requests to various information sources such as news sites, financial data providers, and social media to obtain the latest data. Specifically, it obtains corporate news using a news API, market data such as stock prices and trading volume from the financial data provider's API, and related post data from the social media API.

[1477] Step 2:

[1478] The server analyzes the acquired data, extracts necessary information, and stores it in a database. For example, it extracts keywords related to company names, events, and stock price impacts from news articles, analyzes the tone of social media posts, and stores positive and negative evaluations.

[1479] Step 3:

[1480] The server analyzes positive factors, scoring information from news and social media posts that has a positive impact on the company and assessing its importance. For example, it might assess "Company A's new product announcement: importance 85%."

[1481] Step 4:

[1482] The server analyzes the market conditions. It evaluates the overall market trend and the situation of each sector and evaluates the market conditions. For example, it evaluates the market condition as "Strong upward trend of the overall market."

[1483] Step 5:

[1484] The server analyzes the information on stock manipulation. It analyzes the movements of large investors and detects large transactions for specific stocks. For example, it provides information such as "large buy orders are concentrated on Company A."

[1485] Step 6:

[1486] The server performs technical analysis. It analyzes stock price trends using chart patterns and trend indicators and predicts future stock prices. For example, it may evaluate that "Company A's RSI is above 70, so there is a high possibility of overbuying."

[1487] Step 7:

[1488] The server performs fundamental analysis, evaluating the company's value based on the company's financial data and performance forecasts. For example, it may evaluate that "Company A's EPS forecast is up 20% compared to the same period last year."

[1489] Step 8:

[1490] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85." Based on the overall score, it generates a list of recommended stocks and a risk assessment.

[1491] Step 9:

[1492] The server uses an emotion engine to recognize the user's emotional state. The device analyzes the user's text and voice input to determine positive, negative, or neutral emotions. For example, if a user types, "What will the market be like today?", the tone of the text is analyzed to assess the user's emotion.

[1493] Step 10:

[1494] The server transmits the generated investment decision information to the terminal, which formats the received data and displays it to the user via a user interface.

[1495] Step 11:

[1496] The device adjusts the content of investment decision information provided based on the user's emotional state. For example, if the user is in a negative emotional state, it provides detailed risk assessments and displays more reassuring information. On the other hand, if the user is in a positive emotional state, it emphasizes positive investment suggestions.

[1497] Step 12:

[1498] Users can open the application and see a list of recommended stocks and detailed analysis results, such as "Company A has a 70% chance of rising and is rated medium risk."

[1499] In this way, the server, terminals, and users work together, combining the functions of the emotion engine to provide daily important stock information, allowing users to make investment decisions quickly and accurately.

[1500] Example 2

[1501] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1502] In recent years, information in the stock market has changed very rapidly, and investors need to be able to quickly extract useful information from the vast amount of information available and make investment decisions. However, conventional systems lack the ability to provide information that takes emotional factors into account, making it difficult for investors to make rational investment decisions without being influenced by their emotions. Furthermore, there is a need for an efficient method that can automatically extract important elements such as company names and events from news articles and social media posts, and provide users with information that is appropriate for them based on the analysis results.

[1503] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring positive information, the overall market state, large-scale investment information, technical indicator data, and fundamental data from various information sources; means for analyzing the acquired information, extracting necessary information, and storing it in a database; means for performing analysis to evaluate the value of financial products based on the stored information; means for analyzing the emotional state of the user using an emotion engine; and means for transmitting the generated investment decision information to the user's terminal and adjusting the content of the information provided in accordance with the emotional state. This makes it possible to provide investment decision information that takes emotions into consideration, allowing users to make quick and rational investment decisions.

[1504] "Positive information" is information that has a positive impact on a company or the market.

[1505] "Overall market conditions" refers to information that represents the overall trends of a particular stock market and the situation of each sector.

[1506] "Large-scale investment information" is information that shows the investment trends of large investors in specific stocks.

[1507] "Technical indicator data" refers to data used to analyze stock price fluctuations using chart patterns, trend indicators, etc.

[1508] "Basic data" refers to fundamental data used to evaluate a company's value, such as a company's financial data and earnings forecasts.

[1509] An "emotion engine" is a system that analyzes a user's text and voice input and recognizes emotions such as positive, negative, and neutral.

[1510] A "natural language processing algorithm" is a technology that analyzes text data to understand human language and extract key points about company names, events, and stock price impacts.

[1511] A "database" is a collection of information that collects and stores data in an organized manner so that it can be accessed and queried efficiently at a later time.

[1512] This invention is a system that collects and analyzes information related to stock investment from various sources, recognizes the user's emotions, and provides investment decision information. This system is composed of three elements: a server, a terminal, and a user, and also has an emotion engine.

[1513] The server accesses various information sources, such as news sites, financial data providers, and social media, to obtain the latest data related to stock investments. For example, it uses a news API to collect the latest news about a company, obtains market data such as stock prices and trading volume from a financial data provider's API, and collects related post data from social media. This allows the server to obtain a wide range of information in real time.

[1514] The server then runs the acquired data through a natural language processing algorithm to extract and organize information that influences company names, events, and stock prices. This process uses a natural language processing library such as NLTK. For example, information such as "Company A has announced a new product" can be extracted from a news article and stored in a database. This allows for structuring and efficient storage of data.

[1515] The server then performs various analyses based on the information stored in the database. These include analysis of positive factors, analysis of the overall market state, analysis of large-scale investment information, technical analysis using technical indicators, and fundamental analysis based on basic data. For example, a Python library can be used to analyze stock price trends using chart patterns and trend indicators and predict future stock prices. An assessment could be made such as, "Company A's RSI is above 70, so there is a high possibility that it is overbought."

[1516] The server integrates the results of various analyses and calculates an overall score. For example, it may evaluate "Company A's overall score is 85" and generate a list of recommended stocks and a risk assessment. This allows users to see comprehensive information at a glance to make investment decisions.

[1517] The device is equipped with an emotion engine that recognizes the user's emotional state. This engine analyzes the user's text and voice input and recognizes emotions such as positive, negative, and neutral. For example, using Python's TextBlob library, the engine analyzes the input text "What will the market be like today?" and recognizes the user's emotional state as "negative."

[1518] The server transmits the generated investment decision information to the terminal. The terminal adjusts the content of the investment decision information provided based on the user's emotional state evaluated by the emotion engine. For example, if the user is in a negative emotional state, the terminal provides detailed risk assessments and displays more reassuring information. On the other hand, if the user is in a positive emotional state, the terminal emphasizes positive investment suggestions.

[1519] As a specific example, at 8:00 AM, a server collects the latest articles from news sites and uses natural language processing to extract information about specific companies. For example, information such as "Company A's new product announcement may lead to a rise in stock price" is extracted and stored in a database. Next, the server analyzes Company A's past stock price data and news about the new product announcement to determine the probability of a stock price rise as 70%. The server then adds Company A to the recommended stocks list with a 70% probability of an increase and a "medium" risk assessment, generating a result.

[1520] At 9:00 a.m., the user opens the app, and the device's emotion engine recognizes the user's emotional state as "positive." Therefore, investment decision information is adjusted to reflect the user's emotions, emphasizing positive investment recommendations. Information such as "Company A has a 70% chance of growth and a medium risk assessment" is displayed.

[1521] As described above, this system works in conjunction with three elements - the server, the terminal, and the user - and combines the functions of the emotion engine to provide daily stock investment information, allowing users to make quick and accurate investment decisions.

[1522] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1523] Step 1: Data collection

[1524] The server accesses various information sources such as news sites, financial data providers, and social media to obtain the latest stock investment-related data. Specifically, the server calls a news API (e.g., NewsAPI) to obtain the latest news about a company. It also uses the financial data provider's API (e.g., Alpha Vantage or Yahoo Finance API) to obtain market data such as stock prices and trading volume. It also obtains related post data from social media APIs (e.g., Twitter API). The input is the API endpoint, and the output is the obtained raw data.

[1525] Step 2: Data organization

[1526] The server runs the acquired raw data through natural language processing algorithms to organize the information. Specifically, the server uses Python's NLTK library to extract company names, events, and key points that affect stock prices from news articles and social media posts. For example, it extracts information from a news article that "Company A has announced a new product." The input is the acquired raw data, and the output is structured information (company names, event information, etc.). This information is stored in a database.

[1527] Step 3: Save data

[1528] The server stores the organized data in a database, for example using a relational database system such as MySQL. The input is structured information and the output is the stored data in the database.

[1529] Step 4: Analyze the positives

[1530] The server scores positive information based on the information stored in the database. Specifically, the server evaluates positive news and social media posts and quantifies their importance. For example, it may evaluate "Company A's new product announcement: importance 85%." The input is the data stored in the database, and the output is scored positive information.

[1531] Step 5: Analyze the formation

[1532] The server analyzes the overall market condition. Specifically, it evaluates the overall market trend and the situation of each sector. For example, it makes an evaluation such as "Overall market uptrend: strong." The input is market data, and the output is an evaluation result that indicates the overall market condition.

[1533] Step 6: Analyze the information

[1534] The server analyzes the trends of large investors in specific stocks. For example, it provides information such as "large buy orders are concentrated on Company A." The input is stock price and trading volume data, and the output is information on the trends of large investors.

[1535] Step 7: Technical analysis

[1536] The server analyzes stock price trends using chart patterns and trend indicators to predict future stock prices. For example, it may evaluate that "Company A's RSI is above 70, so there is a high possibility of overbuying." The input is stock price data and technical indicator data, and the output is the technical analysis results.

[1537] Step 8: Fundamental analysis

[1538] The server evaluates a company's value based on its financial data and performance forecast. For example, it provides information such as "Company A's EPS forecast is up 20% compared to the same period last year." The input is the company's financial data, and the output is the results of fundamental analysis.

[1539] Step 9: Result integration and generation

[1540] The server integrates the results of various analyses and calculates an overall score. For example, it evaluates "Company A has an overall score of 85" and generates a list of recommended stocks and a risk assessment. The input is the results of various analyses, and the output is integrated investment decision information.

[1541] Step 10: Emotion Recognition

[1542] The device analyzes the user's text and voice input to recognize their emotional state. Specifically, the device uses Python's TextBlob library to classify the emotion of the input text as "positive," "negative," or "neutral." The input is the user's text or voice data, and the output is the user's emotional state.

[1543] Step 11: Provide information

[1544] The server sends the generated investment decision information to the terminal, and the terminal adjusts the content of the information provided based on the user's emotional state. For example, if the user is in a negative emotional state, detailed risk assessments are provided and more information that gives a sense of security is displayed. If the user is in a positive emotional state, positive investment suggestions are emphasized. The input is the generated investment decision information and the user's emotional state, and the output is the optimized information content provided.

[1545] (Application example 2)

[1546] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1547] In today's world, users are required to make important decisions based on large amounts of data provided by many sources. However, making appropriate decisions can be difficult because a user's emotional state significantly influences how they interpret the data. In particular, food and delivery services require appropriate suggestions based on the user's emotions, but existing systems are unable to fully meet this need.

[1548] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1549] In this invention, the server includes means for acquiring positive factors, market conditions, speculation information, technical data, and fundamental data from various information sources, means for analyzing the acquired data, extracting necessary information, and storing it in a database, means for performing analysis for evaluation based on the stored data, means for transmitting the generated judgment information to the user's terminal, means for analyzing the user's emotions, and means for adjusting the content of the offer based on the emotion analysis results. This makes it possible to provide proposals optimized for the user's emotional state.

[1550] "Various information sources" are external sources that provide various types of information, such as news sites, data providers, and social media.

[1551] "Positive factors" are elements or information that have a positive influence on the evaluation of the event or object in question.

[1552] "Condition" refers to the overall market environment or economic situation, or a means of assessing such conditions.

[1553] "Stock manipulation information" is information about the trends and transactions of large investors in specific stocks in the market.

[1554] "Technical data" refers to data collected using technical methods, such as stock prices, trading volume, and trend indicators.

[1555] "Fundamental data" refers to data used for basic analysis, such as a company's financial information, performance, and economic indicators.

[1556] "Analysis" is the process of analyzing collected data and extracting and understanding the necessary information.

[1557] A "database" is a system or structure for systematically storing and managing information.

[1558] "Evaluation" is the act of measuring the value and quality of an object based on collected information and data.

[1559] "Judgment information" is information provided based on evaluation results to support decision-making.

[1560] "Emotion analysis" is the process of detecting a user's emotional state and analyzing that information.

[1561] "Adjusting the content provided" refers to the act of optimizing the information and suggestions displayed to users based on the analysis results.

[1562] A "terminal" is a device through which a user receives information, and examples include smartphones and tablets.

[1563] This invention is a system that provides suggestions optimized for the user's emotional state. This system consists of three elements: a server, a terminal, and a user. In addition, by combining it with an emotion engine, it is possible to analyze the user's emotions.

[1564] Hardware and software used

[1565] 1. Hardware: Smartphones, smart glasses, head-mounted displays (HMDs)

[1566] 2. Software: Facial expression recognition API (Amazon Rekognition, etc.), voice emotion analysis API (IBM Watson Tone Analyzer), natural language processing algorithms (SpaCy, NLTK), machine learning frameworks (TensorFlow, Keras)

[1567] Data collection

[1568] The server accesses various information sources such as news sites, data providers, and social media to obtain the latest relevant data. For example, it may collect the latest articles using a news API, obtain market data from a data provider's API, and collect relevant post data from social media.

[1569] Data organization

[1570] The server runs the acquired data through natural language processing algorithms (SpaCy or NLTK) to extract and organize company names, events, and impact information. For example, it extracts information from a news article such as "A certain company has announced a new product" and stores it in a database.

[1571] Analytical Processing

[1572] The server performs various analyses based on the information stored in the database. Examples of the main analysis processes are shown below.

[1573] Positive information analysis: Scores information that has a positive impact from news and social media posts and evaluates the importance of that information.

[1574] Market Analysis: Analyze overall market trends and assess the current state of the market.

[1575] Analysis of stock manipulation information: Analyze the movements of large investors in specific stocks.

[1576] Technical analysis: Analyzing stock price trends using chart patterns and trend indicators.

[1577] Fundamental analysis: Evaluating a company's value based on its financial data and performance forecasts.

[1578] Emotion analysis

[1579] The device is equipped with an emotion engine that recognizes the user's emotional state. This engine analyzes the user's facial expressions and voice to recognize positive, negative, and neutral emotions. For example, the device captures the user's facial expressions using a smartphone or HMD camera and analyzes emotions using the Amazon Rekognition API. The device uses the IBM Watson Tone Analyzer API for voice tone analysis.

[1580] Information provision

[1581] The server sends the generated judgment information to the device, and the device adjusts the information provided based on the user's emotional state analyzed by the emotion engine. For example, if the user is in a negative emotional state, detailed risk assessment information is provided and more information that gives a sense of security is displayed. If the user is in a positive emotional state, positive suggestions are emphasized.

[1582] Specific examples

[1583] Consider an example where a user launches the app at 8:00 AM and performs sentiment analysis using the device's camera. In this example, a smartphone is used. The server collects the latest articles from news sites and extracts information about specific companies using natural language processing. For example, based on the information that "a certain company has announced a new product," the probability of a stock price increase is analyzed and assessed as 70%. The generated information is sent to the device, and if the sentiment engine recognizes it as "positive," information such as "70% chance of increase due to new product announcement, risk assessment is medium" is displayed.

[1584] Prompt Sentence Examples

[1585] 1. Sentiment Analysis Prompt:

[1586] Capture facial expressions and analyze emotions.

[1587] Input image: {user's face image}

[1588] Output: Happiness, sadness, surprise, anger, etc. scores

[1589] 2. Data Collection Prompt:

[1590] Get the latest menu information from our partner data providers.

[1591] Output: Restaurant name, menu name, price, user rating, etc.

[1592] 3. Analytical Processing Prompt:

[1593] Generate optimal meal suggestions based on user sentiment data and past ordering history.

[1594] Input: Happiness score, past order history

[1595] Output: Recommended restaurant name, menu name, reason

[1596] As described above, the present invention makes it possible to provide suggestions optimized for the emotional state of the user.

[1597] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1598] Step 1: Data collection

[1599] The server accesses information sources such as news sites, data providers, and social media to obtain relevant data. It uses news APIs to obtain the latest articles, obtains market data from data provider APIs, and collects relevant post data from social media.

[1600] Input: News API, data provider API, SNS data

[1601] Output: Raw data collected

[1602] Step 2: Data organization

[1603] The server runs the collected data through natural language processing algorithms (SpaCy or NLTK) to extract company names, event information, etc., and stores them in a database. For example, this includes extracting information such as "a company has announced a new product" from a news article.

[1604] Input: Raw data collected

[1605] Output: Organized data, data stored in a database

[1606] Step 3: Emotion analysis (facial expressions)

[1607] The device captures the user's facial expressions using the smartphone or HMD camera and analyzes their emotions using the Amazon Rekognition API, generating scores such as happiness, sadness, surprise, and anger.

[1608] Input: User's face image

[1609] Output: Emotion score (happiness, sadness, surprise, anger, etc.)

[1610] Step 4: Sentiment Analysis (Audio)

[1611] The device captures the user's voice using the smartphone or HMD microphone and analyzes the voice tone using the IBM Watson Tone Analyzer API, generating a voice-based emotion score in the process.

[1612] Input: User's voice data

[1613] Output: Emotion score based on audio tone

[1614] Step 5: Data analysis

[1615] The server performs various analyses based on the information stored in the database and sentiment scores, such as positive analysis, market sentiment analysis, speculation analysis, technical analysis, and fundamental analysis, and generates related evaluations for each.

[1616] Input: Data in the database, sentiment scores

[1617] Output: Evaluation information (positive factors, market conditions, speculation information, technical analysis results, fundamental analysis results)

[1618] Step 6: Information Generation

[1619] The server integrates the results of various analyses to generate comprehensive judgment information, which is adjusted based on the results of sentiment analysis and provided in an optimized format.

[1620] Input: Evaluation information

[1621] Output: Judgment information (total score, recommendation list, risk assessment)

[1622] Step 7: Provide information

[1623] The server sends the generated judgment information to the device, which then displays the information in an appropriate format to the user. For example, if the positive emotion score is high, proactive suggestions are displayed.

[1624] Input: Judgment information

[1625] Output: Information displayed in the user interface (recommended menu, risk assessment)

[1626] Examples:

[1627] An example of a prompt sentence is the following emotion analysis prompt: "Capture an image of the user's facial expression and analyze their emotions. Input image: {user's facial image} Output: scores such as happiness, sadness, surprise, and anger."

[1628] Other examples include a data collection prompt: "Get the latest menu information from our partner data providers. Output: Restaurant name, menu name, price, user rating, etc."

[1629] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1630] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1631] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1632] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1633] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1634] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1635] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1636] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1637] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1638] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1639] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system accordin...

Claims

1. A means of obtaining positive information, market conditions, speculation information, technical data, and fundamental data from various sources; A means of analyzing the acquired data, extracting necessary information, and storing it in a database; A means for performing analysis to assess the value of stocks based on the stored data; A means for generating investment decision information based on the analysis results; means for transmitting the generated investment decision information to a user's terminal; A system including:

2. The system according to claim 1, further comprising means for accessing information sources such as news sites, financial data providers, and social networking sites.

3. 10. The system of claim 1, further comprising means for extracting key points about company names, events, and stock price impacts from news articles using natural language processing algorithms.

4. 2. The system according to claim 1, further comprising means for performing technical analysis using chart patterns and indicators.

5. 2. The system according to claim 1, further comprising means for performing fundamental analysis to evaluate financial indicators and performance forecasts of a company.

6. The system according to claim 1, further comprising means for determining the probability of increase, recommending stocks, and evaluating risk based on the analysis results.

Images