System

Abstract

A system is provided.SOLUTION: A system comprising: a data collection means for collecting trend information; a data pre-processing means for pre-processing the collected trend information; a detection means for detecting trends based on the pre-processed trend information; a correlation analysis means for analyzing correlations using the detected trend information and market data; an algorithmic trading means for automatically executing stock trades based on correlation analysis results; and a monitoring means for monitoring and verifying trade results.SELECTED DRAWING: Figure 1

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 recent years, advances in artificial intelligence (AI) technology have improved the ability to detect trends from a wide range of information. However, there are still few systems that can predict the correlation between this trend information and stock prices and automatically link it to stock trading, resulting in a lack of investment trust products in the market that are efficient and maximize profits. The purpose of this invention is to improve investment efficiency and maximize profits by accurately predicting the correlation between trend information and stock prices and automating algorithmic trading. [Means for solving the problem]

[0005] The present invention solves the above problems by providing the following means:

[0006] a data collection means for collecting trend information;

[0007] a data preprocessing means for preprocessing the collected trend information;

[0008] detection means for detecting trends based on the preprocessed trend information;

[0009] a correlation analysis means for analyzing correlations using the detected trend information and market data;

[0010] an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results;

[0011] a monitoring means for monitoring and verifying trading results;

[0012] By using a system that includes this, it is possible to accurately predict the correlation between trend information and stock prices, enabling efficient algorithmic trading that maximizes profits.

[0013] "Trending information" means current events data collected from the Internet and other sources relating to a particular topic or event.

[0014] "Data collection means" refers to methods and devices for obtaining trend information and market data.

[0015] "Data pre-processing means" refers to methods or devices for shaping and processing collected data and converting it into a format that is easy to analyze and detect.

[0016] "Trend detection means" means a method or device for analyzing pre-processed data to discover and classify new trends or tendencies.

[0017] "Correlation analysis means" refers to a method or device for statistically analyzing the relationship between trend information and stock price data.

[0018] An "algorithmic trading tool" is a method or device for automatically buying and selling stocks based on the results of correlation analysis.

[0019] "Monitoring means" refers to methods or devices for monitoring trading results in real time and evaluating and verifying the effectiveness of transactions. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] This invention is a system that automatically executes stock buying and selling using trend information and stock price data. In this system, a server collects trend information and stock price data from various data sources, performs preprocessing, detects and predicts trends using an AI model, and executes algorithmic trading based on the results.

[0042] System Program Overview

[0043] The system is implemented by a program with the following main functions:

[0044] 1. Data Collection:

[0045] The server uses news APIs and social media APIs to collect trending information on the Internet in real time.

[0046] The server obtains stock price data from a financial market data provider and updates it in real time.

[0047] 2. Data Preprocessing:

[0048] The server preprocesses the collected trend information, removing unnecessary elements from the text data and performing tokenization and normalization.

[0049] The server also pre-processes the stock price data, standardizing and normalizing it.

[0050] 3. Trend detection and forecasting:

[0051] The server then feeds the pre-processed data into an AI model to detect trends, such as classifying a particular news article as a "hit" or "outdated."

[0052] The server uses AI models to predict future trends, allowing the impact of certain events on stock prices to be known in advance.

[0053] 4. Correlation analysis:

[0054] The server analyzes the correlation between the detected trends and stock price data and calculates how much the trends affect stock prices.

[0055] 5. Algorithmic Trading Execution:

[0056] The server generates a trading strategy based on the correlation analysis results: if the trend is positive, it generates a "buy" instruction, and if it is negative, it generates a "sell" instruction.

[0057] The server connects to the trading platform and automatically executes the generated buy and sell orders.

[0058] 6. Monitoring and Feedback:

[0059] The server monitors the performance of executed trades in real time and records the results.

[0060] The server retrains the AI ​​model based on trading results, creating a feedback loop to improve prediction accuracy.

[0061] Specific examples

[0062] Data collection and preprocessing

[0063] The server collects articles such as "Company B announces innovative new product" from the news API.

[0064] The server removes HTML tags and special characters from the collected article data and splits it into words (tokenization).

[0065] Trend detection and forecasting

[0066] The server uses the AI ​​model to determine whether a news article is a "hit" or "outdated" based on the preprocessed news article. In this example, the announcement of a new product is deemed a "hit."

[0067] The server uses past data to predict how much this "hit" will increase the stock price. For example, it predicts that "Company B's stock price will rise by 10% over the next week."

[0068] Correlation Analysis and Algorithmic Trading

[0069] The server analyzes the correlation between the trend data and stock price data and calculates the extent to which a "hit" will affect stock price increases.

[0070] Based on the analysis results, the server generates a trading instruction to "immediately buy 100 shares of Company B's stock" and executes algorithmic trading.

[0071] Monitoring and Feedback

[0072] The server monitors the stock price movement after the transaction in real time and records the actual results. For example, if the stock price actually rises by 10% after one week, it will confirm that a profit was made as a result of the transaction.

[0073] The server retrains the AI ​​model based on these trading results to further improve the accuracy of the next prediction.

[0074] In this way, this system uses trend information and stock price data to efficiently and automatically buy and sell stocks, reducing human error and enabling advanced analysis.

[0075] The processing flow will be explained below.

[0076] Step 1:

[0077] The server periodically collects trending information from the Internet using news APIs and social media APIs. For example, it accesses the APIs every hour to retrieve articles such as "Company B announces an innovative new product."

[0078] Step 2:

[0079] The server obtains real-time stock price data from a financial market data provider. For example, it periodically collects stock price information for Company B from the Yahoo Finance API and stores it in a database, including past stock price history.

[0080] Step 3:

[0081] The server stores the collected news articles and social media posts in a database, along with metadata such as article IDs and post IDs.

[0082] Step 4:

[0083] The server removes HTML tags and special characters from the collected text data, extracts only the text, and then performs tokenization to split the text into words.

[0084] Step 5:

[0085] The server also preprocesses the collected stock price data, specifically by normalizing and standardizing stock prices to scale them to a range of 0 to 1.

[0086] Step 6:

[0087] The server then feeds the preprocessed news articles into a natural language processing (NLP) model to detect trends, such as classifying them as "hit" or "outdated."

[0088] Step 7:

[0089] The server uses past trend data and stock price data to predict future trends using an AI model. For example, it generates a prediction that "Company B's new product announcement will lead to a 10% increase in stock prices within one week."

[0090] Step 8:

[0091] The server analyzes the correlation between the detected trend and stock price data, specifically by calculating the correlation coefficient and evaluating the degree of impact of the trend on stock prices.

[0092] Step 9:

[0093] The server generates a trading strategy based on the results of the correlation analysis, for example, if the trend is evaluated as "hit", it generates a "buy" instruction and sends it to the trading platform.

[0094] Step 10:

[0095] The server connects to the trading platform and automatically executes the generated buy and sell orders, for example, "Buy 100 shares of Company B" through the API.

[0096] Step 11:

[0097] The server monitors the results of executed trades in real time and evaluates performance, including profits and losses.

[0098] Step 12:

[0099] The server retrains the AI ​​model based on the monitoring results to improve prediction accuracy, thereby increasing the accuracy of trend detection and stock price predictions from the next time onwards.

[0100] In this way, the server automatically buys and sells stocks using trend information and stock price data, realizing efficient algorithmic trading.

[0101] Example 1

[0102] 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."

[0103] Conventional stock trading systems have difficulty quickly and accurately analyzing market trend information to generate trading strategies. They also lack real-time monitoring and feedback functions to respond sensitively to changes in market trends, making it difficult to improve trading accuracy. As a result, investors find it difficult to avoid the risk of losses due to human error or misjudgment.

[0104] 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.

[0105] In this invention, the server includes: a data collection means for collecting trend information including news information and social media information; a data preprocessing means for removing unnecessary elements from the collected trend information and performing tokenization and normalization; a detection means for detecting and predicting trends using an artificial intelligence model based on the preprocessed trend information; a correlation analysis means for analyzing correlations using the detected trend information and market data and calculating the impact of the trends on market movements; an algorithmic trading means for generating a trading strategy based on the correlation analysis results and automatically executing stock purchases and sales; and a monitoring means for monitoring the results of executed transactions in real time and recording and verifying the trading results. This enables fast and accurate analysis of trend information and market data and real-time automated trading.

[0106] "Data collection means" refers to a device or method for obtaining trend information, including news information and social media information, from multiple data sources on the Internet in real time.

[0107] "Data preprocessing means" refers to a device or method that removes unnecessary elements from collected trend information and performs tokenization and normalization.

[0108] "Detection means" refers to a device or method that detects and predicts trends using artificial intelligence models based on pre-processed trend information.

[0109] "Correlation analysis means" refers to a device or method that uses detected trend information and market data to analyze correlations and calculate the impact of trends on market movements.

[0110] "Algorithmic trading tools" refer to devices or methods that generate trading strategies based on correlation analysis results and automatically execute stock buying and selling.

[0111] "Monitoring means" refers to a device or method for monitoring the results of executed transactions in real time, and for recording and verifying the results of the transactions.

[0112] "Artificial intelligence model" refers to a machine learning algorithm that makes predictions and classifications based on trend information.

[0113] "Trending information" refers to information about events and topics that affect the market, gathered through news and social media.

[0114] "Market data" refers to data including price information and trading volume of stocks and other financial instruments traded in financial markets.

[0115] The present invention is a system for automatically executing stock trading using trend information and market data. In this system, a server collects trend information and market data from various data sources, performs preprocessing, detects and predicts trends using an artificial intelligence model, and executes algorithmic trading based on the results. Specific embodiments of this system are described in detail below.

[0116] Data collection

[0117] The server collects trending information on the Internet in real time using a news API (e.g., NewsAPI) or a social media API (e.g., Twitter API). For example, the server retrieves news using the URL https: / / newsapi.org / v2 / everything?q=stock market&apiKey=your_api_key and collects tweets related to the Twitter hashtag "stockmarket." The server also collects real-time stock price data using a financial market data provider (e.g., Yahoo Finance API).

[0118] Data Preprocessing

[0119] The server removes unnecessary elements (e.g., HTML tags and special characters) from the collected trend information and performs tokenization and normalization. For example, the sentence "Company B announced an innovative new product" is tokenized as "Company B," "innovative," "new product," and "announcement." Twitter posts are also tokenized and normalized in the same way. Furthermore, scaling is performed to standardize the collected stock price data, for example, by constraining values ​​to a range from 0 to 1.

[0120] Trend detection and forecasting

[0121] The server inputs preprocessed news articles and social media posts into an artificial intelligence model (e.g., BERT or LSTM) to detect and predict trends. As a specific example, in trend detection using news articles, an article stating "Company B has announced an innovative new product" is classified as a "hit." When making predictions, a scenario such as "Company B's stock price will rise by 10% in the next week" is generated.

[0122] Correlation analysis

[0123] The server analyzes correlations using detected trend information and past market data. For example, it calculates a correlation coefficient based on past data to see how much a trend like "new product announcement" affects stock price increases. This analysis makes it possible to evaluate which trends affect stock prices and how they affect them.

[0124] Algorithmic trading execution

[0125] The server generates a trading strategy based on the results of the correlation analysis. For example, it creates a specific trading strategy such as "Purchase 100 shares of Company B because the stock price is predicted to rise by 10%." This trading strategy is then connected to a trading platform such as the Interactive Brokers API and executed automatically.

[0126] Monitoring and Feedback

[0127] The server monitors the results of executed trades in real time, recording and verifying the results. For example, it monitors stock price movements after a trade and evaluates how accurate the predictions were. Based on these results, the AI ​​model can be retrained to improve the accuracy of future predictions.

[0128] Prompt Sentence Examples

[0129] To input trend information into the generative AI model, the server uses a prompt like this:

[0130] "Predict the impact this news will have on stock prices." The generative AI model responds to the prompt with a prediction such as, "This news could increase stock prices by 10%."

[0131] In this way, the system efficiently and automatically utilizes trend information and market data to buy and sell stocks, minimizing human error and enabling advanced analysis.

[0132] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0133] Step 1: Data collection

[0134] The server uses news and social media APIs to collect trending information on the Internet in real time. Specifically, it retrieves the latest news articles from the News API and collects posts related to a specific hashtag (e.g., stockmarket) using the Twitter API. This provides the data of the news articles and tweets retrieved as input. This data is saved in JSON format for processing in subsequent steps.

[0135] Step 2: Data Preprocessing

[0136] The server removes unnecessary elements from the collected trend information and tokenizes and normalizes the text data. This process involves, for example, removing HTML tags using BeautifulSoup and dividing sentences into tokens using NLTK. Specifically, the news article "Company B announces innovative new product" is tokenized into "Company B," "innovative," "new product," and "announcement." The input data is text information, and the output is tokenized and normalized text data. Similar processing is applied to tweets.

[0137] Step 3: Trend detection and forecasting

[0138] The server uses an artificial intelligence model (e.g., BERT or LSTM) to detect and predict trends based on the preprocessed trend information. Specifically, tokenized news articles are input into the BERT model, which classifies them as "hits" or "outdated." In this example, an article stating "Company B announced an innovative new product" is classified as a "hit." Furthermore, the LSTM model predicts that "Company B's stock price will rise by 10% over the next week." The input data is preprocessed text data, and the output is trend detection results and stock price predictions.

[0139] Step 4: Correlation analysis

[0140] The server analyzes correlations using detected trend information and past market data. Specifically, it uses Python's Pandas and Numpy libraries to align past stock price data and trend data in chronological order and calculate the correlation coefficient. For example, it calculates how much impact the trend of "new product announcements" has had on stock price increases in the past. The input data are trend data and stock price data, and the output is the correlation coefficient.

[0141] Step 5: Execute algorithmic trading

[0142] The server generates a trading strategy based on the correlation analysis results and automatically buys and sells stocks. Specifically, it generates trading instructions such as "buy 100 shares of Company B because the stock price will rise by 10%" based on the correlation coefficient and predicted trend, and actually executes the trade using the Interactive Brokers API. The input data are the correlation analysis results and predicted trend, and the output is trading instructions and execution.

[0143] Step 6: Monitoring and feedback

[0144] The server monitors the results of executed trades in real time, recording and verifying the data. Specifically, it monitors post-trade stock price movements and evaluates the profits and losses of the trades. Furthermore, it retrains the AI ​​model based on these results and makes adjustments to improve the accuracy of the next prediction. The input data are trading results and market data, and the output is trading performance data and an updated AI model.

[0145] In this way, the system efficiently and automatically utilizes trend information and market data to buy and sell stocks.

[0146] (Application example 1)

[0147] 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."

[0148] While conventional systems were able to trade stocks based on trend information and market data, they lacked a way to optimize the display position of best-selling items in virtual stores in real time. As a result, it was difficult to effectively display products that would attract consumer interest, making it difficult to maximize sales. Furthermore, there was a lack of technology to efficiently analyze market trends and inventory data and quickly reflect new trends.

[0149] 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.

[0150] In this invention, the server includes a data collection means for collecting trend information, a data preprocessing means for preprocessing the collected trend information, a detection means for detecting trends based on the preprocessed trend information, a correlation analysis means for analyzing correlations using the detected trend information and market data, an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results, a monitoring means for monitoring and verifying the buying and selling results, and an analysis means for analyzing the trend information and inventory data in real time, automatically selecting best-selling products, and adjusting their display positions within the virtual store. This makes it possible to effectively display products that attract consumers' interest and maximize sales.

[0151] "Trend information" is data collected from online news, social media, etc., that shows current market and consumer trends.

[0152] "Data collection means" refers to a means for obtaining trend information and market data in real time from multiple data sources on the Internet.

[0153] The "data preprocessing means" is a means for removing unnecessary elements from collected trend information and performing preprocessing such as tokenization and normalization.

[0154] "Detection means" means a means for detecting trends using an AI model based on pre-processed trend information.

[0155] A "correlation analysis means" is a means for analyzing the correlation between detected trend information and market data.

[0156] An "algorithmic trading tool" is a tool for automatically executing stock buying and selling based on the results of correlation analysis.

[0157] "Monitoring means" refers to a means for monitoring trading results in real time and verifying trading performance.

[0158] "Inventory data" is data that indicates the inventory status of products sold in the virtual store.

[0159] The "analysis means" is a means for analyzing trend information and inventory data in real time, automatically selecting best-selling items, and adjusting their display position within the virtual store.

[0160] System Overview

[0161] This invention provides a system that automatically selects best-selling items based on trend information and inventory data in a virtual store and optimizes their display position. The system has the following main functions:

[0162] Hardware Configuration

[0163] 1. Server: Performs data collection, pre-processing, trend detection, correlation analysis, algorithmic trading, monitoring and analysis.

[0164] 2. Client terminal: A device (smartphone, tablet, PC, etc.) through which a user accesses the virtual store.

[0165] 3. Network connection: A network for data communication between the server and client terminals.

[0166] Software Configuration

[0167] 1. Data collection method: Use news APIs and social media APIs to collect trend information in real time and obtain inventory information from the inventory database.

[0168] 2. Data preprocessing methods: Remove unnecessary elements from the collected trend information, and perform tokenization and normalization.

[0169] 3. Detection method: Based on the pre-processed trend information, trends are detected using a generative AI model.

[0170] 4. Correlation analysis method: Based on the detected trend information and market data, the correlation between them is analyzed.

[0171] 5. Algorithmic trading tools: Automatically buy and sell stocks based on correlation analysis results.

[0172] 6. Monitoring: Monitor trading results in real time and verify trading performance.

[0173] 7. Analysis method: Trend information and inventory data are analyzed in real time, and best-selling items are automatically selected and their display position within the virtual store is adjusted.

[0174] System Operation

[0175] The server collects trend information in real time from news APIs and social media APIs. For example, information such as "a new smartphone is all the rage" is collected. Stock information for the relevant product is obtained from the inventory database. This collected data is then tokenized and normalized using data preprocessing means to remove unnecessary elements.

[0176] The pre-processed data is input into the detection means, and trends are detected using a generative AI model. The detected trend information is analyzed for correlation with market data by the correlation analysis means. Based on the results of this correlation analysis, buy and sell instructions are automatically executed by the algorithmic trading means.

[0177] The monitoring means monitors and verifies the results in real time. At the same time, the analysis means analyzes trend information and inventory data in real time and automatically selects best-selling items. As a result, products that attract consumers' interest are automatically placed in prominent positions in the virtual store.

[0178] For example, based on trend information such as "A new smartphone is all the rage" obtained from a news API and inventory information from an inventory database, the smartphone is picked up as a best-selling item by the analysis method and placed in a prominent position in the virtual store.

[0179] Prompt Sentence Examples

[0180] "We collect the latest trend information from news APIs, and based on that information, we predict which products will be popular and select recommended products for the virtual store."

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1:

[0183] The server collects trending information on the Internet using news and social media APIs. It receives API responses as input and obtains raw trending information as output. This trending information includes keywords and topics that indicate consumer interest.

[0184] Step 2:

[0185] The server retrieves inventory information for products in the virtual store from the inventory database. It executes a database query as input and obtains product availability data as output. This inventory information includes the current stock quantity and price of each product.

[0186] Step 3:

[0187] The server preprocesses the collected trend information. Specifically, it removes HTML tags and special characters from the trend information, and performs tokenization and normalization. It receives raw trend information data as input and generates preprocessed, clean trend data as output.

[0188] Step 4:

[0189] The server uses a generative AI model to detect trends based on the preprocessed trend data. The clean trend data is input to the AI ​​model, and the detected trend information is output. This output is information about a trend, such as "A new smartphone is becoming all the rage."

[0190] Step 5:

[0191] The server analyzes the correlation using the detected trend information and inventory data. Specifically, it calculates the correlation coefficient based on past trend data and inventory data, and analyzes which trends affect which products. Using the detected trend information and inventory data as input, the server obtains the correlation analysis results as output.

[0192] Step 6:

[0193] The server automatically selects best-selling products based on the correlation analysis results using analytical means. Specifically, it prioritizes products with high correlation and calculates a score for those products. It uses the correlation analysis results as input and generates a list of the selected best-selling products as output.

[0194] Step 7:

[0195] The server adjusts the display position of the selected best-selling items to automatically place them in prominent positions within the virtual store. Specifically, it updates the virtual store interface so that they are displayed as recommended items on the user's device. It uses the list of selected best-selling items as input and generates the updated display content of the virtual store as output.

[0196] Step 8:

[0197] The server monitors trading results and post-product placement performance in real time and adjusts system behavior as needed. Specifically, it collects and analyzes trading performance data and sales data, and uses it to retrain the generative AI model. It uses real-time performance data as input and outputs it to adjust system behavior and update the AI ​​model.

[0198] 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.

[0199] The present invention is a system for automatically executing stock buying and selling using trend information and stock price data, and also includes an emotion engine that analyzes user emotion data to augment trading strategies. In this system, a server collects trend information and stock price data from various data sources, performs preprocessing, uses an AI model to detect and predict trends, and further uses the emotion engine to evaluate and consider the user's emotional state to execute algorithmic trading.

[0200] System Program Overview

[0201] The system is implemented by a program with the following main functions:

[0202] 1. Data Collection:

[0203] The server collects trending information from the Internet in real time through news APIs and social media APIs.

[0204] The server uses a financial market data provider service to obtain real-time stock price data.

[0205] 2. Data Preprocessing:

[0206] The server preprocesses the collected trend information, removing unnecessary elements from the text data and performing tokenization and normalization.

[0207] The server also performs preprocessing on the acquired stock price data, scaling it, etc.

[0208] 3. Trend detection and forecasting:

[0209] The server inputs the pre-processed data into an AI model to detect trends and make predictions.

[0210] For example, if the launch of a new product is evaluated as a "hit," it predicts that the stock price will rise thereafter.

[0211] 4. Correlation analysis:

[0212] The server analyzes the correlation between the trend data and the stock price data and evaluates the extent to which the trend affects the stock price.

[0213] 5. Algorithmic Trading Execution:

[0214] The server generates a trading strategy based on the correlation analysis results and automatically executes the buying and selling of stocks.

[0215] 6. Monitoring and Feedback:

[0216] The server monitors the results of executed transactions and feeds back the evaluation results to improve the AI ​​model.

[0217] 7. Emotion engine integration:

[0218] The server collects user input data and behavioral data and analyzes it using an emotion engine.

[0219] The server reinforces the evaluation of trend information based on the emotion recognition results and influences trading strategies.

[0220] Specific examples

[0221] Data collection and preprocessing

[0222] The server collects articles from the news API such as "Company C announces new innovative product."

[0223] The server removes HTML tags from this data and splits the text into words (tokenization).

[0224] Trend detection and forecasting

[0225] The server inputs the preprocessed article data into the AI ​​model and detects trends as "hits."

[0226] Based on this trend, the server predicts that Company C's stock price will rise 20% over the next week.

[0227] Correlation Analysis and Algorithmic Trading

[0228] The server analyzes the correlation between the trend and stock price data and calculates how much the "hit" trend affects stock prices.

[0229] Based on the correlation analysis results, the server generates a trading instruction to "purchase 100 shares of Company C's stock" and executes this as algorithmic trading.

[0230] Emotion engine integration

[0231] The server collects user input data (e.g., investment comments and operation logs) and analyzes it using an emotion engine.

[0232] If the user has positive feelings about the transaction, the server reflects the evaluation in the trend information.

[0233] For example, if a user comments, "This news looks very promising," this can be taken as a positive evaluation and reflected in trading strategies.

[0234] Monitoring and Feedback

[0235] The server monitors the results of the executed transactions in real time and records the data.

[0236] The server retrains the AI ​​model and emotion engine based on the monitoring results, improving prediction accuracy from next time onwards.

[0237] In this way, the system integrates trend information, stock price data, and user sentiment data to efficiently and automatically trade stocks, reducing human error and utilizing both quantitative and qualitative data to achieve more advanced forecasting and trading.

[0238] The processing flow will be explained below.

[0239] Step 1:

[0240] The server uses news and social media APIs to gather the latest trending information in real time. For example, it accesses the API every hour to retrieve articles such as "Company D announces innovative new product."

[0241] Step 2:

[0242] The server uses the API of a financial market data provider to obtain real-time stock price data. For example, it collects stock price information for Company D from the Yahoo Finance API and stores it in a database, including past stock price history.

[0243] Step 3:

[0244] The server stores the collected news articles and social media posts in a database, along with metadata such as the article ID, posting date and time, and poster ID.

[0245] Step 4:

[0246] The server removes HTML tags and special characters from the collected text data to generate clean text data, then performs tokenization to split the text into words.

[0247] Step 5:

[0248] The server performs standardization or normalization on the collected stock price data, for example, scaling the stock price data to a range of 0 to 1.

[0249] Step 6:

[0250] The server inputs preprocessed news articles and social media posts into a natural language processing (NLP) model to detect trends. For example, the article "Company D launches new product" is classified as a "hit."

[0251] Step 7:

[0252] The server analyzes past trend data and stock price data based on an AI model to predict future trends. For example, it predicts that the stock price of Company D will rise by 20% within one week following the release of a new product.

[0253] Step 8:

[0254] The server performs correlation analysis based on past trends and detected trend data, and evaluates the specific impact (correlation coefficient) that the trend has on stock prices.

[0255] Step 9:

[0256] The server generates a trading strategy based on the correlation analysis results, for example, generating a trading instruction to "immediately purchase 100 shares of Company D's stock" and sending it to the algorithmic trading platform.

[0257] Step 10:

[0258] The server executes the generated buy / sell orders through the trading platform API. For example, it issues a command to "immediately purchase 100 shares of Company D's stock" to the market.

[0259] Step 11:

[0260] The server inputs the user's input data and behavioral data into an emotion engine to analyze the user's emotions. For example, a user comment such as "This news is promising" is recognized as a positive emotion.

[0261] Step 12:

[0262] The server uses the emotion data obtained from the emotion engine to evaluate trend information. For example, if the user has positive emotions, the server strengthens the trend evaluation.

[0263] Step 13:

[0264] The server further refines the trading strategy based on the sentiment data and reflects it in the final buy / sell instructions, for example, increasing the number of shares to buy if the sentiment data is very positive.

[0265] Step 14:

[0266] The server monitors the results of executed trades in real time and records their performance data, e.g., evaluating stock price fluctuations and profits after a trade.

[0267] Step 15:

[0268] Based on the monitoring results, the server retrains the AI ​​model and emotion engine to improve prediction accuracy for future transactions. For example, if the trading results are as predicted, the reliability of the model is evaluated and further improvements are made.

[0269] In this way, the server integrates trend information, stock price data, and user emotion data to realize a system for efficient and automatic stock buying and selling.

[0270] Example 2

[0271] 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."

[0272] In the stock market, there is a demand for systems that can automatically execute highly accurate trading strategies that take into account not only trend information and market data, but also user sentiment data. However, conventional systems have difficulty integrating and utilizing this data, resulting in insufficient prediction accuracy and trading strategy flexibility. As a result, trading efficiency is lacking and human error is likely to occur.

[0273] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0274] In this invention, the server includes a data collection means for collecting trend information, a data preprocessing means for preprocessing the collected trend information and market data, a detection means for detecting and predicting trends based on the preprocessed trend information, a correlation analysis means for analyzing correlations using the detected trend information and market data, an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results, an emotion engine integration means for collecting user emotion data and using it to reinforce trading strategies, and a monitoring means for monitoring and verifying trading results. This enables a system that can automatically execute highly accurate and flexible trading strategies by integrating trend information, market data, and user emotion data.

[0275] "Trending information" refers to popular market events and topics collected from online news articles, social media posts, etc.

[0276] "Data Collection Means" means the technical means for obtaining trend information and market data in real time from multiple data sources on the Internet.

[0277] "Data Pre-processing Measures" are the processes and technical measures used to convert collected trend information and market data into a format that is easy to analyze.

[0278] "Detection methods" are technical methods that utilize AI and machine learning models to detect and predict trends based on pre-processed data.

[0279] "Correlation analysis means" refers to a technical means for analyzing correlations using detected trend information and market data.

[0280] An "algorithmic trading tool" is a technical tool for automatically executing stock buying and selling based on the results of correlation analysis.

[0281] The "emotion engine integration means" is a technical means for collecting and analyzing user emotion data and using it to reinforce trading strategies.

[0282] "Monitoring Means" means technical means for monitoring and verifying the results of executed transactions.

[0283] The present invention is a system for automatically executing stock buying and selling using trend information and stock price data, and also includes an emotion engine that analyzes user emotion data to augment trading strategies. In this system, a server collects trend information and stock price data from various data sources, performs preprocessing, uses a generative AI model to detect and predict trends, and further uses the emotion engine to evaluate and consider the user's emotional state to execute algorithmic trading.

[0284] Data collection

[0285] The server uses news APIs and social media APIs to collect trending information from the Internet. Specifically, it uses the News API and Twitter API to obtain news articles and social media posts in real time. The server also obtains real-time stock price data using a financial market data provider service (e.g., Alpha Vantage API). For example, the server uses a request URL such as "https: / / newsapi.org / v2 / everything?q=NewProduct&apiKey=your_api_key".

[0286] Data Preprocessing

[0287] The trend information collected by the server is first preprocessed. Specifically, the HTML tags of news articles are removed using Python's BeautifulSoup library, and then tokenized (divided into words) using the NLTK library. Furthermore, stock price data undergoes standardization processes such as scaling using scikit-learn's StandardScaler.

[0288] Trend detection and forecasting

[0289] The server inputs the preprocessed data into a generative AI model (e.g., an LSTM model using TENSORFLOW (registered trademark) or PyTorch) to detect trends and make predictions. For example, if "Company C announces a new product" is a trend evaluated as a "hit," the server predicts that "Company C's stock price will rise by 20% over the next week."

[0290] Correlation analysis

[0291] The server analyzes the correlation between trend data and stock price data using the pandas library. By calculating the correlation coefficient, it quantifies the impact of trend information on stock prices. For example, if the correlation coefficient between trend information and stock price data is 0.8, the server adjusts its trading strategy based on this information.

[0292] Algorithmic trading execution

[0293] Based on the correlation analysis results, the server automatically buys and sells stocks. Specifically, it executes transactions using the Interactive Brokers API or Alpaca API. For example, based on the correlation analysis results, a trading instruction to "purchase 100 shares of Company C" is generated and executed.

[0294] Monitoring and Feedback

[0295] The server monitors the results of executed transactions in real time using ElasticSearch (registered trademark) and Kibana, records the data, and retrains the AI ​​model based on the monitoring results to improve prediction accuracy for future transactions.

[0296] Emotion engine integration

[0297] The server collects user input data and behavioral data and analyzes it using the Microsoft® Text Analytics API. If a user has positive sentiment toward trading, that evaluation is reflected in trend information and influences trading strategies. For example, if a user comments, "This news looks very promising," this is taken as a positive evaluation and reflected in trading strategies.

[0298] Prompt Sentence Examples

[0299] Trend detection prompt:

[0300] Preprocess the text of the news article "Company C announces new product" into the following format:

[0301] Remove HTML tags from text

[0302] Tokenization is performed

[0303] Normalize

[0304] Input prompt for the emotion engine:

[0305] Perform sentiment analysis on the user comment "This news looks very promising" and return the result as either positive or negative.

[0306] In this way, the system integrates trend information, stock price data, and user sentiment data to efficiently and automatically trade stocks, reducing human error and utilizing both quantitative and qualitative data to achieve more advanced forecasting and trading.

[0307] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0308] Step 1: Collect data

[0309] The server collects trending information in real time using news APIs (e.g., NewsAPI) and social media APIs (e.g., Twitter API). It sends HTTP requests based on user-defined keywords and receives news data and social media posts in JSON format.

[0310] Input: Search keyword, News API URL

[0311] Output: News article data and social media posts in JSON format

[0312] Step 2: Preprocessing the data

[0313] The server preprocesses the collected trend information by first removing HTML tags using the BeautifulSoup library, then tokenizing it using the NLTK library, and scaling the data using StandardScaler from scikit-learn if financial market data is available.

[0314] Input: JSON-formatted news article data, social media posts, and stock price data

[0315] Output: Preprocessed text data, scaled stock price data

[0316] Step 3: Trend detection and forecasting

[0317] The server inputs the preprocessed data into a generative AI model (e.g., an LSTM model using TensorFlow or PyTorch) to detect and predict trends. Specifically, it feeds the input data into the model and outputs trend labels (e.g., "hit" or "miss") and predicted stock price fluctuations.

[0318] Input: Preprocessed text data, scaled stock price data

[0319] Output: Trend label, predicted stock price fluctuations

[0320] Step 4: Correlation analysis

[0321] To analyze the correlation between the trend data and stock price data, the server calculates the correlation coefficient using the pandas library. Specifically, it creates a DataFrame and calculates the correlation coefficient using the corr() method.

[0322] Input: Trend label, stock price data

[0323] Output: Correlation coefficient between trend and stock price

[0324] Step 5: Execute algorithmic trading

[0325] The server automatically executes stock purchases and sales based on the correlation analysis results. It uses the Interactive Brokers API or Alpaca API to generate and execute trading instructions based on specific conditions. Specifically, it generates JSON for the trading instructions and sends them to the API.

[0326] Input: Trend and stock price correlation coefficient, predicted stock price movement

[0327] Output: Executed trading instructions

[0328] Step 6: Monitoring and feedback

[0329] The server monitors the results of executed trades in real time, stores the data in Elasticsearch, and visualizes the results using Kibana. Furthermore, the AI ​​model is retrained based on the monitoring results to improve prediction accuracy for future transactions.

[0330] Input: Result data of executed trading instructions

[0331] Output: Monitoring report, retrained AI model

[0332] Step 7: Integrating the Emotion Engine

[0333] The server collects user input data and behavioral data, analyzes the sentiment data using a sentiment analysis API (e.g., Microsoft Text Analytics API), and reinforces the trading strategy based on the results. If the user has positive sentiment, that evaluation is reflected in the trend forecast.

[0334] Input: User comments, operation log

[0335] Output: Sentiment analysis results, reinforced trading strategies

[0336] (Application example 2)

[0337] 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."

[0338] Conventional stock trading systems exist that automatically buy and sell stocks using trend information and stock price data, but they lack a mechanism to utilize user emotional data to reinforce trading strategies. As a result, inefficient trading can occur, ignoring the user's emotional state. Furthermore, there is a lack of technology to improve the customer experience in brick-and-mortar stores and realize personalized product recommendations. This makes it difficult to provide a richer user experience.

[0339] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means for collecting trend information, a data preprocessing means for preprocessing the collected trend information, a detection means for detecting trends based on the preprocessed trend information, a correlation analysis means for analyzing correlations using the detected trend information and market data, an algorithmic trading means for automatically executing stock trading based on the correlation analysis results, a monitoring means for monitoring and verifying trading results, a sentiment analysis means for analyzing user sentiment data and reinforcing trading strategies, and an information provision means for displaying on a smart device. This enables more effective and personalized trading by trading stocks while also referencing user sentiment data. Furthermore, trend information can be provided in real time using smart devices in brick-and-mortar stores, improving the user experience and providing personalized suggestions.

[0340] definition statement

[0341] "Data collection means" refers to a hardware or software input interface for acquiring predetermined data from an information source.

[0342] A "data pre-processing means" is a device or program that performs operations or processes to convert collected data into a form suitable for analysis or processing.

[0343] "Detection methods" refer to algorithms and techniques that utilize pre-processed data to find specific patterns or events.

[0344] A "correlation analysis tool" is a technique or device for calculating and analyzing the relationships and correlations between multiple data sets.

[0345] An "algorithmic trading vehicle" is a system or program for automatically buying and selling stocks based on a pre-set algorithm.

[0346] "Monitoring means" means functions or means for monitoring the status of a process or transaction during or after execution and collecting data.

[0347] "Emotion analysis means" refers to algorithms and technologies for collecting and analyzing user emotion data.

[0348] "Information providing means" refers to a device or interface that displays and provides data and analysis results to users.

[0349] A "smart device" is a device that can connect to the Internet or other networks and can collect and process information.

[0350] MODE FOR CARRYING OUT THE INVENTION

[0351] This invention is a system that uses trend information, stock price data, and user emotion data, and a specific embodiment for actually implementing the system will be described in detail.

[0352] Data collection methods

[0353] The server uses a news API to obtain trend information in real time from multiple data sources on the Internet, including various data sources such as commercial news sites and social media, and also uses a financial market data provider to obtain real-time stock price data.

[0354] Data preprocessing measures

[0355] The server performs preprocessing on the collected trend information, such as removing HTML tags, tokenizing, and normalizing. It also normalizes and scales stock price data.

[0356] Detection Method

[0357] The preprocessed data is then analyzed using a trend detection model powered by TensorFlow and Keras to detect specific trends and predict their impact on stock prices.

[0358] Correlation Analysis Tools

[0359] The server performs correlation analysis using the detected trend information and market data, which includes a technique for calculating correlation coefficients based on past trend data and stock price data.

[0360] Algorithmic Trading Instruments

[0361] Based on the results of the correlation analysis, algorithmic trading is automatically executed. Specifically, stock buy and sell instructions are generated and executed according to a pre-set trading algorithm.

[0362] Monitoring Methods

[0363] The server monitors the results of executed trades in real time and collects evaluation data, which allows the system to evaluate overall performance and optimize trading strategies.

[0364] sentiment analysis tool

[0365] It collects user input and behavioral data and analyzes it using an emotion engine, for example, to detect positive or negative emotions from voice inputs and facial expressions, which can then be used to augment trading strategies.

[0366] Information provision means

[0367] It provides information to smart devices, specifically smart glasses and mobile devices, allowing users to check trend information and stock price data in real time, and also makes personalized product recommendations based on user sentiment.

[0368] Specific examples

[0369] For example, suppose the server collects news articles about "new product announcements" from a news API, preprocesses them, and then uses an AI model to determine that they are "hits." Based on this trend, the AI ​​model predicts that the target company's stock price will rise by 20% over the next week. Furthermore, the sentiment engine analyzes the user's comment, "This news looks very promising," and determines that this is a positive reaction. This information is provided to the user in real time via smart glasses.

[0370] Examples of prompts are:

[0371] "This product is so attractive!"

[0372] To implement this invention, it is necessary to build a system that integrates the above-mentioned means, allowing users to enjoy a personalized trading experience based on trend information and stock price data.

[0373] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0374] Program processing steps

[0375] Step 1: Data collection

[0376] The server uses the news API to collect the latest trending information. Specifically, it retrieves news articles based on specific keywords and categories. At this point, the input is the keywords and categories, and the output is the retrieved news article data.

[0377] Step 2: Collect stock data

[0378] The server uses a financial market data provider to collect relevant stock price data. The input is the ticker symbol of the target company, and the output is real-time stock price data.

[0379] Step 3: Data Preprocessing

[0380] The server performs preprocessing using the retrieved news articles, such as removing HTML tags, tokenizing, and normalizing the text. The input is the retrieved news article, and the output is the preprocessed text data. In addition, it also scales the stock price data.

[0381] Step 4: Trend detection

[0382] The server inputs the preprocessed news data into an AI model (e.g., TensorFlow or Keras model) to perform trend detection and prediction. The input is the preprocessed news data, and the output is the detected trend information and its predicted value.

[0383] Step 5: Correlation analysis

[0384] The server performs correlation analysis using the detected trend information and stock price data. Specifically, it calculates the correlation coefficient from past trend data and stock price data. The input is the trend information and stock price data, and the output is the correlation coefficient.

[0385] Step 6: Algorithmic trading

[0386] The server then applies a trading algorithm based on the results of the correlation analysis to automatically execute stock purchases and sales. The input is the correlation analysis results, and the output is specific trading instructions and their execution results.

[0387] Step 7: Monitoring

[0388] The server monitors the results of executed trades in real time and collects evaluation data. The input is the results of trade execution, and the output is the evaluation data and its analysis results.

[0389] Step 8: Sentiment analysis

[0390] The server collects user input data (e.g., voice input and comments) and analyzes them using an emotion engine. The input is user comments and voice, and the output is the emotion recognition results.

[0391] Step 9: Provide information

[0392] The server provides the detected trend information and emotion analysis results to smart devices, specifically smart glasses or mobile devices. The input is the trend information and emotion recognition results, and the output is the information provided to the user.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] [Second embodiment]

[0397] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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).

[0403] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] In the smart glasses 214, 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.

[0408] 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."

[0409] This invention is a system that automatically executes stock buying and selling using trend information and stock price data. In this system, a server collects trend information and stock price data from various data sources, performs preprocessing, detects and predicts trends using an AI model, and executes algorithmic trading based on the results.

[0410] System Program Overview

[0411] The system is implemented by a program with the following main functions:

[0412] 1. Data Collection:

[0413] The server uses news APIs and social media APIs to collect trending information on the Internet in real time.

[0414] The server obtains stock price data from a financial market data provider and updates it in real time.

[0415] 2. Data Preprocessing:

[0416] The server preprocesses the collected trend information, removing unnecessary elements from the text data and performing tokenization and normalization.

[0417] The server also pre-processes the stock price data, standardizing and normalizing it.

[0418] 3. Trend detection and forecasting:

[0419] The server then feeds the pre-processed data into an AI model to detect trends, such as classifying a particular news article as a "hit" or "outdated."

[0420] The server uses AI models to predict future trends, allowing the impact of certain events on stock prices to be known in advance.

[0421] 4. Correlation analysis:

[0422] The server analyzes the correlation between the detected trends and stock price data and calculates how much the trends affect stock prices.

[0423] 5. Algorithmic Trading Execution:

[0424] The server generates a trading strategy based on the correlation analysis results: if the trend is positive, it generates a "buy" instruction, and if it is negative, it generates a "sell" instruction.

[0425] The server connects to the trading platform and automatically executes the generated buy and sell orders.

[0426] 6. Monitoring and Feedback:

[0427] The server monitors the performance of executed trades in real time and records the results.

[0428] The server retrains the AI ​​model based on trading results, creating a feedback loop to improve prediction accuracy.

[0429] Specific examples

[0430] Data collection and preprocessing

[0431] The server collects articles such as "Company B announces innovative new product" from the news API.

[0432] The server removes HTML tags and special characters from the collected article data and splits it into words (tokenization).

[0433] Trend detection and forecasting

[0434] The server uses the AI ​​model to determine whether a news article is a "hit" or "outdated" based on the preprocessed news article. In this example, the announcement of a new product is deemed a "hit."

[0435] The server uses past data to predict how much this "hit" will increase the stock price. For example, it predicts that "Company B's stock price will rise by 10% over the next week."

[0436] Correlation Analysis and Algorithmic Trading

[0437] The server analyzes the correlation between the trend data and stock price data and calculates the extent to which a "hit" will affect stock price increases.

[0438] Based on the analysis results, the server generates a trading instruction to "immediately buy 100 shares of Company B's stock" and executes algorithmic trading.

[0439] Monitoring and Feedback

[0440] The server monitors the stock price movement after the transaction in real time and records the actual results. For example, if the stock price actually rises by 10% after one week, it will confirm that a profit was made as a result of the transaction.

[0441] The server retrains the AI ​​model based on these trading results to further improve the accuracy of the next prediction.

[0442] In this way, this system uses trend information and stock price data to efficiently and automatically buy and sell stocks, reducing human error and enabling advanced analysis.

[0443] The processing flow will be explained below.

[0444] Step 1:

[0445] The server periodically collects trending information from the Internet using news APIs and social media APIs. For example, it accesses the APIs every hour to retrieve articles such as "Company B announces an innovative new product."

[0446] Step 2:

[0447] The server obtains real-time stock price data from a financial market data provider. For example, it periodically collects stock price information for Company B from the Yahoo Finance API and stores it in a database, including past stock price history.

[0448] Step 3:

[0449] The server stores the collected news articles and social media posts in a database, along with metadata such as article IDs and post IDs.

[0450] Step 4:

[0451] The server removes HTML tags and special characters from the collected text data, extracts only the text, and then performs tokenization to split the text into words.

[0452] Step 5:

[0453] The server also preprocesses the collected stock price data, specifically by normalizing and standardizing stock prices to scale them to a range of 0 to 1.

[0454] Step 6:

[0455] The server then feeds the preprocessed news articles into a natural language processing (NLP) model to detect trends, such as classifying them as "hit" or "outdated."

[0456] Step 7:

[0457] The server uses past trend data and stock price data to predict future trends using an AI model. For example, it generates a prediction that "Company B's new product announcement will lead to a 10% increase in stock prices within one week."

[0458] Step 8:

[0459] The server analyzes the correlation between the detected trend and stock price data, specifically by calculating the correlation coefficient and evaluating the degree of impact of the trend on stock prices.

[0460] Step 9:

[0461] The server generates a trading strategy based on the results of the correlation analysis, for example, if the trend is evaluated as "hit", it generates a "buy" instruction and sends it to the trading platform.

[0462] Step 10:

[0463] The server connects to the trading platform and automatically executes the generated buy and sell orders, for example, "Buy 100 shares of Company B" through the API.

[0464] Step 11:

[0465] The server monitors the results of executed trades in real time and evaluates performance, including profits and losses.

[0466] Step 12:

[0467] The server retrains the AI ​​model based on the monitoring results to improve prediction accuracy, thereby increasing the accuracy of trend detection and stock price predictions from the next time onwards.

[0468] In this way, the server automatically buys and sells stocks using trend information and stock price data, realizing efficient algorithmic trading.

[0469] Example 1

[0470] 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."

[0471] Conventional stock trading systems have difficulty quickly and accurately analyzing market trend information to generate trading strategies. They also lack real-time monitoring and feedback functions to respond sensitively to changes in market trends, making it difficult to improve trading accuracy. As a result, investors find it difficult to avoid the risk of losses due to human error or misjudgment.

[0472] 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.

[0473] In this invention, the server includes: a data collection means for collecting trend information including news information and social media information; a data preprocessing means for removing unnecessary elements from the collected trend information and performing tokenization and normalization; a detection means for detecting and predicting trends using an artificial intelligence model based on the preprocessed trend information; a correlation analysis means for analyzing correlations using the detected trend information and market data and calculating the impact of the trends on market movements; an algorithmic trading means for generating a trading strategy based on the correlation analysis results and automatically executing stock purchases and sales; and a monitoring means for monitoring the results of executed transactions in real time and recording and verifying the trading results. This enables fast and accurate analysis of trend information and market data and real-time automated trading.

[0474] "Data collection means" refers to a device or method for obtaining trend information, including news information and social media information, from multiple data sources on the Internet in real time.

[0475] "Data preprocessing means" refers to a device or method that removes unnecessary elements from collected trend information and performs tokenization and normalization.

[0476] "Detection means" refers to a device or method that detects and predicts trends using artificial intelligence models based on pre-processed trend information.

[0477] "Correlation analysis means" refers to a device or method that uses detected trend information and market data to analyze correlations and calculate the impact of trends on market movements.

[0478] "Algorithmic trading tools" refer to devices or methods that generate trading strategies based on correlation analysis results and automatically execute stock buying and selling.

[0479] "Monitoring means" refers to a device or method for monitoring the results of executed transactions in real time, and for recording and verifying the results of the transactions.

[0480] "Artificial intelligence model" refers to a machine learning algorithm that makes predictions and classifications based on trend information.

[0481] "Trending information" refers to information about events and topics that affect the market, gathered through news and social media.

[0482] "Market data" refers to data including price information and trading volume of stocks and other financial instruments traded in financial markets.

[0483] The present invention is a system for automatically executing stock trading using trend information and market data. In this system, a server collects trend information and market data from various data sources, performs preprocessing, detects and predicts trends using an artificial intelligence model, and executes algorithmic trading based on the results. Specific embodiments of this system are described in detail below.

[0484] Data collection

[0485] The server collects trending information on the Internet in real time using a news API (e.g., NewsAPI) or a social media API (e.g., Twitter API). For example, the server retrieves news using the URL https: / / newsapi.org / v2 / everything?q=stock market&apiKey=your_api_key and collects tweets related to the Twitter hashtag "stockmarket." The server also collects real-time stock price data using a financial market data provider (e.g., Yahoo Finance API).

[0486] Data Preprocessing

[0487] The server removes unnecessary elements (e.g., HTML tags and special characters) from the collected trend information and performs tokenization and normalization. For example, the sentence "Company B announced an innovative new product" is tokenized as "Company B," "innovative," "new product," and "announcement." Twitter posts are also tokenized and normalized in the same way. Furthermore, scaling is performed to standardize the collected stock price data, for example, by constraining values ​​to a range from 0 to 1.

[0488] Trend detection and forecasting

[0489] The server inputs preprocessed news articles and social media posts into an artificial intelligence model (e.g., BERT or LSTM) to detect and predict trends. As a specific example, in trend detection using news articles, an article stating "Company B has announced an innovative new product" is classified as a "hit." When making predictions, a scenario such as "Company B's stock price will rise by 10% in the next week" is generated.

[0490] Correlation analysis

[0491] The server analyzes correlations using detected trend information and past market data. For example, it calculates a correlation coefficient based on past data to see how much a trend like "new product announcement" affects stock price increases. This analysis makes it possible to evaluate which trends affect stock prices and how they affect them.

[0492] Algorithmic trading execution

[0493] The server generates a trading strategy based on the results of the correlation analysis. For example, it creates a specific trading strategy such as "Purchase 100 shares of Company B because the stock price is predicted to rise by 10%." This trading strategy is then connected to a trading platform such as the Interactive Brokers API and executed automatically.

[0494] Monitoring and Feedback

[0495] The server monitors the results of executed trades in real time, recording and verifying the results. For example, it monitors stock price movements after a trade and evaluates how accurate the predictions were. Based on these results, the AI ​​model can be retrained to improve the accuracy of future predictions.

[0496] Prompt Sentence Examples

[0497] To input trend information into the generative AI model, the server uses a prompt like this:

[0498] "Predict the impact this news will have on stock prices." The generative AI model responds to the prompt with a prediction such as, "This news could increase stock prices by 10%."

[0499] In this way, the system efficiently and automatically utilizes trend information and market data to buy and sell stocks, minimizing human error and enabling advanced analysis.

[0500] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0501] Step 1: Data collection

[0502] The server uses news and social media APIs to collect trending information on the Internet in real time. Specifically, it retrieves the latest news articles from the News API and collects posts related to a specific hashtag (e.g., stockmarket) using the Twitter API. This provides the data of the news articles and tweets retrieved as input. This data is saved in JSON format for processing in subsequent steps.

[0503] Step 2: Data Preprocessing

[0504] The server removes unnecessary elements from the collected trend information and tokenizes and normalizes the text data. This process involves, for example, removing HTML tags using BeautifulSoup and dividing sentences into tokens using NLTK. Specifically, the news article "Company B announces innovative new product" is tokenized into "Company B," "innovative," "new product," and "announcement." The input data is text information, and the output is tokenized and normalized text data. Similar processing is applied to tweets.

[0505] Step 3: Trend detection and forecasting

[0506] The server uses an artificial intelligence model (e.g., BERT or LSTM) to detect and predict trends based on the preprocessed trend information. Specifically, tokenized news articles are input into the BERT model, which classifies them as "hits" or "outdated." In this example, an article stating "Company B announced an innovative new product" is classified as a "hit." Furthermore, the LSTM model predicts that "Company B's stock price will rise by 10% over the next week." The input data is preprocessed text data, and the output is trend detection results and stock price predictions.

[0507] Step 4: Correlation analysis

[0508] The server analyzes correlations using detected trend information and past market data. Specifically, it uses Python's Pandas and Numpy libraries to align past stock price data and trend data in chronological order and calculate the correlation coefficient. For example, it calculates how much impact the trend of "new product announcements" has had on stock price increases in the past. The input data are trend data and stock price data, and the output is the correlation coefficient.

[0509] Step 5: Execute algorithmic trading

[0510] The server generates a trading strategy based on the correlation analysis results and automatically buys and sells stocks. Specifically, it generates trading instructions such as "buy 100 shares of Company B because the stock price will rise by 10%" based on the correlation coefficient and predicted trend, and actually executes the trade using the Interactive Brokers API. The input data are the correlation analysis results and predicted trend, and the output is trading instructions and execution.

[0511] Step 6: Monitoring and feedback

[0512] The server monitors the results of executed trades in real time, recording and verifying the data. Specifically, it monitors post-trade stock price movements and evaluates the profits and losses of the trades. Furthermore, it retrains the AI ​​model based on these results and makes adjustments to improve the accuracy of the next prediction. The input data are trading results and market data, and the output is trading performance data and an updated AI model.

[0513] In this way, the system efficiently and automatically utilizes trend information and market data to buy and sell stocks.

[0514] (Application example 1)

[0515] 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."

[0516] While conventional systems were able to trade stocks based on trend information and market data, they lacked a way to optimize the display position of best-selling items in virtual stores in real time. As a result, it was difficult to effectively display products that would attract consumer interest, making it difficult to maximize sales. Furthermore, there was a lack of technology to efficiently analyze market trends and inventory data and quickly reflect new trends.

[0517] 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.

[0518] In this invention, the server includes a data collection means for collecting trend information, a data preprocessing means for preprocessing the collected trend information, a detection means for detecting trends based on the preprocessed trend information, a correlation analysis means for analyzing correlations using the detected trend information and market data, an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results, a monitoring means for monitoring and verifying the buying and selling results, and an analysis means for analyzing the trend information and inventory data in real time, automatically selecting best-selling products, and adjusting their display positions within the virtual store. This makes it possible to effectively display products that attract consumers' interest and maximize sales.

[0519] "Trend information" is data collected from online news, social media, etc., that shows current market and consumer trends.

[0520] "Data collection means" refers to a means for obtaining trend information and market data in real time from multiple data sources on the Internet.

[0521] The "data preprocessing means" is a means for removing unnecessary elements from collected trend information and performing preprocessing such as tokenization and normalization.

[0522] "Detection means" means a means for detecting trends using an AI model based on pre-processed trend information.

[0523] A "correlation analysis means" is a means for analyzing the correlation between detected trend information and market data.

[0524] An "algorithmic trading tool" is a tool for automatically executing stock buying and selling based on the results of correlation analysis.

[0525] "Monitoring means" refers to a means for monitoring trading results in real time and verifying trading performance.

[0526] "Inventory data" is data that indicates the inventory status of products sold in the virtual store.

[0527] The "analysis means" is a means for analyzing trend information and inventory data in real time, automatically selecting best-selling items, and adjusting their display position within the virtual store.

[0528] System Overview

[0529] This invention provides a system that automatically selects best-selling items based on trend information and inventory data in a virtual store and optimizes their display position. The system has the following main functions:

[0530] Hardware Configuration

[0531] 1. Server: Performs data collection, pre-processing, trend detection, correlation analysis, algorithmic trading, monitoring and analysis.

[0532] 2. Client terminal: A device (smartphone, tablet, PC, etc.) through which a user accesses the virtual store.

[0533] 3. Network connection: A network for data communication between the server and client terminals.

[0534] Software Configuration

[0535] 1. Data collection method: Use news APIs and social media APIs to collect trend information in real time and obtain inventory information from the inventory database.

[0536] 2. Data preprocessing methods: Remove unnecessary elements from the collected trend information, and perform tokenization and normalization.

[0537] 3. Detection method: Based on the pre-processed trend information, trends are detected using a generative AI model.

[0538] 4. Correlation analysis method: Based on the detected trend information and market data, the correlation between them is analyzed.

[0539] 5. Algorithmic trading tools: Automatically buy and sell stocks based on correlation analysis results.

[0540] 6. Monitoring: Monitor trading results in real time and verify trading performance.

[0541] 7. Analysis method: Trend information and inventory data are analyzed in real time, and best-selling items are automatically selected and their display position within the virtual store is adjusted.

[0542] System Operation

[0543] The server collects trend information in real time from news APIs and social media APIs. For example, information such as "a new smartphone is all the rage" is collected. Stock information for the relevant product is obtained from the inventory database. This collected data is then tokenized and normalized using data preprocessing means to remove unnecessary elements.

[0544] The pre-processed data is input into the detection means, and trends are detected using a generative AI model. The detected trend information is analyzed for correlation with market data by the correlation analysis means. Based on the results of this correlation analysis, buy and sell instructions are automatically executed by the algorithmic trading means.

[0545] The monitoring means monitors and verifies the results in real time. At the same time, the analysis means analyzes trend information and inventory data in real time and automatically selects best-selling items. As a result, products that attract consumers' interest are automatically placed in prominent positions in the virtual store.

[0546] For example, based on trend information such as "A new smartphone is all the rage" obtained from a news API and inventory information from an inventory database, the smartphone is picked up as a best-selling item by the analysis method and placed in a prominent position in the virtual store.

[0547] Prompt Sentence Examples

[0548] "We collect the latest trend information from news APIs, and based on that information, we predict which products will be popular and select recommended products for the virtual store."

[0549] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0550] Step 1:

[0551] The server collects trending information on the Internet using news and social media APIs. It receives API responses as input and obtains raw trending information as output. This trending information includes keywords and topics that indicate consumer interest.

[0552] Step 2:

[0553] The server retrieves inventory information for products in the virtual store from the inventory database. It executes a database query as input and obtains product availability data as output. This inventory information includes the current stock quantity and price of each product.

[0554] Step 3:

[0555] The server preprocesses the collected trend information. Specifically, it removes HTML tags and special characters from the trend information, and performs tokenization and normalization. It receives raw trend information data as input and generates preprocessed, clean trend data as output.

[0556] Step 4:

[0557] The server uses a generative AI model to detect trends based on the preprocessed trend data. The clean trend data is input to the AI ​​model, and the detected trend information is output. This output is information about a trend, such as "A new smartphone is becoming all the rage."

[0558] Step 5:

[0559] The server analyzes the correlation using the detected trend information and inventory data. Specifically, it calculates the correlation coefficient based on past trend data and inventory data, and analyzes which trends affect which products. Using the detected trend information and inventory data as input, the server obtains the correlation analysis results as output.

[0560] Step 6:

[0561] The server automatically selects best-selling products based on the correlation analysis results using analytical means. Specifically, it prioritizes products with high correlation and calculates a score for those products. It uses the correlation analysis results as input and generates a list of the selected best-selling products as output.

[0562] Step 7:

[0563] The server adjusts the display position of the selected best-selling items to automatically place them in prominent positions within the virtual store. Specifically, it updates the virtual store interface so that they are displayed as recommended items on the user's device. It uses the list of selected best-selling items as input and generates the updated display content of the virtual store as output.

[0564] Step 8:

[0565] The server monitors trading results and post-product placement performance in real time and adjusts system behavior as needed. Specifically, it collects and analyzes trading performance data and sales data, and uses it to retrain the generative AI model. It uses real-time performance data as input and outputs it to adjust system behavior and update the AI ​​model.

[0566] 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.

[0567] The present invention is a system for automatically executing stock buying and selling using trend information and stock price data, and also includes an emotion engine that analyzes user emotion data to augment trading strategies. In this system, a server collects trend information and stock price data from various data sources, performs preprocessing, uses an AI model to detect and predict trends, and further uses the emotion engine to evaluate and consider the user's emotional state to execute algorithmic trading.

[0568] System Program Overview

[0569] The system is implemented by a program with the following main functions:

[0570] 1. Data Collection:

[0571] The server collects trending information from the Internet in real time through news APIs and social media APIs.

[0572] The server uses a financial market data provider service to obtain real-time stock price data.

[0573] 2. Data Preprocessing:

[0574] The server preprocesses the collected trend information, removing unnecessary elements from the text data and performing tokenization and normalization.

[0575] The server also performs preprocessing on the acquired stock price data, scaling it, etc.

[0576] 3. Trend detection and forecasting:

[0577] The server inputs the pre-processed data into an AI model to detect trends and make predictions.

[0578] For example, if the launch of a new product is evaluated as a "hit," it predicts that the stock price will rise thereafter.

[0579] 4. Correlation analysis:

[0580] The server analyzes the correlation between the trend data and the stock price data and evaluates the extent to which the trend affects the stock price.

[0581] 5. Algorithmic Trading Execution:

[0582] The server generates a trading strategy based on the correlation analysis results and automatically executes the buying and selling of stocks.

[0583] 6. Monitoring and Feedback:

[0584] The server monitors the results of executed transactions and feeds back the evaluation results to improve the AI ​​model.

[0585] 7. Emotion engine integration:

[0586] The server collects user input data and behavioral data and analyzes it using an emotion engine.

[0587] The server reinforces the evaluation of trend information based on the emotion recognition results and influences trading strategies.

[0588] Specific examples

[0589] Data collection and preprocessing

[0590] The server collects articles from the news API such as "Company C announces new innovative product."

[0591] The server removes HTML tags from this data and splits the text into words (tokenization).

[0592] Trend detection and forecasting

[0593] The server inputs the preprocessed article data into the AI ​​model and detects trends as "hits."

[0594] Based on this trend, the server predicts that Company C's stock price will rise 20% over the next week.

[0595] Correlation Analysis and Algorithmic Trading

[0596] The server analyzes the correlation between the trend and stock price data and calculates how much the "hit" trend affects stock prices.

[0597] Based on the correlation analysis results, the server generates a trading instruction to "purchase 100 shares of Company C's stock" and executes this as algorithmic trading.

[0598] Emotion engine integration

[0599] The server collects user input data (e.g., investment comments and operation logs) and analyzes it using an emotion engine.

[0600] If the user has positive feelings about the transaction, the server reflects the evaluation in the trend information.

[0601] For example, if a user comments, "This news looks very promising," this can be taken as a positive evaluation and reflected in trading strategies.

[0602] Monitoring and Feedback

[0603] The server monitors the results of the executed transactions in real time and records the data.

[0604] The server retrains the AI ​​model and emotion engine based on the monitoring results, improving prediction accuracy from next time onwards.

[0605] In this way, the system integrates trend information, stock price data, and user sentiment data to efficiently and automatically trade stocks, reducing human error and utilizing both quantitative and qualitative data to achieve more advanced forecasting and trading.

[0606] The processing flow will be explained below.

[0607] Step 1:

[0608] The server uses news and social media APIs to gather the latest trending information in real time. For example, it accesses the API every hour to retrieve articles such as "Company D announces innovative new product."

[0609] Step 2:

[0610] The server uses the API of a financial market data provider to obtain real-time stock price data. For example, it collects stock price information for Company D from the Yahoo Finance API and stores it in a database, including past stock price history.

[0611] Step 3:

[0612] The server stores the collected news articles and social media posts in a database, along with metadata such as the article ID, posting date and time, and poster ID.

[0613] Step 4:

[0614] The server removes HTML tags and special characters from the collected text data to generate clean text data, then performs tokenization to split the text into words.

[0615] Step 5:

[0616] The server performs standardization or normalization on the collected stock price data, for example, scaling the stock price data to a range of 0 to 1.

[0617] Step 6:

[0618] The server inputs preprocessed news articles and social media posts into a natural language processing (NLP) model to detect trends. For example, the article "Company D launches new product" is classified as a "hit."

[0619] Step 7:

[0620] The server analyzes past trend data and stock price data based on an AI model to predict future trends. For example, it predicts that the stock price of Company D will rise by 20% within one week following the release of a new product.

[0621] Step 8:

[0622] The server performs correlation analysis based on past trends and detected trend data, and evaluates the specific impact (correlation coefficient) that the trend has on stock prices.

[0623] Step 9:

[0624] The server generates a trading strategy based on the correlation analysis results, for example, generating a trading instruction to "immediately purchase 100 shares of Company D's stock" and sending it to the algorithmic trading platform.

[0625] Step 10:

[0626] The server executes the generated buy / sell orders through the trading platform API. For example, it issues a command to "immediately purchase 100 shares of Company D's stock" to the market.

[0627] Step 11:

[0628] The server inputs the user's input data and behavioral data into an emotion engine to analyze the user's emotions. For example, a user comment such as "This news is promising" is recognized as a positive emotion.

[0629] Step 12:

[0630] The server uses the emotion data obtained from the emotion engine to evaluate trend information. For example, if the user has positive emotions, the server strengthens the trend evaluation.

[0631] Step 13:

[0632] The server further refines the trading strategy based on the sentiment data and reflects it in the final buy / sell instructions, for example, increasing the number of shares to buy if the sentiment data is very positive.

[0633] Step 14:

[0634] The server monitors the results of executed trades in real time and records their performance data, e.g., evaluating stock price fluctuations and profits after a trade.

[0635] Step 15:

[0636] Based on the monitoring results, the server retrains the AI ​​model and emotion engine to improve prediction accuracy for future transactions. For example, if the trading results are as predicted, the reliability of the model is evaluated and further improvements are made.

[0637] In this way, the server integrates trend information, stock price data, and user emotion data to realize a system for efficient and automatic stock buying and selling.

[0638] Example 2

[0639] 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."

[0640] In the stock market, there is a demand for systems that can automatically execute highly accurate trading strategies that take into account not only trend information and market data, but also user sentiment data. However, conventional systems have difficulty integrating and utilizing this data, resulting in insufficient prediction accuracy and trading strategy flexibility. As a result, trading efficiency is lacking and human error is likely to occur.

[0641] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0642] In this invention, the server includes a data collection means for collecting trend information, a data preprocessing means for preprocessing the collected trend information and market data, a detection means for detecting and predicting trends based on the preprocessed trend information, a correlation analysis means for analyzing correlations using the detected trend information and market data, an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results, an emotion engine integration means for collecting user emotion data and using it to reinforce trading strategies, and a monitoring means for monitoring and verifying trading results. This enables a system that can automatically execute highly accurate and flexible trading strategies by integrating trend information, market data, and user emotion data.

[0643] "Trending information" refers to popular market events and topics collected from online news articles, social media posts, etc.

[0644] "Data Collection Means" means the technical means for obtaining trend information and market data in real time from multiple data sources on the Internet.

[0645] "Data Pre-processing Measures" are the processes and technical measures used to convert collected trend information and market data into a format that is easy to analyze.

[0646] "Detection methods" are technical methods that utilize AI and machine learning models to detect and predict trends based on pre-processed data.

[0647] "Correlation analysis means" refers to a technical means for analyzing correlations using detected trend information and market data.

[0648] An "algorithmic trading tool" is a technical tool for automatically executing stock buying and selling based on the results of correlation analysis.

[0649] The "emotion engine integration means" is a technical means for collecting and analyzing user emotion data and using it to reinforce trading strategies.

[0650] "Monitoring Means" means technical means for monitoring and verifying the results of executed transactions.

[0651] The present invention is a system for automatically executing stock buying and selling using trend information and stock price data, and also includes an emotion engine that analyzes user emotion data to augment trading strategies. In this system, a server collects trend information and stock price data from various data sources, performs preprocessing, uses a generative AI model to detect and predict trends, and further uses the emotion engine to evaluate and consider the user's emotional state to execute algorithmic trading.

[0652] Data collection

[0653] The server uses news APIs and social media APIs to collect trending information from the Internet. Specifically, it uses the News API and Twitter API to obtain news articles and social media posts in real time. The server also obtains real-time stock price data using a financial market data provider service (e.g., Alpha Vantage API). For example, the server uses a request URL such as "https: / / newsapi.org / v2 / everything?q=NewProduct&apiKey=your_api_key".

[0654] Data Preprocessing

[0655] The trend information collected by the server is first preprocessed. Specifically, the HTML tags of news articles are removed using Python's BeautifulSoup library, and then tokenized (divided into words) using the NLTK library. Furthermore, stock price data undergoes standardization processes such as scaling using scikit-learn's StandardScaler.

[0656] Trend detection and forecasting

[0657] The server inputs the preprocessed data into a generative AI model (e.g., an LSTM model using TensorFlow or PyTorch) to detect trends and make predictions. For example, if "Company C announces a new product" is a trend evaluated as a "hit," the server predicts that "Company C's stock price will rise by 20% over the next week."

[0658] Correlation analysis

[0659] The server analyzes the correlation between trend data and stock price data using the pandas library. By calculating the correlation coefficient, it quantifies the impact of trend information on stock prices. For example, if the correlation coefficient between trend information and stock price data is 0.8, the server adjusts its trading strategy based on this information.

[0660] Algorithmic trading execution

[0661] Based on the correlation analysis results, the server automatically buys and sells stocks. Specifically, it executes transactions using the Interactive Brokers API or Alpaca API. For example, based on the correlation analysis results, a trading instruction to "purchase 100 shares of Company C" is generated and executed.

[0662] Monitoring and Feedback

[0663] The server monitors the results of executed transactions in real time using Elasticsearch and Kibana, records the data, and retrains the AI ​​model based on the monitoring results to improve prediction accuracy in future transactions.

[0664] Emotion engine integration

[0665] The server collects user input and behavioral data and analyzes it using the Microsoft Text Analytics API. If a user has positive sentiment toward trading, that sentiment is reflected in trend information and influences trading strategies. For example, if a user comments, "This news looks very promising," that sentiment is taken into account as a positive sentiment and reflected in trading strategies.

[0666] Prompt Sentence Examples

[0667] Trend detection prompt:

[0668] Preprocess the text of the news article "Company C announces new product" into the following format:

[0669] Remove HTML tags from text

[0670] Tokenization is performed

[0671] Normalize

[0672] Input prompt for the emotion engine:

[0673] Perform sentiment analysis on the user comment "This news looks very promising" and return the result as either positive or negative.

[0674] In this way, the system integrates trend information, stock price data, and user sentiment data to efficiently and automatically trade stocks, reducing human error and utilizing both quantitative and qualitative data to achieve more advanced forecasting and trading.

[0675] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0676] Step 1: Collect data

[0677] The server collects trending information in real time using news APIs (e.g., NewsAPI) and social media APIs (e.g., Twitter API). It sends HTTP requests based on user-defined keywords and receives news data and social media posts in JSON format.

[0678] Input: Search keyword, News API URL

[0679] Output: News article data and social media posts in JSON format

[0680] Step 2: Preprocessing the data

[0681] The server preprocesses the collected trend information by first removing HTML tags using the BeautifulSoup library, then tokenizing it using the NLTK library, and scaling the data using StandardScaler from scikit-learn if financial market data is available.

[0682] Input: JSON-formatted news article data, social media posts, and stock price data

[0683] Output: Preprocessed text data, scaled stock price data

[0684] Step 3: Trend detection and forecasting

[0685] The server inputs the preprocessed data into a generative AI model (e.g., an LSTM model using TensorFlow or PyTorch) to detect and predict trends. Specifically, it feeds the input data into the model and outputs trend labels (e.g., "hit" or "miss") and predicted stock price fluctuations.

[0686] Input: Preprocessed text data, scaled stock price data

[0687] Output: Trend label, predicted stock price fluctuations

[0688] Step 4: Correlation analysis

[0689] To analyze the correlation between the trend data and stock price data, the server calculates the correlation coefficient using the pandas library. Specifically, it creates a DataFrame and calculates the correlation coefficient using the corr() method.

[0690] Input: Trend label, stock price data

[0691] Output: Correlation coefficient between trend and stock price

[0692] Step 5: Execute algorithmic trading

[0693] The server automatically executes stock purchases and sales based on the correlation analysis results. It uses the Interactive Brokers API or Alpaca API to generate and execute trading instructions based on specific conditions. Specifically, it generates JSON for the trading instructions and sends them to the API.

[0694] Input: Trend and stock price correlation coefficient, predicted stock price movement

[0695] Output: Executed trading instructions

[0696] Step 6: Monitoring and feedback

[0697] The server monitors the results of executed trades in real time, stores the data in Elasticsearch, and visualizes the results using Kibana. Furthermore, the AI ​​model is retrained based on the monitoring results to improve prediction accuracy for future transactions.

[0698] Input: Result data of executed trading instructions

[0699] Output: Monitoring report, retrained AI model

[0700] Step 7: Integrating the Emotion Engine

[0701] The server collects user input data and behavioral data, analyzes the sentiment data using a sentiment analysis API (e.g., Microsoft Text Analytics API), and reinforces the trading strategy based on the results. If the user has positive sentiment, that evaluation is reflected in the trend forecast.

[0702] Input: User comments, operation log

[0703] Output: Sentiment analysis results, reinforced trading strategies

[0704] (Application example 2)

[0705] 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."

[0706] Conventional stock trading systems exist that automatically buy and sell stocks using trend information and stock price data, but they lack a mechanism to utilize user emotional data to reinforce trading strategies. As a result, inefficient trading can occur, ignoring the user's emotional state. Furthermore, there is a lack of technology to improve the customer experience in brick-and-mortar stores and realize personalized product recommendations. This makes it difficult to provide a richer user experience.

[0707] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means for collecting trend information, a data preprocessing means for preprocessing the collected trend information, a detection means for detecting trends based on the preprocessed trend information, a correlation analysis means for analyzing correlations using the detected trend information and market data, an algorithmic trading means for automatically executing stock trading based on the correlation analysis results, a monitoring means for monitoring and verifying trading results, a sentiment analysis means for analyzing user sentiment data and reinforcing trading strategies, and an information provision means for displaying on a smart device. This enables more effective and personalized trading by trading stocks while also referencing user sentiment data. Furthermore, trend information can be provided in real time using smart devices in brick-and-mortar stores, improving the user experience and providing personalized suggestions.

[0708] definition statement

[0709] "Data collection means" refers to a hardware or software input interface for acquiring predetermined data from an information source.

[0710] A "data pre-processing means" is a device or program that performs operations or processes to convert collected data into a form suitable for analysis or processing.

[0711] "Detection methods" refer to algorithms and techniques that utilize pre-processed data to find specific patterns or events.

[0712] A "correlation analysis tool" is a technique or device for calculating and analyzing the relationships and correlations between multiple data sets.

[0713] An "algorithmic trading vehicle" is a system or program for automatically buying and selling stocks based on a pre-set algorithm.

[0714] "Monitoring means" means functions or means for monitoring the status of a process or transaction during or after execution and collecting data.

[0715] "Emotion analysis means" refers to algorithms and technologies for collecting and analyzing user emotion data.

[0716] "Information providing means" refers to a device or interface that displays and provides data and analysis results to users.

[0717] A "smart device" is a device that can connect to the Internet or other networks and can collect and process information.

[0718] MODE FOR CARRYING OUT THE INVENTION

[0719] This invention is a system that uses trend information, stock price data, and user emotion data, and a specific embodiment for actually implementing the system will be described in detail.

[0720] Data collection methods

[0721] The server uses a news API to obtain trend information in real time from multiple data sources on the Internet, including various data sources such as commercial news sites and social media, and also uses a financial market data provider to obtain real-time stock price data.

[0722] Data preprocessing measures

[0723] The server performs preprocessing on the collected trend information, such as removing HTML tags, tokenizing, and normalizing. It also normalizes and scales stock price data.

[0724] Detection Method

[0725] The preprocessed data is then analyzed using a trend detection model powered by TensorFlow and Keras to detect specific trends and predict their impact on stock prices.

[0726] Correlation Analysis Tools

[0727] The server performs correlation analysis using the detected trend information and market data, which includes a technique for calculating correlation coefficients based on past trend data and stock price data.

[0728] Algorithmic Trading Instruments

[0729] Based on the results of the correlation analysis, algorithmic trading is automatically executed. Specifically, stock buy and sell instructions are generated and executed according to a pre-set trading algorithm.

[0730] Monitoring Methods

[0731] The server monitors the results of executed trades in real time and collects evaluation data, which allows the system to evaluate overall performance and optimize trading strategies.

[0732] sentiment analysis tool

[0733] It collects user input and behavioral data and analyzes it using an emotion engine, for example, to detect positive or negative emotions from voice inputs and facial expressions, which can then be used to augment trading strategies.

[0734] Information provision means

[0735] It provides information to smart devices, specifically smart glasses and mobile devices, allowing users to check trend information and stock price data in real time, and also makes personalized product recommendations based on user sentiment.

[0736] Specific examples

[0737] For example, suppose the server collects news articles about "new product announcements" from a news API, preprocesses them, and then uses an AI model to determine that they are "hits." Based on this trend, the AI ​​model predicts that the target company's stock price will rise by 20% over the next week. Furthermore, the sentiment engine analyzes the user's comment, "This news looks very promising," and determines that this is a positive reaction. This information is provided to the user in real time via smart glasses.

[0738] Examples of prompts are:

[0739] "This product is so attractive!"

[0740] To implement this invention, it is necessary to build a system that integrates the above-mentioned means, allowing users to enjoy a personalized trading experience based on trend information and stock price data.

[0741] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0742] Program processing steps

[0743] Step 1: Data collection

[0744] The server uses the news API to collect the latest trending information. Specifically, it retrieves news articles based on specific keywords and categories. At this point, the input is the keywords and categories, and the output is the retrieved news article data.

[0745] Step 2: Collect stock data

[0746] The server uses a financial market data provider to collect relevant stock price data. The input is the ticker symbol of the target company, and the output is real-time stock price data.

[0747] Step 3: Data Preprocessing

[0748] The server performs preprocessing using the retrieved news articles, such as removing HTML tags, tokenizing, and normalizing the text. The input is the retrieved news article, and the output is the preprocessed text data. In addition, it also scales the stock price data.

[0749] Step 4: Trend detection

[0750] The server inputs the preprocessed news data into an AI model (e.g., TensorFlow or Keras model) to perform trend detection and prediction. The input is the preprocessed news data, and the output is the detected trend information and its predicted value.

[0751] Step 5: Correlation analysis

[0752] The server performs correlation analysis using the detected trend information and stock price data. Specifically, it calculates the correlation coefficient from past trend data and stock price data. The input is the trend information and stock price data, and the output is the correlation coefficient.

[0753] Step 6: Algorithmic trading

[0754] The server then applies a trading algorithm based on the results of the correlation analysis to automatically execute stock purchases and sales. The input is the correlation analysis results, and the output is specific trading instructions and their execution results.

[0755] Step 7: Monitoring

[0756] The server monitors the results of executed trades in real time and collects evaluation data. The input is the results of trade execution, and the output is the evaluation data and its analysis results.

[0757] Step 8: Sentiment analysis

[0758] The server collects user input data (e.g., voice input and comments) and analyzes them using an emotion engine. The input is user comments and voice, and the output is the emotion recognition results.

[0759] Step 9: Provide information

[0760] The server provides the detected trend information and emotion analysis results to smart devices, specifically smart glasses or mobile devices. The input is the trend information and emotion recognition results, and the output is the information provided to the user.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] [Third embodiment]

[0765] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0766] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0767] 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).

[0768] 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.

[0769] 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.

[0770] 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).

[0771] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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."

[0777] This invention is a system that automatically executes stock buying and selling using trend information and stock price data. In this system, a server collects trend information and stock price data from various data sources, performs preprocessing, detects and predicts trends using an AI model, and executes algorithmic trading based on the results.

[0778] System Program Overview

[0779] The system is implemented by a program with the following main functions:

[0780] 1. Data Collection:

[0781] The server uses news APIs and social media APIs to collect trending information on the Internet in real time.

[0782] The server obtains stock price data from a financial market data provider and updates it in real time.

[0783] 2. Data Preprocessing:

[0784] The server preprocesses the collected trend information, removing unnecessary elements from the text data and performing tokenization and normalization.

[0785] The server also pre-processes the stock price data, standardizing and normalizing it.

[0786] 3. Trend detection and forecasting:

[0787] The server then feeds the pre-processed data into an AI model to detect trends, such as classifying a particular news article as a "hit" or "outdated."

[0788] The server uses AI models to predict future trends, allowing the impact of certain events on stock prices to be known in advance.

[0789] 4. Correlation analysis:

[0790] The server analyzes the correlation between the detected trends and stock price data and calculates how much the trends affect stock prices.

[0791] 5. Algorithmic Trading Execution:

[0792] The server generates a trading strategy based on the correlation analysis results: if the trend is positive, it generates a "buy" instruction, and if it is negative, it generates a "sell" instruction.

[0793] The server connects to the trading platform and automatically executes the generated buy and sell orders.

[0794] 6. Monitoring and Feedback:

[0795] The server monitors the performance of executed trades in real time and records the results.

[0796] The server retrains the AI ​​model based on trading results, creating a feedback loop to improve prediction accuracy.

[0797] Specific examples

[0798] Data collection and preprocessing

[0799] The server collects articles such as "Company B announces innovative new product" from the news API.

[0800] The server removes HTML tags and special characters from the collected article data and splits it into words (tokenization).

[0801] Trend detection and forecasting

[0802] The server uses the AI ​​model to determine whether a news article is a "hit" or "outdated" based on the preprocessed news article. In this example, the announcement of a new product is deemed a "hit."

[0803] The server uses past data to predict how much this "hit" will increase the stock price. For example, it predicts that "Company B's stock price will rise by 10% over the next week."

[0804] Correlation Analysis and Algorithmic Trading

[0805] The server analyzes the correlation between the trend data and stock price data and calculates the extent to which a "hit" will affect stock price increases.

[0806] Based on the analysis results, the server generates a trading instruction to "immediately buy 100 shares of Company B's stock" and executes algorithmic trading.

[0807] Monitoring and Feedback

[0808] The server monitors the stock price movement after the transaction in real time and records the actual results. For example, if the stock price actually rises by 10% after one week, it will confirm that a profit was made as a result of the transaction.

[0809] The server retrains the AI ​​model based on these trading results to further improve the accuracy of the next prediction.

[0810] In this way, this system uses trend information and stock price data to efficiently and automatically buy and sell stocks, reducing human error and enabling advanced analysis.

[0811] The processing flow will be explained below.

[0812] Step 1:

[0813] The server periodically collects trending information from the Internet using news APIs and social media APIs. For example, it accesses the APIs every hour to retrieve articles such as "Company B announces an innovative new product."

[0814] Step 2:

[0815] The server obtains real-time stock price data from a financial market data provider. For example, it periodically collects stock price information for Company B from the Yahoo Finance API and stores it in a database, including past stock price history.

[0816] Step 3:

[0817] The server stores the collected news articles and social media posts in a database, along with metadata such as article IDs and post IDs.

[0818] Step 4:

[0819] The server removes HTML tags and special characters from the collected text data, extracts only the text, and then performs tokenization to split the text into words.

[0820] Step 5:

[0821] The server also preprocesses the collected stock price data, specifically by normalizing and standardizing stock prices to scale them to a range of 0 to 1.

[0822] Step 6:

[0823] The server then feeds the preprocessed news articles into a natural language processing (NLP) model to detect trends, such as classifying them as "hit" or "outdated."

[0824] Step 7:

[0825] The server uses past trend data and stock price data to predict future trends using an AI model. For example, it generates a prediction that "Company B's new product announcement will lead to a 10% increase in stock prices within one week."

[0826] Step 8:

[0827] The server analyzes the correlation between the detected trend and stock price data, specifically by calculating the correlation coefficient and evaluating the degree of impact of the trend on stock prices.

[0828] Step 9:

[0829] The server generates a trading strategy based on the results of the correlation analysis, for example, if the trend is evaluated as "hit", it generates a "buy" instruction and sends it to the trading platform.

[0830] Step 10:

[0831] The server connects to the trading platform and automatically executes the generated buy and sell orders, for example, "Buy 100 shares of Company B" through the API.

[0832] Step 11:

[0833] The server monitors the results of executed trades in real time and evaluates performance, including profits and losses.

[0834] Step 12:

[0835] The server retrains the AI ​​model based on the monitoring results to improve prediction accuracy, thereby increasing the accuracy of trend detection and stock price predictions from the next time onwards.

[0836] In this way, the server automatically buys and sells stocks using trend information and stock price data, realizing efficient algorithmic trading.

[0837] Example 1

[0838] 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."

[0839] Conventional stock trading systems have difficulty quickly and accurately analyzing market trend information to generate trading strategies. They also lack real-time monitoring and feedback functions to respond sensitively to changes in market trends, making it difficult to improve trading accuracy. As a result, investors find it difficult to avoid the risk of losses due to human error or misjudgment.

[0840] 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.

[0841] In this invention, the server includes: a data collection means for collecting trend information including news information and social media information; a data preprocessing means for removing unnecessary elements from the collected trend information and performing tokenization and normalization; a detection means for detecting and predicting trends using an artificial intelligence model based on the preprocessed trend information; a correlation analysis means for analyzing correlations using the detected trend information and market data and calculating the impact of the trends on market movements; an algorithmic trading means for generating a trading strategy based on the correlation analysis results and automatically executing stock purchases and sales; and a monitoring means for monitoring the results of executed transactions in real time and recording and verifying the trading results. This enables fast and accurate analysis of trend information and market data and real-time automated trading.

[0842] "Data collection means" refers to a device or method for obtaining trend information, including news information and social media information, from multiple data sources on the Internet in real time.

[0843] "Data preprocessing means" refers to a device or method that removes unnecessary elements from collected trend information and performs tokenization and normalization.

[0844] "Detection means" refers to a device or method that detects and predicts trends using artificial intelligence models based on pre-processed trend information.

[0845] "Correlation analysis means" refers to a device or method that uses detected trend information and market data to analyze correlations and calculate the impact of trends on market movements.

[0846] "Algorithmic trading tools" refer to devices or methods that generate trading strategies based on correlation analysis results and automatically execute stock buying and selling.

[0847] "Monitoring means" refers to a device or method for monitoring the results of executed transactions in real time, and for recording and verifying the results of the transactions.

[0848] "Artificial intelligence model" refers to a machine learning algorithm that makes predictions and classifications based on trend information.

[0849] "Trending information" refers to information about events and topics that affect the market, gathered through news and social media.

[0850] "Market data" refers to data including price information and trading volume of stocks and other financial instruments traded in financial markets.

[0851] The present invention is a system for automatically executing stock trading using trend information and market data. In this system, a server collects trend information and market data from various data sources, performs preprocessing, detects and predicts trends using an artificial intelligence model, and executes algorithmic trading based on the results. Specific embodiments of this system are described in detail below.

[0852] Data collection

[0853] The server collects trending information on the Internet in real time using a news API (e.g., NewsAPI) or a social media API (e.g., Twitter API). For example, the server retrieves news using the URL https: / / newsapi.org / v2 / everything?q=stock market&apiKey=your_api_key and collects tweets related to the Twitter hashtag "stockmarket." The server also collects real-time stock price data using a financial market data provider (e.g., Yahoo Finance API).

[0854] Data Preprocessing

[0855] The server removes unnecessary elements (e.g., HTML tags and special characters) from the collected trend information and performs tokenization and normalization. For example, the sentence "Company B announced an innovative new product" is tokenized as "Company B," "innovative," "new product," and "announcement." Twitter posts are also tokenized and normalized in the same way. Furthermore, scaling is performed to standardize the collected stock price data, for example, by constraining values ​​to a range from 0 to 1.

[0856] Trend detection and forecasting

[0857] The server inputs preprocessed news articles and social media posts into an artificial intelligence model (e.g., BERT or LSTM) to detect and predict trends. As a specific example, in trend detection using news articles, an article stating "Company B has announced an innovative new product" is classified as a "hit." When making predictions, a scenario such as "Company B's stock price will rise by 10% in the next week" is generated.

[0858] Correlation analysis

[0859] The server analyzes correlations using detected trend information and past market data. For example, it calculates a correlation coefficient based on past data to see how much a trend like "new product announcement" affects stock price increases. This analysis makes it possible to evaluate which trends affect stock prices and how they affect them.

[0860] Algorithmic trading execution

[0861] The server generates a trading strategy based on the results of the correlation analysis. For example, it creates a specific trading strategy such as "Purchase 100 shares of Company B because the stock price is predicted to rise by 10%." This trading strategy is then connected to a trading platform such as the Interactive Brokers API and executed automatically.

[0862] Monitoring and Feedback

[0863] The server monitors the results of executed trades in real time, recording and verifying the results. For example, it monitors stock price movements after a trade and evaluates how accurate the predictions were. Based on these results, the AI ​​model can be retrained to improve the accuracy of future predictions.

[0864] Prompt Sentence Examples

[0865] To input trend information into the generative AI model, the server uses a prompt like this:

[0866] "Predict the impact this news will have on stock prices." The generative AI model responds to the prompt with a prediction such as, "This news could increase stock prices by 10%."

[0867] In this way, the system efficiently and automatically utilizes trend information and market data to buy and sell stocks, minimizing human error and enabling advanced analysis.

[0868] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0869] Step 1: Data collection

[0870] The server uses news and social media APIs to collect trending information on the Internet in real time. Specifically, it retrieves the latest news articles from the News API and collects posts related to a specific hashtag (e.g., stockmarket) using the Twitter API. This provides the data of the news articles and tweets retrieved as input. This data is saved in JSON format for processing in subsequent steps.

[0871] Step 2: Data Preprocessing

[0872] The server removes unnecessary elements from the collected trend information and tokenizes and normalizes the text data. This process involves, for example, removing HTML tags using BeautifulSoup and dividing sentences into tokens using NLTK. Specifically, the news article "Company B announces innovative new product" is tokenized into "Company B," "innovative," "new product," and "announcement." The input data is text information, and the output is tokenized and normalized text data. Similar processing is applied to tweets.

[0873] Step 3: Trend detection and forecasting

[0874] The server uses an artificial intelligence model (e.g., BERT or LSTM) to detect and predict trends based on the preprocessed trend information. Specifically, tokenized news articles are input into the BERT model, which classifies them as "hits" or "outdated." In this example, an article stating "Company B announced an innovative new product" is classified as a "hit." Furthermore, the LSTM model predicts that "Company B's stock price will rise by 10% over the next week." The input data is preprocessed text data, and the output is trend detection results and stock price predictions.

[0875] Step 4: Correlation analysis

[0876] The server analyzes correlations using detected trend information and past market data. Specifically, it uses Python's Pandas and Numpy libraries to align past stock price data and trend data in chronological order and calculate the correlation coefficient. For example, it calculates how much impact the trend of "new product announcements" has had on stock price increases in the past. The input data are trend data and stock price data, and the output is the correlation coefficient.

[0877] Step 5: Execute algorithmic trading

[0878] The server generates a trading strategy based on the correlation analysis results and automatically buys and sells stocks. Specifically, it generates trading instructions such as "buy 100 shares of Company B because the stock price will rise by 10%" based on the correlation coefficient and predicted trend, and actually executes the trade using the Interactive Brokers API. The input data are the correlation analysis results and predicted trend, and the output is trading instructions and execution.

[0879] Step 6: Monitoring and feedback

[0880] The server monitors the results of executed trades in real time, recording and verifying the data. Specifically, it monitors post-trade stock price movements and evaluates the profits and losses of the trades. Furthermore, it retrains the AI ​​model based on these results and makes adjustments to improve the accuracy of the next prediction. The input data are trading results and market data, and the output is trading performance data and an updated AI model.

[0881] In this way, the system efficiently and automatically utilizes trend information and market data to buy and sell stocks.

[0882] (Application example 1)

[0883] 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."

[0884] While conventional systems were able to trade stocks based on trend information and market data, they lacked a way to optimize the display position of best-selling items in virtual stores in real time. As a result, it was difficult to effectively display products that would attract consumer interest, making it difficult to maximize sales. Furthermore, there was a lack of technology to efficiently analyze market trends and inventory data and quickly reflect new trends.

[0885] 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.

[0886] In this invention, the server includes a data collection means for collecting trend information, a data preprocessing means for preprocessing the collected trend information, a detection means for detecting trends based on the preprocessed trend information, a correlation analysis means for analyzing correlations using the detected trend information and market data, an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results, a monitoring means for monitoring and verifying the buying and selling results, and an analysis means for analyzing the trend information and inventory data in real time, automatically selecting best-selling products, and adjusting their display positions within the virtual store. This makes it possible to effectively display products that attract consumers' interest and maximize sales.

[0887] "Trend information" is data collected from online news, social media, etc., that shows current market and consumer trends.

[0888] "Data collection means" refers to a means for obtaining trend information and market data in real time from multiple data sources on the Internet.

[0889] The "data preprocessing means" is a means for removing unnecessary elements from collected trend information and performing preprocessing such as tokenization and normalization.

[0890] "Detection means" means a means for detecting trends using an AI model based on pre-processed trend information.

[0891] A "correlation analysis means" is a means for analyzing the correlation between detected trend information and market data.

[0892] An "algorithmic trading tool" is a tool for automatically executing stock buying and selling based on the results of correlation analysis.

[0893] "Monitoring means" refers to a means for monitoring trading results in real time and verifying trading performance.

[0894] "Inventory data" is data that indicates the inventory status of products sold in the virtual store.

[0895] The "analysis means" is a means for analyzing trend information and inventory data in real time, automatically selecting best-selling items, and adjusting their display position within the virtual store.

[0896] System Overview

[0897] This invention provides a system that automatically selects best-selling items based on trend information and inventory data in a virtual store and optimizes their display position. The system has the following main functions:

[0898] Hardware Configuration

[0899] 1. Server: Performs data collection, pre-processing, trend detection, correlation analysis, algorithmic trading, monitoring and analysis.

[0900] 2. Client terminal: A device (smartphone, tablet, PC, etc.) through which a user accesses the virtual store.

[0901] 3. Network connection: A network for data communication between the server and client terminals.

[0902] Software Configuration

[0903] 1. Data collection method: Use news APIs and social media APIs to collect trend information in real time and obtain inventory information from the inventory database.

[0904] 2. Data preprocessing methods: Remove unnecessary elements from the collected trend information, and perform tokenization and normalization.

[0905] 3. Detection method: Based on the pre-processed trend information, trends are detected using a generative AI model.

[0906] 4. Correlation analysis method: Based on the detected trend information and market data, the correlation between them is analyzed.

[0907] 5. Algorithmic trading tools: Automatically buy and sell stocks based on correlation analysis results.

[0908] 6. Monitoring: Monitor trading results in real time and verify trading performance.

[0909] 7. Analysis method: Trend information and inventory data are analyzed in real time, and best-selling items are automatically selected and their display position within the virtual store is adjusted.

[0910] System Operation

[0911] The server collects trend information in real time from news APIs and social media APIs. For example, information such as "a new smartphone is all the rage" is collected. Stock information for the relevant product is obtained from the inventory database. This collected data is then tokenized and normalized using data preprocessing means to remove unnecessary elements.

[0912] The pre-processed data is input into the detection means, and trends are detected using a generative AI model. The detected trend information is analyzed for correlation with market data by the correlation analysis means. Based on the results of this correlation analysis, buy and sell instructions are automatically executed by the algorithmic trading means.

[0913] The monitoring means monitors and verifies the results in real time. At the same time, the analysis means analyzes trend information and inventory data in real time and automatically selects best-selling items. As a result, products that attract consumers' interest are automatically placed in prominent positions in the virtual store.

[0914] For example, based on trend information such as "A new smartphone is all the rage" obtained from a news API and inventory information from an inventory database, the smartphone is picked up as a best-selling item by the analysis method and placed in a prominent position in the virtual store.

[0915] Prompt Sentence Examples

[0916] "We collect the latest trend information from news APIs, and based on that information, we predict which products will be popular and select recommended products for the virtual store."

[0917] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0918] Step 1:

[0919] The server collects trending information on the Internet using news and social media APIs. It receives API responses as input and obtains raw trending information as output. This trending information includes keywords and topics that indicate consumer interest.

[0920] Step 2:

[0921] The server retrieves inventory information for products in the virtual store from the inventory database. It executes a database query as input and obtains product availability data as output. This inventory information includes the current stock quantity and price of each product.

[0922] Step 3:

[0923] The server preprocesses the collected trend information. Specifically, it removes HTML tags and special characters from the trend information, and performs tokenization and normalization. It receives raw trend information data as input and generates preprocessed, clean trend data as output.

[0924] Step 4:

[0925] The server uses a generative AI model to detect trends based on the preprocessed trend data. The clean trend data is input to the AI ​​model, and the detected trend information is output. This output is information about a trend, such as "A new smartphone is becoming all the rage."

[0926] Step 5:

[0927] The server analyzes the correlation using the detected trend information and inventory data. Specifically, it calculates the correlation coefficient based on past trend data and inventory data, and analyzes which trends affect which products. Using the detected trend information and inventory data as input, the server obtains the correlation analysis results as output.

[0928] Step 6:

[0929] The server automatically selects best-selling products based on the correlation analysis results using analytical means. Specifically, it prioritizes products with high correlation and calculates a score for those products. It uses the correlation analysis results as input and generates a list of the selected best-selling products as output.

[0930] Step 7:

[0931] The server adjusts the display position of the selected best-selling items to automatically place them in prominent positions within the virtual store. Specifically, it updates the virtual store interface so that they are displayed as recommended items on the user's device. It uses the list of selected best-selling items as input and generates the updated display content of the virtual store as output.

[0932] Step 8:

[0933] The server monitors trading results and post-product placement performance in real time and adjusts system behavior as needed. Specifically, it collects and analyzes trading performance data and sales data, and uses it to retrain the generative AI model. It uses real-time performance data as input and outputs it to adjust system behavior and update the AI ​​model.

[0934] 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.

[0935] The present invention is a system for automatically executing stock buying and selling using trend information and stock price data, and also includes an emotion engine that analyzes user emotion data to augment trading strategies. In this system, a server collects trend information and stock price data from various data sources, performs preprocessing, uses an AI model to detect and predict trends, and further uses the emotion engine to evaluate and consider the user's emotional state to execute algorithmic trading.

[0936] System Program Overview

[0937] The system is implemented by a program with the following main functions:

[0938] 1. Data Collection:

[0939] The server collects trending information from the Internet in real time through news APIs and social media APIs.

[0940] The server uses a financial market data provider service to obtain real-time stock price data.

[0941] 2. Data Preprocessing:

[0942] The server preprocesses the collected trend information, removing unnecessary elements from the text data and performing tokenization and normalization.

[0943] The server also performs preprocessing on the acquired stock price data, scaling it, etc.

[0944] 3. Trend detection and forecasting:

[0945] The server inputs the pre-processed data into an AI model to detect trends and make predictions.

[0946] For example, if the launch of a new product is evaluated as a "hit," it predicts that the stock price will rise thereafter.

[0947] 4. Correlation analysis:

[0948] The server analyzes the correlation between the trend data and the stock price data and evaluates the extent to which the trend affects the stock price.

[0949] 5. Algorithmic Trading Execution:

[0950] The server generates a trading strategy based on the correlation analysis results and automatically executes the buying and selling of stocks.

[0951] 6. Monitoring and Feedback:

[0952] The server monitors the results of executed transactions and feeds back the evaluation results to improve the AI ​​model.

[0953] 7. Emotion engine integration:

[0954] The server collects user input data and behavioral data and analyzes it using an emotion engine.

[0955] The server reinforces the evaluation of trend information based on the emotion recognition results and influences trading strategies.

[0956] Specific examples

[0957] Data collection and preprocessing

[0958] The server collects articles from the news API such as "Company C announces new innovative product."

[0959] The server removes HTML tags from this data and splits the text into words (tokenization).

[0960] Trend detection and forecasting

[0961] The server inputs the preprocessed article data into the AI ​​model and detects trends as "hits."

[0962] Based on this trend, the server predicts that Company C's stock price will rise 20% over the next week.

[0963] Correlation Analysis and Algorithmic Trading

[0964] The server analyzes the correlation between the trend and stock price data and calculates how much the "hit" trend affects stock prices.

[0965] Based on the correlation analysis results, the server generates a trading instruction to "purchase 100 shares of Company C's stock" and executes this as algorithmic trading.

[0966] Emotion engine integration

[0967] The server collects user input data (e.g., investment comments and operation logs) and analyzes it using an emotion engine.

[0968] If the user has positive feelings about the transaction, the server reflects the evaluation in the trend information.

[0969] For example, if a user comments, "This news looks very promising," this can be taken as a positive evaluation and reflected in trading strategies.

[0970] Monitoring and Feedback

[0971] The server monitors the results of the executed transactions in real time and records the data.

[0972] The server retrains the AI ​​model and emotion engine based on the monitoring results, improving prediction accuracy from next time onwards.

[0973] In this way, the system integrates trend information, stock price data, and user sentiment data to efficiently and automatically trade stocks, reducing human error and utilizing both quantitative and qualitative data to achieve more advanced forecasting and trading.

[0974] The processing flow will be explained below.

[0975] Step 1:

[0976] The server uses news and social media APIs to gather the latest trending information in real time. For example, it accesses the API every hour to retrieve articles such as "Company D announces innovative new product."

[0977] Step 2:

[0978] The server uses the API of a financial market data provider to obtain real-time stock price data. For example, it collects stock price information for Company D from the Yahoo Finance API and stores it in a database, including past stock price history.

[0979] Step 3:

[0980] The server stores the collected news articles and social media posts in a database, along with metadata such as the article ID, posting date and time, and poster ID.

[0981] Step 4:

[0982] The server removes HTML tags and special characters from the collected text data to generate clean text data, then performs tokenization to split the text into words.

[0983] Step 5:

[0984] The server performs standardization or normalization on the collected stock price data, for example, scaling the stock price data to a range of 0 to 1.

[0985] Step 6:

[0986] The server inputs preprocessed news articles and social media posts into a natural language processing (NLP) model to detect trends. For example, the article "Company D launches new product" is classified as a "hit."

[0987] Step 7:

[0988] The server analyzes past trend data and stock price data based on an AI model to predict future trends. For example, it predicts that the stock price of Company D will rise by 20% within one week following the release of a new product.

[0989] Step 8:

[0990] The server performs correlation analysis based on past trends and detected trend data, and evaluates the specific impact (correlation coefficient) that the trend has on stock prices.

[0991] Step 9:

[0992] The server generates a trading strategy based on the correlation analysis results, for example, generating a trading instruction to "immediately purchase 100 shares of Company D's stock" and sending it to the algorithmic trading platform.

[0993] Step 10:

[0994] The server executes the generated buy / sell orders through the trading platform API. For example, it issues a command to "immediately purchase 100 shares of Company D's stock" to the market.

[0995] Step 11:

[0996] The server inputs the user's input data and behavioral data into an emotion engine to analyze the user's emotions. For example, a user comment such as "This news is promising" is recognized as a positive emotion.

[0997] Step 12:

[0998] The server uses the emotion data obtained from the emotion engine to evaluate trend information. For example, if the user has positive emotions, the server strengthens the trend evaluation.

[0999] Step 13:

[1000] The server further refines the trading strategy based on the sentiment data and reflects it in the final buy / sell instructions, for example, increasing the number of shares to buy if the sentiment data is very positive.

[1001] Step 14:

[1002] The server monitors the results of executed trades in real time and records their performance data, e.g., evaluating stock price fluctuations and profits after a trade.

[1003] Step 15:

[1004] Based on the monitoring results, the server retrains the AI ​​model and emotion engine to improve prediction accuracy for future transactions. For example, if the trading results are as predicted, the reliability of the model is evaluated and further improvements are made.

[1005] In this way, the server integrates trend information, stock price data, and user emotion data to realize a system for efficient and automatic stock buying and selling.

[1006] Example 2

[1007] 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."

[1008] In the stock market, there is a demand for systems that can automatically execute highly accurate trading strategies that take into account not only trend information and market data, but also user sentiment data. However, conventional systems have difficulty integrating and utilizing this data, resulting in insufficient prediction accuracy and trading strategy flexibility. As a result, trading efficiency is lacking and human error is likely to occur.

[1009] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1010] In this invention, the server includes a data collection means for collecting trend information, a data preprocessing means for preprocessing the collected trend information and market data, a detection means for detecting and predicting trends based on the preprocessed trend information, a correlation analysis means for analyzing correlations using the detected trend information and market data, an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results, an emotion engine integration means for collecting user emotion data and using it to reinforce trading strategies, and a monitoring means for monitoring and verifying trading results. This enables a system that can automatically execute highly accurate and flexible trading strategies by integrating trend information, market data, and user emotion data.

[1011] "Trending information" refers to popular market events and topics collected from online news articles, social media posts, etc.

[1012] "Data Collection Means" means the technical means for obtaining trend information and market data in real time from multiple data sources on the Internet.

[1013] "Data Pre-processing Measures" are the processes and technical measures used to convert collected trend information and market data into a format that is easy to analyze.

[1014] "Detection methods" are technical methods that utilize AI and machine learning models to detect and predict trends based on pre-processed data.

[1015] "Correlation analysis means" refers to a technical means for analyzing correlations using detected trend information and market data.

[1016] An "algorithmic trading tool" is a technical tool for automatically executing stock buying and selling based on the results of correlation analysis.

[1017] The "emotion engine integration means" is a technical means for collecting and analyzing user emotion data and using it to reinforce trading strategies.

[1018] "Monitoring Means" means technical means for monitoring and verifying the results of executed transactions.

[1019] The present invention is a system for automatically executing stock buying and selling using trend information and stock price data, and also includes an emotion engine that analyzes user emotion data to augment trading strategies. In this system, a server collects trend information and stock price data from various data sources, performs preprocessing, uses a generative AI model to detect and predict trends, and further uses the emotion engine to evaluate and consider the user's emotional state to execute algorithmic trading.

[1020] Data collection

[1021] The server uses news APIs and social media APIs to collect trending information from the Internet. Specifically, it uses the News API and Twitter API to obtain news articles and social media posts in real time. The server also obtains real-time stock price data using a financial market data provider service (e.g., Alpha Vantage API). For example, the server uses a request URL such as "https: / / newsapi.org / v2 / everything?q=NewProduct&apiKey=your_api_key".

[1022] Data Preprocessing

[1023] The trend information collected by the server is first preprocessed. Specifically, the HTML tags of news articles are removed using Python's BeautifulSoup library, and then tokenized (divided into words) using the NLTK library. Furthermore, stock price data undergoes standardization processes such as scaling using scikit-learn's StandardScaler.

[1024] Trend detection and forecasting

[1025] The server inputs the preprocessed data into a generative AI model (e.g., an LSTM model using TensorFlow or PyTorch) to detect trends and make predictions. For example, if "Company C announces a new product" is a trend evaluated as a "hit," the server predicts that "Company C's stock price will rise by 20% over the next week."

[1026] Correlation analysis

[1027] The server analyzes the correlation between trend data and stock price data using the pandas library. By calculating the correlation coefficient, it quantifies the impact of trend information on stock prices. For example, if the correlation coefficient between trend information and stock price data is 0.8, the server adjusts its trading strategy based on this information.

[1028] Algorithmic trading execution

[1029] Based on the correlation analysis results, the server automatically buys and sells stocks. Specifically, it executes transactions using the Interactive Brokers API or Alpaca API. For example, based on the correlation analysis results, a trading instruction to "purchase 100 shares of Company C" is generated and executed.

[1030] Monitoring and Feedback

[1031] The server monitors the results of executed transactions in real time using Elasticsearch and Kibana, records the data, and retrains the AI ​​model based on the monitoring results to improve prediction accuracy in future transactions.

[1032] Emotion engine integration

[1033] The server collects user input and behavioral data and analyzes it using the Microsoft Text Analytics API. If a user has positive sentiment toward trading, that sentiment is reflected in trend information and influences trading strategies. For example, if a user comments, "This news looks very promising," that sentiment is taken into account as a positive sentiment and reflected in trading strategies.

[1034] Prompt Sentence Examples

[1035] Trend detection prompt:

[1036] Preprocess the text of the news article "Company C announces new product" into the following format:

[1037] Remove HTML tags from text

[1038] Tokenization is performed

[1039] Normalize

[1040] Input prompt for the emotion engine:

[1041] Perform sentiment analysis on the user comment "This news looks very promising" and return the result as either positive or negative.

[1042] In this way, the system integrates trend information, stock price data, and user sentiment data to efficiently and automatically trade stocks, reducing human error and utilizing both quantitative and qualitative data to achieve more advanced forecasting and trading.

[1043] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1044] Step 1: Collect data

[1045] The server collects trending information in real time using news APIs (e.g., NewsAPI) and social media APIs (e.g., Twitter API). It sends HTTP requests based on user-defined keywords and receives news data and social media posts in JSON format.

[1046] Input: Search keyword, News API URL

[1047] Output: News article data and social media posts in JSON format

[1048] Step 2: Preprocessing the data

[1049] The server preprocesses the collected trend information by first removing HTML tags using the BeautifulSoup library, then tokenizing it using the NLTK library, and scaling the data using StandardScaler from scikit-learn if financial market data is available.

[1050] Input: JSON-formatted news article data, social media posts, and stock price data

[1051] Output: Preprocessed text data, scaled stock price data

[1052] Step 3: Trend detection and forecasting

[1053] The server inputs the preprocessed data into a generative AI model (e.g., an LSTM model using TensorFlow or PyTorch) to detect and predict trends. Specifically, it feeds the input data into the model and outputs trend labels (e.g., "hit" or "miss") and predicted stock price fluctuations.

[1054] Input: Preprocessed text data, scaled stock price data

[1055] Output: Trend label, predicted stock price fluctuations

[1056] Step 4: Correlation analysis

[1057] To analyze the correlation between the trend data and stock price data, the server calculates the correlation coefficient using the pandas library. Specifically, it creates a DataFrame and calculates the correlation coefficient using the corr() method.

[1058] Input: Trend label, stock price data

[1059] Output: Correlation coefficient between trend and stock price

[1060] Step 5: Execute algorithmic trading

[1061] The server automatically executes stock purchases and sales based on the correlation analysis results. It uses the Interactive Brokers API or Alpaca API to generate and execute trading instructions based on specific conditions. Specifically, it generates JSON for the trading instructions and sends them to the API.

[1062] Input: Trend and stock price correlation coefficient, predicted stock price movement

[1063] Output: Executed trading instructions

[1064] Step 6: Monitoring and feedback

[1065] The server monitors the results of executed trades in real time, stores the data in Elasticsearch, and visualizes the results using Kibana. Furthermore, the AI ​​model is retrained based on the monitoring results to improve prediction accuracy for future transactions.

[1066] Input: Result data of executed trading instructions

[1067] Output: Monitoring report, retrained AI model

[1068] Step 7: Integrating the Emotion Engine

[1069] The server collects user input data and behavioral data, analyzes the sentiment data using a sentiment analysis API (e.g., Microsoft Text Analytics API), and reinforces the trading strategy based on the results. If the user has positive sentiment, that evaluation is reflected in the trend forecast.

[1070] Input: User comments, operation log

[1071] Output: Sentiment analysis results, reinforced trading strategies

[1072] (Application example 2)

[1073] 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."

[1074] Conventional stock trading systems exist that automatically buy and sell stocks using trend information and stock price data, but they lack a mechanism to utilize user emotional data to reinforce trading strategies. As a result, inefficient trading can occur, ignoring the user's emotional state. Furthermore, there is a lack of technology to improve the customer experience in brick-and-mortar stores and realize personalized product recommendations. This makes it difficult to provide a richer user experience.

[1075] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means for collecting trend information, a data preprocessing means for preprocessing the collected trend information, a detection means for detecting trends based on the preprocessed trend information, a correlation analysis means for analyzing correlations using the detected trend information and market data, an algorithmic trading means for automatically executing stock trading based on the correlation analysis results, a monitoring means for monitoring and verifying trading results, a sentiment analysis means for analyzing user sentiment data and reinforcing trading strategies, and an information provision means for displaying on a smart device. This enables more effective and personalized trading by trading stocks while also referencing user sentiment data. Furthermore, trend information can be provided in real time using smart devices in brick-and-mortar stores, improving the user experience and providing personalized suggestions.

[1076] definition statement

[1077] "Data collection means" refers to a hardware or software input interface for acquiring predetermined data from an information source.

[1078] A "data pre-processing means" is a device or program that performs operations or processes to convert collected data into a form suitable for analysis or processing.

[1079] "Detection methods" refer to algorithms and techniques that utilize pre-processed data to find specific patterns or events.

[1080] A "correlation analysis tool" is a technique or device for calculating and analyzing the relationships and correlations between multiple data sets.

[1081] An "algorithmic trading vehicle" is a system or program for automatically buying and selling stocks based on a pre-set algorithm.

[1082] "Monitoring means" means functions or means for monitoring the status of a process or transaction during or after execution and collecting data.

[1083] "Emotion analysis means" refers to algorithms and technologies for collecting and analyzing user emotion data.

[1084] "Information providing means" refers to a device or interface that displays and provides data and analysis results to users.

[1085] A "smart device" is a device that can connect to the Internet or other networks and can collect and process information.

[1086] MODE FOR CARRYING OUT THE INVENTION

[1087] This invention is a system that uses trend information, stock price data, and user emotion data, and a specific embodiment for actually implementing the system will be described in detail.

[1088] Data collection methods

[1089] The server uses a news API to obtain trend information in real time from multiple data sources on the Internet, including various data sources such as commercial news sites and social media, and also uses a financial market data provider to obtain real-time stock price data.

[1090] Data preprocessing measures

[1091] The server performs preprocessing on the collected trend information, such as removing HTML tags, tokenizing, and normalizing. It also normalizes and scales stock price data.

[1092] Detection Method

[1093] The preprocessed data is then analyzed using a trend detection model powered by TensorFlow and Keras to detect specific trends and predict their impact on stock prices.

[1094] Correlation Analysis Tools

[1095] The server performs correlation analysis using the detected trend information and market data, which includes a technique for calculating correlation coefficients based on past trend data and stock price data.

[1096] Algorithmic Trading Instruments

[1097] Based on the results of the correlation analysis, algorithmic trading is automatically executed. Specifically, stock buy and sell instructions are generated and executed according to a pre-set trading algorithm.

[1098] Monitoring Methods

[1099] The server monitors the results of executed trades in real time and collects evaluation data, which allows the system to evaluate overall performance and optimize trading strategies.

[1100] sentiment analysis tool

[1101] It collects user input and behavioral data and analyzes it using an emotion engine, for example, to detect positive or negative emotions from voice inputs and facial expressions, which can then be used to augment trading strategies.

[1102] Information provision means

[1103] It provides information to smart devices, specifically smart glasses and mobile devices, allowing users to check trend information and stock price data in real time, and also makes personalized product recommendations based on user sentiment.

[1104] Specific examples

[1105] For example, suppose the server collects news articles about "new product announcements" from a news API, preprocesses them, and then uses an AI model to determine that they are "hits." Based on this trend, the AI ​​model predicts that the target company's stock price will rise by 20% over the next week. Furthermore, the sentiment engine analyzes the user's comment, "This news looks very promising," and determines that this is a positive reaction. This information is provided to the user in real time via smart glasses.

[1106] Examples of prompts are:

[1107] "This product is so attractive!"

[1108] To implement this invention, it is necessary to build a system that integrates the above-mentioned means, allowing users to enjoy a personalized trading experience based on trend information and stock price data.

[1109] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1110] Program processing steps

[1111] Step 1: Data collection

[1112] The server uses the news API to collect the latest trending information. Specifically, it retrieves news articles based on specific keywords and categories. At this point, the input is the keywords and categories, and the output is the retrieved news article data.

[1113] Step 2: Collect stock data

[1114] The server uses a financial market data provider to collect relevant stock price data. The input is the ticker symbol of the target company, and the output is real-time stock price data.

[1115] Step 3: Data Preprocessing

[1116] The server performs preprocessing using the retrieved news articles, such as removing HTML tags, tokenizing, and normalizing the text. The input is the retrieved news article, and the output is the preprocessed text data. In addition, it also scales the stock price data.

[1117] Step 4: Trend detection

[1118] The server inputs the preprocessed news data into an AI model (e.g., TensorFlow or Keras model) to perform trend detection and prediction. The input is the preprocessed news data, and the output is the detected trend information and its predicted value.

[1119] Step 5: Correlation analysis

[1120] The server performs correlation analysis using the detected trend information and stock price data. Specifically, it calculates the correlation coefficient from past trend data and stock price data. The input is the trend information and stock price data, and the output is the correlation coefficient.

[1121] Step 6: Algorithmic trading

[1122] The server then applies a trading algorithm based on the results of the correlation analysis to automatically execute stock purchases and sales. The input is the correlation analysis results, and the output is specific trading instructions and their execution results.

[1123] Step 7: Monitoring

[1124] The server monitors the results of executed trades in real time and collects evaluation data. The input is the results of trade execution, and the output is the evaluation data and its analysis results.

[1125] Step 8: Sentiment analysis

[1126] The server collects user input data (e.g., voice input and comments) and analyzes them using an emotion engine. The input is user comments and voice, and the output is the emotion recognition results.

[1127] Step 9: Provide information

[1128] The server provides the detected trend information and emotion analysis results to smart devices, specifically smart glasses or mobile devices. The input is the trend information and emotion recognition results, and the output is the information provided to the user.

[1129] 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.

[1130] 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.

[1131] 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.

[1132] [Fourth embodiment]

[1133] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1134] 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.

[1135] 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).

[1136] 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.

[1137] 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.

[1138] 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).

[1139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1140] 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.

[1141] 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.

[1142] 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.

[1143] 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.

[1144] 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.

[1145] 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."

[1146] This invention is a system that automatically executes stock buying and selling using trend information and stock price data. In this system, a server collects trend information and stock price data from various data sources, performs preprocessing, detects and predicts trends using an AI model, and executes algorithmic trading based on the results.

[1147] System Program Overview

[1148] The system is implemented by a program with the following main functions:

[1149] 1. Data Collection:

[1150] The server uses news APIs and social media APIs to collect trending information on the Internet in real time.

[1151] The server obtains stock price data from a financial market data provider and updates it in real time.

[1152] 2. Data Preprocessing:

[1153] The server preprocesses the collected trend information, removing unnecessary elements from the text data and performing tokenization and normalization.

[1154] The server also pre-processes the stock price data, standardizing and normalizing it.

[1155] 3. Trend detection and forecasting:

[1156] The server then feeds the pre-processed data into an AI model to detect trends, such as classifying a particular news article as a "hit" or "outdated."

[1157] The server uses AI models to predict future trends, allowing the impact of certain events on stock prices to be known in advance.

[1158] 4. Correlation analysis:

[1159] The server analyzes the correlation between the detected trends and stock price data and calculates how much the trends affect stock prices.

[1160] 5. Algorithmic Trading Execution:

[1161] The server generates a trading strategy based on the correlation analysis results: if the trend is positive, it generates a "buy" instruction, and if it is negative, it generates a "sell" instruction.

[1162] The server connects to the trading platform and automatically executes the generated buy and sell orders.

[1163] 6. Monitoring and Feedback:

[1164] The server monitors the performance of executed trades in real time and records the results.

[1165] The server retrains the AI ​​model based on trading results, creating a feedback loop to improve prediction accuracy.

[1166] Specific examples

[1167] Data collection and preprocessing

[1168] The server collects articles such as "Company B announces innovative new product" from the news API.

[1169] The server removes HTML tags and special characters from the collected article data and splits it into words (tokenization).

[1170] Trend detection and forecasting

[1171] The server uses the AI ​​model to determine whether a news article is a "hit" or "outdated" based on the preprocessed news article. In this example, the announcement of a new product is deemed a "hit."

[1172] The server uses past data to predict how much this "hit" will increase the stock price. For example, it predicts that "Company B's stock price will rise by 10% over the next week."

[1173] Correlation Analysis and Algorithmic Trading

[1174] The server analyzes the correlation between the trend data and stock price data and calculates the extent to which a "hit" will affect stock price increases.

[1175] Based on the analysis results, the server generates a trading instruction to "immediately buy 100 shares of Company B's stock" and executes algorithmic trading.

[1176] Monitoring and Feedback

[1177] The server monitors the stock price movement after the transaction in real time and records the actual results. For example, if the stock price actually rises by 10% after one week, it will confirm that a profit was made as a result of the transaction.

[1178] The server retrains the AI ​​model based on these trading results to further improve the accuracy of the next prediction.

[1179] In this way, this system uses trend information and stock price data to efficiently and automatically buy and sell stocks, reducing human error and enabling advanced analysis.

[1180] The processing flow will be explained below.

[1181] Step 1:

[1182] The server periodically collects trending information from the Internet using news APIs and social media APIs. For example, it accesses the APIs every hour to retrieve articles such as "Company B announces an innovative new product."

[1183] Step 2:

[1184] The server obtains real-time stock price data from a financial market data provider. For example, it periodically collects stock price information for Company B from the Yahoo Finance API and stores it in a database, including past stock price history.

[1185] Step 3:

[1186] The server stores the collected news articles and social media posts in a database, along with metadata such as article IDs and post IDs.

[1187] Step 4:

[1188] The server removes HTML tags and special characters from the collected text data, extracts only the text, and then performs tokenization to split the text into words.

[1189] Step 5:

[1190] The server also preprocesses the collected stock price data, specifically by normalizing and standardizing stock prices to scale them to a range of 0 to 1.

[1191] Step 6:

[1192] The server then feeds the preprocessed news articles into a natural language processing (NLP) model to detect trends, such as classifying them as "hit" or "outdated."

[1193] Step 7:

[1194] The server uses past trend data and stock price data to predict future trends using an AI model. For example, it generates a prediction that "Company B's new product announcement will lead to a 10% increase in stock prices within one week."

[1195] Step 8:

[1196] The server analyzes the correlation between the detected trend and stock price data, specifically by calculating the correlation coefficient and evaluating the degree of impact of the trend on stock prices.

[1197] Step 9:

[1198] The server generates a trading strategy based on the results of the correlation analysis, for example, if the trend is evaluated as "hit", it generates a "buy" instruction and sends it to the trading platform.

[1199] Step 10:

[1200] The server connects to the trading platform and automatically executes the generated buy and sell orders, for example, "Buy 100 shares of Company B" through the API.

[1201] Step 11:

[1202] The server monitors the results of executed trades in real time and evaluates performance, including profits and losses.

[1203] Step 12:

[1204] The server retrains the AI ​​model based on the monitoring results to improve prediction accuracy, thereby increasing the accuracy of trend detection and stock price predictions from the next time onwards.

[1205] In this way, the server automatically buys and sells stocks using trend information and stock price data, realizing efficient algorithmic trading.

[1206] Example 1

[1207] 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."

[1208] Conventional stock trading systems have difficulty quickly and accurately analyzing market trend information to generate trading strategies. They also lack real-time monitoring and feedback functions to respond sensitively to changes in market trends, making it difficult to improve trading accuracy. As a result, investors find it difficult to avoid the risk of losses due to human error or misjudgment.

[1209] 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.

[1210] In this invention, the server includes: a data collection means for collecting trend information including news information and social media information; a data preprocessing means for removing unnecessary elements from the collected trend information and performing tokenization and normalization; a detection means for detecting and predicting trends using an artificial intelligence model based on the preprocessed trend information; a correlation analysis means for analyzing correlations using the detected trend information and market data and calculating the impact of the trends on market movements; an algorithmic trading means for generating a trading strategy based on the correlation analysis results and automatically executing stock purchases and sales; and a monitoring means for monitoring the results of executed transactions in real time and recording and verifying the trading results. This enables fast and accurate analysis of trend information and market data and real-time automated trading.

[1211] "Data collection means" refers to a device or method for obtaining trend information, including news information and social media information, from multiple data sources on the Internet in real time.

[1212] "Data preprocessing means" refers to a device or method that removes unnecessary elements from collected trend information and performs tokenization and normalization.

[1213] "Detection means" refers to a device or method that detects and predicts trends using artificial intelligence models based on pre-processed trend information.

[1214] "Correlation analysis means" refers to a device or method that uses detected trend information and market data to analyze correlations and calculate the impact of trends on market movements.

[1215] "Algorithmic trading tools" refer to devices or methods that generate trading strategies based on correlation analysis results and automatically execute stock buying and selling.

[1216] "Monitoring means" refers to a device or method for monitoring the results of executed transactions in real time, and for recording and verifying the results of the transactions.

[1217] "Artificial intelligence model" refers to a machine learning algorithm that makes predictions and classifications based on trend information.

[1218] "Trending information" refers to information about events and topics that affect the market, gathered through news and social media.

[1219] "Market data" refers to data including price information and trading volume of stocks and other financial instruments traded in financial markets.

[1220] The present invention is a system for automatically executing stock trading using trend information and market data. In this system, a server collects trend information and market data from various data sources, performs preprocessing, detects and predicts trends using an artificial intelligence model, and executes algorithmic trading based on the results. Specific embodiments of this system are described in detail below.

[1221] Data collection

[1222] The server collects trending information on the Internet in real time using a news API (e.g., NewsAPI) or a social media API (e.g., Twitter API). For example, the server retrieves news using the URL https: / / newsapi.org / v2 / everything?q=stock market&apiKey=your_api_key and collects tweets related to the Twitter hashtag "stockmarket." The server also collects real-time stock price data using a financial market data provider (e.g., Yahoo Finance API).

[1223] Data Preprocessing

[1224] The server removes unnecessary elements (e.g., HTML tags and special characters) from the collected trend information and performs tokenization and normalization. For example, the sentence "Company B announced an innovative new product" is tokenized as "Company B," "innovative," "new product," and "announcement." Twitter posts are also tokenized and normalized in the same way. Furthermore, scaling is performed to standardize the collected stock price data, for example, by constraining values ​​to a range from 0 to 1.

[1225] Trend detection and forecasting

[1226] The server inputs preprocessed news articles and social media posts into an artificial intelligence model (e.g., BERT or LSTM) to detect and predict trends. As a specific example, in trend detection using news articles, an article stating "Company B has announced an innovative new product" is classified as a "hit." When making predictions, a scenario such as "Company B's stock price will rise by 10% in the next week" is generated.

[1227] Correlation analysis

[1228] The server analyzes correlations using detected trend information and past market data. For example, it calculates a correlation coefficient based on past data to see how much a trend like "new product announcement" affects stock price increases. This analysis makes it possible to evaluate which trends affect stock prices and how they affect them.

[1229] Algorithmic trading execution

[1230] The server generates a trading strategy based on the results of the correlation analysis. For example, it creates a specific trading strategy such as "Purchase 100 shares of Company B because the stock price is predicted to rise by 10%." This trading strategy is then connected to a trading platform such as the Interactive Brokers API and executed automatically.

[1231] Monitoring and Feedback

[1232] The server monitors the results of executed trades in real time, recording and verifying the results. For example, it monitors stock price movements after a trade and evaluates how accurate the predictions were. Based on these results, the AI ​​model can be retrained to improve the accuracy of future predictions.

[1233] Prompt Sentence Examples

[1234] To input trend information into the generative AI model, the server uses a prompt like this:

[1235] "Predict the impact this news will have on stock prices." The generative AI model responds to the prompt with a prediction such as, "This news could increase stock prices by 10%."

[1236] In this way, the system efficiently and automatically utilizes trend information and market data to buy and sell stocks, minimizing human error and enabling advanced analysis.

[1237] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1238] Step 1: Data collection

[1239] The server uses news and social media APIs to collect trending information on the Internet in real time. Specifically, it retrieves the latest news articles from the News API and collects posts related to a specific hashtag (e.g., stockmarket) using the Twitter API. This provides the data of the news articles and tweets retrieved as input. This data is saved in JSON format for processing in subsequent steps.

[1240] Step 2: Data Preprocessing

[1241] The server removes unnecessary elements from the collected trend information and tokenizes and normalizes the text data. This process involves, for example, removing HTML tags using BeautifulSoup and dividing sentences into tokens using NLTK. Specifically, the news article "Company B announces innovative new product" is tokenized into "Company B," "innovative," "new product," and "announcement." The input data is text information, and the output is tokenized and normalized text data. Similar processing is applied to tweets.

[1242] Step 3: Trend detection and forecasting

[1243] The server uses an artificial intelligence model (e.g., BERT or LSTM) to detect and predict trends based on the preprocessed trend information. Specifically, tokenized news articles are input into the BERT model, which classifies them as "hits" or "outdated." In this example, an article stating "Company B announced an innovative new product" is classified as a "hit." Furthermore, the LSTM model predicts that "Company B's stock price will rise by 10% over the next week." The input data is preprocessed text data, and the output is trend detection results and stock price predictions.

[1244] Step 4: Correlation analysis

[1245] The server analyzes correlations using detected trend information and past market data. Specifically, it uses Python's Pandas and Numpy libraries to align past stock price data and trend data in chronological order and calculate the correlation coefficient. For example, it calculates how much impact the trend of "new product announcements" has had on stock price increases in the past. The input data are trend data and stock price data, and the output is the correlation coefficient.

[1246] Step 5: Execute algorithmic trading

[1247] The server generates a trading strategy based on the correlation analysis results and automatically buys and sells stocks. Specifically, it generates trading instructions such as "buy 100 shares of Company B because the stock price will rise by 10%" based on the correlation coefficient and predicted trend, and actually executes the trade using the Interactive Brokers API. The input data are the correlation analysis results and predicted trend, and the output is trading instructions and execution.

[1248] Step 6: Monitoring and feedback

[1249] The server monitors the results of executed trades in real time, recording and verifying the data. Specifically, it monitors post-trade stock price movements and evaluates the profits and losses of the trades. Furthermore, it retrains the AI ​​model based on these results and makes adjustments to improve the accuracy of the next prediction. The input data are trading results and market data, and the output is trading performance data and an updated AI model.

[1250] In this way, the system efficiently and automatically utilizes trend information and market data to buy and sell stocks.

[1251] (Application example 1)

[1252] 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."

[1253] While conventional systems were able to trade stocks based on trend information and market data, they lacked a way to optimize the display position of best-selling items in virtual stores in real time. As a result, it was difficult to effectively display products that would attract consumer interest, making it difficult to maximize sales. Furthermore, there was a lack of technology to efficiently analyze market trends and inventory data and quickly reflect new trends.

[1254] 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.

[1255] In this invention, the server includes a data collection means for collecting trend information, a data preprocessing means for preprocessing the collected trend information, a detection means for detecting trends based on the preprocessed trend information, a correlation analysis means for analyzing correlations using the detected trend information and market data, an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results, a monitoring means for monitoring and verifying the buying and selling results, and an analysis means for analyzing the trend information and inventory data in real time, automatically selecting best-selling products, and adjusting their display positions within the virtual store. This makes it possible to effectively display products that attract consumers' interest and maximize sales.

[1256] "Trend information" is data collected from online news, social media, etc., that shows current market and consumer trends.

[1257] "Data collection means" refers to a means for obtaining trend information and market data in real time from multiple data sources on the Internet.

[1258] The "data preprocessing means" is a means for removing unnecessary elements from collected trend information and performing preprocessing such as tokenization and normalization.

[1259] "Detection means" means a means for detecting trends using an AI model based on pre-processed trend information.

[1260] A "correlation analysis means" is a means for analyzing the correlation between detected trend information and market data.

[1261] An "algorithmic trading tool" is a tool for automatically executing stock buying and selling based on the results of correlation analysis.

[1262] "Monitoring means" refers to a means for monitoring trading results in real time and verifying trading performance.

[1263] "Inventory data" is data that indicates the inventory status of products sold in the virtual store.

[1264] The "analysis means" is a means for analyzing trend information and inventory data in real time, automatically selecting best-selling items, and adjusting their display position within the virtual store.

[1265] System Overview

[1266] This invention provides a system that automatically selects best-selling items based on trend information and inventory data in a virtual store and optimizes their display position. The system has the following main functions:

[1267] Hardware Configuration

[1268] 1. Server: Performs data collection, pre-processing, trend detection, correlation analysis, algorithmic trading, monitoring and analysis.

[1269] 2. Client terminal: A device (smartphone, tablet, PC, etc.) through which a user accesses the virtual store.

[1270] 3. Network connection: A network for data communication between the server and client terminals.

[1271] Software Configuration

[1272] 1. Data collection method: Use news APIs and social media APIs to collect trend information in real time and obtain inventory information from the inventory database.

[1273] 2. Data preprocessing methods: Remove unnecessary elements from the collected trend information, and perform tokenization and normalization.

[1274] 3. Detection method: Based on the pre-processed trend information, trends are detected using a generative AI model.

[1275] 4. Correlation analysis method: Based on the detected trend information and market data, the correlation between them is analyzed.

[1276] 5. Algorithmic trading tools: Automatically buy and sell stocks based on correlation analysis results.

[1277] 6. Monitoring: Monitor trading results in real time and verify trading performance.

[1278] 7. Analysis method: Trend information and inventory data are analyzed in real time, and best-selling items are automatically selected and their display position within the virtual store is adjusted.

[1279] System Operation

[1280] The server collects trend information in real time from news APIs and social media APIs. For example, information such as "a new smartphone is all the rage" is collected. Stock information for the relevant product is obtained from the inventory database. This collected data is then tokenized and normalized using data preprocessing means to remove unnecessary elements.

[1281] The pre-processed data is input into the detection means, and trends are detected using a generative AI model. The detected trend information is analyzed for correlation with market data by the correlation analysis means. Based on the results of this correlation analysis, buy and sell instructions are automatically executed by the algorithmic trading means.

[1282] The monitoring means monitors and verifies the results in real time. At the same time, the analysis means analyzes trend information and inventory data in real time and automatically selects best-selling items. As a result, products that attract consumers' interest are automatically placed in prominent positions in the virtual store.

[1283] For example, based on trend information such as "A new smartphone is all the rage" obtained from a news API and inventory information from an inventory database, the smartphone is picked up as a best-selling item by the analysis method and placed in a prominent position in the virtual store.

[1284] Prompt Sentence Examples

[1285] "We collect the latest trend information from news APIs, and based on that information, we predict which products will be popular and select recommended products for the virtual store."

[1286] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1287] Step 1:

[1288] The server collects trending information on the Internet using news and social media APIs. It receives API responses as input and obtains raw trending information as output. This trending information includes keywords and topics that indicate consumer interest.

[1289] Step 2:

[1290] The server retrieves inventory information for products in the virtual store from the inventory database. It executes a database query as input and obtains product availability data as output. This inventory information includes the current stock quantity and price of each product.

[1291] Step 3:

[1292] The server preprocesses the collected trend information. Specifically, it removes HTML tags and special characters from the trend information, and performs tokenization and normalization. It receives raw trend information data as input and generates preprocessed, clean trend data as output.

[1293] Step 4:

[1294] The server uses a generative AI model to detect trends based on the preprocessed trend data. The clean trend data is input to the AI ​​model, and the detected trend information is output. This output is information about a trend, such as "A new smartphone is becoming all the rage."

[1295] Step 5:

[1296] The server analyzes the correlation using the detected trend information and inventory data. Specifically, it calculates the correlation coefficient based on past trend data and inventory data, and analyzes which trends affect which products. Using the detected trend information and inventory data as input, the server obtains the correlation analysis results as output.

[1297] Step 6:

[1298] The server automatically selects best-selling products based on the correlation analysis results using analytical means. Specifically, it prioritizes products with high correlation and calculates a score for those products. It uses the correlation analysis results as input and generates a list of the selected best-selling products as output.

[1299] Step 7:

[1300] The server adjusts the display position of the selected best-selling items to automatically place them in prominent positions within the virtual store. Specifically, it updates the virtual store interface so that they are displayed as recommended items on the user's device. It uses the list of selected best-selling items as input and generates the updated display content of the virtual store as output.

[1301] Step 8:

[1302] The server monitors trading results and post-product placement performance in real time and adjusts system behavior as needed. Specifically, it collects and analyzes trading performance data and sales data, and uses it to retrain the generative AI model. It uses real-time performance data as input and outputs it to adjust system behavior and update the AI ​​model.

[1303] 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.

[1304] The present invention is a system for automatically executing stock buying and selling using trend information and stock price data, and also includes an emotion engine that analyzes user emotion data to augment trading strategies. In this system, a server collects trend information and stock price data from various data sources, performs preprocessing, uses an AI model to detect and predict trends, and further uses the emotion engine to evaluate and consider the user's emotional state to execute algorithmic trading.

[1305] System Program Overview

[1306] The system is implemented by a program with the following main functions:

[1307] 1. Data Collection:

[1308] The server collects trending information from the Internet in real time through news APIs and social media APIs.

[1309] The server uses a financial market data provider service to obtain real-time stock price data.

[1310] 2. Data Preprocessing:

[1311] The server preprocesses the collected trend information, removing unnecessary elements from the text data and performing tokenization and normalization.

[1312] The server also performs preprocessing on the acquired stock price data, scaling it, etc.

[1313] 3. Trend detection and forecasting:

[1314] The server inputs the pre-processed data into an AI model to detect trends and make predictions.

[1315] For example, if the launch of a new product is evaluated as a "hit," it predicts that the stock price will rise thereafter.

[1316] 4. Correlation analysis:

[1317] The server analyzes the correlation between the trend data and the stock price data and evaluates the extent to which the trend affects the stock price.

[1318] 5. Algorithmic Trading Execution:

[1319] The server generates a trading strategy based on the correlation analysis results and automatically executes the buying and selling of stocks.

[1320] 6. Monitoring and Feedback:

[1321] The server monitors the results of executed transactions and feeds back the evaluation results to improve the AI ​​model.

[1322] 7. Emotion engine integration:

[1323] The server collects user input data and behavioral data and analyzes it using an emotion engine.

[1324] The server reinforces the evaluation of trend information based on the emotion recognition results and influences trading strategies.

[1325] Specific examples

[1326] Data collection and preprocessing

[1327] The server collects articles from the news API such as "Company C announces new innovative product."

[1328] The server removes HTML tags from this data and splits the text into words (tokenization).

[1329] Trend detection and forecasting

[1330] The server inputs the preprocessed article data into the AI ​​model and detects trends as "hits."

[1331] Based on this trend, the server predicts that Company C's stock price will rise 20% over the next week.

[1332] Correlation Analysis and Algorithmic Trading

[1333] The server analyzes the correlation between the trend and stock price data and calculates how much the "hit" trend affects stock prices.

[1334] Based on the correlation analysis results, the server generates a trading instruction to "purchase 100 shares of Company C's stock" and executes this as algorithmic trading.

[1335] Emotion engine integration

[1336] The server collects user input data (e.g., investment comments and operation logs) and analyzes it using an emotion engine.

[1337] If the user has positive feelings about the transaction, the server reflects the evaluation in the trend information.

[1338] For example, if a user comments, "This news looks very promising," this can be taken as a positive evaluation and reflected in trading strategies.

[1339] Monitoring and Feedback

[1340] The server monitors the results of the executed transactions in real time and records the data.

[1341] The server retrains the AI ​​model and emotion engine based on the monitoring results, improving prediction accuracy from next time onwards.

[1342] In this way, the system integrates trend information, stock price data, and user sentiment data to efficiently and automatically trade stocks, reducing human error and utilizing both quantitative and qualitative data to achieve more advanced forecasting and trading.

[1343] The processing flow will be explained below.

[1344] Step 1:

[1345] The server uses news and social media APIs to gather the latest trending information in real time. For example, it accesses the API every hour to retrieve articles such as "Company D announces innovative new product."

[1346] Step 2:

[1347] The server uses the API of a financial market data provider to obtain real-time stock price data. For example, it collects stock price information for Company D from the Yahoo Finance API and stores it in a database, including past stock price history.

[1348] Step 3:

[1349] The server stores the collected news articles and social media posts in a database, along with metadata such as the article ID, posting date and time, and poster ID.

[1350] Step 4:

[1351] The server removes HTML tags and special characters from the collected text data to generate clean text data, then performs tokenization to split the text into words.

[1352] Step 5:

[1353] The server performs standardization or normalization on the collected stock price data, for example, scaling the stock price data to a range of 0 to 1.

[1354] Step 6:

[1355] The server inputs preprocessed news articles and social media posts into a natural language processing (NLP) model to detect trends. For example, the article "Company D launches new product" is classified as a "hit."

[1356] Step 7:

[1357] The server analyzes past trend data and stock price data based on an AI model to predict future trends. For example, it predicts that the stock price of Company D will rise by 20% within one week following the release of a new product.

[1358] Step 8:

[1359] The server performs correlation analysis based on past trends and detected trend data, and evaluates the specific impact (correlation coefficient) that the trend has on stock prices.

[1360] Step 9:

[1361] The server generates a trading strategy based on the correlation analysis results, for example, generating a trading instruction to "immediately purchase 100 shares of Company D's stock" and sending it to the algorithmic trading platform.

[1362] Step 10:

[1363] The server executes the generated buy / sell orders through the trading platform API. For example, it issues a command to "immediately purchase 100 shares of Company D's stock" to the market.

[1364] Step 11:

[1365] The server inputs the user's input data and behavioral data into an emotion engine to analyze the user's emotions. For example, a user comment such as "This news is promising" is recognized as a positive emotion.

[1366] Step 12:

[1367] The server uses the emotion data obtained from the emotion engine to evaluate trend information. For example, if the user has positive emotions, the server strengthens the trend evaluation.

[1368] Step 13:

[1369] The server further refines the trading strategy based on the sentiment data and reflects it in the final buy / sell instructions, for example, increasing the number of shares to buy if the sentiment data is very positive.

[1370] Step 14:

[1371] The server monitors the results of executed trades in real time and records their performance data, e.g., evaluating stock price fluctuations and profits after a trade.

[1372] Step 15:

[1373] Based on the monitoring results, the server retrains the AI ​​model and emotion engine to improve prediction accuracy for future transactions. For example, if the trading results are as predicted, the reliability of the model is evaluated and further improvements are made.

[1374] In this way, the server integrates trend information, stock price data, and user emotion data to realize a system for efficient and automatic stock buying and selling.

[1375] Example 2

[1376] 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."

[1377] In the stock market, there is a demand for systems that can automatically execute highly accurate trading strategies that take into account not only trend information and market data, but also user sentiment data. However, conventional systems have difficulty integrating and utilizing this data, resulting in insufficient prediction accuracy and trading strategy flexibility. As a result, trading efficiency is lacking and human error is likely to occur.

[1378] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1379] In this invention, the server includes a data collection means for collecting trend information, a data preprocessing means for preprocessing the collected trend information and market data, a detection means for detecting and predicting trends based on the preprocessed trend information, a correlation analysis means for analyzing correlations using the detected trend information and market data, an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results, an emotion engine integration means for collecting user emotion data and using it to reinforce trading strategies, and a monitoring means for monitoring and verifying trading results. This enables a system that can automatically execute highly accurate and flexible trading strategies by integrating trend information, market data, and user emotion data.

[1380] "Trending information" refers to popular market events and topics collected from online news articles, social media posts, etc.

[1381] "Data Collection Means" means the technical means for obtaining trend information and market data in real time from multiple data sources on the Internet.

[1382] "Data Pre-processing Measures" are the processes and technical measures used to convert collected trend information and market data into a format that is easy to analyze.

[1383] "Detection methods" are technical methods that utilize AI and machine learning models to detect and predict trends based on pre-processed data.

[1384] "Correlation analysis means" refers to a technical means for analyzing correlations using detected trend information and market data.

[1385] An "algorithmic trading tool" is a technical tool for automatically executing stock buying and selling based on the results of correlation analysis.

[1386] The "emotion engine integration means" is a technical means for collecting and analyzing user emotion data and using it to reinforce trading strategies.

[1387] "Monitoring Means" means technical means for monitoring and verifying the results of executed transactions.

[1388] The present invention is a system for automatically executing stock buying and selling using trend information and stock price data, and also includes an emotion engine that analyzes user emotion data to augment trading strategies. In this system, a server collects trend information and stock price data from various data sources, performs preprocessing, uses a generative AI model to detect and predict trends, and further uses the emotion engine to evaluate and consider the user's emotional state to execute algorithmic trading.

[1389] Data collection

[1390] The server uses news APIs and social media APIs to collect trending information from the Internet. Specifically, it uses the News API and Twitter API to obtain news articles and social media posts in real time. The server also obtains real-time stock price data using a financial market data provider service (e.g., Alpha Vantage API). For example, the server uses a request URL such as "https: / / newsapi.org / v2 / everything?q=NewProduct&apiKey=your_api_key".

[1391] Data Preprocessing

[1392] The trend information collected by the server is first preprocessed. Specifically, the HTML tags of news articles are removed using Python's BeautifulSoup library, and then tokenized (divided into words) using the NLTK library. Furthermore, stock price data undergoes standardization processes such as scaling using scikit-learn's StandardScaler.

[1393] Trend detection and forecasting

[1394] The server inputs the preprocessed data into a generative AI model (e.g., an LSTM model using TensorFlow or PyTorch) to detect trends and make predictions. For example, if "Company C announces a new product" is a trend evaluated as a "hit," the server predicts that "Company C's stock price will rise by 20% over the next week."

[1395] Correlation analysis

[1396] The server analyzes the correlation between trend data and stock price data using the pandas library. By calculating the correlation coefficient, it quantifies the impact of trend information on stock prices. For example, if the correlation coefficient between trend information and stock price data is 0.8, the server adjusts its trading strategy based on this information.

[1397] Algorithmic trading execution

[1398] Based on the correlation analysis results, the server automatically buys and sells stocks. Specifically, it executes transactions using the Interactive Brokers API or Alpaca API. For example, based on the correlation analysis results, a trading instruction to "purchase 100 shares of Company C" is generated and executed.

[1399] Monitoring and Feedback

[1400] The server monitors the results of executed transactions in real time using Elasticsearch and Kibana, records the data, and retrains the AI ​​model based on the monitoring results to improve prediction accuracy in future transactions.

[1401] Emotion engine integration

[1402] The server collects user input and behavioral data and analyzes it using the Microsoft Text Analytics API. If a user has positive sentiment toward trading, that sentiment is reflected in trend information and influences trading strategies. For example, if a user comments, "This news looks very promising," that sentiment is taken into account as a positive sentiment and reflected in trading strategies.

[1403] Prompt Sentence Examples

[1404] Trend detection prompt:

[1405] Preprocess the text of the news article "Company C announces new product" into the following format:

[1406] Remove HTML tags from text

[1407] Tokenization is performed

[1408] Normalize

[1409] Input prompt for the emotion engine:

[1410] Perform sentiment analysis on the user comment "This news looks very promising" and return the result as either positive or negative.

[1411] In this way, the system integrates trend information, stock price data, and user sentiment data to efficiently and automatically trade stocks, reducing human error and utilizing both quantitative and qualitative data to achieve more advanced forecasting and trading.

[1412] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1413] Step 1: Collect data

[1414] The server collects trending information in real time using news APIs (e.g., NewsAPI) and social media APIs (e.g., Twitter API). It sends HTTP requests based on user-defined keywords and receives news data and social media posts in JSON format.

[1415] Input: Search keyword, News API URL

[1416] Output: News article data and social media posts in JSON format

[1417] Step 2: Preprocessing the data

[1418] The server preprocesses the collected trend information by first removing HTML tags using the BeautifulSoup library, then tokenizing it using the NLTK library, and scaling the data using StandardScaler from scikit-learn if financial market data is available.

[1419] Input: JSON-formatted news article data, social media posts, and stock price data

[1420] Output: Preprocessed text data, scaled stock price data

[1421] Step 3: Trend detection and forecasting

[1422] The server inputs the preprocessed data into a generative AI model (e.g., an LSTM model using TensorFlow or PyTorch) to detect and predict trends. Specifically, it feeds the input data into the model and outputs trend labels (e.g., "hit" or "miss") and predicted stock price fluctuations.

[1423] Input: Preprocessed text data, scaled stock price data

[1424] Output: Trend label, predicted stock price fluctuations

[1425] Step 4: Correlation analysis

[1426] To analyze the correlation between the trend data and stock price data, the server calculates the correlation coefficient using the pandas library. Specifically, it creates a DataFrame and calculates the correlation coefficient using the corr() method.

[1427] Input: Trend label, stock price data

[1428] Output: Correlation coefficient between trend and stock price

[1429] Step 5: Execute algorithmic trading

[1430] The server automatically executes stock purchases and sales based on the correlation analysis results. It uses the Interactive Brokers API or Alpaca API to generate and execute trading instructions based on specific conditions. Specifically, it generates JSON for the trading instructions and sends them to the API.

[1431] Input: Trend and stock price correlation coefficient, predicted stock price movement

[1432] Output: Executed trading instructions

[1433] Step 6: Monitoring and feedback

[1434] The server monitors the results of executed trades in real time, stores the data in Elasticsearch, and visualizes the results using Kibana. Furthermore, the AI ​​model is retrained based on the monitoring results to improve prediction accuracy for future transactions.

[1435] Input: Result data of executed trading instructions

[1436] Output: Monitoring report, retrained AI model

[1437] Step 7: Integrating the Emotion Engine

[1438] The server collects user input data and behavioral data, analyzes the sentiment data using a sentiment analysis API (e.g., Microsoft Text Analytics API), and reinforces the trading strategy based on the results. If the user has positive sentiment, that evaluation is reflected in the trend forecast.

[1439] Input: User comments, operation log

[1440] Output: Sentiment analysis results, reinforced trading strategies

[1441] (Application example 2)

[1442] 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."

[1443] Conventional stock trading systems exist that automatically buy and sell stocks using trend information and stock price data, but they lack a mechanism to utilize user emotional data to reinforce trading strategies. As a result, inefficient trading can occur, ignoring the user's emotional state. Furthermore, there is a lack of technology to improve the customer experience in brick-and-mortar stores and realize personalized product recommendations. This makes it difficult to provide a richer user experience.

[1444] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means for collecting trend information, a data preprocessing means for preprocessing the collected trend information, a detection means for detecting trends based on the preprocessed trend information, a correlation analysis means for analyzing correlations using the detected trend information and market data, an algorithmic trading means for automatically executing stock trading based on the correlation analysis results, a monitoring means for monitoring and verifying trading results, a sentiment analysis means for analyzing user sentiment data and reinforcing trading strategies, and an information provision means for displaying on a smart device. This enables more effective and personalized trading by trading stocks while also referencing user sentiment data. Furthermore, trend information can be provided in real time using smart devices in brick-and-mortar stores, improving the user experience and providing personalized suggestions.

[1445] definition statement

[1446] "Data collection means" refers to a hardware or software input interface for acquiring predetermined data from an information source.

[1447] A "data pre-processing means" is a device or program that performs operations or processes to convert collected data into a form suitable for analysis or processing.

[1448] "Detection methods" refer to algorithms and techniques that utilize pre-processed data to find specific patterns or events.

[1449] A "correlation analysis tool" is a technique or device for calculating and analyzing the relationships and correlations between multiple data sets.

[1450] An "algorithmic trading vehicle" is a system or program for automatically buying and selling stocks based on a pre-set algorithm.

[1451] "Monitoring means" means functions or means for monitoring the status of a process or transaction during or after execution and collecting data.

[1452] "Emotion analysis means" refers to algorithms and technologies for collecting and analyzing user emotion data.

[1453] "Information providing means" refers to a device or interface that displays and provides data and analysis results to users.

[1454] A "smart device" is a device that can connect to the Internet or other networks and can collect and process information.

[1455] MODE FOR CARRYING OUT THE INVENTION

[1456] This invention is a system that uses trend information, stock price data, and user emotion data, and a specific embodiment for actually implementing the system will be described in detail.

[1457] Data collection methods

[1458] The server uses a news API to obtain trend information in real time from multiple data sources on the Internet, including various data sources such as commercial news sites and social media, and also uses a financial market data provider to obtain real-time stock price data.

[1459] Data preprocessing measures

[1460] The server performs preprocessing on the collected trend information, such as removing HTML tags, tokenizing, and normalizing. It also normalizes and scales stock price data.

[1461] Detection Method

[1462] The preprocessed data is then analyzed using a trend detection model powered by TensorFlow and Keras to detect specific trends and predict their impact on stock prices.

[1463] Correlation Analysis Tools

[1464] The server performs correlation analysis using the detected trend information and market data, which includes a technique for calculating correlation coefficients based on past trend data and stock price data.

[1465] Algorithmic Trading Instruments

[1466] Based on the results of the correlation analysis, algorithmic trading is automatically executed. Specifically, stock buy and sell instructions are generated and executed according to a pre-set trading algorithm.

[1467] Monitoring Methods

[1468] The server monitors the results of executed trades in real time and collects evaluation data, which allows the system to evaluate overall performance and optimize trading strategies.

[1469] sentiment analysis tool

[1470] It collects user input and behavioral data and analyzes it using an emotion engine, for example, to detect positive or negative emotions from voice inputs and facial expressions, which can then be used to augment trading strategies.

[1471] Information provision means

[1472] It provides information to smart devices, specifically smart glasses and mobile devices, allowing users to check trend information and stock price data in real time, and also makes personalized product recommendations based on user sentiment.

[1473] Specific examples

[1474] For example, suppose the server collects news articles about "new product announcements" from a news API, preprocesses them, and then uses an AI model to determine that they are "hits." Based on this trend, the AI ​​model predicts that the target company's stock price will rise by 20% over the next week. Furthermore, the sentiment engine analyzes the user's comment, "This news looks very promising," and determines that this is a positive reaction. This information is provided to the user in real time via smart glasses.

[1475] Examples of prompts are:

[1476] "This product is so attractive!"

[1477] To implement this invention, it is necessary to build a system that integrates the above-mentioned means, allowing users to enjoy a personalized trading experience based on trend information and stock price data.

[1478] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1479] Program processing steps

[1480] Step 1: Data collection

[1481] The server uses the news API to collect the latest trending information. Specifically, it retrieves news articles based on specific keywords and categories. At this point, the input is the keywords and categories, and the output is the retrieved news article data.

[1482] Step 2: Collect stock data

[1483] The server uses a financial market data provider to collect relevant stock price data. The input is the ticker symbol of the target company, and the output is real-time stock price data.

[1484] Step 3: Data Preprocessing

[1485] The server performs preprocessing using the retrieved news articles, such as removing HTML tags, tokenizing, and normalizing the text. The input is the retrieved news article, and the output is the preprocessed text data. In addition, it also scales the stock price data.

[1486] Step 4: Trend detection

[1487] The server inputs the preprocessed news data into an AI model (e.g., TensorFlow or Keras model) to perform trend detection and prediction. The input is the preprocessed news data, and the output is the detected trend information and its predicted value.

[1488] Step 5: Correlation analysis

[1489] The server performs correlation analysis using the detected trend information and stock price data. Specifically, it calculates the correlation coefficient from past trend data and stock price data. The input is the trend information and stock price data, and the output is the correlation coefficient.

[1490] Step 6: Algorithmic trading

[1491] The server then applies a trading algorithm based on the results of the correlation analysis to automatically execute stock purchases and sales. The input is the correlation analysis results, and the output is specific trading instructions and their execution results.

[1492] Step 7: Monitoring

[1493] The server monitors the results of executed trades in real time and collects evaluation data. The input is the results of trade execution, and the output is the evaluation data and its analysis results.

[1494] Step 8: Sentiment analysis

[1495] The server collects user input data (e.g., voice input and comments) and analyzes them using an emotion engine. The input is user comments and voice, and the output is the emotion recognition results.

[1496] Step 9: Provide information

[1497] The server provides the detected trend information and emotion analysis results to smart devices, specifically smart glasses or mobile devices. The input is the trend information and emotion recognition results, and the output is the information provided to the user.

[1498] 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.

[1499] 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.

[1500] 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 robot 414.

[1501] 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.

[1502] 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.

[1503] 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.

[1504] 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).

[1505] 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.

[1506] 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."

[1507] 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.

[1508] 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 according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1509] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1510] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1511] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1512] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1513] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1514] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1515] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1516] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1517] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1518] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1519] The following is further disclosed regarding the above embodiment.

[1520] (Claim 1)

[1521] a data collection means for collecting trend information;

[1522] a data preprocessing means for preprocessing the collected trend information;

[1523] detection means for detecting trends based on the preprocessed trend information;

[1524] a correlation analysis means for analyzing correlations using the detected trend information and market data;

[1525] an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results;

[1526] a monitoring means for monitoring and verifying trading results;

[1527] A system including:

[1528] (Claim 2)

[1529] 2. The system according to claim 1, wherein the data collection means is a means for obtaining trend information in real time from a plurality of data sources on the Internet.

[1530] (Claim 3)

[1531] 2. The system according to claim 1, wherein the correlation analysis means calculates a correlation coefficient based on past trend data and stock price data.

[1532] "Example 1"

[1533] (Claim 1)

[1534] data collection means for collecting trend information, including news information and social media information;

[1535] a data preprocessing means for removing unnecessary elements from the collected trend information and performing tokenization and normalization;

[1536] detection means for detecting and predicting trends using an artificial intelligence model based on the preprocessed trend information;

[1537] a correlation analysis means for analyzing correlations using detected trend information and market data and calculating the impact of the trend on market movements;

[1538] an algorithmic trading means for generating a trading strategy based on the correlation analysis result and automatically executing the buying and selling of stocks;

[1539] monitoring means for monitoring the results of executed transactions in real time and for recording and verifying the results of the transactions;

[1540] A system including:

[1541] (Claim 2)

[1542] 2. The system according to claim 1, wherein the data collection means is a means for acquiring news information and social media information in real time from multiple data sources on the Internet.

[1543] (Claim 3)

[1544] 2. The system according to claim 1, wherein the correlation analysis means calculates a correlation coefficient based on past trend data and market data.

[1545] "Application Example 1"

[1546] (Claim 1)

[1547] a data collection means for collecting trend information;

[1548] a data preprocessing means for preprocessing the collected trend information;

[1549] detection means for detecting trends based on the preprocessed trend information;

[1550] a correlation analysis means for analyzing correlations using the detected trend information and market data;

[1551] an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results;

[1552] a monitoring means for monitoring and verifying trading results;

[1553] A means of analysis to analyze trend information and inventory data in real time, automatically pick out best-selling products, and adjust their display position within the virtual store.

[1554] A system including:

[1555] (Claim 2)

[1556] 2. The system according to claim 1, wherein the data collection means is a means for obtaining trend information in real time from a plurality of data sources on the Internet.

[1557] (Claim 3)

[1558] 2. The system according to claim 1, wherein the correlation analysis means calculates a correlation coefficient based on past trend data and market data.

[1559] "Example 2: Combining Emotion Engines"

[1560] (Claim 1)

[1561] a data collection means for collecting trend information;

[1562] a data pre-processing means for pre-processing the collected trend information and market data;

[1563] detection means for detecting and predicting trends based on the preprocessed trend information;

[1564] a correlation analysis means for analyzing correlations using the detected trend information and market data;

[1565] an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results;

[1566] an emotion engine integration means for collecting user emotion data and using it to augment trading strategies;

[1567] a monitoring means for monitoring and verifying trading results;

[1568] A system including:

[1569] (Claim 2)

[1570] 10. The system of claim 1, which is a means for obtaining trend information in real time from multiple data sources on the Internet.

[1571] (Claim 3)

[1572] 2. The system according to claim 1, wherein the system is a means for calculating a correlation coefficient based on past trend data and market data.

[1573] "Application example 2 when combining emotion engines"

[1574] (Claim 1)

[1575] a data collection means for collecting trend information;

[1576] a data preprocessing means for preprocessing the collected trend information;

[1577] detection means for detecting trends based on the preprocessed trend information;

[1578] a correlation analysis means for analyzing correlations using the detected trend information and market data;

[1579] an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results;

[1580] a monitoring means for monitoring and verifying trading results;

[1581] a sentiment analysis means for analyzing user sentiment data to augment a trading strategy;

[1582] a means for providing information for display on a smart device;

[1583] A system including:

[1584] (Claim 2)

[1585] The system of claim 1, wherein the data collection means is a means for obtaining trend information in real time from multiple data sources on the Internet, and the information provision means is a means for using smart glasses or a mobile device.

[1586] (Claim 3)

[1587] 2. The system according to claim 1, wherein the correlation analysis means is a means for calculating a correlation coefficient based on past trend data and stock price data, and the emotion analysis means is a means for analyzing voice input and facial expressions. [Explanation of symbols]

[1588] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a data collection means for collecting trend information; a data preprocessing means for preprocessing the collected trend information; detection means for detecting trends based on the preprocessed trend information; a correlation analysis means for analyzing correlations using the detected trend information and market data; an algorithmic trading means for automatically executing stock buying and selling based on the correlation analysis results; a monitoring means for monitoring and verifying trading results; A system including:

2. 2. The system according to claim 1, wherein said data collection means is means for obtaining trend information in real time from a plurality of data sources on the Internet.

3. 2. The system according to claim 1, wherein said correlation analysis means calculates a correlation coefficient based on past trend data and stock price data.

Images