System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting market data in real-time; means for collecting social media data; means for collecting trend information from news; generative artificial intelligence means for integrating and analyzing the market data, social media data, and news trends; means for identifying investment opportunities; and means for notifying user terminals of the identified investment opportunities.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 today's markets, day traders, analysts, and investors seeking to make quick investment decisions find it difficult to integrate and analyze large amounts of real-time data. In order to instantly grasp the impact of minute market fluctuations, social media, and news, and make appropriate investment decisions, it is necessary to efficiently process large amounts of information. However, current systems make it extremely difficult to integrate and analyze data from these diverse sources in real time, often resulting in an inability to instantly identify investment opportunities. To solve this problem, a system is needed that can integrate diverse data sources in real time and quickly identify investment opportunities. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes a means for collecting market data, social media data, and news trend information in real time, a generating artificial intelligence means for integrating and analyzing this data, a means for identifying investment opportunities based on the analysis results, and a means for notifying a user terminal of the identified investment opportunities. The system also includes a means for data preprocessing to improve the accuracy of the collected market data, social media data, and news trend information. The generating artificial intelligence means also performs market fluctuation pattern, sentiment analysis, and news analysis to enable comprehensive analysis. This allows users to instantly grasp subtle market fluctuations and social trends and make prompt and appropriate investment decisions.

[0006] "Real-time" refers to data and information being processed and retrieved immediately on the spot.

[0007] "Market Data" refers to specific information related to financial markets, such as stock prices, trading volumes, and financial information.

[0008] "Social media data" refers to information such as user posts, comments, and ratings collected from social media platforms on the Internet.

[0009] "News trends" refers to the latest topical information collected from news sources such as newspapers, websites, and broadcast media.

[0010] "Integration" means bringing together data obtained from multiple different sources into a single, consistent format.

[0011] "Analysis" refers to the process of using collected data to extract specific information or insights.

[0012] "Generative AI" refers to AI that uses advanced machine learning techniques to analyze collected data and generate new insights and knowledge.

[0013] "Investment opportunity" refers to the possibility of trading or investing to make a profit in the financial markets.

[0014] "Notification" refers to the means by which a system communicates information to a user.

[0015] A "user terminal" is a device that a user uses to access the system, including smartphones, tablets, computers, etc. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention is a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time, and identifies investment opportunities to help users make quick investment decisions. Specific embodiments of the system are described below.

[0038] Data collection

[0039] The server uses APIs to collect real-time market data, social media data, and news trend information. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0040] Data integration and analysis

[0041] The server compiles the collected data into a single integrated dataset. During this process, data preprocessing is performed, including cleansing and formatting. The integrated data is then analyzed by generative artificial intelligence (AI). The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes news content to generate comprehensive insights.

[0042] Identifying investment opportunities

[0043] Based on the insights analyzed by AI, the server identifies investment opportunities. If an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is deemed an investment opportunity.

[0044] User Notification

[0045] The server notifies the user of identified investment opportunities via push notifications, in-app messages, emails, etc. The notification includes detailed investment information and recommended actions.

[0046] User investment support

[0047] Users receive investment opportunities notified through their terminals and make quick investment decisions based on that information. Users review the notified insights and execute trades on the trading platform as needed.

[0048] Specific examples

[0049] Suppose a company's stock price is rising sharply. Positive social media posts about the company increase, and major news outlets publish positive articles about the company. The server collects and integrates this data in real time and analyzes it using AI. The analysis results indicate that the company's stock price is likely to surge in the short term.

[0050] The server notifies the user of this investment opportunity. The user receives the notification and immediately decides to purchase the company's stock, executing the trade on the trading platform. This allows the user to instantly grasp minute market fluctuations and social trends and make appropriate investment decisions.

[0051] The present invention provides a new type of investment support system that supports quick and accurate investment decisions by comprehensively analyzing complex market information and diverse social trends.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The server collects real-time market data through APIs. Specifically, it calls the APIs of financial information providers to obtain market data such as stock price data and trading volume. It also uses APIs from social media to obtain related data such as tweets. For news trends, it calls news APIs to collect the latest news articles.

[0055] Step 2:

[0056] The server consolidates the collected data. It cleanses and pre-processes the data, converting it all into a consistent format. This process combines data from different sources and makes it easier to analyze.

[0057] Step 3:

[0058] The server then analyzes the integrated data using Generative Artificial Intelligence (AI), which analyzes market fluctuation patterns, performs social media sentiment analysis, and evaluates the content of news articles to extract useful insights from the data.

[0059] Step 4:

[0060] The server identifies investment opportunities based on AI-generated insights by detecting insights that meet certain thresholds or conditions (e.g., high probability and high impact information) and identifying them as investment opportunities.

[0061] Step 5:

[0062] The server notifies the user device of identified investment opportunities via push notifications, in-app messages, emails, etc. The notification includes details about the investment opportunity and recommended actions.

[0063] Step 6:

[0064] After receiving the notification, the user confirms its contents and uses the device to review the provided insights and understand the information about the investment opportunity.

[0065] Step 7:

[0066] The user makes an investment decision based on the notified investment opportunity, and once the decision is complete, executes the trade through the trading platform, specifically by issuing a purchase or sale instruction and completing the transaction.

[0067] Step 8:

[0068] Once the trade is complete, the user can view the results on their device, and based on the results, the next step is to collect and analyze data again, or to look for other investment opportunities.

[0069] This system allows users to grasp minute market fluctuations and social trends in real time, enabling them to make quick and appropriate investment decisions.

[0070] Example 1

[0071] 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."

[0072] Conventional investment support systems typically collect and analyze market data, social media data, and news trend information separately, making it difficult to integrate them and quickly identify investment opportunities.Furthermore, few systems apply advanced analytical techniques such as data preprocessing and sentiment analysis, making it difficult to provide accurate insights that allow users to make immediate investment decisions.

[0073] 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.

[0074] In this invention, the server includes a means for collecting market data in real time, a means for collecting social media data, and a means for collecting trend information from news. This allows for efficient data collection, integration, and preprocessing of the data. Furthermore, the preprocessed data is analyzed using a generative AI model to identify investment opportunities, and detailed information about the identified investment opportunities and recommended actions are notified to the user's terminal, allowing the user to make prompt and appropriate investment decisions.

[0075] "Market data" refers to numerical information related to financial markets, such as stock price information and trading volume.

[0076] "Social Media Data" refers to text and metadata generated on social media platforms, such as user posts, comments, and retweets.

[0077] "News trend information" refers to the latest information and topics obtained from news articles and reports.

[0078] "Data preprocessing" refers to the process of cleansing collected data and processing it into a state suitable for analysis, such as by deleting duplicate data and standardizing formats.

[0079] "Generative AI means" refers to AI that uses collected and integrated data to analyze market fluctuation patterns, sentiment analysis, and news text analysis to generate comprehensive insights.

[0080] "Means for identifying investment opportunities" refers to the process of extracting investment options that meet certain thresholds and conditions based on the generated insights, and evaluating and determining them as investment opportunities.

[0081] "User terminal" refers to a device (smartphone, tablet, PC, etc.) on which a user receives notifications from the system, views insights, and makes investment decisions.

[0082] The present invention is a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time, and identifies investment opportunities to help users make quick investment decisions. Specific embodiments of the system are described below.

[0083] Data collection

[0084] The server uses APIs to collect market data, social media data, and news trend information in real time. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles. Specifically, the server uses Yahoo Finance API and Alpha Vantage API for market data, Twitter API and Facebook Graph API for social media data, and Google News API and News API for trend information.

[0085] Data integration and analysis

[0086] The server compiles the various collected data into a single integrated dataset. During this process, data preprocessing is performed, including cleansing and formatting. For example, this includes removing duplicate data and filling in missing values. The integrated data is then analyzed using generative artificial intelligence (AI). Specifically, generative AI models are used to analyze market fluctuation patterns, perform social media sentiment analysis, and perform text analysis of news content to generate comprehensive insights. Machine learning frameworks such as TensorFlow and PyTorch are used for the analysis.

[0087] Identifying investment opportunities

[0088] Based on the AI-generated insights, the server identifies investment opportunities. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is deemed an investment opportunity, specifically based on predicted stock price growth or positive social media sentiment score.

[0089] User Notification

[0090] The server notifies the user device of the identified investment opportunity. This notification is sent in the form of a push notification, in-app message, email, or other format. The notification includes detailed information about the investment and recommended actions. For example, a message such as "The stock price of Company X is expected to rise sharply. The current stock price is X yen. Please consider purchasing now" is sent.

[0091] User investment support

[0092] Users receive notifications of investment opportunities through their devices and make quick investment decisions based on the information. They review the notified insights and execute trades on the trading platform as needed. For example, after receiving a notification on their device, the user opens a trading app and purchases the indicated stocks.

[0093] Specific examples

[0094] For example, suppose a company's stock price is rising sharply. Positive social media posts about the company increase, and major news outlets publish positive articles about the company. The server collects and integrates this data in real time and analyzes it using AI. The analysis results indicate that the company's stock price is likely to rise sharply in the short term.

[0095] The server notifies the user of this investment opportunity. The user receives the notification and immediately decides to purchase the company's stock, executing the trade on the trading platform. This allows the user to instantly grasp minute market fluctuations and social trends and make appropriate investment decisions.

[0096] Example prompts to be input to the generative AI model

[0097] "How can I integrate market data, social media data, and news trend information to identify investment opportunities?"

[0098] Based on this prompt, the AI ​​will walk you through each step of collection, synthesis, and analysis to provide a method for identifying investment opportunities.

[0099] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0100] Step 1: Gather market data

[0101] The server uses APIs to collect market data in real time. Specifically, it uses the Yahoo Finance API and Alpha Vantage API to obtain stock price information and trading volume. It uses a list of stocks to be collected as input and obtains the current stock price and trading volume data for each stock as output. This operation obtains the latest market data.

[0102] Step 2: Collect social media data

[0103] The server uses the Twitter API and Facebook Graph API to collect user posts and comments on social media. It uses search queries related to specific companies or keywords as input and obtains text data of the relevant posts and comments as output. This operation obtains social media reactions in real time.

[0104] Step 3: Gathering news trends

[0105] The server uses the Google News API or News API to collect the latest news articles. It uses keywords related to a specific company name or topic as input, and obtains the URL, title, summary, and publication date of the relevant news article as output. This operation allows you to understand the latest news trends.

[0106] Step 4: Data integration and preprocessing

[0107] The server aggregates the collected market data, social media data, and news trend information into a single integrated data set. It uses each of the previously collected data sources (market data, social media data, and news trend information) as input and generates an integrated data set as output. This process includes deduplication, outlier correction, and standardization of data formats.

[0108] Step 5: Data analysis using AI

[0109] The server runs the generative AI model with the integrated dataset. It uses the integrated dataset as input and outputs market movement patterns, social media sentiment scores, and news content analysis. In this operation, the AI ​​analyzes the collected data and generates comprehensive insights on investment opportunities.

[0110] Step 6: Identifying investment opportunities

[0111] The server evaluates the AI-generated insights and identifies investment opportunities. It uses the analysis results of the generative AI model as input and obtains identified investment opportunities (e.g., stocks predicted to surge) as output. This operation extracts insights with high probability and high impact and determines them as investment opportunities.

[0112] Step 7: Notify users

[0113] The server notifies the user device of the identified investment opportunity. Using the details of the identified investment opportunity as input, a push notification, an in-app message, or an email is generated as output to the user device. This operation allows the user to quickly learn about the investment opportunity.

[0114] Step 8: User investment decision and execution

[0115] Users receive notifications and make quick investment decisions based on the information, using notifications from the server as input and trade execution on the trading platform as output, where users review insights and buy or sell stocks as needed.

[0116] Step 9: Feedback Loop

[0117] The server collects the user's investment behavior and results as feedback and uses it to improve the system's analytical model. The user's investment result data is used as input, and the analytical model's parameter adjustment and algorithm improvement are obtained as output. This operation improves the accuracy and effectiveness of the system.

[0118] (Application example 1)

[0119] 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."

[0120] While conventional investment support systems can identify investment opportunities through integrated analysis of real-time market data, social media data, and news trend information, they lack the functionality to suggest the next optimal purchase based on the user's purchasing patterns in electronic payment services. As a result, users may miss the right timing or opportunity to make a purchase. To solve this issue, a system is needed that not only identifies investment opportunities but also analyzes the user's purchasing patterns and makes personalized purchasing recommendations.

[0121] 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.

[0122] In this invention, the server includes a means for collecting market data in real time, a means for collecting social media data, and a means for collecting trend information from news. This enables a generating artificial intelligence means for integrating and analyzing market data, social media data, and news trend information, a means for identifying investment opportunities, a means for notifying a user terminal of the identified investment opportunities, and a means for analyzing a user's purchasing patterns in electronic payment services and providing purchasing recommendations. This allows users to grasp market fluctuations and social trends in real time and receive personalized recommendations for their next product or service purchase.

[0123] "Market data" refers to information such as stock prices, trading volumes, and exchange rates in financial markets.

[0124] "Social media data" refers to information such as posts and comments posted by users on social networking services.

[0125] "News trend information" refers to information on the latest trends and events analyzed based on news articles and reports.

[0126] "Generative AI" refers to artificial intelligence technology that has algorithms that comprehensively analyze collected data and generate predictions and insights.

[0127] "Investment Opportunities" refers to the timing and targets of investments that are likely to be advantageous to the user based on collected and analyzed data.

[0128] "User terminal" refers to an electronic device, such as a smartphone or tablet, that allows a user to receive and operate information.

[0129] "Electronic payment service" refers to a platform or system for making monetary payments using electronic means.

[0130] "Purchasing patterns" refer to the tendencies and habits based on a user's past purchasing history and behavior.

[0131] "Purchase recommendation" refers to analyzing a user's purchasing patterns and suggesting the next product or service they should purchase.

[0132] The present invention provides a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time, identifies investment opportunities based on the collected data, and notifies users of these opportunities. It also has the function of analyzing purchasing patterns of electronic payment services and making purchasing recommendations. Specific embodiments of the present invention are described below.

[0133] Data collection

[0134] The server uses APIs to collect real-time market data, social media data, and news trend information. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0135] Data integration and analysis

[0136] The server compiles the various collected data into a single integrated dataset. During this process, data preprocessing includes cleansing and formatting standardization. The integrated data is then analyzed by generative artificial intelligence (AI). The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes news content to generate comprehensive insights. It also has the ability to analyze user purchasing patterns for electronic payment services.

[0137] Identifying investment opportunities and purchase recommendations

[0138] Based on the insights analyzed by AI, the server identifies investment opportunities. It also analyzes purchasing patterns based on the user's past purchase history and recommends the next optimal purchase. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is determined to be an investment opportunity or purchase recommendation.

[0139] User Notification

[0140] The server notifies the user of identified investment opportunities and purchase recommendations via push notifications, in-app messages, emails, etc. The notification content includes detailed investment information, recommended actions, and purchase recommendations.

[0141] User Support

[0142] Users receive the information via their devices and make quick investment or purchasing decisions based on that information. Users review the insights and execute operations on trading or purchasing platforms as needed.

[0143] Hardware or software used

[0144] This system uses user devices such as smartphones and tablets, and uses the Python programming language, the Requests library, and the Scikit-learn library to collect, integrate, and analyze data.

[0145] Examples of concrete examples and prompts

[0146] For example, if market data, social media data, and news trend information is obtained as follows:

[0147] Market Data: "ABC Product" is on the rise

[0148] Social media data: Increased mentions of "buy ABC product"

[0149] News Trend Information: Reports that "ABC product is very popular"

[0150] An example prompt generated using this information is:

[0151] "We've discovered a new buying opportunity! 'Product ABC' is extremely popular right now. It's getting widespread mentions on social media and high ratings in the news. Check it out now!"

[0152] By sending these notifications to users and providing investment opportunities and purchase recommendations, users can understand market fluctuations and social trends in real time and make appropriate investment and purchasing decisions.

[0153] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0154] Step 1:

[0155] The server uses APIs to collect market data, social media data, and news trend information in real time. This collected data is obtained from each data source in JSON format. The input is raw data obtained from the APIs, and the server stores this data. The output is a collection of raw data.

[0156] Step 2:

[0157] The server integrates the collected market data, social media data, and news trend information into a single dataset. As part of data preprocessing, it fills in missing data, removes inappropriate data, and standardizes formats. The input is the collected raw data, which the server cleanses and standardizes. The output is a cleansed, integrated dataset.

[0158] Step 3:

[0159] The server uses generative artificial intelligence to analyze the cleansed integrated dataset. Here, it performs scaling, PCA (principal component analysis), and KMeans clustering to extract features from each data point. The input is the integrated dataset, and the server reduces the dimensions using scaling and PCA and performs clustering. The output is the analysis results and the centers of each cluster.

[0160] Step 4:

[0161] The server identifies investment opportunities and purchase recommendations based on the generated analysis results. In particular, if the cluster center value exceeds a certain threshold, the server determines that the data points in that cluster are investment opportunities or purchase recommendations. The inputs are the analysis results and the cluster center values, and the server performs threshold judgment. The output is the identified investment opportunities and purchase recommendations.

[0162] Step 5:

[0163] The server generates prompt messages for the identified investment opportunities and purchase recommendations and notifies the user device. Here, prompt messages are generated based on templates and sent to the user via push notifications, in-app messages, emails, etc. The input is the information on the identified investment opportunities and purchase recommendations, and the server creates the prompt messages using a generative AI model. The output is a notification message to the user.

[0164] Step 6:

[0165] Users receive the information notified through their terminals and make quick investment or purchasing decisions based on that information. Here, users check the notified insights and access the trading or purchasing platform to execute operations. The input is the notification message, and the user decides on the next action based on this. The output is the executed purchase or investment action.

[0166] 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.

[0167] The present invention is a system that identifies investment opportunities and supports quick investment decisions by collecting, integrating, and analyzing market data, social media data, and news trend information in real time, and by combining this with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0168] Data collection

[0169] The server uses APIs to collect real-time market data, social media data, and news trend information. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0170] Data integration and analysis

[0171] The server converts the collected market data, social media data, and news trend information into a unified format and performs data preprocessing. The preprocessed data is compiled into an integrated dataset and analyzed using generative artificial intelligence (AI). The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes the content of news articles, thereby extracting useful insights from the data.

[0172] Utilizing the Emotion Engine

[0173] Furthermore, the emotion engine analyzes user emotions from user input data (e.g., text input or voice input) and utilizes the results together with the integrated data. The emotion analysis results from the emotion engine are used to identify investment opportunities and optimize the content of notifications to users.

[0174] Identifying investment opportunities

[0175] Based on the AI-generated insights and user sentiment data analyzed by the sentiment engine, the server identifies investment opportunities. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is identified as an investment opportunity.

[0176] User Notification

[0177] The server then notifies the user of the best investment opportunities based on the identified investment opportunities and the results of sentiment analysis via push notifications, in-app messages, emails, etc. The notification content includes detailed information about the investment opportunity and recommended actions.

[0178] User investment support

[0179] The user receives a notification from the terminal and checks its contents. Taking into account the information and the user's own emotional state, the user makes an investment decision. The user then executes a trade through the trading platform and checks the results on the terminal.

[0180] Specific examples

[0181] For example, suppose a company's stock price is rising sharply. Positive social media posts about the company are increasing, and positive articles about the company are published in major news media. Furthermore, the emotion engine analyzes that users themselves are excited (positive emotions). The server collects and integrates this data in real time, and analyzes it using AI and the emotion engine. The analysis results indicate that the company's stock price is likely to rise sharply in the short term.

[0182] The server notifies the user of this investment opportunity, and the user confirms it and immediately decides to purchase the company's stock and executes the trade on the trading platform. This allows the user to make appropriate investment decisions that comprehensively take into account minute market fluctuations, social trends, and their own emotional state.

[0183] The present invention provides a new type of investment support system that supports quick and accurate investment decisions by comprehensively analyzing complex market information, diverse social trends, and the user's emotional state.

[0184] The processing flow will be explained below.

[0185] Step 1:

[0186] The server collects real-time market data through APIs. Specifically, it calls the API of a financial information service to obtain market data such as stock prices and trading volumes. It also uses APIs from social media to collect data such as tweets and comments. It also uses news APIs to obtain the latest news articles.

[0187] Step 2:

[0188] The server performs pre-processing on the collected market data, social media data, and news trend information to cleanse and standardize the format, converting data from each data source into a consistent format and compiling it into an integrated data set.

[0189] Step 3:

[0190] The server provides the integrated data set to the Generator AI, which analyzes each data set, analyzing market fluctuation patterns, social media sentiment analysis, and news content to extract useful insights.

[0191] Step 4:

[0192] The server uses an emotion engine to analyze the user's input data (e.g., text input or voice input) and evaluate the user's current emotional state. The results of this emotion analysis are used together with the integrated data.

[0193] Step 5:

[0194] The server identifies investment opportunities based on the insights obtained by the generative AI and the results of user sentiment analysis by the sentiment engine. It detects insights that meet certain thresholds and conditions (e.g., high probability and high impact) and identifies them as investment opportunities.

[0195] Step 6:

[0196] The server then sends information about identified investment opportunities and sentiment analysis results to the user's device via push notifications, in-app messages, emails, etc. The notification content includes detailed information about the investment opportunity and recommended actions.

[0197] Step 7:

[0198] Users receive notifications through their devices, check the content, and make investment decisions based on the information and their emotional state.

[0199] Step 8:

[0200] Users execute trades through the trading platform, specifically by issuing instructions to buy or sell stocks based on the provided insights and completing the trades.

[0201] Step 9:

[0202] Once the transaction is complete, the user can view the results on their device, and based on the results, the next step is to collect and analyze data again, or look for other investment opportunities.

[0203] This system allows users to comprehensively grasp minute market fluctuations, social trends, and their own emotional state, allowing them to make quick and appropriate investment decisions.

[0204] Example 2

[0205] 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."

[0206] Conventional investment support systems often collect and analyze market data, social media data, and news trend information separately, resulting in low-accuracy insights and making it difficult to properly identify investment opportunities. Furthermore, because they do not take user emotions into account, it is difficult to support optimal investment decisions that reflect the user's emotional state. Therefore, there is a demand for an integrated, highly accurate system that supports quick and accurate investment decisions.

[0207] 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.

[0208] In this invention, the server includes means for collecting market data in real time, means for collecting social media data, means for collecting trend information from news, artificial intelligence generation means, emotion analysis means for analyzing user emotions, emotion analysis results and means for identifying investment opportunities based on the analysis results, and means for notifying the user terminal of the identified investment opportunities. This enables support for quick and accurate investment decisions by integrating and analyzing multiple data sources with high accuracy and taking into account the user's emotional state.

[0209] "Market Data" refers to data relating to financial markets, such as price information, trading volumes, and indicators.

[0210] "Social media data" refers to data such as user posts, comments, and reactions on online social networking services and platforms.

[0211] "News trend information" refers to information such as news articles, reports, and analyses about current events and topics.

[0212] "Generative AI tools" refers to machine learning models and algorithms that integrate diverse data sources and perform advanced analysis.

[0213] "Emotion analysis means" refers to technologies and algorithms for determining a user's emotions from user input data (e.g., text, voice, etc.).

[0214] "Means for identifying investment opportunities" refers to technologies that analyze market data, social media data, news trend information, and user sentiment data to identify potential investment opportunities.

[0215] "User terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) that a user operates and receives information.

[0216] The present invention is a system that identifies investment opportunities and supports quick investment decisions by collecting, integrating, and analyzing market data, social media data, and news trend information in real time, and by combining this with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0217] First, the server collects data using a dedicated API. To collect market data, the server uses the API to obtain price information and trading volumes of financial markets. To collect social media data, the server uses the API of a social media platform to obtain posts and comments. To collect news trend information, the server obtains the latest news articles via the API of a news service.

[0218] The server then converts the collected data into a unified format and performs data preprocessing. For example, stock quotes are converted into CSV format, tweets and comments are formatted into JSON format, news articles are subjected to text analysis to generate summaries, and the data is then integrated using a dataframe manipulation library to fill in any inaccurate or missing data.

[0219] The combined data set is then analyzed by server-based generative AI models, which use machine learning frameworks to analyze market fluctuation patterns, natural language processing libraries for social media sentiment analysis, and natural language generation models to analyze the content of news articles and extract useful insights.

[0220] Furthermore, the server uses an emotion engine to analyze the user's emotions from the user's input data (e.g., text input or voice input). This analysis can use a natural language processing library as an emotion classification model to accurately determine the user's positive or negative emotional state.

[0221] Based on the analysis results from the AI ​​model and sentiment engine, the server identifies investment opportunities, which are then assigned trust and influence scores by the algorithm, and are confirmed as investment opportunities if they exceed a certain threshold.

[0222] Confirmed investment opportunities are notified to the user's device from the server using a cloud messaging service. Notification details are also sent via email and in-app message. Notification content includes the investment opportunity analysis results, recommended actions, and an assessed confidence score.

[0223] The user receives a notification on their device, checks the details, makes an investment decision based on the provided data and their own judgment, and executes the trade through the trading platform.

[0224] Specific examples

[0225] For example, suppose a company's stock price is rising sharply. The server obtains the company's stock price and trading volume data through a financial market API, collects a large number of related positive posts using a social media API, and collects positive news articles about the company using a news service API. After integrating and preprocessing this data, it analyzes it using a generative AI model. The resulting insight is that the company's stock price is likely to rise further.

[0226] Additionally, the emotion engine analyzes the user's input text to determine whether the user is in a positive emotional state, and the server uses this information to identify investment opportunities with high confidence scores.

[0227] The server then notifies the user of the investment opportunity and suggests specific investment actions. A push notification is sent stating, "The stock price of a specific company is rising. Check the details and consider purchasing."

[0228] The user then checks the notification, decides to invest based on the suggested information, and purchases shares through the trading platform. Finally, the user sees the results of the transaction displayed on the terminal in real time.

[0229] Prompt Sentence Examples

[0230] "Tell me which companies I should invest in next based on recent market data, social media comments, and trending news. Also, please suggest the best investment opportunities given my emotional state: positive and excited."

[0231] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0232] Step 1:

[0233] The server uses APIs to collect market data, social media data, and news trend information in real time. Access information to each API endpoint is used as input. For market data, a financial market API is used, for social media data, a social media API is used, and for news trend information, a news service API is used. The output is the raw data of the various types of data collected.

[0234] Step 2:

[0235] The server converts the collected market data, social media data, and news trend information into a unified format. It uses the raw data collected in step 1 as input. Specifically, it converts stock quotes into CSV format, formats social media posts and comments into JSON format, and performs text analysis on news articles to generate summaries. The output is the data converted into a unified format.

[0236] Step 3:

[0237] The server preprocesses the converted data. As input, it uses the data converted to a unified format in step 2. It uses the Pandas library to create a data frame and imputes inaccurate or missing data. It also removes outliers. The output is a clean dataset that has been preprocessed.

[0238] Step 4:

[0239] The server combines the preprocessed datasets and inputs them into the generative AI model. It uses the clean dataset obtained in step 3 as input. After combining the datasets, it uses a machine learning framework (TensorFlow or PyTorch) to analyze market fluctuation patterns. At the same time, it uses a natural language processing library (NLTK or Transformers) to perform social media sentiment analysis and content analysis of news articles. The output is insights as a result of the analysis.

[0240] Step 5:

[0241] The server uses an emotion engine to analyze the user's emotions. The input is the user's input data (text input or voice input). A natural language processing library is used as an emotion classification model to analyze the user's positive and negative emotional state. The output is the user's emotion analysis results.

[0242] Step 6:

[0243] The server identifies investment opportunities based on the analysis results and sentiment analysis results. It uses the insights from step 4 and the sentiment analysis results from step 5 as inputs. The algorithm sets trust and influence scores and identifies insights that exceed certain thresholds as investment opportunities. The output is the identified investment opportunities.

[0244] Step 7:

[0245] The server notifies the user device of the identified investment opportunities. As input, it uses the investment opportunity data identified in step 6. It uses a cloud messaging service (e.g., Firebase Cloud Messaging) to send a push notification. Details are also delivered via email and in-app message. The output is the notification sent to the user.

[0246] Step 8:

[0247] The user receives the notification on their device and checks its contents. As input, they use the notification sent from the server. The user makes an investment decision based on the provided data and their own judgment. The output is an investment decision.

[0248] Step 9:

[0249] The user executes a trade using the trading platform. As input, they use the investment decision made in step 8. They log in to the trading platform, select the financial instrument, and perform a buy / sell operation. The output is the executed trade.

[0250] (Application example 2)

[0251] 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."

[0252] While conventional investment support systems excel at collecting and analyzing real-time data, they do not take into account the user's emotional state and therefore are unable to provide optimal investment timing or decisions. This makes it difficult for users to grasp minute market fluctuations and social trends, making it difficult to make appropriate investment decisions.

[0253] The identification process by the identification 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 means for collecting market data in real time, means for collecting social media data, means for collecting trend information from news, generative artificial intelligence means for integrating and analyzing the market data, social media data, and news trends, emotion engine means for analyzing user emotions, means for identifying investment opportunities, and means for notifying the user terminal of the identified investment opportunities. This enables fast and accurate investment support that takes into account the user's emotional state.

[0254] "Market data" refers to data such as price information and trading volume related to financial markets.

[0255] "Social Media Data" refers to data posted by users on social media platforms, such as comments, tweets, and reviews.

[0256] "News trend information" refers to data about the latest events and topics obtained from news articles and information distribution services.

[0257] "Generative AI" refers to artificial intelligence techniques for data integration and analysis.

[0258] An "emotion engine" is a mechanism that analyzes the user's emotional state from input data.

[0259] An "investment opportunity" is a time or condition in the financial markets that offers high potential for making a profit.

[0260] A "user terminal" is a computing device used by a user, such as a smartphone or PC.

[0261] This invention is a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time while taking into account the user's emotional state, and notifies the user of optimal investment opportunities. The system that realizes this application example is described in detail below.

[0262] Data collection

[0263] The server uses APIs to collect real-time market data, social media data, and news trend information. A specific software example is the requests library. Market data includes price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0264] Data integration and analysis

[0265] The server converts the collected market data, social media data, and news trend information into a unified format and performs data preprocessing. The preprocessed data is compiled into an integrated dataset and analyzed using generative artificial intelligence (AI) such as TensorFlow or PyTorch. The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes the content of news articles, thereby extracting useful insights from the data.

[0266] Utilizing the Emotion Engine

[0267] The server is equipped with an emotion engine that analyzes user emotions from user input data (e.g., text input or voice input). This emotion analysis is performed to recognize the user's emotional state, and the results are utilized together with the integrated data. Natural language processing (NLP) models are used for emotion analysis.

[0268] Identifying investment opportunities

[0269] Based on the AI-generated insights and user sentiment data analyzed by the sentiment engine, the server identifies investment opportunities. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is identified as an investment opportunity.

[0270] User Notification

[0271] The server then notifies the user of the best investment opportunities based on the identified investment opportunities and the results of sentiment analysis via push notifications, in-app messages, emails, etc. The notification content includes detailed information about the investment opportunity and recommended actions.

[0272] User investment support

[0273] The user receives a notification from the terminal and checks its contents. Taking into account the information and the user's own emotional state, the user makes an investment decision. The user then executes a trade through the trading platform and checks the results on the terminal.

[0274] Specific examples

[0275] For example, consider a situation where a company's stock price is rising sharply. Positive social media posts about the company increase, and major news media publish positive articles about the company. Furthermore, the emotion engine analyzes that users themselves are excited (positive emotions). The server collects and integrates this data in real time, and analyzes it using AI and the emotion engine. The analysis results identify that the company's stock price is likely to rise sharply in the short term.

[0276] The server notifies the user of this investment opportunity, and the user confirms it and immediately decides to purchase the company's stock and executes the trade on the trading platform. This allows the user to make appropriate investment decisions that comprehensively take into account minute market fluctuations, social trends, and their own emotional state.

[0277] An example of a prompt to be input to a generative AI model might be, "Integrate and analyze market data, social media data, news trends, and user sentiment data to generate optimal purchasing suggestions."

[0278] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0279] Step 1:

[0280] The server uses APIs to collect market data, social media data, and news trend information in real time. It uses the requests library to send data retrieval requests to specific API endpoints and receives responses in JSON format. The input here is the API endpoint URL and required parameters, and the output is a JSON object of the various retrieved data.

[0281] Step 2:

[0282] The server converts the collected market data, social media data, and news trend information into a unified format and performs preprocessing. Specifically, it performs missing value imputation, data normalization, and format conversion. The input is the raw data obtained in the previous step, and the output is a dataset in a unified format.

[0283] Step 3:

[0284] The server aggregates the preprocessed data and performs analysis using generative artificial intelligence (AI) such as TensorFlow or PyTorch. This includes analyzing market fluctuation patterns, social media sentiment analysis, and semantic analysis of news articles. The input is a unified dataset, and the output is analyzed, useful insights.

[0285] Step 4:

[0286] The server uses an emotion engine to analyze emotions from user input data (e.g., text input or voice input). It uses an NLP model (e.g., BERT or GPT) to identify the user's emotional state. The input is the user's raw text or voice data, and the output is the analyzed emotion data.

[0287] Step 5:

[0288] The server identifies investment opportunities based on AI-generated insights and user sentiment data analyzed by the sentiment engine. It evaluates the integrated data to identify suitable investment opportunities based on certain thresholds and conditions (e.g., high probability and high impact). The inputs are insights and sentiment data, and the output is data on identified investment opportunities.

[0289] Step 6:

[0290] The server notifies the user device of identified investment opportunities. Information is sent to the user in the form of push notifications, in-app messages, emails, etc. The notification includes detailed information about the investment opportunity and recommended actions. The input is the investment opportunity data, and the output is the notification sent to the user device.

[0291] Step 7:

[0292] The user receives notifications from the terminal and checks their contents. They take the information and their emotional state into consideration to make appropriate investment decisions. The user executes trades through the trading platform and checks the results on the terminal. The input is notification information from the server, and the output is the user's investment actions and their results.

[0293] 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.

[0294] 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.

[0295] 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.

[0296] [Second embodiment]

[0297] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0298] 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.

[0299] 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).

[0300] 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.

[0301] 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.

[0302] 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).

[0303] 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.

[0304] 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.

[0305] 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.

[0306] 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.

[0307] 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.

[0308] 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."

[0309] The present invention is a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time, and identifies investment opportunities to help users make quick investment decisions. Specific embodiments of the system are described below.

[0310] Data collection

[0311] The server uses APIs to collect real-time market data, social media data, and news trend information. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0312] Data integration and analysis

[0313] The server compiles the collected data into a single integrated dataset. During this process, data preprocessing is performed, including cleansing and formatting. The integrated data is then analyzed by generative artificial intelligence (AI). The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes news content to generate comprehensive insights.

[0314] Identifying investment opportunities

[0315] Based on the insights analyzed by AI, the server identifies investment opportunities. If an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is deemed an investment opportunity.

[0316] User Notification

[0317] The server notifies the user of identified investment opportunities via push notifications, in-app messages, emails, etc. The notification includes detailed investment information and recommended actions.

[0318] User investment support

[0319] Users receive investment opportunities notified through their terminals and make quick investment decisions based on that information. Users review the notified insights and execute trades on the trading platform as needed.

[0320] Specific examples

[0321] Suppose a company's stock price is rising sharply. Positive social media posts about the company increase, and major news outlets publish positive articles about the company. The server collects and integrates this data in real time and analyzes it using AI. The analysis results indicate that the company's stock price is likely to surge in the short term.

[0322] The server notifies the user of this investment opportunity. The user receives the notification and immediately decides to purchase the company's stock, executing the trade on the trading platform. This allows the user to instantly grasp minute market fluctuations and social trends and make appropriate investment decisions.

[0323] The present invention provides a new type of investment support system that supports quick and accurate investment decisions by comprehensively analyzing complex market information and diverse social trends.

[0324] The processing flow will be explained below.

[0325] Step 1:

[0326] The server collects real-time market data through APIs. Specifically, it calls the APIs of financial information providers to obtain market data such as stock price data and trading volume. It also uses APIs from social media to obtain related data such as tweets. For news trends, it calls news APIs to collect the latest news articles.

[0327] Step 2:

[0328] The server consolidates the collected data. It cleanses and pre-processes the data, converting it all into a consistent format. This process combines data from different sources and makes it easier to analyze.

[0329] Step 3:

[0330] The server then analyzes the integrated data using Generative Artificial Intelligence (AI), which analyzes market fluctuation patterns, performs social media sentiment analysis, and evaluates the content of news articles to extract useful insights from the data.

[0331] Step 4:

[0332] The server identifies investment opportunities based on AI-generated insights by detecting insights that meet certain thresholds or conditions (e.g., high probability and high impact information) and identifying them as investment opportunities.

[0333] Step 5:

[0334] The server notifies the user device of identified investment opportunities via push notifications, in-app messages, emails, etc. The notification includes details about the investment opportunity and recommended actions.

[0335] Step 6:

[0336] After receiving the notification, the user confirms its contents and uses the device to review the provided insights and understand the information about the investment opportunity.

[0337] Step 7:

[0338] The user makes an investment decision based on the notified investment opportunity, and once the decision is complete, executes the trade through the trading platform, specifically by issuing a purchase or sale instruction and completing the transaction.

[0339] Step 8:

[0340] Once the trade is complete, the user can view the results on their device, and based on the results, the next step is to collect and analyze data again, or to look for other investment opportunities.

[0341] This system allows users to grasp minute market fluctuations and social trends in real time, enabling them to make quick and appropriate investment decisions.

[0342] Example 1

[0343] 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."

[0344] Conventional investment support systems typically collect and analyze market data, social media data, and news trend information separately, making it difficult to integrate them and quickly identify investment opportunities.Furthermore, few systems apply advanced analytical techniques such as data preprocessing and sentiment analysis, making it difficult to provide accurate insights that allow users to make immediate investment decisions.

[0345] 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.

[0346] In this invention, the server includes a means for collecting market data in real time, a means for collecting social media data, and a means for collecting trend information from news. This allows for efficient data collection, integration, and preprocessing of the data. Furthermore, the preprocessed data is analyzed using a generative AI model to identify investment opportunities, and detailed information about the identified investment opportunities and recommended actions are notified to the user's terminal, allowing the user to make prompt and appropriate investment decisions.

[0347] "Market data" refers to numerical information related to financial markets, such as stock price information and trading volume.

[0348] "Social Media Data" refers to text and metadata generated on social media platforms, such as user posts, comments, and retweets.

[0349] "News trend information" refers to the latest information and topics obtained from news articles and reports.

[0350] "Data preprocessing" refers to the process of cleansing collected data and processing it into a state suitable for analysis, such as by deleting duplicate data and standardizing formats.

[0351] "Generative AI means" refers to AI that uses collected and integrated data to analyze market fluctuation patterns, sentiment analysis, and news text analysis to generate comprehensive insights.

[0352] "Means for identifying investment opportunities" refers to the process of extracting investment options that meet certain thresholds and conditions based on the generated insights, and evaluating and determining them as investment opportunities.

[0353] "User terminal" refers to a device (smartphone, tablet, PC, etc.) on which a user receives notifications from the system, views insights, and makes investment decisions.

[0354] The present invention is a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time, and identifies investment opportunities to help users make quick investment decisions. Specific embodiments of the system are described below.

[0355] Data collection

[0356] The server uses APIs to collect market data, social media data, and news trend information in real time. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles. Specifically, the server uses Yahoo Finance API and Alpha Vantage API for market data, Twitter API and Facebook Graph API for social media data, and Google News API and News API for trend information.

[0357] Data integration and analysis

[0358] The server compiles the various collected data into a single integrated dataset. During this process, data preprocessing is performed, including cleansing and formatting. For example, this includes removing duplicate data and filling in missing values. The integrated data is then analyzed using generative artificial intelligence (AI). Specifically, generative AI models are used to analyze market fluctuation patterns, perform social media sentiment analysis, and perform text analysis of news content to generate comprehensive insights. Machine learning frameworks such as TensorFlow and PyTorch are used for the analysis.

[0359] Identifying investment opportunities

[0360] Based on the AI-generated insights, the server identifies investment opportunities. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is deemed an investment opportunity, specifically based on predicted stock price growth or positive social media sentiment score.

[0361] User Notification

[0362] The server notifies the user device of the identified investment opportunity. This notification is sent in the form of a push notification, in-app message, email, or other format. The notification includes detailed information about the investment and recommended actions. For example, a message such as "The stock price of Company X is expected to rise sharply. The current stock price is X yen. Please consider purchasing now" is sent.

[0363] User investment support

[0364] Users receive notifications of investment opportunities through their devices and make quick investment decisions based on the information. They review the notified insights and execute trades on the trading platform as needed. For example, after receiving a notification on their device, the user opens a trading app and purchases the indicated stocks.

[0365] Specific examples

[0366] For example, suppose a company's stock price is rising sharply. Positive social media posts about the company increase, and major news outlets publish positive articles about the company. The server collects and integrates this data in real time and analyzes it using AI. The analysis results indicate that the company's stock price is likely to rise sharply in the short term.

[0367] The server notifies the user of this investment opportunity. The user receives the notification and immediately decides to purchase the company's stock, executing the trade on the trading platform. This allows the user to instantly grasp minute market fluctuations and social trends and make appropriate investment decisions.

[0368] Example prompts to be input to the generative AI model

[0369] "How can I integrate market data, social media data, and news trend information to identify investment opportunities?"

[0370] Based on this prompt, the AI ​​will walk you through each step of collection, synthesis, and analysis to provide a method for identifying investment opportunities.

[0371] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0372] Step 1: Gather market data

[0373] The server uses APIs to collect market data in real time. Specifically, it uses the Yahoo Finance API and Alpha Vantage API to obtain stock price information and trading volume. It uses a list of stocks to be collected as input and obtains the current stock price and trading volume data for each stock as output. This operation obtains the latest market data.

[0374] Step 2: Collect social media data

[0375] The server uses the Twitter API and Facebook Graph API to collect user posts and comments on social media. It uses search queries related to specific companies or keywords as input and obtains text data of the relevant posts and comments as output. This operation obtains social media reactions in real time.

[0376] Step 3: Gathering news trends

[0377] The server uses the Google News API or News API to collect the latest news articles. It uses keywords related to a specific company name or topic as input, and obtains the URL, title, summary, and publication date of the relevant news article as output. This operation allows you to understand the latest news trends.

[0378] Step 4: Data integration and preprocessing

[0379] The server aggregates the collected market data, social media data, and news trend information into a single integrated data set. It uses each of the previously collected data sources (market data, social media data, and news trend information) as input and generates an integrated data set as output. This process includes deduplication, outlier correction, and standardization of data formats.

[0380] Step 5: Data analysis using AI

[0381] The server runs the generative AI model with the integrated dataset. It uses the integrated dataset as input and outputs market movement patterns, social media sentiment scores, and news content analysis. In this operation, the AI ​​analyzes the collected data and generates comprehensive insights on investment opportunities.

[0382] Step 6: Identifying investment opportunities

[0383] The server evaluates the AI-generated insights and identifies investment opportunities. It uses the analysis results of the generative AI model as input and obtains identified investment opportunities (e.g., stocks predicted to surge) as output. This operation extracts insights with high probability and high impact and determines them as investment opportunities.

[0384] Step 7: Notify users

[0385] The server notifies the user device of the identified investment opportunity. Using the details of the identified investment opportunity as input, a push notification, an in-app message, or an email is generated as output to the user device. This operation allows the user to quickly learn about the investment opportunity.

[0386] Step 8: User investment decision and execution

[0387] Users receive notifications and make quick investment decisions based on the information, using notifications from the server as input and trade execution on the trading platform as output, where users review insights and buy or sell stocks as needed.

[0388] Step 9: Feedback Loop

[0389] The server collects the user's investment behavior and results as feedback and uses it to improve the system's analytical model. The user's investment result data is used as input, and the analytical model's parameter adjustment and algorithm improvement are obtained as output. This operation improves the accuracy and effectiveness of the system.

[0390] (Application example 1)

[0391] 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."

[0392] While conventional investment support systems can identify investment opportunities through integrated analysis of real-time market data, social media data, and news trend information, they lack the functionality to suggest the next optimal purchase based on the user's purchasing patterns in electronic payment services. As a result, users may miss the right timing or opportunity to make a purchase. To solve this issue, a system is needed that not only identifies investment opportunities but also analyzes the user's purchasing patterns and makes personalized purchasing recommendations.

[0393] 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.

[0394] In this invention, the server includes a means for collecting market data in real time, a means for collecting social media data, and a means for collecting trend information from news. This enables a generating artificial intelligence means for integrating and analyzing market data, social media data, and news trend information, a means for identifying investment opportunities, a means for notifying a user terminal of the identified investment opportunities, and a means for analyzing a user's purchasing patterns in electronic payment services and providing purchasing recommendations. This allows users to grasp market fluctuations and social trends in real time and receive personalized recommendations for their next product or service purchase.

[0395] "Market data" refers to information such as stock prices, trading volumes, and exchange rates in financial markets.

[0396] "Social media data" refers to information such as posts and comments posted by users on social networking services.

[0397] "News trend information" refers to information on the latest trends and events analyzed based on news articles and reports.

[0398] "Generative AI" refers to artificial intelligence technology that has algorithms that comprehensively analyze collected data and generate predictions and insights.

[0399] "Investment Opportunities" refers to the timing and targets of investments that are likely to be advantageous to the user based on collected and analyzed data.

[0400] "User terminal" refers to an electronic device, such as a smartphone or tablet, that allows a user to receive and operate information.

[0401] "Electronic payment service" refers to a platform or system for making monetary payments using electronic means.

[0402] "Purchasing patterns" refer to the tendencies and habits based on a user's past purchasing history and behavior.

[0403] "Purchase recommendation" refers to analyzing a user's purchasing patterns and suggesting the next product or service they should purchase.

[0404] The present invention provides a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time, identifies investment opportunities based on the collected data, and notifies users of these opportunities. It also has the function of analyzing purchasing patterns of electronic payment services and making purchasing recommendations. Specific embodiments of the present invention are described below.

[0405] Data collection

[0406] The server uses APIs to collect real-time market data, social media data, and news trend information. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0407] Data integration and analysis

[0408] The server compiles the various collected data into a single integrated dataset. During this process, data preprocessing includes cleansing and formatting standardization. The integrated data is then analyzed by generative artificial intelligence (AI). The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes news content to generate comprehensive insights. It also has the ability to analyze user purchasing patterns for electronic payment services.

[0409] Identifying investment opportunities and purchase recommendations

[0410] Based on the insights analyzed by AI, the server identifies investment opportunities. It also analyzes purchasing patterns based on the user's past purchase history and recommends the next optimal purchase. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is determined to be an investment opportunity or purchase recommendation.

[0411] User Notification

[0412] The server notifies the user of identified investment opportunities and purchase recommendations via push notifications, in-app messages, emails, etc. The notification content includes detailed investment information, recommended actions, and purchase recommendations.

[0413] User Support

[0414] Users receive the information via their devices and make quick investment or purchasing decisions based on that information. Users review the insights and execute operations on trading or purchasing platforms as needed.

[0415] Hardware or software used

[0416] This system uses user devices such as smartphones and tablets, and uses the Python programming language, the Requests library, and the Scikit-learn library to collect, integrate, and analyze data.

[0417] Examples of concrete examples and prompts

[0418] For example, if market data, social media data, and news trend information is obtained as follows:

[0419] Market Data: "ABC Product" is on the rise

[0420] Social media data: Increased mentions of "buy ABC product"

[0421] News Trend Information: Reports that "ABC product is very popular"

[0422] An example prompt generated using this information is:

[0423] "We've discovered a new buying opportunity! 'Product ABC' is extremely popular right now. It's getting widespread mentions on social media and high ratings in the news. Check it out now!"

[0424] By sending these notifications to users and providing investment opportunities and purchase recommendations, users can understand market fluctuations and social trends in real time and make appropriate investment and purchasing decisions.

[0425] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0426] Step 1:

[0427] The server uses APIs to collect market data, social media data, and news trend information in real time. This collected data is obtained from each data source in JSON format. The input is raw data obtained from the APIs, and the server stores this data. The output is a collection of raw data.

[0428] Step 2:

[0429] The server integrates the collected market data, social media data, and news trend information into a single dataset. As part of data preprocessing, it fills in missing data, removes inappropriate data, and standardizes formats. The input is the collected raw data, which the server cleanses and standardizes. The output is a cleansed, integrated dataset.

[0430] Step 3:

[0431] The server uses generative artificial intelligence to analyze the cleansed integrated dataset. Here, it performs scaling, PCA (principal component analysis), and KMeans clustering to extract features from each data point. The input is the integrated dataset, and the server reduces the dimensions using scaling and PCA and performs clustering. The output is the analysis results and the centers of each cluster.

[0432] Step 4:

[0433] The server identifies investment opportunities and purchase recommendations based on the generated analysis results. In particular, if the cluster center value exceeds a certain threshold, the server determines that the data points in that cluster are investment opportunities or purchase recommendations. The inputs are the analysis results and the cluster center values, and the server performs threshold judgment. The output is the identified investment opportunities and purchase recommendations.

[0434] Step 5:

[0435] The server generates prompt messages for the identified investment opportunities and purchase recommendations and notifies the user device. Here, prompt messages are generated based on templates and sent to the user via push notifications, in-app messages, emails, etc. The input is the information on the identified investment opportunities and purchase recommendations, and the server creates the prompt messages using a generative AI model. The output is a notification message to the user.

[0436] Step 6:

[0437] Users receive the information notified through their terminals and make quick investment or purchasing decisions based on that information. Here, users check the notified insights and access the trading or purchasing platform to execute operations. The input is the notification message, and the user decides on the next action based on this. The output is the executed purchase or investment action.

[0438] 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.

[0439] The present invention is a system that identifies investment opportunities and supports quick investment decisions by collecting, integrating, and analyzing market data, social media data, and news trend information in real time, and by combining this with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0440] Data collection

[0441] The server uses APIs to collect real-time market data, social media data, and news trend information. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0442] Data integration and analysis

[0443] The server converts the collected market data, social media data, and news trend information into a unified format and performs data preprocessing. The preprocessed data is compiled into an integrated dataset and analyzed using generative artificial intelligence (AI). The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes the content of news articles, thereby extracting useful insights from the data.

[0444] Utilizing the Emotion Engine

[0445] Furthermore, the emotion engine analyzes user emotions from user input data (e.g., text input or voice input) and utilizes the results together with the integrated data. The emotion analysis results from the emotion engine are used to identify investment opportunities and optimize the content of notifications to users.

[0446] Identifying investment opportunities

[0447] Based on the AI-generated insights and user sentiment data analyzed by the sentiment engine, the server identifies investment opportunities. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is identified as an investment opportunity.

[0448] User Notification

[0449] The server then notifies the user of the best investment opportunities based on the identified investment opportunities and the results of sentiment analysis via push notifications, in-app messages, emails, etc. The notification content includes detailed information about the investment opportunity and recommended actions.

[0450] User investment support

[0451] The user receives a notification from the terminal and checks its contents. Taking into account the information and the user's own emotional state, the user makes an investment decision. The user then executes a trade through the trading platform and checks the results on the terminal.

[0452] Specific examples

[0453] For example, suppose a company's stock price is rising sharply. Positive social media posts about the company are increasing, and positive articles about the company are published in major news media. Furthermore, the emotion engine analyzes that users themselves are excited (positive emotions). The server collects and integrates this data in real time, and analyzes it using AI and the emotion engine. The analysis results indicate that the company's stock price is likely to rise sharply in the short term.

[0454] The server notifies the user of this investment opportunity, and the user confirms it and immediately decides to purchase the company's stock and executes the trade on the trading platform. This allows the user to make appropriate investment decisions that comprehensively take into account minute market fluctuations, social trends, and their own emotional state.

[0455] The present invention provides a new type of investment support system that supports quick and accurate investment decisions by comprehensively analyzing complex market information, diverse social trends, and the user's emotional state.

[0456] The processing flow will be explained below.

[0457] Step 1:

[0458] The server collects real-time market data through APIs. Specifically, it calls the API of a financial information service to obtain market data such as stock prices and trading volumes. It also uses APIs from social media to collect data such as tweets and comments. It also uses news APIs to obtain the latest news articles.

[0459] Step 2:

[0460] The server performs pre-processing on the collected market data, social media data, and news trend information to cleanse and standardize the format, converting data from each data source into a consistent format and compiling it into an integrated data set.

[0461] Step 3:

[0462] The server provides the integrated data set to the Generator AI, which analyzes each data set, analyzing market fluctuation patterns, social media sentiment analysis, and news content to extract useful insights.

[0463] Step 4:

[0464] The server uses an emotion engine to analyze the user's input data (e.g., text input or voice input) and evaluate the user's current emotional state. The results of this emotion analysis are used together with the integrated data.

[0465] Step 5:

[0466] The server identifies investment opportunities based on the insights obtained by the generative AI and the results of user sentiment analysis by the sentiment engine. It detects insights that meet certain thresholds and conditions (e.g., high probability and high impact) and identifies them as investment opportunities.

[0467] Step 6:

[0468] The server then sends information about identified investment opportunities and sentiment analysis results to the user's device via push notifications, in-app messages, emails, etc. The notification content includes detailed information about the investment opportunity and recommended actions.

[0469] Step 7:

[0470] Users receive notifications through their devices, check the content, and make investment decisions based on the information and their emotional state.

[0471] Step 8:

[0472] Users execute trades through the trading platform, specifically by issuing instructions to buy or sell stocks based on the provided insights and completing the trades.

[0473] Step 9:

[0474] Once the transaction is complete, the user can view the results on their device, and based on the results, the next step is to collect and analyze data again, or look for other investment opportunities.

[0475] This system allows users to comprehensively grasp minute market fluctuations, social trends, and their own emotional state, allowing them to make quick and appropriate investment decisions.

[0476] Example 2

[0477] 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."

[0478] Conventional investment support systems often collect and analyze market data, social media data, and news trend information separately, resulting in low-accuracy insights and making it difficult to properly identify investment opportunities. Furthermore, because they do not take user emotions into account, it is difficult to support optimal investment decisions that reflect the user's emotional state. Therefore, there is a demand for an integrated, highly accurate system that supports quick and accurate investment decisions.

[0479] 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.

[0480] In this invention, the server includes means for collecting market data in real time, means for collecting social media data, means for collecting trend information from news, artificial intelligence generation means, emotion analysis means for analyzing user emotions, emotion analysis results and means for identifying investment opportunities based on the analysis results, and means for notifying the user terminal of the identified investment opportunities. This enables support for quick and accurate investment decisions by integrating and analyzing multiple data sources with high accuracy and taking into account the user's emotional state.

[0481] "Market Data" refers to data relating to financial markets, such as price information, trading volumes, and indicators.

[0482] "Social media data" refers to data such as user posts, comments, and reactions on online social networking services and platforms.

[0483] "News trend information" refers to information such as news articles, reports, and analyses about current events and topics.

[0484] "Generative AI tools" refers to machine learning models and algorithms that integrate diverse data sources and perform advanced analysis.

[0485] "Emotion analysis means" refers to technologies and algorithms for determining a user's emotions from user input data (e.g., text, voice, etc.).

[0486] "Means for identifying investment opportunities" refers to technologies that analyze market data, social media data, news trend information, and user sentiment data to identify potential investment opportunities.

[0487] "User terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) that a user operates and receives information.

[0488] The present invention is a system that identifies investment opportunities and supports quick investment decisions by collecting, integrating, and analyzing market data, social media data, and news trend information in real time, and by combining this with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0489] First, the server collects data using a dedicated API. To collect market data, the server uses the API to obtain price information and trading volumes of financial markets. To collect social media data, the server uses the API of a social media platform to obtain posts and comments. To collect news trend information, the server obtains the latest news articles via the API of a news service.

[0490] The server then converts the collected data into a unified format and performs data preprocessing. For example, stock quotes are converted into CSV format, tweets and comments are formatted into JSON format, news articles are subjected to text analysis to generate summaries, and the data is then integrated using a dataframe manipulation library to fill in any inaccurate or missing data.

[0491] The combined data set is then analyzed by server-based generative AI models, which use machine learning frameworks to analyze market fluctuation patterns, natural language processing libraries for social media sentiment analysis, and natural language generation models to analyze the content of news articles and extract useful insights.

[0492] Furthermore, the server uses an emotion engine to analyze the user's emotions from the user's input data (e.g., text input or voice input). This analysis can use a natural language processing library as an emotion classification model to accurately determine the user's positive or negative emotional state.

[0493] Based on the analysis results from the AI ​​model and sentiment engine, the server identifies investment opportunities, which are then assigned trust and influence scores by the algorithm, and are confirmed as investment opportunities if they exceed a certain threshold.

[0494] Confirmed investment opportunities are notified to the user's device from the server using a cloud messaging service. Notification details are also sent via email and in-app message. Notification content includes the investment opportunity analysis results, recommended actions, and an assessed confidence score.

[0495] The user receives a notification on their device, checks the details, makes an investment decision based on the provided data and their own judgment, and executes the trade through the trading platform.

[0496] Specific examples

[0497] For example, suppose a company's stock price is rising sharply. The server obtains the company's stock price and trading volume data through a financial market API, collects a large number of related positive posts using a social media API, and collects positive news articles about the company using a news service API. After integrating and preprocessing this data, it analyzes it using a generative AI model. The resulting insight is that the company's stock price is likely to rise further.

[0498] Additionally, the emotion engine analyzes the user's input text to determine whether the user is in a positive emotional state, and the server uses this information to identify investment opportunities with high confidence scores.

[0499] The server then notifies the user of the investment opportunity and suggests specific investment actions. A push notification is sent stating, "The stock price of a specific company is rising. Check the details and consider purchasing."

[0500] The user then checks the notification, decides to invest based on the suggested information, and purchases shares through the trading platform. Finally, the user sees the results of the transaction displayed on the terminal in real time.

[0501] Prompt Sentence Examples

[0502] "Tell me which companies I should invest in next based on recent market data, social media comments, and trending news. Also, please suggest the best investment opportunities given my emotional state: positive and excited."

[0503] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0504] Step 1:

[0505] The server uses APIs to collect market data, social media data, and news trend information in real time. Access information to each API endpoint is used as input. For market data, a financial market API is used, for social media data, a social media API is used, and for news trend information, a news service API is used. The output is the raw data of the various types of data collected.

[0506] Step 2:

[0507] The server converts the collected market data, social media data, and news trend information into a unified format. It uses the raw data collected in step 1 as input. Specifically, it converts stock quotes into CSV format, formats social media posts and comments into JSON format, and performs text analysis on news articles to generate summaries. The output is the data converted into a unified format.

[0508] Step 3:

[0509] The server preprocesses the converted data. As input, it uses the data converted to a unified format in step 2. It uses the Pandas library to create a data frame and imputes inaccurate or missing data. It also removes outliers. The output is a clean dataset that has been preprocessed.

[0510] Step 4:

[0511] The server combines the preprocessed datasets and inputs them into the generative AI model. It uses the clean dataset obtained in step 3 as input. After combining the datasets, it uses a machine learning framework (TensorFlow or PyTorch) to analyze market fluctuation patterns. At the same time, it uses a natural language processing library (NLTK or Transformers) to perform social media sentiment analysis and content analysis of news articles. The output is insights as a result of the analysis.

[0512] Step 5:

[0513] The server uses an emotion engine to analyze the user's emotions. The input is the user's input data (text input or voice input). A natural language processing library is used as an emotion classification model to analyze the user's positive and negative emotional state. The output is the user's emotion analysis results.

[0514] Step 6:

[0515] The server identifies investment opportunities based on the analysis results and sentiment analysis results. It uses the insights from step 4 and the sentiment analysis results from step 5 as inputs. The algorithm sets trust and influence scores and identifies insights that exceed certain thresholds as investment opportunities. The output is the identified investment opportunities.

[0516] Step 7:

[0517] The server notifies the user device of the identified investment opportunities. As input, it uses the investment opportunity data identified in step 6. It uses a cloud messaging service (e.g., Firebase Cloud Messaging) to send a push notification. Details are also delivered via email and in-app message. The output is the notification sent to the user.

[0518] Step 8:

[0519] The user receives the notification on their device and checks its contents. As input, they use the notification sent from the server. The user makes an investment decision based on the provided data and their own judgment. The output is an investment decision.

[0520] Step 9:

[0521] The user executes a trade using the trading platform. As input, they use the investment decision made in step 8. They log in to the trading platform, select the financial instrument, and perform a buy / sell operation. The output is the executed trade.

[0522] (Application example 2)

[0523] 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."

[0524] While conventional investment support systems excel at collecting and analyzing real-time data, they do not take into account the user's emotional state and therefore are unable to provide optimal investment timing or decisions. This makes it difficult for users to grasp minute market fluctuations and social trends, making it difficult to make appropriate investment decisions.

[0525] The identification process by the identification 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 means for collecting market data in real time, means for collecting social media data, means for collecting trend information from news, generative artificial intelligence means for integrating and analyzing the market data, social media data, and news trends, emotion engine means for analyzing user emotions, means for identifying investment opportunities, and means for notifying the user terminal of the identified investment opportunities. This enables fast and accurate investment support that takes into account the user's emotional state.

[0526] "Market data" refers to data such as price information and trading volume related to financial markets.

[0527] "Social Media Data" refers to data posted by users on social media platforms, such as comments, tweets, and reviews.

[0528] "News trend information" refers to data about the latest events and topics obtained from news articles and information distribution services.

[0529] "Generative AI" refers to artificial intelligence techniques for data integration and analysis.

[0530] An "emotion engine" is a mechanism that analyzes the user's emotional state from input data.

[0531] An "investment opportunity" is a time or condition in the financial markets that offers high potential for making a profit.

[0532] A "user terminal" is a computing device used by a user, such as a smartphone or PC.

[0533] This invention is a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time while taking into account the user's emotional state, and notifies the user of optimal investment opportunities. The system that realizes this application example is described in detail below.

[0534] Data collection

[0535] The server uses APIs to collect real-time market data, social media data, and news trend information. A specific software example is the requests library. Market data includes price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0536] Data integration and analysis

[0537] The server converts the collected market data, social media data, and news trend information into a unified format and performs data preprocessing. The preprocessed data is compiled into an integrated dataset and analyzed using generative artificial intelligence (AI) such as TensorFlow or PyTorch. The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes the content of news articles, thereby extracting useful insights from the data.

[0538] Utilizing the Emotion Engine

[0539] The server is equipped with an emotion engine that analyzes user emotions from user input data (e.g., text input or voice input). This emotion analysis is performed to recognize the user's emotional state, and the results are utilized together with the integrated data. Natural language processing (NLP) models are used for emotion analysis.

[0540] Identifying investment opportunities

[0541] Based on the AI-generated insights and user sentiment data analyzed by the sentiment engine, the server identifies investment opportunities. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is identified as an investment opportunity.

[0542] User Notification

[0543] The server then notifies the user of the best investment opportunities based on the identified investment opportunities and the results of sentiment analysis via push notifications, in-app messages, emails, etc. The notification content includes detailed information about the investment opportunity and recommended actions.

[0544] User investment support

[0545] The user receives a notification from the terminal and checks its contents. Taking into account the information and the user's own emotional state, the user makes an investment decision. The user then executes a trade through the trading platform and checks the results on the terminal.

[0546] Specific examples

[0547] For example, consider a situation where a company's stock price is rising sharply. Positive social media posts about the company increase, and major news media publish positive articles about the company. Furthermore, the emotion engine analyzes that users themselves are excited (positive emotions). The server collects and integrates this data in real time, and analyzes it using AI and the emotion engine. The analysis results identify that the company's stock price is likely to rise sharply in the short term.

[0548] The server notifies the user of this investment opportunity, and the user confirms it and immediately decides to purchase the company's stock and executes the trade on the trading platform. This allows the user to make appropriate investment decisions that comprehensively take into account minute market fluctuations, social trends, and their own emotional state.

[0549] An example of a prompt to be input to a generative AI model might be, "Integrate and analyze market data, social media data, news trends, and user sentiment data to generate optimal purchasing suggestions."

[0550] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0551] Step 1:

[0552] The server uses APIs to collect market data, social media data, and news trend information in real time. It uses the requests library to send data retrieval requests to specific API endpoints and receives responses in JSON format. The input here is the API endpoint URL and required parameters, and the output is a JSON object of the various retrieved data.

[0553] Step 2:

[0554] The server converts the collected market data, social media data, and news trend information into a unified format and performs preprocessing. Specifically, it performs missing value imputation, data normalization, and format conversion. The input is the raw data obtained in the previous step, and the output is a dataset in a unified format.

[0555] Step 3:

[0556] The server aggregates the preprocessed data and performs analysis using generative artificial intelligence (AI) such as TensorFlow or PyTorch. This includes analyzing market fluctuation patterns, social media sentiment analysis, and semantic analysis of news articles. The input is a unified dataset, and the output is analyzed, useful insights.

[0557] Step 4:

[0558] The server uses an emotion engine to analyze emotions from user input data (e.g., text input or voice input). It uses an NLP model (e.g., BERT or GPT) to identify the user's emotional state. The input is the user's raw text or voice data, and the output is the analyzed emotion data.

[0559] Step 5:

[0560] The server identifies investment opportunities based on AI-generated insights and user sentiment data analyzed by the sentiment engine. It evaluates the integrated data to identify suitable investment opportunities based on certain thresholds and conditions (e.g., high probability and high impact). The inputs are insights and sentiment data, and the output is data on identified investment opportunities.

[0561] Step 6:

[0562] The server notifies the user device of identified investment opportunities. Information is sent to the user in the form of push notifications, in-app messages, emails, etc. The notification includes detailed information about the investment opportunity and recommended actions. The input is the investment opportunity data, and the output is the notification sent to the user device.

[0563] Step 7:

[0564] The user receives notifications from the terminal and checks their contents. They take the information and their emotional state into consideration to make appropriate investment decisions. The user executes trades through the trading platform and checks the results on the terminal. The input is notification information from the server, and the output is the user's investment actions and their results.

[0565] 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.

[0566] 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.

[0567] 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.

[0568] [Third embodiment]

[0569] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0570] 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.

[0571] 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).

[0572] 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.

[0573] 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.

[0574] 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).

[0575] 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.

[0576] 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.

[0577] 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.

[0578] 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.

[0579] 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.

[0580] 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."

[0581] The present invention is a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time, and identifies investment opportunities to help users make quick investment decisions. Specific embodiments of the system are described below.

[0582] Data collection

[0583] The server uses APIs to collect real-time market data, social media data, and news trend information. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0584] Data integration and analysis

[0585] The server compiles the collected data into a single integrated dataset. During this process, data preprocessing is performed, including cleansing and formatting. The integrated data is then analyzed by generative artificial intelligence (AI). The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes news content to generate comprehensive insights.

[0586] Identifying investment opportunities

[0587] Based on the insights analyzed by AI, the server identifies investment opportunities. If an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is deemed an investment opportunity.

[0588] User Notification

[0589] The server notifies the user of identified investment opportunities via push notifications, in-app messages, emails, etc. The notification includes detailed investment information and recommended actions.

[0590] User investment support

[0591] Users receive investment opportunities notified through their terminals and make quick investment decisions based on that information. Users review the notified insights and execute trades on the trading platform as needed.

[0592] Specific examples

[0593] Suppose a company's stock price is rising sharply. Positive social media posts about the company increase, and major news outlets publish positive articles about the company. The server collects and integrates this data in real time and analyzes it using AI. The analysis results indicate that the company's stock price is likely to surge in the short term.

[0594] The server notifies the user of this investment opportunity. The user receives the notification and immediately decides to purchase the company's stock, executing the trade on the trading platform. This allows the user to instantly grasp minute market fluctuations and social trends and make appropriate investment decisions.

[0595] The present invention provides a new type of investment support system that supports quick and accurate investment decisions by comprehensively analyzing complex market information and diverse social trends.

[0596] The processing flow will be explained below.

[0597] Step 1:

[0598] The server collects real-time market data through APIs. Specifically, it calls the APIs of financial information providers to obtain market data such as stock price data and trading volume. It also uses APIs from social media to obtain related data such as tweets. For news trends, it calls news APIs to collect the latest news articles.

[0599] Step 2:

[0600] The server consolidates the collected data. It cleanses and pre-processes the data, converting it all into a consistent format. This process combines data from different sources and makes it easier to analyze.

[0601] Step 3:

[0602] The server then analyzes the integrated data using Generative Artificial Intelligence (AI), which analyzes market fluctuation patterns, performs social media sentiment analysis, and evaluates the content of news articles to extract useful insights from the data.

[0603] Step 4:

[0604] The server identifies investment opportunities based on AI-generated insights by detecting insights that meet certain thresholds or conditions (e.g., high probability and high impact information) and identifying them as investment opportunities.

[0605] Step 5:

[0606] The server notifies the user device of identified investment opportunities via push notifications, in-app messages, emails, etc. The notification includes details about the investment opportunity and recommended actions.

[0607] Step 6:

[0608] After receiving the notification, the user confirms its contents and uses the device to review the provided insights and understand the information about the investment opportunity.

[0609] Step 7:

[0610] The user makes an investment decision based on the notified investment opportunity, and once the decision is complete, executes the trade through the trading platform, specifically by issuing a purchase or sale instruction and completing the transaction.

[0611] Step 8:

[0612] Once the trade is complete, the user can view the results on their device, and based on the results, the next step is to collect and analyze data again, or to look for other investment opportunities.

[0613] This system allows users to grasp minute market fluctuations and social trends in real time, enabling them to make quick and appropriate investment decisions.

[0614] Example 1

[0615] 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."

[0616] Conventional investment support systems typically collect and analyze market data, social media data, and news trend information separately, making it difficult to integrate them and quickly identify investment opportunities.Furthermore, few systems apply advanced analytical techniques such as data preprocessing and sentiment analysis, making it difficult to provide accurate insights that allow users to make immediate investment decisions.

[0617] 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.

[0618] In this invention, the server includes a means for collecting market data in real time, a means for collecting social media data, and a means for collecting trend information from news. This allows for efficient data collection, integration, and preprocessing of the data. Furthermore, the preprocessed data is analyzed using a generative AI model to identify investment opportunities, and detailed information about the identified investment opportunities and recommended actions are notified to the user's terminal, allowing the user to make prompt and appropriate investment decisions.

[0619] "Market data" refers to numerical information related to financial markets, such as stock price information and trading volume.

[0620] "Social Media Data" refers to text and metadata generated on social media platforms, such as user posts, comments, and retweets.

[0621] "News trend information" refers to the latest information and topics obtained from news articles and reports.

[0622] "Data preprocessing" refers to the process of cleansing collected data and processing it into a state suitable for analysis, such as by deleting duplicate data and standardizing formats.

[0623] "Generative AI means" refers to AI that uses collected and integrated data to analyze market fluctuation patterns, sentiment analysis, and news text analysis to generate comprehensive insights.

[0624] "Means for identifying investment opportunities" refers to the process of extracting investment options that meet certain thresholds and conditions based on the generated insights, and evaluating and determining them as investment opportunities.

[0625] "User terminal" refers to a device (smartphone, tablet, PC, etc.) on which a user receives notifications from the system, views insights, and makes investment decisions.

[0626] The present invention is a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time, and identifies investment opportunities to help users make quick investment decisions. Specific embodiments of the system are described below.

[0627] Data collection

[0628] The server uses APIs to collect market data, social media data, and news trend information in real time. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles. Specifically, the server uses Yahoo Finance API and Alpha Vantage API for market data, Twitter API and Facebook Graph API for social media data, and Google News API and News API for trend information.

[0629] Data integration and analysis

[0630] The server compiles the various collected data into a single integrated dataset. During this process, data preprocessing is performed, including cleansing and formatting. For example, this includes removing duplicate data and filling in missing values. The integrated data is then analyzed using generative artificial intelligence (AI). Specifically, generative AI models are used to analyze market fluctuation patterns, perform social media sentiment analysis, and perform text analysis of news content to generate comprehensive insights. Machine learning frameworks such as TensorFlow and PyTorch are used for the analysis.

[0631] Identifying investment opportunities

[0632] Based on the AI-generated insights, the server identifies investment opportunities. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is deemed an investment opportunity, specifically based on predicted stock price growth or positive social media sentiment score.

[0633] User Notification

[0634] The server notifies the user device of the identified investment opportunity. This notification is sent in the form of a push notification, in-app message, email, or other format. The notification includes detailed information about the investment and recommended actions. For example, a message such as "The stock price of Company X is expected to rise sharply. The current stock price is X yen. Please consider purchasing now" is sent.

[0635] User investment support

[0636] Users receive notifications of investment opportunities through their devices and make quick investment decisions based on the information. They review the notified insights and execute trades on the trading platform as needed. For example, after receiving a notification on their device, the user opens a trading app and purchases the indicated stocks.

[0637] Specific examples

[0638] For example, suppose a company's stock price is rising sharply. Positive social media posts about the company increase, and major news outlets publish positive articles about the company. The server collects and integrates this data in real time and analyzes it using AI. The analysis results indicate that the company's stock price is likely to rise sharply in the short term.

[0639] The server notifies the user of this investment opportunity. The user receives the notification and immediately decides to purchase the company's stock, executing the trade on the trading platform. This allows the user to instantly grasp minute market fluctuations and social trends and make appropriate investment decisions.

[0640] Example prompts to be input to the generative AI model

[0641] "How can I integrate market data, social media data, and news trend information to identify investment opportunities?"

[0642] Based on this prompt, the AI ​​will walk you through each step of collection, synthesis, and analysis to provide a method for identifying investment opportunities.

[0643] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0644] Step 1: Gather market data

[0645] The server uses APIs to collect market data in real time. Specifically, it uses the Yahoo Finance API and Alpha Vantage API to obtain stock price information and trading volume. It uses a list of stocks to be collected as input and obtains the current stock price and trading volume data for each stock as output. This operation obtains the latest market data.

[0646] Step 2: Collect social media data

[0647] The server uses the Twitter API and Facebook Graph API to collect user posts and comments on social media. It uses search queries related to specific companies or keywords as input and obtains text data of the relevant posts and comments as output. This operation obtains social media reactions in real time.

[0648] Step 3: Gathering news trends

[0649] The server uses the Google News API or News API to collect the latest news articles. It uses keywords related to a specific company name or topic as input, and obtains the URL, title, summary, and publication date of the relevant news article as output. This operation allows you to understand the latest news trends.

[0650] Step 4: Data integration and preprocessing

[0651] The server aggregates the collected market data, social media data, and news trend information into a single integrated data set. It uses each of the previously collected data sources (market data, social media data, and news trend information) as input and generates an integrated data set as output. This process includes deduplication, outlier correction, and standardization of data formats.

[0652] Step 5: Data analysis using AI

[0653] The server runs the generative AI model with the integrated dataset. It uses the integrated dataset as input and outputs market movement patterns, social media sentiment scores, and news content analysis. In this operation, the AI ​​analyzes the collected data and generates comprehensive insights on investment opportunities.

[0654] Step 6: Identifying investment opportunities

[0655] The server evaluates the AI-generated insights and identifies investment opportunities. It uses the analysis results of the generative AI model as input and obtains identified investment opportunities (e.g., stocks predicted to surge) as output. This operation extracts insights with high probability and high impact and determines them as investment opportunities.

[0656] Step 7: Notify users

[0657] The server notifies the user device of the identified investment opportunity. Using the details of the identified investment opportunity as input, a push notification, an in-app message, or an email is generated as output to the user device. This operation allows the user to quickly learn about the investment opportunity.

[0658] Step 8: User investment decision and execution

[0659] Users receive notifications and make quick investment decisions based on the information, using notifications from the server as input and trade execution on the trading platform as output, where users review insights and buy or sell stocks as needed.

[0660] Step 9: Feedback Loop

[0661] The server collects the user's investment behavior and results as feedback and uses it to improve the system's analytical model. The user's investment result data is used as input, and the analytical model's parameter adjustment and algorithm improvement are obtained as output. This operation improves the accuracy and effectiveness of the system.

[0662] (Application example 1)

[0663] 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."

[0664] While conventional investment support systems can identify investment opportunities through integrated analysis of real-time market data, social media data, and news trend information, they lack the functionality to suggest the next optimal purchase based on the user's purchasing patterns in electronic payment services. As a result, users may miss the right timing or opportunity to make a purchase. To solve this issue, a system is needed that not only identifies investment opportunities but also analyzes the user's purchasing patterns and makes personalized purchasing recommendations.

[0665] 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.

[0666] In this invention, the server includes a means for collecting market data in real time, a means for collecting social media data, and a means for collecting trend information from news. This enables a generating artificial intelligence means for integrating and analyzing market data, social media data, and news trend information, a means for identifying investment opportunities, a means for notifying a user terminal of the identified investment opportunities, and a means for analyzing a user's purchasing patterns in electronic payment services and providing purchasing recommendations. This allows users to grasp market fluctuations and social trends in real time and receive personalized recommendations for their next product or service purchase.

[0667] "Market data" refers to information such as stock prices, trading volumes, and exchange rates in financial markets.

[0668] "Social media data" refers to information such as posts and comments posted by users on social networking services.

[0669] "News trend information" refers to information on the latest trends and events analyzed based on news articles and reports.

[0670] "Generative AI" refers to artificial intelligence technology that has algorithms that comprehensively analyze collected data and generate predictions and insights.

[0671] "Investment Opportunities" refers to the timing and targets of investments that are likely to be advantageous to the user based on collected and analyzed data.

[0672] "User terminal" refers to an electronic device, such as a smartphone or tablet, that allows a user to receive and operate information.

[0673] "Electronic payment service" refers to a platform or system for making monetary payments using electronic means.

[0674] "Purchasing patterns" refer to the tendencies and habits based on a user's past purchasing history and behavior.

[0675] "Purchase recommendation" refers to analyzing a user's purchasing patterns and suggesting the next product or service they should purchase.

[0676] The present invention provides a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time, identifies investment opportunities based on the collected data, and notifies users of these opportunities. It also has the function of analyzing purchasing patterns of electronic payment services and making purchasing recommendations. Specific embodiments of the present invention are described below.

[0677] Data collection

[0678] The server uses APIs to collect real-time market data, social media data, and news trend information. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0679] Data integration and analysis

[0680] The server compiles the various collected data into a single integrated dataset. During this process, data preprocessing includes cleansing and formatting standardization. The integrated data is then analyzed by generative artificial intelligence (AI). The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes news content to generate comprehensive insights. It also has the ability to analyze user purchasing patterns for electronic payment services.

[0681] Identifying investment opportunities and purchase recommendations

[0682] Based on the insights analyzed by AI, the server identifies investment opportunities. It also analyzes purchasing patterns based on the user's past purchase history and recommends the next optimal purchase. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is determined to be an investment opportunity or purchase recommendation.

[0683] User Notification

[0684] The server notifies the user of identified investment opportunities and purchase recommendations via push notifications, in-app messages, emails, etc. The notification content includes detailed investment information, recommended actions, and purchase recommendations.

[0685] User Support

[0686] Users receive the information via their devices and make quick investment or purchasing decisions based on that information. Users review the insights and execute operations on trading or purchasing platforms as needed.

[0687] Hardware or software used

[0688] This system uses user devices such as smartphones and tablets, and uses the Python programming language, the Requests library, and the Scikit-learn library to collect, integrate, and analyze data.

[0689] Examples of concrete examples and prompts

[0690] For example, if market data, social media data, and news trend information is obtained as follows:

[0691] Market Data: "ABC Product" is on the rise

[0692] Social media data: Increased mentions of "buy ABC product"

[0693] News Trend Information: Reports that "ABC product is very popular"

[0694] An example prompt generated using this information is:

[0695] "We've discovered a new buying opportunity! 'Product ABC' is extremely popular right now. It's getting widespread mentions on social media and high ratings in the news. Check it out now!"

[0696] By sending these notifications to users and providing investment opportunities and purchase recommendations, users can understand market fluctuations and social trends in real time and make appropriate investment and purchasing decisions.

[0697] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0698] Step 1:

[0699] The server uses APIs to collect market data, social media data, and news trend information in real time. This collected data is obtained from each data source in JSON format. The input is raw data obtained from the APIs, and the server stores this data. The output is a collection of raw data.

[0700] Step 2:

[0701] The server integrates the collected market data, social media data, and news trend information into a single dataset. As part of data preprocessing, it fills in missing data, removes inappropriate data, and standardizes formats. The input is the collected raw data, which the server cleanses and standardizes. The output is a cleansed, integrated dataset.

[0702] Step 3:

[0703] The server uses generative artificial intelligence to analyze the cleansed integrated dataset. Here, it performs scaling, PCA (principal component analysis), and KMeans clustering to extract features from each data point. The input is the integrated dataset, and the server reduces the dimensions using scaling and PCA and performs clustering. The output is the analysis results and the centers of each cluster.

[0704] Step 4:

[0705] The server identifies investment opportunities and purchase recommendations based on the generated analysis results. In particular, if the cluster center value exceeds a certain threshold, the server determines that the data points in that cluster are investment opportunities or purchase recommendations. The inputs are the analysis results and the cluster center values, and the server performs threshold judgment. The output is the identified investment opportunities and purchase recommendations.

[0706] Step 5:

[0707] The server generates prompt messages for the identified investment opportunities and purchase recommendations and notifies the user device. Here, prompt messages are generated based on templates and sent to the user via push notifications, in-app messages, emails, etc. The input is the information on the identified investment opportunities and purchase recommendations, and the server creates the prompt messages using a generative AI model. The output is a notification message to the user.

[0708] Step 6:

[0709] Users receive the information notified through their terminals and make quick investment or purchasing decisions based on that information. Here, users check the notified insights and access the trading or purchasing platform to execute operations. The input is the notification message, and the user decides on the next action based on this. The output is the executed purchase or investment action.

[0710] 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.

[0711] The present invention is a system that identifies investment opportunities and supports quick investment decisions by collecting, integrating, and analyzing market data, social media data, and news trend information in real time, and by combining this with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0712] Data collection

[0713] The server uses APIs to collect real-time market data, social media data, and news trend information. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0714] Data integration and analysis

[0715] The server converts the collected market data, social media data, and news trend information into a unified format and performs data preprocessing. The preprocessed data is compiled into an integrated dataset and analyzed using generative artificial intelligence (AI). The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes the content of news articles, thereby extracting useful insights from the data.

[0716] Utilizing the Emotion Engine

[0717] Furthermore, the emotion engine analyzes user emotions from user input data (e.g., text input or voice input) and utilizes the results together with the integrated data. The emotion analysis results from the emotion engine are used to identify investment opportunities and optimize the content of notifications to users.

[0718] Identifying investment opportunities

[0719] Based on the AI-generated insights and user sentiment data analyzed by the sentiment engine, the server identifies investment opportunities. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is identified as an investment opportunity.

[0720] User Notification

[0721] The server then notifies the user of the best investment opportunities based on the identified investment opportunities and the results of sentiment analysis via push notifications, in-app messages, emails, etc. The notification content includes detailed information about the investment opportunity and recommended actions.

[0722] User investment support

[0723] The user receives a notification from the terminal and checks its contents. Taking into account the information and the user's own emotional state, the user makes an investment decision. The user then executes a trade through the trading platform and checks the results on the terminal.

[0724] Specific examples

[0725] For example, suppose a company's stock price is rising sharply. Positive social media posts about the company are increasing, and positive articles about the company are published in major news media. Furthermore, the emotion engine analyzes that users themselves are excited (positive emotions). The server collects and integrates this data in real time, and analyzes it using AI and the emotion engine. The analysis results indicate that the company's stock price is likely to rise sharply in the short term.

[0726] The server notifies the user of this investment opportunity, and the user confirms it and immediately decides to purchase the company's stock and executes the trade on the trading platform. This allows the user to make appropriate investment decisions that comprehensively take into account minute market fluctuations, social trends, and their own emotional state.

[0727] The present invention provides a new type of investment support system that supports quick and accurate investment decisions by comprehensively analyzing complex market information, diverse social trends, and the user's emotional state.

[0728] The processing flow will be explained below.

[0729] Step 1:

[0730] The server collects real-time market data through APIs. Specifically, it calls the API of a financial information service to obtain market data such as stock prices and trading volumes. It also uses APIs from social media to collect data such as tweets and comments. It also uses news APIs to obtain the latest news articles.

[0731] Step 2:

[0732] The server performs pre-processing on the collected market data, social media data, and news trend information to cleanse and standardize the format, converting data from each data source into a consistent format and compiling it into an integrated data set.

[0733] Step 3:

[0734] The server provides the integrated data set to the Generator AI, which analyzes each data set, analyzing market fluctuation patterns, social media sentiment analysis, and news content to extract useful insights.

[0735] Step 4:

[0736] The server uses an emotion engine to analyze the user's input data (e.g., text input or voice input) and evaluate the user's current emotional state. The results of this emotion analysis are used together with the integrated data.

[0737] Step 5:

[0738] The server identifies investment opportunities based on the insights obtained by the generative AI and the results of user sentiment analysis by the sentiment engine. It detects insights that meet certain thresholds and conditions (e.g., high probability and high impact) and identifies them as investment opportunities.

[0739] Step 6:

[0740] The server then sends information about identified investment opportunities and sentiment analysis results to the user's device via push notifications, in-app messages, emails, etc. The notification content includes detailed information about the investment opportunity and recommended actions.

[0741] Step 7:

[0742] Users receive notifications through their devices, check the content, and make investment decisions based on the information and their emotional state.

[0743] Step 8:

[0744] Users execute trades through the trading platform, specifically by issuing instructions to buy or sell stocks based on the provided insights and completing the trades.

[0745] Step 9:

[0746] Once the transaction is complete, the user can view the results on their device, and based on the results, the next step is to collect and analyze data again, or look for other investment opportunities.

[0747] This system allows users to comprehensively grasp minute market fluctuations, social trends, and their own emotional state, allowing them to make quick and appropriate investment decisions.

[0748] Example 2

[0749] 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."

[0750] Conventional investment support systems often collect and analyze market data, social media data, and news trend information separately, resulting in low-accuracy insights and making it difficult to properly identify investment opportunities. Furthermore, because they do not take user emotions into account, it is difficult to support optimal investment decisions that reflect the user's emotional state. Therefore, there is a demand for an integrated, highly accurate system that supports quick and accurate investment decisions.

[0751] 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.

[0752] In this invention, the server includes means for collecting market data in real time, means for collecting social media data, means for collecting trend information from news, artificial intelligence generation means, emotion analysis means for analyzing user emotions, emotion analysis results and means for identifying investment opportunities based on the analysis results, and means for notifying the user terminal of the identified investment opportunities. This enables support for quick and accurate investment decisions by integrating and analyzing multiple data sources with high accuracy and taking into account the user's emotional state.

[0753] "Market Data" refers to data relating to financial markets, such as price information, trading volumes, and indicators.

[0754] "Social media data" refers to data such as user posts, comments, and reactions on online social networking services and platforms.

[0755] "News trend information" refers to information such as news articles, reports, and analyses about current events and topics.

[0756] "Generative AI tools" refers to machine learning models and algorithms that integrate diverse data sources and perform advanced analysis.

[0757] "Emotion analysis means" refers to technologies and algorithms for determining a user's emotions from user input data (e.g., text, voice, etc.).

[0758] "Means for identifying investment opportunities" refers to technologies that analyze market data, social media data, news trend information, and user sentiment data to identify potential investment opportunities.

[0759] "User terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) that a user operates and receives information.

[0760] The present invention is a system that identifies investment opportunities and supports quick investment decisions by collecting, integrating, and analyzing market data, social media data, and news trend information in real time, and by combining this with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0761] First, the server collects data using a dedicated API. To collect market data, the server uses the API to obtain price information and trading volumes of financial markets. To collect social media data, the server uses the API of a social media platform to obtain posts and comments. To collect news trend information, the server obtains the latest news articles via the API of a news service.

[0762] The server then converts the collected data into a unified format and performs data preprocessing. For example, stock quotes are converted into CSV format, tweets and comments are formatted into JSON format, news articles are subjected to text analysis to generate summaries, and the data is then integrated using a dataframe manipulation library to fill in any inaccurate or missing data.

[0763] The combined data set is then analyzed by server-based generative AI models, which use machine learning frameworks to analyze market fluctuation patterns, natural language processing libraries for social media sentiment analysis, and natural language generation models to analyze the content of news articles and extract useful insights.

[0764] Furthermore, the server uses an emotion engine to analyze the user's emotions from the user's input data (e.g., text input or voice input). This analysis can use a natural language processing library as an emotion classification model to accurately determine the user's positive or negative emotional state.

[0765] Based on the analysis results from the AI ​​model and sentiment engine, the server identifies investment opportunities, which are then assigned trust and influence scores by the algorithm, and are confirmed as investment opportunities if they exceed a certain threshold.

[0766] Confirmed investment opportunities are notified to the user's device from the server using a cloud messaging service. Notification details are also sent via email and in-app message. Notification content includes the investment opportunity analysis results, recommended actions, and an assessed confidence score.

[0767] The user receives a notification on their device, checks the details, makes an investment decision based on the provided data and their own judgment, and executes the trade through the trading platform.

[0768] Specific examples

[0769] For example, suppose a company's stock price is rising sharply. The server obtains the company's stock price and trading volume data through a financial market API, collects a large number of related positive posts using a social media API, and collects positive news articles about the company using a news service API. After integrating and preprocessing this data, it analyzes it using a generative AI model. The resulting insight is that the company's stock price is likely to rise further.

[0770] Additionally, the emotion engine analyzes the user's input text to determine whether the user is in a positive emotional state, and the server uses this information to identify investment opportunities with high confidence scores.

[0771] The server then notifies the user of the investment opportunity and suggests specific investment actions. A push notification is sent stating, "The stock price of a specific company is rising. Check the details and consider purchasing."

[0772] The user then checks the notification, decides to invest based on the suggested information, and purchases shares through the trading platform. Finally, the user sees the results of the transaction displayed on the terminal in real time.

[0773] Prompt Sentence Examples

[0774] "Tell me which companies I should invest in next based on recent market data, social media comments, and trending news. Also, please suggest the best investment opportunities given my emotional state: positive and excited."

[0775] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0776] Step 1:

[0777] The server uses APIs to collect market data, social media data, and news trend information in real time. Access information to each API endpoint is used as input. For market data, a financial market API is used, for social media data, a social media API is used, and for news trend information, a news service API is used. The output is the raw data of the various types of data collected.

[0778] Step 2:

[0779] The server converts the collected market data, social media data, and news trend information into a unified format. It uses the raw data collected in step 1 as input. Specifically, it converts stock quotes into CSV format, formats social media posts and comments into JSON format, and performs text analysis on news articles to generate summaries. The output is the data converted into a unified format.

[0780] Step 3:

[0781] The server preprocesses the converted data. As input, it uses the data converted to a unified format in step 2. It uses the Pandas library to create a data frame and imputes inaccurate or missing data. It also removes outliers. The output is a clean dataset that has been preprocessed.

[0782] Step 4:

[0783] The server combines the preprocessed datasets and inputs them into the generative AI model. It uses the clean dataset obtained in step 3 as input. After combining the datasets, it uses a machine learning framework (TensorFlow or PyTorch) to analyze market fluctuation patterns. At the same time, it uses a natural language processing library (NLTK or Transformers) to perform social media sentiment analysis and content analysis of news articles. The output is insights as a result of the analysis.

[0784] Step 5:

[0785] The server uses an emotion engine to analyze the user's emotions. The input is the user's input data (text input or voice input). A natural language processing library is used as an emotion classification model to analyze the user's positive and negative emotional state. The output is the user's emotion analysis results.

[0786] Step 6:

[0787] The server identifies investment opportunities based on the analysis results and sentiment analysis results. It uses the insights from step 4 and the sentiment analysis results from step 5 as inputs. The algorithm sets trust and influence scores and identifies insights that exceed certain thresholds as investment opportunities. The output is the identified investment opportunities.

[0788] Step 7:

[0789] The server notifies the user device of the identified investment opportunities. As input, it uses the investment opportunity data identified in step 6. It uses a cloud messaging service (e.g., Firebase Cloud Messaging) to send a push notification. Details are also delivered via email and in-app message. The output is the notification sent to the user.

[0790] Step 8:

[0791] The user receives the notification on their device and checks its contents. As input, they use the notification sent from the server. The user makes an investment decision based on the provided data and their own judgment. The output is an investment decision.

[0792] Step 9:

[0793] The user executes a trade using the trading platform. As input, they use the investment decision made in step 8. They log in to the trading platform, select the financial instrument, and perform a buy / sell operation. The output is the executed trade.

[0794] (Application example 2)

[0795] 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."

[0796] While conventional investment support systems excel at collecting and analyzing real-time data, they do not take into account the user's emotional state and therefore are unable to provide optimal investment timing or decisions. This makes it difficult for users to grasp minute market fluctuations and social trends, making it difficult to make appropriate investment decisions.

[0797] The identification process by the identification 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 means for collecting market data in real time, means for collecting social media data, means for collecting trend information from news, generative artificial intelligence means for integrating and analyzing the market data, social media data, and news trends, emotion engine means for analyzing user emotions, means for identifying investment opportunities, and means for notifying the user terminal of the identified investment opportunities. This enables fast and accurate investment support that takes into account the user's emotional state.

[0798] "Market data" refers to data such as price information and trading volume related to financial markets.

[0799] "Social Media Data" refers to data posted by users on social media platforms, such as comments, tweets, and reviews.

[0800] "News trend information" refers to data about the latest events and topics obtained from news articles and information distribution services.

[0801] "Generative AI" refers to artificial intelligence techniques for data integration and analysis.

[0802] An "emotion engine" is a mechanism that analyzes the user's emotional state from input data.

[0803] An "investment opportunity" is a time or condition in the financial markets that offers high potential for making a profit.

[0804] A "user terminal" is a computing device used by a user, such as a smartphone or PC.

[0805] This invention is a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time while taking into account the user's emotional state, and notifies the user of optimal investment opportunities. The system that realizes this application example is described in detail below.

[0806] Data collection

[0807] The server uses APIs to collect real-time market data, social media data, and news trend information. A specific software example is the requests library. Market data includes price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0808] Data integration and analysis

[0809] The server converts the collected market data, social media data, and news trend information into a unified format and performs data preprocessing. The preprocessed data is compiled into an integrated dataset and analyzed using generative artificial intelligence (AI) such as TensorFlow or PyTorch. The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes the content of news articles, thereby extracting useful insights from the data.

[0810] Utilizing the Emotion Engine

[0811] The server is equipped with an emotion engine that analyzes user emotions from user input data (e.g., text input or voice input). This emotion analysis is performed to recognize the user's emotional state, and the results are utilized together with the integrated data. Natural language processing (NLP) models are used for emotion analysis.

[0812] Identifying investment opportunities

[0813] Based on the AI-generated insights and user sentiment data analyzed by the sentiment engine, the server identifies investment opportunities. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is identified as an investment opportunity.

[0814] User Notification

[0815] The server then notifies the user of the best investment opportunities based on the identified investment opportunities and the results of sentiment analysis via push notifications, in-app messages, emails, etc. The notification content includes detailed information about the investment opportunity and recommended actions.

[0816] User investment support

[0817] The user receives a notification from the terminal and checks its contents. Taking into account the information and the user's own emotional state, the user makes an investment decision. The user then executes a trade through the trading platform and checks the results on the terminal.

[0818] Specific examples

[0819] For example, consider a situation where a company's stock price is rising sharply. Positive social media posts about the company increase, and major news media publish positive articles about the company. Furthermore, the emotion engine analyzes that users themselves are excited (positive emotions). The server collects and integrates this data in real time, and analyzes it using AI and the emotion engine. The analysis results identify that the company's stock price is likely to rise sharply in the short term.

[0820] The server notifies the user of this investment opportunity, and the user confirms it and immediately decides to purchase the company's stock and executes the trade on the trading platform. This allows the user to make appropriate investment decisions that comprehensively take into account minute market fluctuations, social trends, and their own emotional state.

[0821] An example of a prompt to be input to a generative AI model might be, "Integrate and analyze market data, social media data, news trends, and user sentiment data to generate optimal purchasing suggestions."

[0822] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0823] Step 1:

[0824] The server uses APIs to collect market data, social media data, and news trend information in real time. It uses the requests library to send data retrieval requests to specific API endpoints and receives responses in JSON format. The input here is the API endpoint URL and required parameters, and the output is a JSON object of the various retrieved data.

[0825] Step 2:

[0826] The server converts the collected market data, social media data, and news trend information into a unified format and performs preprocessing. Specifically, it performs missing value imputation, data normalization, and format conversion. The input is the raw data obtained in the previous step, and the output is a dataset in a unified format.

[0827] Step 3:

[0828] The server aggregates the preprocessed data and performs analysis using generative artificial intelligence (AI) such as TensorFlow or PyTorch. This includes analyzing market fluctuation patterns, social media sentiment analysis, and semantic analysis of news articles. The input is a unified dataset, and the output is analyzed, useful insights.

[0829] Step 4:

[0830] The server uses an emotion engine to analyze emotions from user input data (e.g., text input or voice input). It uses an NLP model (e.g., BERT or GPT) to identify the user's emotional state. The input is the user's raw text or voice data, and the output is the analyzed emotion data.

[0831] Step 5:

[0832] The server identifies investment opportunities based on AI-generated insights and user sentiment data analyzed by the sentiment engine. It evaluates the integrated data to identify suitable investment opportunities based on certain thresholds and conditions (e.g., high probability and high impact). The inputs are insights and sentiment data, and the output is data on identified investment opportunities.

[0833] Step 6:

[0834] The server notifies the user device of identified investment opportunities. Information is sent to the user in the form of push notifications, in-app messages, emails, etc. The notification includes detailed information about the investment opportunity and recommended actions. The input is the investment opportunity data, and the output is the notification sent to the user device.

[0835] Step 7:

[0836] The user receives notifications from the terminal and checks their contents. They take the information and their emotional state into consideration to make appropriate investment decisions. The user executes trades through the trading platform and checks the results on the terminal. The input is notification information from the server, and the output is the user's investment actions and their results.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] [Fourth embodiment]

[0841] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0842] 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.

[0843] 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).

[0844] 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.

[0845] 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.

[0846] 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).

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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."

[0854] The present invention is a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time, and identifies investment opportunities to help users make quick investment decisions. Specific embodiments of the system are described below.

[0855] Data collection

[0856] The server uses APIs to collect real-time market data, social media data, and news trend information. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0857] Data integration and analysis

[0858] The server compiles the collected data into a single integrated dataset. During this process, data preprocessing is performed, including cleansing and formatting. The integrated data is then analyzed by generative artificial intelligence (AI). The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes news content to generate comprehensive insights.

[0859] Identifying investment opportunities

[0860] Based on the insights analyzed by AI, the server identifies investment opportunities. If an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is deemed an investment opportunity.

[0861] User Notification

[0862] The server notifies the user of identified investment opportunities via push notifications, in-app messages, emails, etc. The notification includes detailed investment information and recommended actions.

[0863] User investment support

[0864] Users receive investment opportunities notified through their terminals and make quick investment decisions based on that information. Users review the notified insights and execute trades on the trading platform as needed.

[0865] Specific examples

[0866] Suppose a company's stock price is rising sharply. Positive social media posts about the company increase, and major news outlets publish positive articles about the company. The server collects and integrates this data in real time and analyzes it using AI. The analysis results indicate that the company's stock price is likely to surge in the short term.

[0867] The server notifies the user of this investment opportunity. The user receives the notification and immediately decides to purchase the company's stock, executing the trade on the trading platform. This allows the user to instantly grasp minute market fluctuations and social trends and make appropriate investment decisions.

[0868] The present invention provides a new type of investment support system that supports quick and accurate investment decisions by comprehensively analyzing complex market information and diverse social trends.

[0869] The processing flow will be explained below.

[0870] Step 1:

[0871] The server collects real-time market data through APIs. Specifically, it calls the APIs of financial information providers to obtain market data such as stock price data and trading volume. It also uses APIs from social media to obtain related data such as tweets. For news trends, it calls news APIs to collect the latest news articles.

[0872] Step 2:

[0873] The server consolidates the collected data. It cleanses and pre-processes the data, converting it all into a consistent format. This process combines data from different sources and makes it easier to analyze.

[0874] Step 3:

[0875] The server then analyzes the integrated data using Generative Artificial Intelligence (AI), which analyzes market fluctuation patterns, performs social media sentiment analysis, and evaluates the content of news articles to extract useful insights from the data.

[0876] Step 4:

[0877] The server identifies investment opportunities based on AI-generated insights by detecting insights that meet certain thresholds or conditions (e.g., high probability and high impact information) and identifying them as investment opportunities.

[0878] Step 5:

[0879] The server notifies the user device of identified investment opportunities via push notifications, in-app messages, emails, etc. The notification includes details about the investment opportunity and recommended actions.

[0880] Step 6:

[0881] After receiving the notification, the user confirms its contents and uses the device to review the provided insights and understand the information about the investment opportunity.

[0882] Step 7:

[0883] The user makes an investment decision based on the notified investment opportunity, and once the decision is complete, executes the trade through the trading platform, specifically by issuing a purchase or sale instruction and completing the transaction.

[0884] Step 8:

[0885] Once the trade is complete, the user can view the results on their device, and based on the results, the next step is to collect and analyze data again, or to look for other investment opportunities.

[0886] This system allows users to grasp minute market fluctuations and social trends in real time, enabling them to make quick and appropriate investment decisions.

[0887] Example 1

[0888] 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."

[0889] Conventional investment support systems typically collect and analyze market data, social media data, and news trend information separately, making it difficult to integrate them and quickly identify investment opportunities.Furthermore, few systems apply advanced analytical techniques such as data preprocessing and sentiment analysis, making it difficult to provide accurate insights that allow users to make immediate investment decisions.

[0890] 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.

[0891] In this invention, the server includes a means for collecting market data in real time, a means for collecting social media data, and a means for collecting trend information from news. This allows for efficient data collection, integration, and preprocessing of the data. Furthermore, the preprocessed data is analyzed using a generative AI model to identify investment opportunities, and detailed information about the identified investment opportunities and recommended actions are notified to the user's terminal, allowing the user to make prompt and appropriate investment decisions.

[0892] "Market data" refers to numerical information related to financial markets, such as stock price information and trading volume.

[0893] "Social Media Data" refers to text and metadata generated on social media platforms, such as user posts, comments, and retweets.

[0894] "News trend information" refers to the latest information and topics obtained from news articles and reports.

[0895] "Data preprocessing" refers to the process of cleansing collected data and processing it into a state suitable for analysis, such as by deleting duplicate data and standardizing formats.

[0896] "Generative AI means" refers to AI that uses collected and integrated data to analyze market fluctuation patterns, sentiment analysis, and news text analysis to generate comprehensive insights.

[0897] "Means for identifying investment opportunities" refers to the process of extracting investment options that meet certain thresholds and conditions based on the generated insights, and evaluating and determining them as investment opportunities.

[0898] "User terminal" refers to a device (smartphone, tablet, PC, etc.) on which a user receives notifications from the system, views insights, and makes investment decisions.

[0899] The present invention is a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time, and identifies investment opportunities to help users make quick investment decisions. Specific embodiments of the system are described below.

[0900] Data collection

[0901] The server uses APIs to collect market data, social media data, and news trend information in real time. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles. Specifically, the server uses Yahoo Finance API and Alpha Vantage API for market data, Twitter API and Facebook Graph API for social media data, and Google News API and News API for trend information.

[0902] Data integration and analysis

[0903] The server compiles the various collected data into a single integrated dataset. During this process, data preprocessing is performed, including cleansing and formatting. For example, this includes removing duplicate data and filling in missing values. The integrated data is then analyzed using generative artificial intelligence (AI). Specifically, generative AI models are used to analyze market fluctuation patterns, perform social media sentiment analysis, and perform text analysis of news content to generate comprehensive insights. Machine learning frameworks such as TensorFlow and PyTorch are used for the analysis.

[0904] Identifying investment opportunities

[0905] Based on the AI-generated insights, the server identifies investment opportunities. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is deemed an investment opportunity, specifically based on predicted stock price growth or positive social media sentiment score.

[0906] User Notification

[0907] The server notifies the user device of the identified investment opportunity. This notification is sent in the form of a push notification, in-app message, email, or other format. The notification includes detailed information about the investment and recommended actions. For example, a message such as "The stock price of Company X is expected to rise sharply. The current stock price is X yen. Please consider purchasing now" is sent.

[0908] User investment support

[0909] Users receive notifications of investment opportunities through their devices and make quick investment decisions based on the information. They review the notified insights and execute trades on the trading platform as needed. For example, after receiving a notification on their device, the user opens a trading app and purchases the indicated stocks.

[0910] Specific examples

[0911] For example, suppose a company's stock price is rising sharply. Positive social media posts about the company increase, and major news outlets publish positive articles about the company. The server collects and integrates this data in real time and analyzes it using AI. The analysis results indicate that the company's stock price is likely to rise sharply in the short term.

[0912] The server notifies the user of this investment opportunity. The user receives the notification and immediately decides to purchase the company's stock, executing the trade on the trading platform. This allows the user to instantly grasp minute market fluctuations and social trends and make appropriate investment decisions.

[0913] Example prompts to be input to the generative AI model

[0914] "How can I integrate market data, social media data, and news trend information to identify investment opportunities?"

[0915] Based on this prompt, the AI ​​will walk you through each step of collection, synthesis, and analysis to provide a method for identifying investment opportunities.

[0916] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0917] Step 1: Gather market data

[0918] The server uses APIs to collect market data in real time. Specifically, it uses the Yahoo Finance API and Alpha Vantage API to obtain stock price information and trading volume. It uses a list of stocks to be collected as input and obtains the current stock price and trading volume data for each stock as output. This operation obtains the latest market data.

[0919] Step 2: Collect social media data

[0920] The server uses the Twitter API and Facebook Graph API to collect user posts and comments on social media. It uses search queries related to specific companies or keywords as input and obtains text data of the relevant posts and comments as output. This operation obtains social media reactions in real time.

[0921] Step 3: Gathering news trends

[0922] The server uses the Google News API or News API to collect the latest news articles. It uses keywords related to a specific company name or topic as input, and obtains the URL, title, summary, and publication date of the relevant news article as output. This operation allows you to understand the latest news trends.

[0923] Step 4: Data integration and preprocessing

[0924] The server aggregates the collected market data, social media data, and news trend information into a single integrated data set. It uses each of the previously collected data sources (market data, social media data, and news trend information) as input and generates an integrated data set as output. This process includes deduplication, outlier correction, and standardization of data formats.

[0925] Step 5: Data analysis using AI

[0926] The server runs the generative AI model with the integrated dataset. It uses the integrated dataset as input and outputs market movement patterns, social media sentiment scores, and news content analysis. In this operation, the AI ​​analyzes the collected data and generates comprehensive insights on investment opportunities.

[0927] Step 6: Identifying investment opportunities

[0928] The server evaluates the AI-generated insights and identifies investment opportunities. It uses the analysis results of the generative AI model as input and obtains identified investment opportunities (e.g., stocks predicted to surge) as output. This operation extracts insights with high probability and high impact and determines them as investment opportunities.

[0929] Step 7: Notify users

[0930] The server notifies the user device of the identified investment opportunity. Using the details of the identified investment opportunity as input, a push notification, an in-app message, or an email is generated as output to the user device. This operation allows the user to quickly learn about the investment opportunity.

[0931] Step 8: User investment decision and execution

[0932] Users receive notifications and make quick investment decisions based on the information, using notifications from the server as input and trade execution on the trading platform as output, where users review insights and buy or sell stocks as needed.

[0933] Step 9: Feedback Loop

[0934] The server collects the user's investment behavior and results as feedback and uses it to improve the system's analytical model. The user's investment result data is used as input, and the analytical model's parameter adjustment and algorithm improvement are obtained as output. This operation improves the accuracy and effectiveness of the system.

[0935] (Application example 1)

[0936] 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."

[0937] While conventional investment support systems can identify investment opportunities through integrated analysis of real-time market data, social media data, and news trend information, they lack the functionality to suggest the next optimal purchase based on the user's purchasing patterns in electronic payment services. As a result, users may miss the right timing or opportunity to make a purchase. To solve this issue, a system is needed that not only identifies investment opportunities but also analyzes the user's purchasing patterns and makes personalized purchasing recommendations.

[0938] 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.

[0939] In this invention, the server includes a means for collecting market data in real time, a means for collecting social media data, and a means for collecting trend information from news. This enables a generating artificial intelligence means for integrating and analyzing market data, social media data, and news trend information, a means for identifying investment opportunities, a means for notifying a user terminal of the identified investment opportunities, and a means for analyzing a user's purchasing patterns in electronic payment services and providing purchasing recommendations. This allows users to grasp market fluctuations and social trends in real time and receive personalized recommendations for their next product or service purchase.

[0940] "Market data" refers to information such as stock prices, trading volumes, and exchange rates in financial markets.

[0941] "Social media data" refers to information such as posts and comments posted by users on social networking services.

[0942] "News trend information" refers to information on the latest trends and events analyzed based on news articles and reports.

[0943] "Generative AI" refers to artificial intelligence technology that has algorithms that comprehensively analyze collected data and generate predictions and insights.

[0944] "Investment Opportunities" refers to the timing and targets of investments that are likely to be advantageous to the user based on collected and analyzed data.

[0945] "User terminal" refers to an electronic device, such as a smartphone or tablet, that allows a user to receive and operate information.

[0946] "Electronic payment service" refers to a platform or system for making monetary payments using electronic means.

[0947] "Purchasing patterns" refer to the tendencies and habits based on a user's past purchasing history and behavior.

[0948] "Purchase recommendation" refers to analyzing a user's purchasing patterns and suggesting the next product or service they should purchase.

[0949] The present invention provides a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time, identifies investment opportunities based on the collected data, and notifies users of these opportunities. It also has the function of analyzing purchasing patterns of electronic payment services and making purchasing recommendations. Specific embodiments of the present invention are described below.

[0950] Data collection

[0951] The server uses APIs to collect real-time market data, social media data, and news trend information. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0952] Data integration and analysis

[0953] The server compiles the various collected data into a single integrated dataset. During this process, data preprocessing includes cleansing and formatting standardization. The integrated data is then analyzed by generative artificial intelligence (AI). The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes news content to generate comprehensive insights. It also has the ability to analyze user purchasing patterns for electronic payment services.

[0954] Identifying investment opportunities and purchase recommendations

[0955] Based on the insights analyzed by AI, the server identifies investment opportunities. It also analyzes purchasing patterns based on the user's past purchase history and recommends the next optimal purchase. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is determined to be an investment opportunity or purchase recommendation.

[0956] User Notification

[0957] The server notifies the user of identified investment opportunities and purchase recommendations via push notifications, in-app messages, emails, etc. The notification content includes detailed investment information, recommended actions, and purchase recommendations.

[0958] User Support

[0959] Users receive the information via their devices and make quick investment or purchasing decisions based on that information. Users review the insights and execute operations on trading or purchasing platforms as needed.

[0960] Hardware or software used

[0961] This system uses user devices such as smartphones and tablets, and uses the Python programming language, the Requests library, and the Scikit-learn library to collect, integrate, and analyze data.

[0962] Examples of concrete examples and prompts

[0963] For example, if market data, social media data, and news trend information is obtained as follows:

[0964] Market Data: "ABC Product" is on the rise

[0965] Social media data: Increased mentions of "buy ABC product"

[0966] News Trend Information: Reports that "ABC product is very popular"

[0967] An example prompt generated using this information is:

[0968] "We've discovered a new buying opportunity! 'Product ABC' is extremely popular right now. It's getting widespread mentions on social media and high ratings in the news. Check it out now!"

[0969] By sending these notifications to users and providing investment opportunities and purchase recommendations, users can understand market fluctuations and social trends in real time and make appropriate investment and purchasing decisions.

[0970] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0971] Step 1:

[0972] The server uses APIs to collect market data, social media data, and news trend information in real time. This collected data is obtained from each data source in JSON format. The input is raw data obtained from the APIs, and the server stores this data. The output is a collection of raw data.

[0973] Step 2:

[0974] The server integrates the collected market data, social media data, and news trend information into a single dataset. As part of data preprocessing, it fills in missing data, removes inappropriate data, and standardizes formats. The input is the collected raw data, which the server cleanses and standardizes. The output is a cleansed, integrated dataset.

[0975] Step 3:

[0976] The server uses generative artificial intelligence to analyze the cleansed integrated dataset. Here, it performs scaling, PCA (principal component analysis), and KMeans clustering to extract features from each data point. The input is the integrated dataset, and the server reduces the dimensions using scaling and PCA and performs clustering. The output is the analysis results and the centers of each cluster.

[0977] Step 4:

[0978] The server identifies investment opportunities and purchase recommendations based on the generated analysis results. In particular, if the cluster center value exceeds a certain threshold, the server determines that the data points in that cluster are investment opportunities or purchase recommendations. The inputs are the analysis results and the cluster center values, and the server performs threshold judgment. The output is the identified investment opportunities and purchase recommendations.

[0979] Step 5:

[0980] The server generates prompt messages for the identified investment opportunities and purchase recommendations and notifies the user device. Here, prompt messages are generated based on templates and sent to the user via push notifications, in-app messages, emails, etc. The input is the information on the identified investment opportunities and purchase recommendations, and the server creates the prompt messages using a generative AI model. The output is a notification message to the user.

[0981] Step 6:

[0982] Users receive the information notified through their terminals and make quick investment or purchasing decisions based on that information. Here, users check the notified insights and access the trading or purchasing platform to execute operations. The input is the notification message, and the user decides on the next action based on this. The output is the executed purchase or investment action.

[0983] 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.

[0984] The present invention is a system that identifies investment opportunities and supports quick investment decisions by collecting, integrating, and analyzing market data, social media data, and news trend information in real time, and by combining this with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0985] Data collection

[0986] The server uses APIs to collect real-time market data, social media data, and news trend information. Market data includes stock price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[0987] Data integration and analysis

[0988] The server converts the collected market data, social media data, and news trend information into a unified format and performs data preprocessing. The preprocessed data is compiled into an integrated dataset and analyzed using generative artificial intelligence (AI). The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes the content of news articles, thereby extracting useful insights from the data.

[0989] Utilizing the Emotion Engine

[0990] Furthermore, the emotion engine analyzes user emotions from user input data (e.g., text input or voice input) and utilizes the results together with the integrated data. The emotion analysis results from the emotion engine are used to identify investment opportunities and optimize the content of notifications to users.

[0991] Identifying investment opportunities

[0992] Based on the AI-generated insights and user sentiment data analyzed by the sentiment engine, the server identifies investment opportunities. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is identified as an investment opportunity.

[0993] User Notification

[0994] The server then notifies the user of the best investment opportunities based on the identified investment opportunities and the results of sentiment analysis via push notifications, in-app messages, emails, etc. The notification content includes detailed information about the investment opportunity and recommended actions.

[0995] User investment support

[0996] The user receives a notification from the terminal and checks its contents. Taking into account the information and the user's own emotional state, the user makes an investment decision. The user then executes a trade through the trading platform and checks the results on the terminal.

[0997] Specific examples

[0998] For example, suppose a company's stock price is rising sharply. Positive social media posts about the company are increasing, and positive articles about the company are published in major news media. Furthermore, the emotion engine analyzes that users themselves are excited (positive emotions). The server collects and integrates this data in real time, and analyzes it using AI and the emotion engine. The analysis results indicate that the company's stock price is likely to rise sharply in the short term.

[0999] The server notifies the user of this investment opportunity, and the user confirms it and immediately decides to purchase the company's stock and executes the trade on the trading platform. This allows the user to make appropriate investment decisions that comprehensively take into account minute market fluctuations, social trends, and their own emotional state.

[1000] The present invention provides a new type of investment support system that supports quick and accurate investment decisions by comprehensively analyzing complex market information, diverse social trends, and the user's emotional state.

[1001] The processing flow will be explained below.

[1002] Step 1:

[1003] The server collects real-time market data through APIs. Specifically, it calls the API of a financial information service to obtain market data such as stock prices and trading volumes. It also uses APIs from social media to collect data such as tweets and comments. It also uses news APIs to obtain the latest news articles.

[1004] Step 2:

[1005] The server performs pre-processing on the collected market data, social media data, and news trend information to cleanse and standardize the format, converting data from each data source into a consistent format and compiling it into an integrated data set.

[1006] Step 3:

[1007] The server provides the integrated data set to the Generator AI, which analyzes each data set, analyzing market fluctuation patterns, social media sentiment analysis, and news content to extract useful insights.

[1008] Step 4:

[1009] The server uses an emotion engine to analyze the user's input data (e.g., text input or voice input) and evaluate the user's current emotional state. The results of this emotion analysis are used together with the integrated data.

[1010] Step 5:

[1011] The server identifies investment opportunities based on the insights obtained by the generative AI and the results of user sentiment analysis by the sentiment engine. It detects insights that meet certain thresholds and conditions (e.g., high probability and high impact) and identifies them as investment opportunities.

[1012] Step 6:

[1013] The server then sends information about identified investment opportunities and sentiment analysis results to the user's device via push notifications, in-app messages, emails, etc. The notification content includes detailed information about the investment opportunity and recommended actions.

[1014] Step 7:

[1015] Users receive notifications through their devices, check the content, and make investment decisions based on the information and their emotional state.

[1016] Step 8:

[1017] Users execute trades through the trading platform, specifically by issuing instructions to buy or sell stocks based on the provided insights and completing the trades.

[1018] Step 9:

[1019] Once the transaction is complete, the user can view the results on their device, and based on the results, the next step is to collect and analyze data again, or look for other investment opportunities.

[1020] This system allows users to comprehensively grasp minute market fluctuations, social trends, and their own emotional state, allowing them to make quick and appropriate investment decisions.

[1021] Example 2

[1022] 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."

[1023] Conventional investment support systems often collect and analyze market data, social media data, and news trend information separately, resulting in low-accuracy insights and making it difficult to properly identify investment opportunities. Furthermore, because they do not take user emotions into account, it is difficult to support optimal investment decisions that reflect the user's emotional state. Therefore, there is a demand for an integrated, highly accurate system that supports quick and accurate investment decisions.

[1024] 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.

[1025] In this invention, the server includes means for collecting market data in real time, means for collecting social media data, means for collecting trend information from news, artificial intelligence generation means, emotion analysis means for analyzing user emotions, emotion analysis results and means for identifying investment opportunities based on the analysis results, and means for notifying the user terminal of the identified investment opportunities. This enables support for quick and accurate investment decisions by integrating and analyzing multiple data sources with high accuracy and taking into account the user's emotional state.

[1026] "Market Data" refers to data relating to financial markets, such as price information, trading volumes, and indicators.

[1027] "Social media data" refers to data such as user posts, comments, and reactions on online social networking services and platforms.

[1028] "News trend information" refers to information such as news articles, reports, and analyses about current events and topics.

[1029] "Generative AI tools" refers to machine learning models and algorithms that integrate diverse data sources and perform advanced analysis.

[1030] "Emotion analysis means" refers to technologies and algorithms for determining a user's emotions from user input data (e.g., text, voice, etc.).

[1031] "Means for identifying investment opportunities" refers to technologies that analyze market data, social media data, news trend information, and user sentiment data to identify potential investment opportunities.

[1032] "User terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) that a user operates and receives information.

[1033] The present invention is a system that identifies investment opportunities and supports quick investment decisions by collecting, integrating, and analyzing market data, social media data, and news trend information in real time, and by combining this with an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[1034] First, the server collects data using a dedicated API. To collect market data, the server uses the API to obtain price information and trading volumes of financial markets. To collect social media data, the server uses the API of a social media platform to obtain posts and comments. To collect news trend information, the server obtains the latest news articles via the API of a news service.

[1035] The server then converts the collected data into a unified format and performs data preprocessing. For example, stock quotes are converted into CSV format, tweets and comments are formatted into JSON format, news articles are subjected to text analysis to generate summaries, and the data is then integrated using a dataframe manipulation library to fill in any inaccurate or missing data.

[1036] The combined data set is then analyzed by server-based generative AI models, which use machine learning frameworks to analyze market fluctuation patterns, natural language processing libraries for social media sentiment analysis, and natural language generation models to analyze the content of news articles and extract useful insights.

[1037] Furthermore, the server uses an emotion engine to analyze the user's emotions from the user's input data (e.g., text input or voice input). This analysis can use a natural language processing library as an emotion classification model to accurately determine the user's positive or negative emotional state.

[1038] Based on the analysis results from the AI ​​model and sentiment engine, the server identifies investment opportunities, which are then assigned trust and influence scores by the algorithm, and are confirmed as investment opportunities if they exceed a certain threshold.

[1039] Confirmed investment opportunities are notified to the user's device from the server using a cloud messaging service. Notification details are also sent via email and in-app message. Notification content includes the investment opportunity analysis results, recommended actions, and an assessed confidence score.

[1040] The user receives a notification on their device, checks the details, makes an investment decision based on the provided data and their own judgment, and executes the trade through the trading platform.

[1041] Specific examples

[1042] For example, suppose a company's stock price is rising sharply. The server obtains the company's stock price and trading volume data through a financial market API, collects a large number of related positive posts using a social media API, and collects positive news articles about the company using a news service API. After integrating and preprocessing this data, it analyzes it using a generative AI model. The resulting insight is that the company's stock price is likely to rise further.

[1043] Additionally, the emotion engine analyzes the user's input text to determine whether the user is in a positive emotional state, and the server uses this information to identify investment opportunities with high confidence scores.

[1044] The server then notifies the user of the investment opportunity and suggests specific investment actions. A push notification is sent stating, "The stock price of a specific company is rising. Check the details and consider purchasing."

[1045] The user then checks the notification, decides to invest based on the suggested information, and purchases shares through the trading platform. Finally, the user sees the results of the transaction displayed on the terminal in real time.

[1046] Prompt Sentence Examples

[1047] "Tell me which companies I should invest in next based on recent market data, social media comments, and trending news. Also, please suggest the best investment opportunities given my emotional state: positive and excited."

[1048] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1049] Step 1:

[1050] The server uses APIs to collect market data, social media data, and news trend information in real time. Access information to each API endpoint is used as input. For market data, a financial market API is used, for social media data, a social media API is used, and for news trend information, a news service API is used. The output is the raw data of the various types of data collected.

[1051] Step 2:

[1052] The server converts the collected market data, social media data, and news trend information into a unified format. It uses the raw data collected in step 1 as input. Specifically, it converts stock quotes into CSV format, formats social media posts and comments into JSON format, and performs text analysis on news articles to generate summaries. The output is the data converted into a unified format.

[1053] Step 3:

[1054] The server preprocesses the converted data. As input, it uses the data converted to a unified format in step 2. It uses the Pandas library to create a data frame and imputes inaccurate or missing data. It also removes outliers. The output is a clean dataset that has been preprocessed.

[1055] Step 4:

[1056] The server combines the preprocessed datasets and inputs them into the generative AI model. It uses the clean dataset obtained in step 3 as input. After combining the datasets, it uses a machine learning framework (TensorFlow or PyTorch) to analyze market fluctuation patterns. At the same time, it uses a natural language processing library (NLTK or Transformers) to perform social media sentiment analysis and content analysis of news articles. The output is insights as a result of the analysis.

[1057] Step 5:

[1058] The server uses an emotion engine to analyze the user's emotions. The input is the user's input data (text input or voice input). A natural language processing library is used as an emotion classification model to analyze the user's positive and negative emotional state. The output is the user's emotion analysis results.

[1059] Step 6:

[1060] The server identifies investment opportunities based on the analysis results and sentiment analysis results. It uses the insights from step 4 and the sentiment analysis results from step 5 as inputs. The algorithm sets trust and influence scores and identifies insights that exceed certain thresholds as investment opportunities. The output is the identified investment opportunities.

[1061] Step 7:

[1062] The server notifies the user device of the identified investment opportunities. As input, it uses the investment opportunity data identified in step 6. It uses a cloud messaging service (e.g., Firebase Cloud Messaging) to send a push notification. Details are also delivered via email and in-app message. The output is the notification sent to the user.

[1063] Step 8:

[1064] The user receives the notification on their device and checks its contents. As input, they use the notification sent from the server. The user makes an investment decision based on the provided data and their own judgment. The output is an investment decision.

[1065] Step 9:

[1066] The user executes a trade using the trading platform. As input, they use the investment decision made in step 8. They log in to the trading platform, select the financial instrument, and perform a buy / sell operation. The output is the executed trade.

[1067] (Application example 2)

[1068] 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."

[1069] While conventional investment support systems excel at collecting and analyzing real-time data, they do not take into account the user's emotional state and therefore are unable to provide optimal investment timing or decisions. This makes it difficult for users to grasp minute market fluctuations and social trends, making it difficult to make appropriate investment decisions.

[1070] The identification process by the identification 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 means for collecting market data in real time, means for collecting social media data, means for collecting trend information from news, generative artificial intelligence means for integrating and analyzing the market data, social media data, and news trends, emotion engine means for analyzing user emotions, means for identifying investment opportunities, and means for notifying the user terminal of the identified investment opportunities. This enables fast and accurate investment support that takes into account the user's emotional state.

[1071] "Market data" refers to data such as price information and trading volume related to financial markets.

[1072] "Social Media Data" refers to data posted by users on social media platforms, such as comments, tweets, and reviews.

[1073] "News trend information" refers to data about the latest events and topics obtained from news articles and information distribution services.

[1074] "Generative AI" refers to artificial intelligence techniques for data integration and analysis.

[1075] An "emotion engine" is a mechanism that analyzes the user's emotional state from input data.

[1076] An "investment opportunity" is a time or condition in the financial markets that offers high potential for making a profit.

[1077] A "user terminal" is a computing device used by a user, such as a smartphone or PC.

[1078] This invention is a system that collects, integrates, and analyzes market data, social media data, and news trend information in real time while taking into account the user's emotional state, and notifies the user of optimal investment opportunities. The system that realizes this application example is described in detail below.

[1079] Data collection

[1080] The server uses APIs to collect real-time market data, social media data, and news trend information. A specific software example is the requests library. Market data includes price information and trading volume, social media data includes user posts and comments, and news trend information includes the latest news articles.

[1081] Data integration and analysis

[1082] The server converts the collected market data, social media data, and news trend information into a unified format and performs data preprocessing. The preprocessed data is compiled into an integrated dataset and analyzed using generative artificial intelligence (AI) such as TensorFlow or PyTorch. The AI ​​analyzes market fluctuation patterns, performs social media sentiment analysis, and analyzes the content of news articles, thereby extracting useful insights from the data.

[1083] Utilizing the Emotion Engine

[1084] The server is equipped with an emotion engine that analyzes user emotions from user input data (e.g., text input or voice input). This emotion analysis is performed to recognize the user's emotional state, and the results are utilized together with the integrated data. Natural language processing (NLP) models are used for emotion analysis.

[1085] Identifying investment opportunities

[1086] Based on the AI-generated insights and user sentiment data analyzed by the sentiment engine, the server identifies investment opportunities. When an insight is detected that meets certain thresholds or conditions (e.g., high probability and high impact), it is identified as an investment opportunity.

[1087] User Notification

[1088] The server then notifies the user of the best investment opportunities based on the identified investment opportunities and the results of sentiment analysis via push notifications, in-app messages, emails, etc. The notification content includes detailed information about the investment opportunity and recommended actions.

[1089] User investment support

[1090] The user receives a notification from the terminal and checks its contents. Taking into account the information and the user's own emotional state, the user makes an investment decision. The user then executes a trade through the trading platform and checks the results on the terminal.

[1091] Specific examples

[1092] For example, consider a situation where a company's stock price is rising sharply. Positive social media posts about the company increase, and major news media publish positive articles about the company. Furthermore, the emotion engine analyzes that users themselves are excited (positive emotions). The server collects and integrates this data in real time, and analyzes it using AI and the emotion engine. The analysis results identify that the company's stock price is likely to rise sharply in the short term.

[1093] The server notifies the user of this investment opportunity, and the user confirms it and immediately decides to purchase the company's stock and executes the trade on the trading platform. This allows the user to make appropriate investment decisions that comprehensively take into account minute market fluctuations, social trends, and their own emotional state.

[1094] An example of a prompt to be input to a generative AI model might be, "Integrate and analyze market data, social media data, news trends, and user sentiment data to generate optimal purchasing suggestions."

[1095] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1096] Step 1:

[1097] The server uses APIs to collect market data, social media data, and news trend information in real time. It uses the requests library to send data retrieval requests to specific API endpoints and receives responses in JSON format. The input here is the API endpoint URL and required parameters, and the output is a JSON object of the various retrieved data.

[1098] Step 2:

[1099] The server converts the collected market data, social media data, and news trend information into a unified format and performs preprocessing. Specifically, it performs missing value imputation, data normalization, and format conversion. The input is the raw data obtained in the previous step, and the output is a dataset in a unified format.

[1100] Step 3:

[1101] The server aggregates the preprocessed data and performs analysis using generative artificial intelligence (AI) such as TensorFlow or PyTorch. This includes analyzing market fluctuation patterns, social media sentiment analysis, and semantic analysis of news articles. The input is a unified dataset, and the output is analyzed, useful insights.

[1102] Step 4:

[1103] The server uses an emotion engine to analyze emotions from user input data (e.g., text input or voice input). It uses an NLP model (e.g., BERT or GPT) to identify the user's emotional state. The input is the user's raw text or voice data, and the output is the analyzed emotion data.

[1104] Step 5:

[1105] The server identifies investment opportunities based on AI-generated insights and user sentiment data analyzed by the sentiment engine. It evaluates the integrated data to identify suitable investment opportunities based on certain thresholds and conditions (e.g., high probability and high impact). The inputs are insights and sentiment data, and the output is data on identified investment opportunities.

[1106] Step 6:

[1107] The server notifies the user device of identified investment opportunities. Information is sent to the user in the form of push notifications, in-app messages, emails, etc. The notification includes detailed information about the investment opportunity and recommended actions. The input is the investment opportunity data, and the output is the notification sent to the user device.

[1108] Step 7:

[1109] The user receives notifications from the terminal and checks their contents. They take the information and their emotional state into consideration to make appropriate investment decisions. The user executes trades through the trading platform and checks the results on the terminal. The input is notification information from the server, and the output is the user's investment actions and their results.

[1110] 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.

[1111] 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.

[1112] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1113] 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.

[1114] 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.

[1115] 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.

[1116] 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).

[1117] 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.

[1118] 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."

[1119] 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.

[1120] 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).

[1121] 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.

[1122] 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.

[1123] 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.

[1124] 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.

[1125] 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.

[1126] 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.

[1127] 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.

[1128] 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.

[1129] 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.

[1130] 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.

[1131] The following is further disclosed regarding the above embodiment.

[1132] (Claim 1)

[1133] A means of collecting market data in real time;

[1134] means of collecting social media data;

[1135] A means of gathering trend information from the news,

[1136] A generating artificial intelligence means for integrating and analyzing the market data, social media data, and news trends;

[1137] a means of identifying investment opportunities;

[1138] means for notifying a user terminal of the identified investment opportunity;

[1139] A system including:

[1140] (Claim 2)

[1141] 10. The system of claim 1, further comprising means for performing data preprocessing when integrating market data, social media data, and news trend information.

[1142] (Claim 3)

[1143] 2. The system of claim 1, wherein the generating artificial intelligence means performs analysis including market fluctuation patterns, sentiment analysis, and news analysis.

[1144] "Example 1"

[1145] (Claim 1)

[1146] A means of collecting market data in real time;

[1147] a means of collecting social media data;

[1148] A means of gathering trend information from the news,

[1149] means for integrating the market data, social media data, and news trends to perform data pre-processing;

[1150] a generating artificial intelligence means for analyzing the pre-processed data;

[1151] a means of identifying investment opportunities;

[1152] means for notifying a user terminal of the identified investment opportunity;

[1153] A system including:

[1154] (Claim 2)

[1155] 2. The system of claim 1, wherein the generating artificial intelligence means performs analyses including market fluctuation analysis, sentiment analysis, and news text analysis.

[1156] (Claim 3)

[1157] 10. The system of claim 1, further comprising means for including detailed information about the investment opportunity and recommended actions in the notification.

[1158] "Application Example 1"

[1159] (Claim 1)

[1160] A means of collecting market data in real time;

[1161] means of collecting social media data;

[1162] A means of gathering trend information from the news,

[1163] A generating artificial intelligence means for integrating and analyzing the market data, social media data, and news trends;

[1164] a means of identifying investment opportunities;

[1165] means for notifying a user terminal of the identified investment opportunity;

[1166] A means for analyzing a user's purchasing pattern in an electronic payment service and providing purchasing recommendations;

[1167] A system including:

[1168] (Claim 2)

[1169] 10. The system of claim 1, further comprising means for performing data preprocessing when integrating market data, social media data, and news trend information.

[1170] (Claim 3)

[1171] 2. The system of claim 1, wherein the generating artificial intelligence means performs analysis including market fluctuation patterns, sentiment analysis, news analysis, and purchasing pattern analysis.

[1172] "Example 2: Combining Emotion Engines"

[1173] (Claim 1)

[1174] A means of collecting market data in real time;

[1175] means of collecting social media data;

[1176] A means of gathering trend information from the news,

[1177] A generating artificial intelligence means for integrating and analyzing the market data, social media data, and news trends;

[1178] emotion analysis means for analyzing the emotions of a user;

[1179] a means for identifying investment opportunities based on the sentiment analysis results and the analysis results;

[1180] means for notifying a user terminal of the identified investment opportunity;

[1181] A system including:

[1182] (Claim 2)

[1183] 10. The system of claim 1, further comprising means for performing data preprocessing when integrating market data, social media data, and news trend information.

[1184] (Claim 3)

[1185] 2. The system of claim 1, wherein the generating artificial intelligence means performs analysis including market fluctuation patterns, sentiment analysis, and news analysis.

[1186] "Application example 2 when combining emotion engines"

[1187] (Claim 1)

[1188] A means of collecting market data in real time;

[1189] means of collecting social media data;

[1190] A means of gathering trend information from the news,

[1191] A generating artificial intelligence means for integrating and analyzing the market data, social media data, and news trends;

[1192] emotion engine means for analyzing the emotion of a user;

[1193] a means of identifying investment opportunities;

[1194] means for notifying a user terminal of the identified investment opportunity;

[1195] A system including:

[1196] (Claim 2)

[1197] 10. The system of claim 1, further comprising: means for performing data preprocessing when integrating market data, social media data, and news trend information; and means for analyzing sentiment from user input data.

[1198] (Claim 3)

[1199] 2. The system of claim 1, wherein the generating artificial intelligence means performs analysis including market fluctuation patterns, sentiment analysis, news analysis, and analysis of user sentiment data. [Explanation of symbols]

[1200] 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 means of collecting market data in real time; means of collecting social media data; A means of gathering trend information from the news, A generating artificial intelligence means for integrating and analyzing the market data, social media data, and news trends; a means of identifying investment opportunities; means for notifying a user terminal of the identified investment opportunity; A system including:

2. The system of claim 1 , further comprising means for performing data pre-processing when integrating market data, social media data, and news trend information.

3. 2. The system of claim 1, wherein the generating artificial intelligence means performs analysis including market fluctuation patterns, sentiment analysis, and news analysis.

Images