system

Abstract

We provide a system that quickly and effectively analyzes market data and supports meetings. [Solution] The system provides means for acquiring market data and economic indicator data from external data sources, means for cleaning and normalizing the acquired data, and means for analyzing the data using generative AI to identify market trends and risk factors. Furthermore, it provides means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start roundtables or crew meetings, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, and means for analyzing meeting content and generating concrete action plans. The system finally includes means for distributing the generated action plans and meeting minutes to users.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern business environment, it is extremely important to quickly and accurately grasp the market and economic situations and formulate appropriate action plans. However, processes such as collecting, analyzing, and sharing vast amounts of data in meetings are time-consuming and make efficient decision-making difficult. Furthermore, there are few systems with the flexibility to handle real-time fluctuating market data. Thus, there is a current need for a system that can quickly and effectively analyze market data and support meetings.

Means for Solving the Problems

[0005] The present invention provides means for acquiring market data and economic indicator data from external data sources, means for cleaning and normalizing the acquired data, and means for analyzing the data using generative AI to identify market trends and risk factors. Furthermore, it provides means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start roundtables or crew meetings, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, and means for analyzing meeting content and generating concrete action plans. The above problems are solved by constructing a system that includes means for distributing the finally generated action plans and meeting minutes to users.

[0006] "External data sources" refer to third-party data providers or APIs that provide information such as market data and economic indicator data.

[0007] "Market data" refers to various types of data related to financial markets, such as stock prices, exchange rates, and commodity prices.

[0008] "Economic indicator data" refers to statistical data that shows the state and trends of economic activity, and examples include GDP and unemployment rates.

[0009] "Cleaning" is the process of removing noise and invalid values ​​from acquired data to maintain data consistency.

[0010] "Normalization" is the process of converting data obtained from different data sources into a standard format to ensure consistency.

[0011] "Generative AI" is an artificial intelligence technology that analyzes large amounts of data, recognizes patterns and trends, and generates analysis results.

[0012] A "dashboard" is a web-based interface that users can access to visually view and interact with data and analysis results.

[0013] A "roundtable discussion" is an informal meeting held to exchange opinions on a specific topic.

[0014] A "crew meeting" is a formal meeting held to discuss the progress of a project or task and to decide on the next course of action.

[0015] "Real-time analysis" is a process that performs analysis immediately upon data input, generating and displaying the results.

[0016] An "action plan" is a plan that outlines specific measures and actions that should be taken based on the results of discussions.

[0017] Meeting minutes are documents that record the content discussed, decisions made, and action plans of a meeting. [Brief explanation of the drawing]

[0018] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] Displays an emotion map to which a plurality of emotions are mapped. [Figure 10] Displays an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be described.

[0021] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0022] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0031] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0039] This invention relates to a system that collects market data and economic indicator data from external data sources, performs analysis using generative AI, and supports roundtable discussions and crew meetings based on the results. Embodiments of this system are described in detail below.

[0040] Data acquisition and preprocessing

[0041] server

[0042] The server collects market and economic indicator data from external data sources. Specifically, the server uses API requests to retrieve information from data providers. This data is received in formats such as JSON and XML.

[0043] The server then cleans and normalizes the acquired data. The cleaning process detects empty values ​​and outliers and corrects or removes them. The normalization process converts information from different data sources into a unified format.

[0044] Data analysis and report generation

[0045] server

[0046] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3® or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in a report format. This report is presented in a visual format, including graphs and charts.

[0047] The analysis results are saved on the server and prepared for display on the dashboard. This dashboard provides an interface for users to view reports and start roundtables or crew meetings.

[0048] Roundtable discussion / crew meeting

[0049] User

[0050] Users access a web-based dashboard from their own devices (PC, tablet, etc.). The dashboard displays reports generated by the server, which users use to initiate roundtables and crew meetings.

[0051] Real-time discussion support

[0052] server

[0053] During the meeting, users enter questions and comments from their devices into the dashboard. The server uses generative AI to analyze these inputs in real time and generate appropriate answers. The generated answers are immediately displayed on the dashboard, supporting the progress of the meeting.

[0054] Generating action items

[0055] server

[0056] By analyzing the content of the meeting discussion, the generative AI automatically generates specific action plans. For example, action plans such as "increase inventory" or "strengthen marketing campaigns" may be generated.

[0057] Minutes creation and distribution

[0058] server

[0059] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are then delivered to the user's device and shared with all meeting participants.

[0060] Specific example

[0061] 1. Data Collection: The server calls an external API to retrieve market data in JSON format.

[0062] 2. Data Cleaning: The server imputes missing values ​​with the mean and detects and corrects outliers.

[0063] 3. Data Analysis: Generative AI identifies market trends and compiles them into reports.

[0064] 4. Dashboard Access: Users access the web-based dashboard from their devices and begin the discussion.

[0065] 5. Real-time answer generation: The server analyzes the user's question, and the generation AI instantly generates and displays the answer.

[0066] 6. Action Plan Generation: During the meeting, a generative AI proposes the next action plan.

[0067] 7. Distribution of meeting minutes: After the meeting ends, the server automatically generates the meeting minutes and sends them to the user's terminal.

[0068] This invention makes it possible to conduct efficient meetings through real-time analysis, which was difficult to achieve with conventional methods, and to formulate highly responsive action plans.

[0069] The following describes the processing flow.

[0070] Step 1:

[0071] Calling an external API

[0072] The server sends requests to external APIs that provide market and economic indicator data. For example, it makes HTTP requests specifying a particular endpoint URL to retrieve the latest data.

[0073] Step 2:

[0074] Receiving API Responses

[0075] The server waits for responses from external APIs and receives data in formats such as JSON and XML. The received data is temporarily stored so that it can be used directly for analysis.

[0076] Step 3:

[0077] Data Cleaning

[0078] The server performs a cleaning process on the acquired data. Specifically, it detects empty values ​​and outliers and removes or imputes them. For example, if there are missing values, it imputes them with the average value of past data. Also, if outliers are found, it replaces them with appropriate values.

[0079] Step 4:

[0080] Data normalization

[0081] The server normalizes the cleaned data. It converts data obtained from different data sources into a unified format to maintain consistency. For example, it converts data in different time formats into a unified timestamp format.

[0082] Step 5:

[0083] Initialization of generative AI

[0084] The server initializes generative AI (e.g., GPT-3 or BERT). It loads the necessary models and parameters and prepares them for analysis.

[0085] Step 6:

[0086] Data input and analysis

[0087] The server feeds pre-processed data into the generative AI and begins analysis. The generative AI identifies market trends and risk factors and retrieves the results.

[0088] Step 7:

[0089] Report generation

[0090] The server generates a report based on the analysis results output by the generative AI. This report includes graphs and charts to visually represent the analysis results. It also explains the analysis results in text format and provides insights into the data.

[0091] Step 8:

[0092] Saving reports and displaying dashboards

[0093] The server stores the generated reports and prepares them for display on a dashboard accessible to the user. The dashboard provides a web-based interface, allowing users to view the reports.

[0094] Step 9:

[0095] Access to the dashboard

[0096] Users access the dashboard from their own devices (PC, tablet, etc.). Users can view generated reports and start roundtables or crew meetings.

[0097] Step 10:

[0098] Enter your questions and comments

[0099] During the meeting, users enter questions and comments from their devices into the dashboard. These entries are then sent to the server.

[0100] Step 11:

[0101] Real-time analysis and response generation

[0102] The server uses generative AI to analyze user questions and comments in real time. The AI ​​generates appropriate answers, which are then displayed on the dashboard.

[0103] Step 12:

[0104] Analysis of discussion content and generation of action plans

[0105] The server analyzes the content of the discussion during the meeting, and a generative AI automatically generates a concrete action plan. For example, it might make specific suggestions such as "strengthen the marketing campaign."

[0106] Step 13:

[0107] Minutes generation

[0108] The server automatically generates meeting minutes based on the meeting content and the generated action plan. The minutes record important items and decisions discussed during the meeting.

[0109] Step 14:

[0110] Distribution of meeting minutes

[0111] After the meeting ends, the server distributes the generated meeting minutes to the users' terminals. This ensures that all meeting participants receive the minutes, facilitating smooth information sharing.

[0112] (Example 1)

[0113] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0114] There is a need for a system that efficiently collects and analyzes market data and economic indicator data, and then uses the results to support meetings in real time. Conventional systems struggled to provide necessary information immediately because cleaning and analyzing large amounts of data was time-consuming. Furthermore, they were unable to smoothly generate appropriate answers to real-time questions and comments during meetings, or automatically generate meeting minutes after meetings.

[0115] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0116] In this invention, the server includes means for acquiring market data and economic indicator data from external data sources; means for cleaning and normalizing the acquired data; means for detecting, correcting, or removing empty values ​​and outliers; means for analyzing the data using generative artificial intelligence to identify market trends and risk factors; means for generating reports based on the analysis results, selecting templates for visual representation, inserting graphs and charts, and saving them; means for users to access the generated reports via a terminal and start a roundtable discussion or meeting; means for analyzing user questions and comments in real time and generating and displaying appropriate answers; means for analyzing meeting content and generating concrete action plans; and means for distributing the generated action plans and meeting minutes to users. This makes it possible to streamline the entire process from data collection to analysis and meeting support.

[0117] "External data sources" refer to external sources of information that provide market data and economic indicator data.

[0118] "Market data" refers to data related to market trends, such as stock prices, trading volume, and exchange rates.

[0119] "Economic indicator data" refers to numerical values ​​that show the state of the economy, such as GDP, unemployment rate, and price index.

[0120] "Generative artificial intelligence" refers to AI models that perform data analysis and information generation in response to given input.

[0121] "Cleaning" refers to the process of detecting empty or outlier values ​​from acquired data and correcting or removing them.

[0122] "Normalization" is the process of converting information obtained from different data sources into a unified format.

[0123] A "prompt statement" is an input statement used to instruct a generative artificial intelligence system to perform analysis or generate information.

[0124] A "report" is a document that summarizes the results of an analysis.

[0125] A "visual representation template" is a template for representing a report in a visual format, such as graphs or charts.

[0126] A "dashboard" is an interface that allows users to view reports and start discussion groups or meetings.

[0127] "Real-time responses" refer to answers that are generated and displayed instantly in response to user questions and comments.

[0128] An "action plan" is a specific plan of action that is generated based on the discussions held at a meeting.

[0129] "Meeting minutes" are documents that record the content and decisions made at a meeting.

[0130] This invention relates to a system that collects market data and economic indicator data from external data sources, analyzes them using generative artificial intelligence, and supports roundtables and meetings based on the results. This system can be implemented using the following hardware and software.

[0131] Data acquisition and preprocessing

[0132] The server collects market data and economic indicator data from external data sources. Specifically, the server calls external APIs (e.g., market data APIs) to retrieve the latest market data in JSON format.

[0133] The server cleans the retrieved data by detecting empty values, imputing them with the median, and detecting and correcting outliers. The Pandas library (Python) is used for dataframe manipulation during the cleaning process.

[0134] The server normalizes the data, converting information from different data sources into a unified format. For example, it converts all price data to USD units.

[0135] Data analysis and report generation

[0136] The server uses the cleaned and normalized data to perform analysis using generative artificial intelligence (e.g., GPT-3 or BERT).

[0137] The server formats the input data for the generative artificial intelligence and generates prompt sentences. For example, it can generate a prompt sentence such as, "Based on the latest NASDAQ data, please explain the market trends and risk factors."

[0138] Generative artificial intelligence identifies market trends and potential risk factors and generates reports. These reports are presented in a visual format, including graphs and charts.

[0139] Report display and dashboard preparation

[0140] The server saves the generated report and prepares it for display on the dashboard. Specifically, it converts the report to HTML format and adds code to visually display graphs and charts.

[0141] The dashboard provides an interface for users to view reports and start roundtables and meetings.

[0142] Access to the dashboard

[0143] Users access the dashboard using a web browser from their own device (PC, tablet, etc.). The device performs user authentication and verifies the user's access permissions.

[0144] The terminal receives report data sent from the server and displays it on the browser screen.

[0145] Real-time discussion support

[0146] Users enter questions and comments on the dashboard from their devices during the meeting. The devices then send the user input data to the server.

[0147] The server receives this input data and uses generative artificial intelligence to analyze it in real time. For example, the server sends the prompt "What are the causes of recent market fluctuations?" to the generative AI and immediately generates an answer. The generative AI generates the answer "Recent market fluctuations are mainly due to the influence of economic conditions."

[0148] The server displays the generated responses on the dashboard.

[0149] Generating action items

[0150] The server analyzes the meeting discussions and uses generative artificial intelligence to automatically generate concrete action plans. For example, the server sends the prompt "Please propose the next action plan" to the generative AI. The generative AI then generates specific action items such as "Increase inventory" or "Develop a new marketing strategy."

[0151] The server displays the generated action items on the dashboard.

[0152] Minutes creation and distribution

[0153] After the meeting ends, the server automatically generates meeting minutes based on the meeting content and the generated action plan. The minutes are generated in text format and converted to PDF format.

[0154] The server sends the generated meeting minutes to the user's terminal. For example, the server might send the minutes as an email attachment or make them available for download on the dashboard.

[0155] Specific example

[0156] 1. Data Collection: The server calls an external API to retrieve NASDAQ market data in JSON format.

[0157] 2. Data Cleaning: The server imputes empty values ​​with the median and corrects outliers to within ±3 standard deviations.

[0158] 3. Data Analysis: Generative artificial intelligence (GPT-3) identifies the latest market trends and compiles them into a report.

[0159] 4. Dashboard Access: Users access the dashboard from their device using a web browser (e.g., Google Chrome® browser) and start a roundtable discussion.

[0160] 5. Real-time answer generation: The server analyzes the user's question, "What are the causes of recent market fluctuations?", and the generative artificial intelligence (BERT) instantly generates and displays the answer.

[0161] 6. Action Plan Generation: During the meeting, the generative artificial intelligence proposes an action plan such as "Strengthen the sales strategy for Q2."

[0162] 7. Distribution of meeting minutes: After the meeting, the server automatically generates meeting minutes and sends them to the user's device in PDF format. The minutes include the discussion content and action plan.

[0163] Example of a prompt:

[0164] 1. "Based on the latest NASDAQ data, please explain the market trends and risk factors."

[0165] 2. "Generate appropriate answers to the question regarding the causes of recent market fluctuations."

[0166] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0167] Step 1: Data Collection

[0168] The server retrieves market data and economic indicator data from external data sources. Specifically, the server calls a market data API to obtain the latest market data in JSON format.

[0169] Input: Market Data API endpoint

[0170] Data processing: Send an API request and save the retrieved market data in JSON format.

[0171] Output: Acquired market data in JSON format

[0172] Step 2: Data Cleaning

[0173] The server cleans the acquired data. Specifically, it detects empty values, imputes them with the median, and detects and corrects outliers.

[0174] Input: Market data in JSON format

[0175] Data processing: Create a dataframe using the Pandas library, impute empty values ​​with the median, and detect and correct outliers.

[0176] Output: Cleaned data frame

[0177] Step 3: Data Normalization

[0178] The server performs data normalization. Specifically, it converts information from different data sources into a unified format.

[0179] Input: Cleaned dataframe

[0180] Data processing: Convert all price data to USD units.

[0181] Output: Normalized data frame

[0182] Step 4: Data Analysis

[0183] The server analyzes the data using generative artificial intelligence. Specifically, it sends a prompt message to the generative AI, and the AI ​​model begins the analysis.

[0184] Input: Normalized data frame, prompt: "Based on the latest NASDAQ data, describe market trends and risk factors."

[0185] Data processing: A prompt message is sent to a generative artificial intelligence (e.g., GPT-3), and the analysis results are received.

[0186] Output: Analysis results including market trends and risk factors

[0187] Step 5: Report Generation

[0188] The server generates a report based on the analysis results. Specifically, it selects a template for visual representation, inserts graphs and charts, and saves the report.

[0189] Input: Analysis results

[0190] Data processing: Generate an HTML report based on the analysis results and insert graphs and charts.

[0191] Output: Generated report (HTML format)

[0192] Step 6: Prepare the dashboard

[0193] The server prepares the generated report for display on the dashboard.

[0194] Input: Generated report (HTML format)

[0195] Data processing: Save reports to a database and make them accessible on the dashboard.

[0196] Output: Reports that can be displayed on the dashboard

[0197] Step 7: Accessing the Dashboard

[0198] Users access the dashboard from their own devices (PC, tablet, etc.).

[0199] Input: User authentication information

[0200] Data processing: The terminal receives report data sent from the server and displays it on the browser screen.

[0201] Output: Report displayed in the browser

[0202] Step 8: Real-time discussion support

[0203] Users enter questions and comments from their devices into a dashboard during the meeting. The server receives this input data and performs real-time analysis using generative artificial intelligence.

[0204] Input: User questions and comments

[0205] Data processing: The prompt "What are the causes of recent market fluctuations?" is sent to a generative AI system, and the answer is generated and displayed.

[0206] Output: Real-time responses generated

[0207] Step 9: Generate action items

[0208] The server analyzes the meeting's discussion content and automatically generates a concrete action plan. For example, it might send a prompt to the generative AI saying, "Please propose the next action plan."

[0209] Input: Discussion log data

[0210] Data processing: Generate specific action items based on generative artificial intelligence.

[0211] Output: Generated action items

[0212] Step 10: Generate and distribute meeting minutes.

[0213] After the meeting ends, the server automatically generates meeting minutes based on the meeting content and the generated action plan, and sends them to the user's terminal.

[0214] Input: Meeting content, action plan

[0215] Data processing: Convert meeting minutes to PDF format and send them to users via email.

[0216] Output: Meeting minutes sent to the user's device (PDF format)

[0217] (Application Example 1)

[0218] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0219] In today's markets, rapid and accurate decision-making is essential, but data collection, cleaning, and analysis are time-consuming and labor-intensive, making efficient operation difficult. Furthermore, the inability to provide timely and appropriate information and answers during meetings and discussions is a significant challenge.

[0220] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0221] In this invention, the server includes means for acquiring market data and economic indicator data from external data sources, means for cleaning and normalizing the acquired data, means for analyzing the data using generative AI to identify market trends and risk factors, means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start a roundtable discussion or crew meeting, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, means for analyzing meeting content and generating concrete action plans, means for distributing the generated action plans and meeting minutes to users, means for displaying graphs and charts that visually represent the analysis results, and means for collecting and analyzing market data, competitor information, and customer behavior data to support strategic planning for virtual store operations. This enables efficient and rapid decision-making and supports optimal strategic planning in real time for virtual store operations.

[0222] "External data sources" refer to external data providers or APIs that provide market data and economic indicator data.

[0223] "Market data" refers to data that includes information such as price, supply, and demand related to a specific market.

[0224] "Economic indicator data" refers to data that includes statistical information indicating the state of the economy, such as GDP, unemployment rate, and inflation rate.

[0225] "Cleaning" is the process of correcting or removing inappropriate or missing values ​​from data.

[0226] "Normalization" is the process of converting data obtained from different data sources into a unified format.

[0227] "Generative AI" is artificial intelligence that analyzes collected data and generates text to perform a specific task.

[0228] "Market trends" refer to information that indicates the fluctuation patterns of prices and demand in the market.

[0229] "Risk factors" refer to elements or events that could have a negative impact on the market or economy.

[0230] A "report" is a document that summarizes the results of an analysis and may include graphs and charts.

[0231] A "dashboard" is a web-based interface that allows users to access analysis results and reports.

[0232] A "roundtable discussion" refers to a small-scale discussion held in a meeting format.

[0233] A "crew meeting" refers to a meeting held to discuss a specific project or issue.

[0234] "Real-time" refers to data processing and information provision at the present moment.

[0235] An "action plan" is a specific plan of actions taken to achieve a particular challenge or objective.

[0236] "Meeting minutes" are documents that record the content discussed and decisions made during a meeting.

[0237] "Competitive information" refers to information about the activities and strategies of other competing companies in the market.

[0238] "Customer behavior data" refers to information about how customers used products and services.

[0239] This invention is a system that supports the operation of virtual stores by collecting market data and economic indicator data from external data sources and performing analysis using generative AI. A detailed embodiment for carrying out this invention is described below.

[0240] Data acquisition and preprocessing

[0241] server

[0242] The server collects market data, economic indicators, competitive information, and customer behavior data from external data sources. Specifically, the server retrieves this information using API requests. This data is received in formats such as JSON and XML. The server then cleans and normalizes the retrieved data. The cleaning process detects empty values ​​and outliers and corrects or removes them. The normalization process converts information from different data sources into a unified format.

[0243] Data analysis and report generation

[0244] server

[0245] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in a report format. This report is created in a visual format, including graphs and charts. The analysis results are stored on a server and prepared for display on a dashboard accessible to users. The dashboard is browser-based, and users can access it from PCs, tablets, smartphones, etc.

[0246] Roundtable discussion / crew meeting

[0247] User

[0248] Users access a web-based dashboard from their devices. The dashboard displays reports generated by the server, which users can use to initiate roundtables and crew meetings.

[0249] Real-time discussion support

[0250] server

[0251] During the meeting, users enter questions and comments from their devices into the dashboard. The server uses generative AI to analyze these inputs in real time and generate appropriate answers. The generated answers are immediately displayed on the dashboard, supporting the progress of the meeting.

[0252] Generating action items

[0253] server

[0254] By analyzing the content of the meeting discussion, the generative AI automatically generates specific action plans. For example, action plans such as "increase inventory" or "strengthen marketing campaigns" may be generated.

[0255] Minutes creation and distribution

[0256] server

[0257] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are then delivered to the user's device and shared with all meeting participants.

[0258] Specific example

[0259] The server calls an external API to retrieve market data in JSON format. The server imputes missing values ​​with averages and detects and corrects outliers. Generative AI identifies market trends and compiles them into a report. The user accesses a web-based dashboard from their terminal and starts a roundtable discussion. The server analyzes the user's questions, and the generative AI instantly generates and displays answers. During the meeting, the generative AI proposes the next action plan. After the meeting ends, the server automatically generates meeting minutes and sends them to the user's terminal.

[0260] Example of a prompt

[0261] Identify trends and risks from the following market data:

[0262] Data: [{'product': 'A', 'price': 100, 'demand': 200}, {'product': 'B', 'price': 150, 'demand': 180}]"

[0263] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0264] Step 1:

[0265] Data collection

[0266] The server retrieves market data, economic indicators, competitive information, and customer behavior data from external data sources via API requests. The server accesses a specified API endpoint and receives data in JSON or XML format. The input is the API request, and the output is the retrieved data in JSON or XML format as a response.

[0267] Step 2:

[0268] Data cleaning and normalization

[0269] The server cleans and normalizes the received data. Data cleaning detects empty values ​​and outliers and corrects or removes them based on statistical methods. Specifically, it imputes missing values ​​with the mean and detects and corrects outliers. The normalization process converts information from different data sources into a unified format. The input is the acquired data, and the output is the cleaned and normalized data.

[0270] Step 3:

[0271] Data Analysis

[0272] The server analyzes the cleaned and normalized data using generative AI (e.g., GPT-3 or BERT). Specifically, it generates prompt sentences suitable for analysis and inputs them into the generative AI. Based on these prompt sentences, the AI ​​identifies market trends and risk factors and returns the analysis results. The input consists of the cleaned and normalized data and prompt sentences, and the output is the analysis results.

[0273] Step 4:

[0274] Report generation

[0275] The server generates a report based on the analysis results. The report includes market trends, risk factors, as well as graphs and charts for easy visual understanding. The generated report is saved in formats such as HTML or PDF. The input is the analysis result, and the output is the generated report.

[0276] Step 5:

[0277] Dashboard display

[0278] The user accesses the web-based dashboard from their terminal. The server displays the generated report on the dashboard. The user can view the report via the dashboard and start symposiums or crew meetings. The input is the generated report, and the output is the dashboard on which the report is displayed.

[0279] Step 6:

[0280] Real-time question and answer

[0281] During the meeting, the user inputs questions and comments from the terminal to the dashboard. The server uses generative AI to analyze these inputs in real time and generate appropriate answers. The generated answers are displayed on the dashboard to assist the progress of the meeting. The input is the user's questions and comments, and the output is the generated answers.

[0282] Step 7:

[0283] Action plan generation

[0284] The server analyzes the discussion content of the meeting, and the generative AI automatically generates a specific action plan. For example, it includes specific proposals such as "increase inventory" and "strengthen the marketing campaign". The input is the discussion content of the meeting, and the output is the generated action plan.

[0285] Step 8:

[0286] Proceedings Generation and Distribution

[0287] When the meeting ends, the server automatically generates minutes based on the content of the meeting and the generated action plan. These minutes are converted into a format such as PDF and distributed to the user's terminal. The input is the discussion content of the meeting and the generated action plan, and the output is the automatically generated minutes.

[0288] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0289] The present invention collects market data and economic indicator data from an external data source, performs analysis using generative AI, and in addition to a system that supports symposiums and crew meetings based on the results, combines an emotion engine that recognizes the user's emotions. Hereinafter, embodiments of this system will be described in detail.

[0290] Data Collection and Pretreatment

[0291] Server

[0292] The server collects market data and economic indicator data from an external data source. Specifically, the server uses an API request to obtain information from a data provider. This data is received in a format such as JSON or XML. Then, the server cleans and normalizes the acquired data. In the cleaning process, empty values and outliers are detected and removed or supplemented. In the normalization process, information from different data sources is converted into a unified format.

[0293] Data Analysis and Report Generation

[0294] Server

[0295] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in report format. This report is created in a visual format, including graphs and charts. The analysis results are stored on a server and prepared for display on a dashboard. This dashboard provides an interface for users to view reports and initiate roundtables and crew meetings.

[0296] Roundtable discussion / crew meeting

[0297] User

[0298] Users access a web-based dashboard from their own devices (PC, tablet, etc.). The dashboard displays reports generated by the server, which users use to initiate roundtables and crew meetings.

[0299] Emotion recognition and real-time discussion support

[0300] server

[0301] During the meeting, users enter questions and comments from their devices into a dashboard. In addition, an emotion engine operates to recognize emotions from user speech and text input. The server uses generative AI and the emotion engine to analyze these inputs in real time and generate appropriate responses. The generated responses are immediately displayed on the dashboard to support the progress of the meeting.

[0302] Analysis of discussion content and generation of action plans

[0303] server

[0304] By analyzing the content of discussions during meetings, the generative AI and emotion engine automatically generate specific action plans. For example, it proposes action plans that reflect emotional data, such as "If user anxiety is detected, review risk management measures."

[0305] Generation and Distribution of Meeting Minutes

[0306] Server

[0307] When the meeting ends, the server automatically generates meeting minutes based on the content of the meeting and the generated action plan. These meeting minutes also include the user's emotion data recognized by the emotion engine. For example, changes in emotion during discussions and the tone of the meeting are also reflected in the meeting minutes. The generated meeting minutes are distributed to the user's terminal and shared among all meeting participants.

[0308] Specific Example

[0309] 1. Data Collection: The server calls an external API to obtain market data in JSON format.

[0310] 2. Data Cleaning: The server fills in missing values with the average value and detects and corrects outliers.

[0311] 3. Data Analysis: The generative AI identifies market trends and summarizes them in a report.

[0312] 4. Dashboard Access: The user accesses a web-based dashboard from the terminal to start a symposium.

[0313] 5. Emotion Recognition: The emotion engine recognizes emotions from the user's speech and text input. [[ID=3​​​​​​​​​​​​

[0317] This invention makes it possible to conduct efficient meetings through real-time analysis, which was difficult to achieve with conventional methods, and to formulate flexible action plans that reflect user sentiment data.

[0318] The following describes the processing flow.

[0319] Step 1:

[0320] Calling an external API

[0321] The server retrieves the latest data by sending HTTP requests to external APIs that provide market and economic indicator data. Specifically, it makes requests using API endpoint URLs and receives data in JSON or XML format.

[0322] Step 2:

[0323] Receiving API Responses

[0324] The server receives a response from an external API and temporarily stores the retrieved data. The stored data is then used in the next processing step.

[0325] Step 3:

[0326] Data Cleaning

[0327] The server cleans the acquired data. Specifically, it detects empty values ​​and outliers in the data and removes or imputes them. For example, missing values ​​are imputed with the mean of past data, and outliers are replaced with appropriate values.

[0328] Step 4:

[0329] Data normalization

[0330] The server normalizes the cleaned data. Specifically, it converts data obtained from different data sources into a unified format to maintain consistency. For example, it converts data in different time formats into a common timestamp format.

[0331] Step 5:

[0332] Initialization of generative AI

[0333] The server initializes generative AI (such as GPT-3 or BERT). It loads the necessary models and parameters and prepares the data for analysis.

[0334] Step 6:

[0335] Data input and analysis

[0336] The server feeds the pre-processed data into the generative AI and begins data analysis. The generative AI identifies market trends and risk factors and generates analysis results based on them.

[0337] Step 7:

[0338] Report generation

[0339] The server generates a report based on the analysis results obtained from the generative AI. This report includes text explanations of the analysis results, as well as graphs and charts. The information is presented in a visually easy-to-understand format.

[0340] Step 8:

[0341] Saving reports and displaying dashboards

[0342] The server stores the generated reports in a database and displays them on a dashboard for user access. The dashboard is provided via a web-based interface.

[0343] Step 9:

[0344] Access to the dashboard

[0345] Users access the dashboard from their own devices (PC, tablet, etc.) and view the generated reports. Based on these reports, users can then initiate roundtable discussions or crew meetings.

[0346] Step 10:

[0347] emotion recognition

[0348] The server uses an emotion engine to recognize emotions from user statements and text input. It analyzes specific keywords and expressions to determine the user's emotional state.

[0349] Step 11:

[0350] Real-time analysis and response generation

[0351] The server analyzes user questions and comments in real time and generates appropriate responses using generative AI and an emotion engine. For example, if a user expresses anxiety, the server analyzes it and generates a reassuring response.

[0352] Step 12:

[0353] Display the answer

[0354] The server displays the generated responses on a dashboard and provides them to users in real time, ensuring a smooth flow of the meeting.

[0355] Step 13:

[0356] Analysis of discussion content and generation of action plans

[0357] The server uses an emotion engine and generative AI to analyze the content of discussions during meetings and automatically generates concrete action plans. For example, it proposes an action plan that reflects the emotions expressed by the user.

[0358] Step 14:

[0359] Minutes generation

[0360] The server automatically generates meeting minutes based on the meeting content, the generated action plan, and the user's emotional state as recognized by the emotion engine.

[0361] Step 15:

[0362] Distribution of meeting minutes

[0363] After the meeting ends, the server distributes the generated meeting minutes to each user's device. This ensures that all meeting participants receive the minutes, facilitating smooth information sharing.

[0364] This system enables efficient collection and analysis of precise information from external data sources, real-time meeting support that takes user sentiment into consideration, and the development of concrete action plans.

[0365] (Example 2)

[0366] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0367] Conventional meeting systems have made it difficult to perform real-time data analysis and generate flexible action plans that reflect user sentiment. Furthermore, efficient analysis of meeting content, automatic generation of concrete action plans based on that analysis, and rapid distribution of meeting minutes to all participants have been challenging. This invention aims to solve these problems and provide a system that streamlines and enhances meeting management.

[0368] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0369] In this invention, the server includes means for acquiring market data and economic indicator data from external data sources, means for cleaning and normalizing the acquired data, means for analyzing the data using generative AI to identify market trends and risk factors, means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start a roundtable discussion or crew meeting, means for recognizing emotions from user statements and text inputs, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, means for analyzing meeting content and generating concrete action plans that reflect user emotion data, and means for automatically generating meeting minutes based on the meeting content and generated action plans and distributing them to users. This enables the generation of flexible action plans through real-time data analysis and emotion recognition, as well as rapid analysis of meeting content and automatic generation and distribution of meeting minutes.

[0370] "External data sources" refer to external information providers, APIs, and other entities that provide market data and economic indicator data.

[0371] "Market data" refers to data related to financial markets, such as stock prices, exchange rates, and commodity prices.

[0372] "Economic indicator data" refers to statistical data that shows the state of the economy, such as GDP, unemployment rate, and consumer price index.

[0373] "Cleaning" refers to the process of detecting, correcting, or removing empty or outlier values ​​in data.

[0374] "Normalization" refers to the process of converting data obtained from different data sources into a unified format.

[0375] "Generative AI" refers to artificial intelligence models that perform tasks such as data analysis and natural language generation (e.g., GPT-3, BERT, etc.).

[0376] "Market trends" refer to the temporal movements and fluctuation patterns of market data.

[0377] "Risk factors" refer to elements that could have a negative impact on markets or economic activity.

[0378] A "report" refers to a document or report that summarizes the results of an analysis.

[0379] A "dashboard" refers to a web-based interface that allows users to access and interact with analytical results and reports.

[0380] A "roundtable discussion" refers to a type of meeting where participants freely exchange opinions on a specific topic.

[0381] A "crew meeting" refers to a meeting held within a specific team or organization.

[0382] "Means of recognizing emotions" refers to algorithms and engines that identify emotions from user statements and text input.

[0383] "Means of real-time analysis" refers to the ability to instantly analyze input data and immediately generate and display results.

[0384] An "action plan" refers to a specific plan of action or measures.

[0385] "Meeting minutes" refers to a document that records the content of a meeting, the matters discussed, the decisions made, and the action plan.

[0386] This invention combines a system that collects market data and economic indicator data from external data sources, performs analysis using generative AI, and supports roundtable discussions and crew meetings based on the results, with an emotion engine that recognizes user emotions. The embodiments of this system are described in detail below.

[0387] The server uses API requests to retrieve market data and economic indicator data from external data sources. Specifically, the server accesses a URL like "https: / / api.example.com / marketdata" and receives the data in JSON format.

[0388] Next, the server cleans and normalizes the received data. Data cleaning involves imputing missing values ​​with the mean and detecting and correcting outliers. This is done using libraries such as Python's pandas library.

[0389] Cleaned and normalized data is analyzed by generative AI models (e.g., GPT-3, BERT, etc.). The server inputs this data into the generative AI to identify market trends and risk factors. The information obtained from the analysis is generated and saved as a report in a visual format (graphs, charts, etc.).

[0390] The analysis results are displayed on a dashboard. This uses web frameworks such as Python's Flask or Django, and is provided as a web-based interface accessible to users. Users access this dashboard from their devices and start roundtables or crew meetings based on the generated reports.

[0391] During the meeting, users enter questions and comments from their devices onto the dashboard. The emotion engine recognizes emotions from the user's statements and text input. For example, if a user enters "What do you think about the current market?", the emotion engine recognizes "anxiety," and the generative AI immediately generates and displays the response, "The market is highly volatile, so caution is needed."

[0392] The meeting content is analyzed in real time, and specific action plans are generated that reflect the user's emotional data. For example, the emotional engine analyzes statements such as "the risk is too high," and the generative AI generates an action plan such as "propose reviewing risk management measures."

[0393] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes also include sentiment data recognized by the sentiment engine, detailing specific points such as "proposed a review of risk management measures." The generated minutes are then delivered to the user's device and shared with all meeting participants.

[0394] This invention enables efficient meeting management through real-time analysis, which was difficult to achieve with conventional methods, and the development of flexible action plans that reflect user sentiment data. An example of a prompt is "Please tell me about future market trends." By entering this prompt, a generative AI can analyze it and provide a specific answer in real time.

[0395] The above details the specific method of the present invention. This system not only dramatically improves the efficiency of business meetings and analysis, but also contributes to an improved user experience.

[0396] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0397] Step 1: Data Collection

[0398] server

[0399] The server sends API requests to external data sources to retrieve market data and economic indicator data. For example, the server accesses a URL like "https: / / api.example.com / marketdata" and receives data in JSON format.

[0400] Input-based action: Request to an external API.

[0401] Output: Acquired market data and economic indicator data.

[0402] Step 2: Data Preprocessing

[0403] server

[0404] The server cleans and normalizes the data it receives. Data cleaning involves imputing missing values ​​with the mean and detecting and correcting outliers. Normalization converts data obtained from different data sources into a unified format.

[0405] Input-based operation: Cleaning and normalizing incoming data.

[0406] Output: Cleaned and normalized data.

[0407] Step 3: Data Analysis

[0408] server

[0409] The cleaned and normalized data is input into a generative AI for analysis. For example, the server supplies data to a generative AI model (e.g., GPT-3) to identify market trends and risk factors.

[0410] Input-based operation: Data input to a generative AI model.

[0411] Output: Analysis results identifying market trends and risk factors.

[0412] Step 4: Prepare to generate reports and display dashboards.

[0413] server

[0414] Based on the analysis results, a visual report is generated. The server uses web frameworks such as Python's Flask or Django to prepare the report in HTML format for display on the dashboard.

[0415] Input-based operation: Generates visual reports and HTML using analysis results.

[0416] Output: HTML for visual reports and dashboards.

[0417] Step 5: Access the Dashboard

[0418] User

[0419] Users access a web-based dashboard from their devices and initiate roundtables or crew meetings based on the displayed analytics reports.

[0420] Input-based action: User accesses the dashboard via browser.

[0421] Output: Analysis report displayed on the dashboard.

[0422] Step 6: Emotion Recognition and Real-Time Discussion Support

[0423] server

[0424] During a meeting, users enter questions and comments from their devices onto a dashboard. The server uses an emotion engine to recognize the user's emotions from these inputs. It then works in conjunction with generative AI to generate and display appropriate answers in real time. For example, if a user enters "What do you think about the current market?", the server's emotion engine recognizes the user's anxiety, and the generative AI instantly generates an answer regarding market fluctuations.

[0425] Input-based operation: Sentiment recognition and response generation based on user input.

[0426] Output: Real-time responses displayed on the dashboard.

[0427] Step 7: Generate an action plan

[0428] server

[0429] The system analyzes meeting content in real time and generates concrete action plans that reflect user sentiment data. For example, the sentiment engine analyzes statements such as "the risk is too high," and the generative AI proposes a revision of risk management measures.

[0430] Input-based actions: Analysis of meeting content and sentiment data.

[0431] Output: A concrete action plan.

[0432] Step 8: Generate and distribute meeting minutes

[0433] server

[0434] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes, which include sentiment data, are delivered to the user's device.

[0435] Input-based operation: Generate meeting minutes based on meeting content and action plan.

[0436] Output: Meeting minutes distributed to users.

[0437] The above outlines the processing steps of this system and the specific operational details of each step. This enables efficient and flexible meeting management through real-time analysis and emotion recognition.

[0438] (Application Example 2)

[0439] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0440] Conventional meeting support systems do not adequately support real-time discussions using market and economic indicator data. Furthermore, they struggle to recognize user emotions and generate effective action plans based on them. In addition, there is a lack of means to conduct meetings and make decisions in a way that takes staff emotions into consideration in the operation of physical stores.

[0441] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for acquiring market data and economic indicator data from an external data source, means for cleaning and normalizing the acquired data, means for analyzing the data using generative AI to identify market trends and risk factors, means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start a roundtable discussion or crew meeting, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, means for analyzing meeting content and generating a concrete action plan, means for distributing the generated action plan and meeting minutes to the user, means for analyzing the emotional state of store staff using market data and sentiment data and proposing an appropriate action plan, and means for conducting a meeting based on emotional state and market data through generative AI. This enables efficient meeting management through real-time analysis and the formulation of flexible action plans that reflect sentiment data.

[0442] "External data sources" refer to sources of information used to collect market data and economic indicator data from outside the system, such as the internet or third-party APIs.

[0443] "Market data" refers to statistical information related to a specific market, such as product sales, price trends, and consumer demand.

[0444] "Economic indicator data" refers to statistical information such as unemployment rates, GDP growth rates, and inflation rates that show the overall trends of the economy.

[0445] "Cleaning" is the process of detecting empty or outlier values ​​from acquired data and correcting or removing them.

[0446] "Normalization" is the process of converting information obtained from different data sources into a unified format.

[0447] "Generative AI" is a type of artificial intelligence that automatically generates new information and content based on large datasets.

[0448] A "dashboard" is an interface that allows users to access analysis results and reports and view visualized information.

[0449] An "emotion engine" is an algorithm or system that recognizes and analyzes emotions from a user's speech or text input.

[0450] "Real-time analysis" is a processing method that performs analysis immediately on collected data or user input and provides the results.

[0451] An "action plan" is a plan that proposes specific action guidelines and countermeasures based on analysis results and sentiment data.

[0452] Meeting minutes are documents that record the content of a meeting, the decisions made, and the proposed action plans, so that they can be referenced later.

[0453] A "physical store" is a sales facility located in a physical place, a store that customers can visit in person.

[0454] This invention is a system that collects market data and economic indicator data and supports the operation of physical stores through analysis using generative AI. This system recognizes user emotions in real time and proposes appropriate action plans. The series of functions for this purpose operate as follows:

[0455] Data acquisition and preprocessing

[0456] The server collects market and economic indicator data from external data sources. Specifically, the server retrieves information using API requests. The retrieved data is often received in JSON format. The server then cleans and normalizes the data. The cleaning process detects empty values ​​and outliers and either fills them in or removes them. The normalization process converts information from different data sources into a unified format.

[0457] Data analysis and report generation

[0458] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, generating the results in a report format. This report is created in a visual format, including graphs and charts. The analysis results are stored on a server and prepared for display on a dashboard. This dashboard includes an interface for users to view the report and initiate discussions or meetings.

[0459] Emotion recognition and argument support

[0460] During the meeting, users access the dashboard from their devices (e.g., smartphones or tablets) to enter questions and comments. The emotion engine recognizes emotions from the user's statements and text input. This emotion recognition works in conjunction with generative AI to generate real-time analysis and responses that correspond to the user's emotional state. The generated responses are immediately displayed on the dashboard to support the progress of the meeting.

[0461] Action plan generation and meeting minutes distribution

[0462] During the meeting, the server analyzes the discussion content, and the generative AI and emotion engine automatically generate a concrete action plan. This action plan includes specific measures that reflect market data and emotion data. For example, if user anxiety is detected, it will suggest reviewing inventory or rearranging staff. After the meeting ends, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes, which also include emotion data, are distributed to the user's device.

[0463] Examples of specific cases and prompt statements

[0464] As a concrete example, suppose a server calls an external API and retrieves economic indicator data in JSON format. This data is cleaned, and missing values ​​are imputed with the mean. A generative AI (e.g., GPT-3) analyzes the data using the "market data" and "sentiment analysis" results as prompts. The following is an example of such prompts:

[0465] Market data: Sales increased by 10% compared to the previous month. Demand for flagship products is increasing.

[0466] Sentiment analysis: Currently, many of the staff are showing positive motivation.

[0467] Please generate a meeting proposal based on the above.

[0468] This process enables the system to efficiently manage meetings by combining real-time analysis and emotion recognition, and allows for the development of flexible action plans that reflect the user's emotions.

[0469] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0470] Step 1: Data Acquisition

[0471] The server sends API requests to external data sources to retrieve market data and economic indicator data. Specifically, the server accesses the API endpoint via the internet and receives data in JSON format. The input is the API request, and the output is the retrieved market data and economic indicator data.

[0472] Step 2: Cleaning

[0473] The server cleans the received market and economic indicator data. The cleaning process detects and removes or imputes empty or outlier values. The input is the acquired market and economic indicator data, and the output is the cleaned data. For example, missing values ​​are imputed with the mean, and outliers are corrected to appropriate values.

[0474] Step 3: Normalize the data

[0475] The server normalizes the cleaned data. The normalization process converts information from different data sources into a unified format. The input is cleaned data, and the output is normalized data. For example, it converts numbers expressed in different units to a unified unit.

[0476] Step 4: Data Analysis

[0477] The server analyzes normalized data using generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in report format. The input is normalized data, and the output is a report containing the analysis results.

[0478] Step 5: Generate and save the report

[0479] The server generates and saves a report based on the analysis results. The report includes graphs and charts for visual representation. The input is the analysis results, and the output is the generated report. The report is stored on the server and accessible via the dashboard.

[0480] Step 6: Access the Dashboard

[0481] Users access the dashboard from their own devices (e.g., smartphones or tablets) and view the generated reports. Based on these reports, users can start roundtables or crew meetings. The input is the user's login information, and the output is the report display screen.

[0482] Step 7: Emotion Recognition

[0483] During the meeting, users enter questions and comments from their terminals into the dashboard. The server receives this information and uses an emotion engine to recognize emotions from the user's statements and text input. The input is the user's text input, and the output is the emotion recognition result.

[0484] Step 8: Real-time response generation

[0485] The server uses generative AI and an emotion engine to analyze user input and generate appropriate responses. The generated responses are immediately displayed on the dashboard. Input consists of emotion recognition results and user text input, while output is the generated response.

[0486] Step 9: Generate an action plan

[0487] The server analyzes the discussion content during the meeting and generates a concrete action plan using an emotion engine and generative AI. The action plan reflects market data and emotion data. The input is the meeting content and emotion recognition results, and the output is the concrete action plan.

[0488] Step 10: Generate and distribute meeting minutes.

[0489] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are then distributed to the user's terminal. The input consists of the meeting content and the generated action plan, while the output is the generated meeting minutes.

[0490] Example of a prompt

[0491] Market data: Sales increased by 10% compared to the previous month. Demand for flagship products is increasing.

[0492] Sentiment analysis: Currently, many of the staff are showing positive motivation.

[0493] Please generate a meeting proposal based on the above.

[0494] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0495] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0496] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0497] [Second Embodiment]

[0498] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0499] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0500] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0501] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0502] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0503] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0504] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0505] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0506] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0507] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0508] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0509] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0510] This invention relates to a system that collects market data and economic indicator data from external data sources, performs analysis using generative AI, and supports roundtable discussions and crew meetings based on the results. Embodiments of this system are described in detail below.

[0511] Data acquisition and preprocessing

[0512] server

[0513] The server collects market and economic indicator data from external data sources. Specifically, the server uses API requests to retrieve information from data providers. This data is received in formats such as JSON and XML.

[0514] The server then cleans and normalizes the acquired data. The cleaning process detects empty values ​​and outliers and corrects or removes them. The normalization process converts information from different data sources into a unified format.

[0515] Data analysis and report generation

[0516] server

[0517] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in a report format. This report is presented in a visual format, including graphs and charts.

[0518] The analysis results are saved on the server and prepared for display on the dashboard. This dashboard provides an interface for users to view reports and start roundtables or crew meetings.

[0519] Roundtable discussion / crew meeting

[0520] User

[0521] Users access a web-based dashboard from their own devices (PC, tablet, etc.). The dashboard displays reports generated by the server, which users use to initiate roundtables and crew meetings.

[0522] Real-time discussion support

[0523] server

[0524] During the meeting, users enter questions and comments from their devices into the dashboard. The server uses generative AI to analyze these inputs in real time and generate appropriate answers. The generated answers are immediately displayed on the dashboard, supporting the progress of the meeting.

[0525] Generating action items

[0526] server

[0527] By analyzing the content of the meeting discussion, the generative AI automatically generates specific action plans. For example, action plans such as "increase inventory" or "strengthen marketing campaigns" may be generated.

[0528] Minutes creation and distribution

[0529] server

[0530] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are then delivered to the user's device and shared with all meeting participants.

[0531] Specific example

[0532] 1. Data Collection: The server calls an external API to retrieve market data in JSON format.

[0533] 2. Data Cleaning: The server imputes missing values ​​with the mean and detects and corrects outliers.

[0534] 3. Data Analysis: Generative AI identifies market trends and compiles them into reports.

[0535] 4. Dashboard Access: Users access the web-based dashboard from their devices and begin the discussion.

[0536] 5. Real-time answer generation: The server analyzes the user's question, and the generation AI instantly generates and displays the answer.

[0537] 6. Action Plan Generation: During the meeting, a generative AI proposes the next action plan.

[0538] 7. Distribution of meeting minutes: After the meeting ends, the server automatically generates the meeting minutes and sends them to the user's terminal.

[0539] This invention makes it possible to conduct efficient meetings through real-time analysis, which was difficult to achieve with conventional methods, and to formulate highly responsive action plans.

[0540] The following describes the processing flow.

[0541] Step 1:

[0542] Calling an external API

[0543] The server sends requests to external APIs that provide market and economic indicator data. For example, it makes HTTP requests specifying a particular endpoint URL to retrieve the latest data.

[0544] Step 2:

[0545] Receiving API Responses

[0546] The server waits for responses from external APIs and receives data in formats such as JSON and XML. The received data is temporarily stored so that it can be used directly for analysis.

[0547] Step 3:

[0548] Data Cleaning

[0549] The server performs a cleaning process on the acquired data. Specifically, it detects empty values ​​and outliers and removes or imputes them. For example, if there are missing values, it imputes them with the average value of past data. Also, if outliers are found, it replaces them with appropriate values.

[0550] Step 4:

[0551] Data normalization

[0552] The server normalizes the cleaned data. It converts data obtained from different data sources into a unified format to maintain consistency. For example, it converts data in different time formats into a unified timestamp format.

[0553] Step 5:

[0554] Initialization of generative AI

[0555] The server initializes generative AI (e.g., GPT-3 or BERT). It loads the necessary models and parameters and prepares them for analysis.

[0556] Step 6:

[0557] Data input and analysis

[0558] The server feeds pre-processed data into the generative AI and begins analysis. The generative AI identifies market trends and risk factors and retrieves the results.

[0559] Step 7:

[0560] Report generation

[0561] The server generates a report based on the analysis results output by the generative AI. This report includes graphs and charts to visually represent the analysis results. It also explains the analysis results in text format and provides insights into the data.

[0562] Step 8:

[0563] Saving reports and displaying dashboards

[0564] The server stores the generated reports and prepares them for display on a dashboard accessible to the user. The dashboard provides a web-based interface, allowing users to view the reports.

[0565] Step 9:

[0566] Access to the dashboard

[0567] Users access the dashboard from their own devices (PC, tablet, etc.). Users can view generated reports and start roundtables or crew meetings.

[0568] Step 10:

[0569] Enter your questions and comments

[0570] During the meeting, users enter questions and comments from their devices into the dashboard. These entries are then sent to the server.

[0571] Step 11:

[0572] Real-time analysis and response generation

[0573] The server uses generative AI to analyze user questions and comments in real time. The AI ​​generates appropriate answers, which are then displayed on the dashboard.

[0574] Step 12:

[0575] Analysis of discussion content and generation of action plans

[0576] The server analyzes the content of the discussion during the meeting, and a generative AI automatically generates a concrete action plan. For example, it might make specific suggestions such as "strengthen the marketing campaign."

[0577] Step 13:

[0578] Minutes generation

[0579] The server automatically generates meeting minutes based on the meeting content and the generated action plan. The minutes record important items and decisions discussed during the meeting.

[0580] Step 14:

[0581] Distribution of meeting minutes

[0582] After the meeting ends, the server distributes the generated meeting minutes to the users' terminals. This ensures that all meeting participants receive the minutes, facilitating smooth information sharing.

[0583] (Example 1)

[0584] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0585] There is a need for a system that efficiently collects and analyzes market data and economic indicator data, and then uses the results to support meetings in real time. Conventional systems struggled to provide necessary information immediately because cleaning and analyzing large amounts of data was time-consuming. Furthermore, they were unable to smoothly generate appropriate answers to real-time questions and comments during meetings, or automatically generate meeting minutes after meetings.

[0586] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0587] In this invention, the server includes means for acquiring market data and economic indicator data from external data sources; means for cleaning and normalizing the acquired data; means for detecting, correcting, or removing empty values ​​and outliers; means for analyzing the data using generative artificial intelligence to identify market trends and risk factors; means for generating reports based on the analysis results, selecting templates for visual representation, inserting graphs and charts, and saving them; means for users to access the generated reports via a terminal and start a roundtable discussion or meeting; means for analyzing user questions and comments in real time and generating and displaying appropriate answers; means for analyzing meeting content and generating concrete action plans; and means for distributing the generated action plans and meeting minutes to users. This makes it possible to streamline the entire process from data collection to analysis and meeting support.

[0588] "External data sources" refer to external sources of information that provide market data and economic indicator data.

[0589] "Market data" refers to data related to market trends, such as stock prices, trading volume, and exchange rates.

[0590] "Economic indicator data" refers to numerical values ​​that show the state of the economy, such as GDP, unemployment rate, and price index.

[0591] "Generative artificial intelligence" refers to AI models that perform data analysis and information generation in response to given input.

[0592] "Cleaning" refers to the process of detecting empty or outlier values ​​from acquired data and correcting or removing them.

[0593] "Normalization" is the process of converting information obtained from different data sources into a unified format.

[0594] A "prompt statement" is an input statement used to instruct a generative artificial intelligence system to perform analysis or generate information.

[0595] A "report" is a document that summarizes the results of an analysis.

[0596] A "visual representation template" is a template for representing a report in a visual format, such as graphs or charts.

[0597] A "dashboard" is an interface that allows users to view reports and start discussion groups or meetings.

[0598] "Real-time responses" refer to answers that are generated and displayed instantly in response to user questions and comments.

[0599] An "action plan" is a specific plan of action that is generated based on the discussions held at a meeting.

[0600] "Meeting minutes" are documents that record the content and decisions made at a meeting.

[0601] This invention relates to a system that collects market data and economic indicator data from external data sources, analyzes them using generative artificial intelligence, and supports roundtables and meetings based on the results. This system can be implemented using the following hardware and software.

[0602] Data acquisition and preprocessing

[0603] The server collects market data and economic indicator data from external data sources. Specifically, the server calls external APIs (e.g., market data APIs) to retrieve the latest market data in JSON format.

[0604] The server cleans the retrieved data by detecting empty values, imputing them with the median, and detecting and correcting outliers. The Pandas library (Python) is used for dataframe manipulation during the cleaning process.

[0605] The server normalizes the data, converting information from different data sources into a unified format. For example, it converts all price data to USD units.

[0606] Data analysis and report generation

[0607] The server uses the cleaned and normalized data to perform analysis using generative artificial intelligence (e.g., GPT-3 or BERT).

[0608] The server formats the input data for the generative artificial intelligence and generates prompt sentences. For example, it can generate a prompt sentence such as, "Based on the latest NASDAQ data, please explain the market trends and risk factors."

[0609] Generative artificial intelligence identifies market trends and potential risk factors and generates reports. These reports are presented in a visual format, including graphs and charts.

[0610] Report display and dashboard preparation

[0611] The server saves the generated report and prepares it for display on the dashboard. Specifically, it converts the report to HTML format and adds code to visually display graphs and charts.

[0612] The dashboard provides an interface for users to view reports and start roundtables and meetings.

[0613] Access to the dashboard

[0614] Users access the dashboard using a web browser from their own device (PC, tablet, etc.). The device performs user authentication and verifies the user's access permissions.

[0615] The terminal receives report data sent from the server and displays it on the browser screen.

[0616] Real-time discussion support

[0617] Users enter questions and comments on the dashboard from their devices during the meeting. The devices then send the user input data to the server.

[0618] The server receives this input data and uses generative artificial intelligence to analyze it in real time. For example, the server sends the prompt "What are the causes of recent market fluctuations?" to the generative AI and immediately generates an answer. The generative AI generates the answer "Recent market fluctuations are mainly due to the influence of economic conditions."

[0619] The server displays the generated responses on the dashboard.

[0620] Generating action items

[0621] The server analyzes the meeting discussions and uses generative artificial intelligence to automatically generate concrete action plans. For example, the server sends the prompt "Please propose the next action plan" to the generative AI. The generative AI then generates specific action items such as "Increase inventory" or "Develop a new marketing strategy."

[0622] The server displays the generated action items on the dashboard.

[0623] Minutes creation and distribution

[0624] After the meeting ends, the server automatically generates meeting minutes based on the meeting content and the generated action plan. The minutes are generated in text format and converted to PDF format.

[0625] The server sends the generated meeting minutes to the user's terminal. For example, the server might send the minutes as an email attachment or make them available for download on the dashboard.

[0626] Specific example

[0627] 1. Data Collection: The server calls an external API to retrieve NASDAQ market data in JSON format.

[0628] 2. Data Cleaning: The server imputes empty values ​​with the median and corrects outliers to within ±3 standard deviations.

[0629] 3. Data Analysis: Generative artificial intelligence (GPT-3) identifies the latest market trends and compiles them into a report.

[0630] 4. Dashboard Access: Users access the dashboard from their device using a web browser (e.g., Google Chrome browser) and start the discussion.

[0631] 5. Real-time answer generation: The server analyzes the user's question, "What are the causes of recent market fluctuations?", and the generative artificial intelligence (BERT) instantly generates and displays the answer.

[0632] 6. Action Plan Generation: During the meeting, the generative artificial intelligence proposes an action plan such as "Strengthen the sales strategy for Q2."

[0633] 7. Distribution of meeting minutes: After the meeting, the server automatically generates meeting minutes and sends them to the user's device in PDF format. The minutes include the discussion content and action plan.

[0634] Example of a prompt:

[0635] 1. "Based on the latest NASDAQ data, please explain the market trends and risk factors."

[0636] 2. "Generate appropriate answers to the question regarding the causes of recent market fluctuations."

[0637] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0638] Step 1: Data Collection

[0639] The server retrieves market data and economic indicator data from external data sources. Specifically, the server calls a market data API to obtain the latest market data in JSON format.

[0640] Input: Market Data API endpoint

[0641] Data processing: Send an API request and save the retrieved market data in JSON format.

[0642] Output: Acquired market data in JSON format

[0643] Step 2: Data Cleaning

[0644] The server cleans the acquired data. Specifically, it detects empty values, imputes them with the median, and detects and corrects outliers.

[0645] Input: Market data in JSON format

[0646] Data processing: Create a dataframe using the Pandas library, impute empty values ​​with the median, and detect and correct outliers.

[0647] Output: Cleaned data frame

[0648] Step 3: Data Normalization

[0649] The server performs data normalization. Specifically, it converts information from different data sources into a unified format.

[0650] Input: Cleaned dataframe

[0651] Data processing: Convert all price data to USD units.

[0652] Output: Normalized data frame

[0653] Step 4: Data Analysis

[0654] The server analyzes the data using generative artificial intelligence. Specifically, it sends a prompt message to the generative AI, and the AI ​​model begins the analysis.

[0655] Input: Normalized data frame, prompt: "Based on the latest NASDAQ data, describe market trends and risk factors."

[0656] Data processing: A prompt message is sent to a generative artificial intelligence (e.g., GPT-3), and the analysis results are received.

[0657] Output: Analysis results including market trends and risk factors

[0658] Step 5: Report Generation

[0659] The server generates a report based on the analysis results. Specifically, it selects a template for visual representation, inserts graphs and charts, and saves the report.

[0660] Input: Analysis results

[0661] Data processing: Generate an HTML report based on the analysis results and insert graphs and charts.

[0662] Output: Generated report (HTML format)

[0663] Step 6: Prepare the dashboard

[0664] The server prepares the generated report for display on the dashboard.

[0665] Input: Generated report (HTML format)

[0666] Data processing: Save reports to a database and make them accessible on the dashboard.

[0667] Output: Reports that can be displayed on the dashboard

[0668] Step 7: Accessing the Dashboard

[0669] Users access the dashboard from their own devices (PC, tablet, etc.).

[0670] Input: User authentication information

[0671] Data processing: The terminal receives report data sent from the server and displays it on the browser screen.

[0672] Output: Report displayed in the browser

[0673] Step 8: Real-time discussion support

[0674] Users enter questions and comments from their devices into a dashboard during the meeting. The server receives this input data and performs real-time analysis using generative artificial intelligence.

[0675] Input: User questions and comments

[0676] Data processing: The prompt "What are the causes of recent market fluctuations?" is sent to a generative AI system, and the answer is generated and displayed.

[0677] Output: Real-time responses generated

[0678] Step 9: Generate action items

[0679] The server analyzes the meeting's discussion content and automatically generates a concrete action plan. For example, it might send a prompt to the generative AI saying, "Please propose the next action plan."

[0680] Input: Discussion log data

[0681] Data processing: Generate specific action items based on generative artificial intelligence.

[0682] Output: Generated action items

[0683] Step 10: Generate and distribute meeting minutes.

[0684] After the meeting ends, the server automatically generates meeting minutes based on the meeting content and the generated action plan, and sends them to the user's terminal.

[0685] Input: Meeting content, action plan

[0686] Data processing: Convert meeting minutes to PDF format and send them to users via email.

[0687] Output: Meeting minutes sent to the user's device (PDF format)

[0688] (Application Example 1)

[0689] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0690] In today's markets, rapid and accurate decision-making is essential, but data collection, cleaning, and analysis are time-consuming and labor-intensive, making efficient operation difficult. Furthermore, the inability to provide timely and appropriate information and answers during meetings and discussions is a significant challenge.

[0691] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0692] In this invention, the server includes means for acquiring market data and economic indicator data from external data sources, means for cleaning and normalizing the acquired data, means for analyzing the data using generative AI to identify market trends and risk factors, means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start a roundtable discussion or crew meeting, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, means for analyzing meeting content and generating concrete action plans, means for distributing the generated action plans and meeting minutes to users, means for displaying graphs and charts that visually represent the analysis results, and means for collecting and analyzing market data, competitor information, and customer behavior data to support strategic planning for virtual store operations. This enables efficient and rapid decision-making and supports optimal strategic planning in real time for virtual store operations.

[0693] "External data sources" refer to external data providers or APIs that provide market data and economic indicator data.

[0694] "Market data" refers to data that includes information such as price, supply, and demand related to a specific market.

[0695] "Economic indicator data" refers to data that includes statistical information indicating the state of the economy, such as GDP, unemployment rate, and inflation rate.

[0696] "Cleaning" is the process of correcting or removing inappropriate or missing values ​​from data.

[0697] "Normalization" is the process of converting data obtained from different data sources into a unified format.

[0698] "Generative AI" is artificial intelligence that analyzes collected data and generates text to perform a specific task.

[0699] "Market trends" refer to information that indicates the fluctuation patterns of prices and demand in the market.

[0700] "Risk factors" refer to elements or events that could have a negative impact on the market or economy.

[0701] A "report" is a document that summarizes the results of an analysis and may include graphs and charts.

[0702] A "dashboard" is a web-based interface that allows users to access analysis results and reports.

[0703] A "roundtable discussion" refers to a small-scale discussion held in a meeting format.

[0704] A "crew meeting" refers to a meeting held to discuss a specific project or issue.

[0705] "Real-time" refers to data processing and information provision at the present moment.

[0706] An "action plan" is a specific plan of actions taken to achieve a particular challenge or objective.

[0707] "Meeting minutes" are documents that record the content discussed and decisions made during a meeting.

[0708] "Competitive information" refers to information about the activities and strategies of other competing companies in the market.

[0709] "Customer behavior data" refers to information about how customers used products and services.

[0710] This invention is a system that supports the operation of virtual stores by collecting market data and economic indicator data from external data sources and performing analysis using generative AI. A detailed embodiment for carrying out this invention is described below.

[0711] Data acquisition and preprocessing

[0712] server

[0713] The server collects market data, economic indicators, competitive information, and customer behavior data from external data sources. Specifically, the server retrieves this information using API requests. This data is received in formats such as JSON and XML. The server then cleans and normalizes the retrieved data. The cleaning process detects empty values ​​and outliers and corrects or removes them. The normalization process converts information from different data sources into a unified format.

[0714] Data analysis and report generation

[0715] server

[0716] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in a report format. This report is created in a visual format, including graphs and charts. The analysis results are stored on a server and prepared for display on a dashboard accessible to users. The dashboard is browser-based, and users can access it from PCs, tablets, smartphones, etc.

[0717] Roundtable discussion / crew meeting

[0718] User

[0719] Users access a web-based dashboard from their devices. The dashboard displays reports generated by the server, which users can use to initiate roundtables and crew meetings.

[0720] Real-time discussion support

[0721] server

[0722] During the meeting, users enter questions and comments from their devices into the dashboard. The server uses generative AI to analyze these inputs in real time and generate appropriate answers. The generated answers are immediately displayed on the dashboard, supporting the progress of the meeting.

[0723] Generating action items

[0724] server

[0725] By analyzing the content of the meeting discussion, the generative AI automatically generates specific action plans. For example, action plans such as "increase inventory" or "strengthen marketing campaigns" may be generated.

[0726] Minutes creation and distribution

[0727] server

[0728] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are then delivered to the user's device and shared with all meeting participants.

[0729] Specific example

[0730] The server calls an external API to retrieve market data in JSON format. The server imputes missing values ​​with averages and detects and corrects outliers. Generative AI identifies market trends and compiles them into a report. The user accesses a web-based dashboard from their terminal and starts a roundtable discussion. The server analyzes the user's questions, and the generative AI instantly generates and displays answers. During the meeting, the generative AI proposes the next action plan. After the meeting ends, the server automatically generates meeting minutes and sends them to the user's terminal.

[0731] Example of a prompt

[0732] Identify trends and risks from the following market data:

[0733] Data: [{'product': 'A', 'price': 100, 'demand': 200}, {'product': 'B', 'price': 150, 'demand': 180}]"

[0734] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0735] Step 1:

[0736] Data collection

[0737] The server retrieves market data, economic indicators, competitive information, and customer behavior data from external data sources via API requests. The server accesses a specified API endpoint and receives data in JSON or XML format. The input is the API request, and the output is the retrieved data in JSON or XML format as a response.

[0738] Step 2:

[0739] Data cleaning and normalization

[0740] The server cleans and normalizes the received data. Data cleaning detects empty values ​​and outliers and corrects or removes them based on statistical methods. Specifically, it imputes missing values ​​with the mean and detects and corrects outliers. The normalization process converts information from different data sources into a unified format. The input is the acquired data, and the output is the cleaned and normalized data.

[0741] Step 3:

[0742] Data Analysis

[0743] The server analyzes the cleaned and normalized data using generative AI (e.g., GPT-3 or BERT). Specifically, it generates prompt sentences suitable for analysis and inputs them into the generative AI. Based on these prompt sentences, the AI ​​identifies market trends and risk factors and returns the analysis results. The input consists of the cleaned and normalized data and prompt sentences, and the output is the analysis results.

[0744] Step 4:

[0745] Report generation

[0746] The server generates a report based on the analysis results. The report includes market trends and risk factors, as well as graphs and charts for visual clarity. The generated report is saved in formats such as HTML and PDF. The input is the analysis results, and the output is the generated report.

[0747] Step 5:

[0748] Dashboard display

[0749] Users access a web-based dashboard from their devices. The server displays the generated reports on the dashboard. Users can view the reports through the dashboard and start roundtables or crew meetings. The input is the generated reports, and the output is the dashboard displaying the reports.

[0750] Step 6:

[0751] Real-time Q&A

[0752] During a meeting, users input questions and comments from their devices into a dashboard. The server uses generative AI to analyze these inputs in real time and generate appropriate answers. The generated answers are displayed on the dashboard to support the progress of the meeting. The input consists of user questions and comments, and the output consists of the generated answers.

[0753] Step 7:

[0754] Action plan generation

[0755] The server analyzes the meeting discussions, and the generative AI automatically generates specific action plans. These plans may include concrete suggestions such as "increase inventory" or "strengthen marketing campaigns." The input is the meeting discussion content, and the output is the generated action plan.

[0756] Step 8:

[0757] Minutes generation and distribution

[0758] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are converted to PDF format or another format and delivered to the user's device. The input is the meeting discussion content and the generated action plan, and the output is the automatically generated meeting minutes.

[0759] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0760] This invention combines a system that collects market data and economic indicator data from external data sources, performs analysis using generative AI, and supports roundtable discussions and crew meetings based on the results, with an emotion engine that recognizes user emotions. The embodiments of this system are described in detail below.

[0761] Data acquisition and preprocessing

[0762] server

[0763] The server collects market and economic indicator data from external data sources. Specifically, the server retrieves information from data providers using API requests. This data is received in formats such as JSON and XML. The server then cleans and normalizes the retrieved data. The cleaning process detects empty values ​​and outliers and removes or fills them in. The normalization process converts information from different data sources into a unified format.

[0764] Data analysis and report generation

[0765] server

[0766] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in report format. This report is created in a visual format, including graphs and charts. The analysis results are stored on a server and prepared for display on a dashboard. This dashboard provides an interface for users to view reports and initiate roundtables and crew meetings.

[0767] Roundtable discussion / crew meeting

[0768] User

[0769] Users access a web-based dashboard from their own devices (PC, tablet, etc.). The dashboard displays reports generated by the server, which users use to initiate roundtables and crew meetings.

[0770] Emotion recognition and real-time discussion support

[0771] server

[0772] During the meeting, users enter questions and comments from their devices into a dashboard. In addition, an emotion engine operates to recognize emotions from user speech and text input. The server uses generative AI and the emotion engine to analyze these inputs in real time and generate appropriate responses. The generated responses are immediately displayed on the dashboard to support the progress of the meeting.

[0773] Analysis of discussion content and generation of action plans

[0774] server

[0775] By analyzing the content of discussions during meetings, the generative AI and emotion engine automatically generate specific action plans. For example, it proposes action plans that reflect emotional data, such as "If user anxiety is detected, review risk management measures."

[0776] Minutes creation and distribution

[0777] server

[0778] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes also include user sentiment data recognized by the sentiment engine. For example, changes in emotions during discussions and the tone of the meeting are reflected in the minutes. The generated minutes are delivered to the user's device and shared with all meeting participants.

[0779] Specific example

[0780] 1. Data Collection: The server calls an external API to retrieve market data in JSON format.

[0781] 2. Data Cleaning: The server imputes missing values ​​with the mean and detects and corrects outliers.

[0782] 3. Data Analysis: Generative AI identifies market trends and compiles them into reports.

[0783] 4. Dashboard Access: Users access the web-based dashboard from their devices and begin the discussion.

[0784] 5. Emotion Recognition: The emotion engine recognizes emotions from the user's speech and text input.

[0785] 6. Real-time response generation: The server analyzes the user's question, and the generative AI and emotion engine instantly generate and display the response.

[0786] 7. Action Plan Generation: During the meeting, generate a concrete action plan based on emotional expression.

[0787] 8. Distribution of meeting minutes: After the meeting ends, the server automatically generates meeting minutes, including sentiment data, and sends them to the user's device.

[0788] This invention makes it possible to conduct efficient meetings through real-time analysis, which was difficult to achieve with conventional methods, and to formulate flexible action plans that reflect user sentiment data.

[0789] The following describes the processing flow.

[0790] Step 1:

[0791] Calling an external API

[0792] The server retrieves the latest data by sending HTTP requests to external APIs that provide market and economic indicator data. Specifically, it makes requests using API endpoint URLs and receives data in JSON or XML format.

[0793] Step 2:

[0794] Receiving API Responses

[0795] The server receives a response from an external API and temporarily stores the retrieved data. The stored data is then used in the next processing step.

[0796] Step 3:

[0797] Data Cleaning

[0798] The server cleans the acquired data. Specifically, it detects empty values ​​and outliers in the data and removes or imputes them. For example, missing values ​​are imputed with the mean of past data, and outliers are replaced with appropriate values.

[0799] Step 4:

[0800] Data normalization

[0801] The server normalizes the cleaned data. Specifically, it converts data obtained from different data sources into a unified format to maintain consistency. For example, it converts data in different time formats into a common timestamp format.

[0802] Step 5:

[0803] Initialization of generative AI

[0804] The server initializes generative AI (such as GPT-3 or BERT). It loads the necessary models and parameters and prepares the data for analysis.

[0805] Step 6:

[0806] Data input and analysis

[0807] The server feeds the pre-processed data into the generative AI and begins data analysis. The generative AI identifies market trends and risk factors and generates analysis results based on them.

[0808] Step 7:

[0809] Report generation

[0810] The server generates a report based on the analysis results obtained from the generative AI. This report includes text explanations of the analysis results, as well as graphs and charts. The information is presented in a visually easy-to-understand format.

[0811] Step 8:

[0812] Saving reports and displaying dashboards

[0813] The server stores the generated reports in a database and displays them on a dashboard for user access. The dashboard is provided via a web-based interface.

[0814] Step 9:

[0815] Access to the dashboard

[0816] Users access the dashboard from their own devices (PC, tablet, etc.) and view the generated reports. Based on these reports, users can then initiate roundtable discussions or crew meetings.

[0817] Step 10:

[0818] emotion recognition

[0819] The server uses an emotion engine to recognize emotions from user statements and text input. It analyzes specific keywords and expressions to determine the user's emotional state.

[0820] Step 11:

[0821] Real-time analysis and response generation

[0822] The server analyzes user questions and comments in real time and generates appropriate responses using generative AI and an emotion engine. For example, if a user expresses anxiety, the server analyzes it and generates a reassuring response.

[0823] Step 12:

[0824] Display the answer

[0825] The server displays the generated responses on a dashboard and provides them to users in real time, ensuring a smooth flow of the meeting.

[0826] Step 13:

[0827] Analysis of discussion content and generation of action plans

[0828] The server uses an emotion engine and generative AI to analyze the content of discussions during meetings and automatically generates concrete action plans. For example, it proposes an action plan that reflects the emotions expressed by the user.

[0829] Step 14:

[0830] Minutes generation

[0831] The server automatically generates meeting minutes based on the meeting content, the generated action plan, and the user's emotional state as recognized by the emotion engine.

[0832] Step 15:

[0833] Distribution of meeting minutes

[0834] After the meeting ends, the server distributes the generated meeting minutes to each user's device. This ensures that all meeting participants receive the minutes, facilitating smooth information sharing.

[0835] This system enables efficient collection and analysis of precise information from external data sources, real-time meeting support that takes user sentiment into consideration, and the development of concrete action plans.

[0836] (Example 2)

[0837] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0838] Conventional meeting systems have made it difficult to perform real-time data analysis and generate flexible action plans that reflect user sentiment. Furthermore, efficient analysis of meeting content, automatic generation of concrete action plans based on that analysis, and rapid distribution of meeting minutes to all participants have been challenging. This invention aims to solve these problems and provide a system that streamlines and enhances meeting management.

[0839] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0840] In this invention, the server includes means for acquiring market data and economic indicator data from external data sources, means for cleaning and normalizing the acquired data, means for analyzing the data using generative AI to identify market trends and risk factors, means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start a roundtable discussion or crew meeting, means for recognizing emotions from user statements and text inputs, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, means for analyzing meeting content and generating concrete action plans that reflect user emotion data, and means for automatically generating meeting minutes based on the meeting content and generated action plans and distributing them to users. This enables the generation of flexible action plans through real-time data analysis and emotion recognition, as well as rapid analysis of meeting content and automatic generation and distribution of meeting minutes.

[0841] "External data sources" refer to external information providers, APIs, and other entities that provide market data and economic indicator data.

[0842] "Market data" refers to data related to financial markets, such as stock prices, exchange rates, and commodity prices.

[0843] "Economic indicator data" refers to statistical data that shows the state of the economy, such as GDP, unemployment rate, and consumer price index.

[0844] "Cleaning" refers to the process of detecting, correcting, or removing empty or outlier values ​​in data.

[0845] "Normalization" refers to the process of converting data obtained from different data sources into a unified format.

[0846] "Generative AI" refers to artificial intelligence models that perform tasks such as data analysis and natural language generation (e.g., GPT-3, BERT, etc.).

[0847] "Market trends" refer to the temporal movements and fluctuation patterns of market data.

[0848] "Risk factors" refer to elements that could have a negative impact on markets or economic activity.

[0849] A "report" refers to a document or report that summarizes the results of an analysis.

[0850] A "dashboard" refers to a web-based interface that allows users to access and interact with analytical results and reports.

[0851] A "roundtable discussion" refers to a type of meeting where participants freely exchange opinions on a specific topic.

[0852] A "crew meeting" refers to a meeting held within a specific team or organization.

[0853] "Means of recognizing emotions" refers to algorithms and engines that identify emotions from user statements and text input.

[0854] "Means of real-time analysis" refers to the ability to instantly analyze input data and immediately generate and display results.

[0855] An "action plan" refers to a specific plan of action or measures.

[0856] "Meeting minutes" refers to a document that records the content of a meeting, the matters discussed, the decisions made, and the action plan.

[0857] This invention combines a system that collects market data and economic indicator data from external data sources, performs analysis using generative AI, and supports roundtable discussions and crew meetings based on the results, with an emotion engine that recognizes user emotions. The embodiments of this system are described in detail below.

[0858] The server uses API requests to retrieve market data and economic indicator data from external data sources. Specifically, the server accesses a URL like "https: / / api.example.com / marketdata" and receives the data in JSON format.

[0859] Next, the server cleans and normalizes the received data. Data cleaning involves imputing missing values ​​with the mean and detecting and correcting outliers. This is done using libraries such as Python's pandas library.

[0860] Cleaned and normalized data is analyzed by generative AI models (e.g., GPT-3, BERT, etc.). The server inputs this data into the generative AI to identify market trends and risk factors. The information obtained from the analysis is generated and saved as a report in a visual format (graphs, charts, etc.).

[0861] The analysis results are displayed on a dashboard. This uses web frameworks such as Python's Flask or Django, and is provided as a web-based interface accessible to users. Users access this dashboard from their devices and start roundtables or crew meetings based on the generated reports.

[0862] During the meeting, users enter questions and comments from their devices onto the dashboard. The emotion engine recognizes emotions from the user's statements and text input. For example, if a user enters "What do you think about the current market?", the emotion engine recognizes "anxiety," and the generative AI immediately generates and displays the response, "The market is highly volatile, so caution is needed."

[0863] The meeting content is analyzed in real time, and specific action plans are generated that reflect the user's emotional data. For example, the emotional engine analyzes statements such as "the risk is too high," and the generative AI generates an action plan such as "propose reviewing risk management measures."

[0864] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes also include sentiment data recognized by the sentiment engine, detailing specific points such as "proposed a review of risk management measures." The generated minutes are then delivered to the user's device and shared with all meeting participants.

[0865] This invention enables efficient meeting management through real-time analysis, which was difficult to achieve with conventional methods, and the development of flexible action plans that reflect user sentiment data. An example of a prompt is "Please tell me about future market trends." By entering this prompt, a generative AI can analyze it and provide a specific answer in real time.

[0866] The above details the specific method of the present invention. This system not only dramatically improves the efficiency of business meetings and analysis, but also contributes to an improved user experience.

[0867] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0868] Step 1: Data Collection

[0869] server

[0870] The server sends API requests to external data sources to retrieve market data and economic indicator data. For example, the server accesses a URL like "https: / / api.example.com / marketdata" and receives data in JSON format.

[0871] Input-based action: Request to an external API.

[0872] Output: Acquired market data and economic indicator data.

[0873] Step 2: Data Preprocessing

[0874] server

[0875] The server cleans and normalizes the data it receives. Data cleaning involves imputing missing values ​​with the mean and detecting and correcting outliers. Normalization converts data obtained from different data sources into a unified format.

[0876] Input-based operation: Cleaning and normalizing incoming data.

[0877] Output: Cleaned and normalized data.

[0878] Step 3: Data Analysis

[0879] server

[0880] The cleaned and normalized data is input into a generative AI for analysis. For example, the server supplies data to a generative AI model (e.g., GPT-3) to identify market trends and risk factors.

[0881] Input-based operation: Data input to a generative AI model.

[0882] Output: Analysis results identifying market trends and risk factors.

[0883] Step 4: Prepare to generate reports and display dashboards.

[0884] server

[0885] Based on the analysis results, a visual report is generated. The server uses web frameworks such as Python's Flask or Django to prepare the report in HTML format for display on the dashboard.

[0886] Input-based operation: Generates visual reports and HTML using analysis results.

[0887] Output: HTML for visual reports and dashboards.

[0888] Step 5: Access the Dashboard

[0889] User

[0890] Users access a web-based dashboard from their devices and initiate roundtables or crew meetings based on the displayed analytics reports.

[0891] Input-based action: User accesses the dashboard via browser.

[0892] Output: Analysis report displayed on the dashboard.

[0893] Step 6: Emotion Recognition and Real-Time Discussion Support

[0894] server

[0895] During a meeting, users enter questions and comments from their devices onto a dashboard. The server uses an emotion engine to recognize the user's emotions from these inputs. It then works in conjunction with generative AI to generate and display appropriate answers in real time. For example, if a user enters "What do you think about the current market?", the server's emotion engine recognizes the user's anxiety, and the generative AI instantly generates an answer regarding market fluctuations.

[0896] Input-based operation: Sentiment recognition and response generation based on user input.

[0897] Output: Real-time responses displayed on the dashboard.

[0898] Step 7: Generate an action plan

[0899] server

[0900] The system analyzes meeting content in real time and generates concrete action plans that reflect user sentiment data. For example, the sentiment engine analyzes statements such as "the risk is too high," and the generative AI proposes a revision of risk management measures.

[0901] Input-based actions: Analysis of meeting content and sentiment data.

[0902] Output: A concrete action plan.

[0903] Step 8: Generate and distribute meeting minutes

[0904] server

[0905] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes, which include sentiment data, are delivered to the user's device.

[0906] Input-based operation: Generate meeting minutes based on meeting content and action plan.

[0907] Output: Meeting minutes distributed to users.

[0908] The above outlines the processing steps of this system and the specific operational details of each step. This enables efficient and flexible meeting management through real-time analysis and emotion recognition.

[0909] (Application Example 2)

[0910] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0911] Conventional meeting support systems do not adequately support real-time discussions using market and economic indicator data. Furthermore, they struggle to recognize user emotions and generate effective action plans based on them. In addition, there is a lack of means to conduct meetings and make decisions in a way that takes staff emotions into consideration in the operation of physical stores.

[0912] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for acquiring market data and economic indicator data from an external data source, means for cleaning and normalizing the acquired data, means for analyzing the data using generative AI to identify market trends and risk factors, means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start a roundtable discussion or crew meeting, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, means for analyzing meeting content and generating a concrete action plan, means for distributing the generated action plan and meeting minutes to the user, means for analyzing the emotional state of store staff using market data and sentiment data and proposing an appropriate action plan, and means for conducting a meeting based on emotional state and market data through generative AI. This enables efficient meeting management through real-time analysis and the formulation of flexible action plans that reflect sentiment data.

[0913] "External data sources" refer to sources of information used to collect market data and economic indicator data from outside the system, such as the internet or third-party APIs.

[0914] "Market data" refers to statistical information related to a specific market, such as product sales, price trends, and consumer demand.

[0915] "Economic indicator data" refers to statistical information such as unemployment rates, GDP growth rates, and inflation rates that show the overall trends of the economy.

[0916] "Cleaning" is the process of detecting empty or outlier values ​​from acquired data and correcting or removing them.

[0917] "Normalization" is the process of converting information obtained from different data sources into a unified format.

[0918] "Generative AI" is a type of artificial intelligence that automatically generates new information and content based on large datasets.

[0919] A "dashboard" is an interface that allows users to access analysis results and reports and view visualized information.

[0920] An "emotion engine" is an algorithm or system that recognizes and analyzes emotions from a user's speech or text input.

[0921] "Real-time analysis" is a processing method that performs analysis immediately on collected data or user input and provides the results.

[0922] An "action plan" is a plan that proposes specific action guidelines and countermeasures based on analysis results and sentiment data.

[0923] Meeting minutes are documents that record the content of a meeting, the decisions made, and the proposed action plans, so that they can be referenced later.

[0924] A "physical store" is a sales facility located in a physical place, a store that customers can visit in person.

[0925] This invention is a system that collects market data and economic indicator data and supports the operation of physical stores through analysis using generative AI. This system recognizes user emotions in real time and proposes appropriate action plans. The series of functions for this purpose operate as follows:

[0926] Data acquisition and preprocessing

[0927] The server collects market and economic indicator data from external data sources. Specifically, the server retrieves information using API requests. The retrieved data is often received in JSON format. The server then cleans and normalizes the data. The cleaning process detects empty values ​​and outliers and either fills them in or removes them. The normalization process converts information from different data sources into a unified format.

[0928] Data analysis and report generation

[0929] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, generating the results in a report format. This report is created in a visual format, including graphs and charts. The analysis results are stored on a server and prepared for display on a dashboard. This dashboard includes an interface for users to view the report and initiate discussions or meetings.

[0930] Emotion recognition and argument support

[0931] During the meeting, users access the dashboard from their devices (e.g., smartphones or tablets) to enter questions and comments. The emotion engine recognizes emotions from the user's statements and text input. This emotion recognition works in conjunction with generative AI to generate real-time analysis and responses that correspond to the user's emotional state. The generated responses are immediately displayed on the dashboard to support the progress of the meeting.

[0932] Action plan generation and meeting minutes distribution

[0933] During the meeting, the server analyzes the discussion content, and the generative AI and emotion engine automatically generate a concrete action plan. This action plan includes specific measures that reflect market data and emotion data. For example, if user anxiety is detected, it will suggest reviewing inventory or rearranging staff. After the meeting ends, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes, which also include emotion data, are distributed to the user's device.

[0934] Examples of specific cases and prompt statements

[0935] As a concrete example, suppose a server calls an external API and retrieves economic indicator data in JSON format. This data is cleaned, and missing values ​​are imputed with the mean. A generative AI (e.g., GPT-3) analyzes the data using the "market data" and "sentiment analysis" results as prompts. The following is an example of such prompts:

[0936] Market data: Sales increased by 10% compared to the previous month. Demand for flagship products is increasing.

[0937] Sentiment analysis: Currently, many of the staff are showing positive motivation.

[0938] Please generate a meeting proposal based on the above.

[0939] This process enables the system to efficiently manage meetings by combining real-time analysis and emotion recognition, and allows for the development of flexible action plans that reflect the user's emotions.

[0940] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0941] Step 1: Data Acquisition

[0942] The server sends API requests to external data sources to retrieve market data and economic indicator data. Specifically, the server accesses the API endpoint via the internet and receives data in JSON format. The input is the API request, and the output is the retrieved market data and economic indicator data.

[0943] Step 2: Cleaning

[0944] The server cleans the received market and economic indicator data. The cleaning process detects and removes or imputes empty or outlier values. The input is the acquired market and economic indicator data, and the output is the cleaned data. For example, missing values ​​are imputed with the mean, and outliers are corrected to appropriate values.

[0945] Step 3: Normalize the data

[0946] The server normalizes the cleaned data. The normalization process converts information from different data sources into a unified format. The input is cleaned data, and the output is normalized data. For example, it converts numbers expressed in different units to a unified unit.

[0947] Step 4: Data Analysis

[0948] The server analyzes normalized data using generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in report format. The input is normalized data, and the output is a report containing the analysis results.

[0949] Step 5: Generate and save the report

[0950] The server generates and saves a report based on the analysis results. The report includes graphs and charts for visual representation. The input is the analysis results, and the output is the generated report. The report is stored on the server and accessible via the dashboard.

[0951] Step 6: Access the Dashboard

[0952] Users access the dashboard from their own devices (e.g., smartphones or tablets) and view the generated reports. Based on these reports, users can start roundtables or crew meetings. The input is the user's login information, and the output is the report display screen.

[0953] Step 7: Emotion Recognition

[0954] During the meeting, users enter questions and comments from their terminals into the dashboard. The server receives this information and uses an emotion engine to recognize emotions from the user's statements and text input. The input is the user's text input, and the output is the emotion recognition result.

[0955] Step 8: Real-time response generation

[0956] The server uses generative AI and an emotion engine to analyze user input and generate appropriate responses. The generated responses are immediately displayed on the dashboard. Input consists of emotion recognition results and user text input, while output is the generated response.

[0957] Step 9: Generate an action plan

[0958] The server analyzes the discussion content during the meeting and generates a concrete action plan using an emotion engine and generative AI. The action plan reflects market data and emotion data. The input is the meeting content and emotion recognition results, and the output is the concrete action plan.

[0959] Step 10: Generate and distribute meeting minutes.

[0960] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are then distributed to the user's terminal. The input consists of the meeting content and the generated action plan, while the output is the generated meeting minutes.

[0961] Example of a prompt

[0962] Market data: Sales increased by 10% compared to the previous month. Demand for flagship products is increasing.

[0963] Sentiment analysis: Currently, many of the staff are showing positive motivation.

[0964] Please generate a meeting proposal based on the above.

[0965] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0966] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0967] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0968] [Third Embodiment]

[0969] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0970] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0971] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0972] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0973] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0974] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0975] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0976] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0977] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0978] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0979] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0980] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0981] This invention relates to a system that collects market data and economic indicator data from external data sources, performs analysis using generative AI, and supports roundtable discussions and crew meetings based on the results. Embodiments of this system are described in detail below.

[0982] Data acquisition and preprocessing

[0983] server

[0984] The server collects market and economic indicator data from external data sources. Specifically, the server uses API requests to retrieve information from data providers. This data is received in formats such as JSON and XML.

[0985] The server then cleans and normalizes the acquired data. The cleaning process detects empty values ​​and outliers and corrects or removes them. The normalization process converts information from different data sources into a unified format.

[0986] Data analysis and report generation

[0987] server

[0988] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in a report format. This report is presented in a visual format, including graphs and charts.

[0989] The analysis results are saved on the server and prepared for display on the dashboard. This dashboard provides an interface for users to view reports and start roundtables or crew meetings.

[0990] Roundtable discussion / crew meeting

[0991] User

[0992] Users access a web-based dashboard from their own devices (PC, tablet, etc.). The dashboard displays reports generated by the server, which users use to initiate roundtables and crew meetings.

[0993] Real-time discussion support

[0994] server

[0995] During the meeting, users enter questions and comments from their devices into the dashboard. The server uses generative AI to analyze these inputs in real time and generate appropriate answers. The generated answers are immediately displayed on the dashboard, supporting the progress of the meeting.

[0996] Generating action items

[0997] server

[0998] By analyzing the content of the meeting discussion, the generative AI automatically generates specific action plans. For example, action plans such as "increase inventory" or "strengthen marketing campaigns" may be generated.

[0999] Minutes creation and distribution

[1000] server

[1001] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are then delivered to the user's device and shared with all meeting participants.

[1002] Specific example

[1003] 1. Data Collection: The server calls an external API to retrieve market data in JSON format.

[1004] 2. Data Cleaning: The server imputes missing values ​​with the mean and detects and corrects outliers.

[1005] 3. Data Analysis: Generative AI identifies market trends and compiles them into reports.

[1006] 4. Dashboard Access: Users access the web-based dashboard from their devices and begin the discussion.

[1007] 5. Real-time answer generation: The server analyzes the user's question, and the generation AI instantly generates and displays the answer.

[1008] 6. Action Plan Generation: During the meeting, a generative AI proposes the next action plan.

[1009] 7. Distribution of meeting minutes: After the meeting ends, the server automatically generates the meeting minutes and sends them to the user's terminal.

[1010] This invention makes it possible to conduct efficient meetings through real-time analysis, which was difficult to achieve with conventional methods, and to formulate highly responsive action plans.

[1011] The following describes the processing flow.

[1012] Step 1:

[1013] Calling an external API

[1014] The server sends requests to external APIs that provide market and economic indicator data. For example, it makes HTTP requests specifying a particular endpoint URL to retrieve the latest data.

[1015] Step 2:

[1016] Receiving API Responses

[1017] The server waits for responses from external APIs and receives data in formats such as JSON and XML. The received data is temporarily stored so that it can be used directly for analysis.

[1018] Step 3:

[1019] Data Cleaning

[1020] The server performs a cleaning process on the acquired data. Specifically, it detects empty values ​​and outliers and removes or imputes them. For example, if there are missing values, it imputes them with the average value of past data. Also, if outliers are found, it replaces them with appropriate values.

[1021] Step 4:

[1022] Data normalization

[1023] The server normalizes the cleaned data. It converts data obtained from different data sources into a unified format to maintain consistency. For example, it converts data in different time formats into a unified timestamp format.

[1024] Step 5:

[1025] Initialization of generative AI

[1026] The server initializes generative AI (e.g., GPT-3 or BERT). It loads the necessary models and parameters and prepares them for analysis.

[1027] Step 6:

[1028] Data input and analysis

[1029] The server feeds pre-processed data into the generative AI and begins analysis. The generative AI identifies market trends and risk factors and retrieves the results.

[1030] Step 7:

[1031] Report generation

[1032] The server generates a report based on the analysis results output by the generative AI. This report includes graphs and charts to visually represent the analysis results. It also explains the analysis results in text format and provides insights into the data.

[1033] Step 8:

[1034] Saving reports and displaying dashboards

[1035] The server stores the generated reports and prepares them for display on a dashboard accessible to the user. The dashboard provides a web-based interface, allowing users to view the reports.

[1036] Step 9:

[1037] Access to the dashboard

[1038] Users access the dashboard from their own devices (PC, tablet, etc.). Users can view generated reports and start roundtables or crew meetings.

[1039] Step 10:

[1040] Enter your questions and comments

[1041] During the meeting, users enter questions and comments from their devices into the dashboard. These entries are then sent to the server.

[1042] Step 11:

[1043] Real-time analysis and response generation

[1044] The server uses generative AI to analyze user questions and comments in real time. The AI ​​generates appropriate answers, which are then displayed on the dashboard.

[1045] Step 12:

[1046] Analysis of discussion content and generation of action plans

[1047] The server analyzes the content of the discussion during the meeting, and a generative AI automatically generates a concrete action plan. For example, it might make specific suggestions such as "strengthen the marketing campaign."

[1048] Step 13:

[1049] Minutes generation

[1050] The server automatically generates meeting minutes based on the meeting content and the generated action plan. The minutes record important items and decisions discussed during the meeting.

[1051] Step 14:

[1052] Distribution of meeting minutes

[1053] After the meeting ends, the server distributes the generated meeting minutes to the users' terminals. This ensures that all meeting participants receive the minutes, facilitating smooth information sharing.

[1054] (Example 1)

[1055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1056] There is a need for a system that efficiently collects and analyzes market data and economic indicator data, and then uses the results to support meetings in real time. Conventional systems struggled to provide necessary information immediately because cleaning and analyzing large amounts of data was time-consuming. Furthermore, they were unable to smoothly generate appropriate answers to real-time questions and comments during meetings, or automatically generate meeting minutes after meetings.

[1057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1058] In this invention, the server includes means for acquiring market data and economic indicator data from external data sources; means for cleaning and normalizing the acquired data; means for detecting, correcting, or removing empty values ​​and outliers; means for analyzing the data using generative artificial intelligence to identify market trends and risk factors; means for generating reports based on the analysis results, selecting templates for visual representation, inserting graphs and charts, and saving them; means for users to access the generated reports via a terminal and start a roundtable discussion or meeting; means for analyzing user questions and comments in real time and generating and displaying appropriate answers; means for analyzing meeting content and generating concrete action plans; and means for distributing the generated action plans and meeting minutes to users. This makes it possible to streamline the entire process from data collection to analysis and meeting support.

[1059] "External data sources" refer to external sources of information that provide market data and economic indicator data.

[1060] "Market data" refers to data related to market trends, such as stock prices, trading volume, and exchange rates.

[1061] "Economic indicator data" refers to numerical values ​​that show the state of the economy, such as GDP, unemployment rate, and price index.

[1062] "Generative artificial intelligence" refers to AI models that perform data analysis and information generation in response to given input.

[1063] "Cleaning" refers to the process of detecting empty or outlier values ​​from acquired data and correcting or removing them.

[1064] "Normalization" is the process of converting information obtained from different data sources into a unified format.

[1065] A "prompt statement" is an input statement used to instruct a generative artificial intelligence system to perform analysis or generate information.

[1066] A "report" is a document that summarizes the results of an analysis.

[1067] A "visual representation template" is a template for representing a report in a visual format, such as graphs or charts.

[1068] A "dashboard" is an interface that allows users to view reports and start discussion groups or meetings.

[1069] "Real-time responses" refer to answers that are generated and displayed instantly in response to user questions and comments.

[1070] An "action plan" is a specific plan of action that is generated based on the discussions held at a meeting.

[1071] "Meeting minutes" are documents that record the content and decisions made at a meeting.

[1072] This invention relates to a system that collects market data and economic indicator data from external data sources, analyzes them using generative artificial intelligence, and supports roundtables and meetings based on the results. This system can be implemented using the following hardware and software.

[1073] Data acquisition and preprocessing

[1074] The server collects market data and economic indicator data from external data sources. Specifically, the server calls external APIs (e.g., market data APIs) to retrieve the latest market data in JSON format.

[1075] The server cleans the retrieved data by detecting empty values, imputing them with the median, and detecting and correcting outliers. The Pandas library (Python) is used for dataframe manipulation during the cleaning process.

[1076] The server normalizes the data, converting information from different data sources into a unified format. For example, it converts all price data to USD units.

[1077] Data analysis and report generation

[1078] The server uses the cleaned and normalized data to perform analysis using generative artificial intelligence (e.g., GPT-3 or BERT).

[1079] The server formats the input data for the generative artificial intelligence and generates prompt sentences. For example, it can generate a prompt sentence such as, "Based on the latest NASDAQ data, please explain the market trends and risk factors."

[1080] Generative artificial intelligence identifies market trends and potential risk factors and generates reports. These reports are presented in a visual format, including graphs and charts.

[1081] Report display and dashboard preparation

[1082] The server saves the generated report and prepares it for display on the dashboard. Specifically, it converts the report to HTML format and adds code to visually display graphs and charts.

[1083] The dashboard provides an interface for users to view reports and start roundtables and meetings.

[1084] Access to the dashboard

[1085] Users access the dashboard using a web browser from their own device (PC, tablet, etc.). The device performs user authentication and verifies the user's access permissions.

[1086] The terminal receives report data sent from the server and displays it on the browser screen.

[1087] Real-time discussion support

[1088] Users enter questions and comments on the dashboard from their devices during the meeting. The devices then send the user input data to the server.

[1089] The server receives this input data and uses generative artificial intelligence to analyze it in real time. For example, the server sends the prompt "What are the causes of recent market fluctuations?" to the generative AI and immediately generates an answer. The generative AI generates the answer "Recent market fluctuations are mainly due to the influence of economic conditions."

[1090] The server displays the generated responses on the dashboard.

[1091] Generating action items

[1092] The server analyzes the meeting discussions and uses generative artificial intelligence to automatically generate concrete action plans. For example, the server sends the prompt "Please propose the next action plan" to the generative AI. The generative AI then generates specific action items such as "Increase inventory" or "Develop a new marketing strategy."

[1093] The server displays the generated action items on the dashboard.

[1094] Minutes creation and distribution

[1095] After the meeting ends, the server automatically generates meeting minutes based on the meeting content and the generated action plan. The minutes are generated in text format and converted to PDF format.

[1096] The server sends the generated meeting minutes to the user's terminal. For example, the server might send the minutes as an email attachment or make them available for download on the dashboard.

[1097] Specific example

[1098] 1. Data Collection: The server calls an external API to retrieve NASDAQ market data in JSON format.

[1099] 2. Data Cleaning: The server imputes empty values ​​with the median and corrects outliers to within ±3 standard deviations.

[1100] 3. Data Analysis: Generative artificial intelligence (GPT-3) identifies the latest market trends and compiles them into a report.

[1101] 4. Dashboard Access: Users access the dashboard from their devices using a web browser (e.g., Google Chrome browser) and start a roundtable discussion.

[1102] 5. Real-time answer generation: The server analyzes the user's question, "What are the causes of recent market fluctuations?", and the generative artificial intelligence (BERT) instantly generates and displays the answer.

[1103] 6. Action Plan Generation: During the meeting, the generative artificial intelligence proposes an action plan such as "Strengthen the sales strategy for Q2."

[1104] 7. Distribution of meeting minutes: After the meeting, the server automatically generates meeting minutes and sends them to the user's device in PDF format. The minutes include the discussion content and action plan.

[1105] Example of a prompt:

[1106] 1. "Based on the latest NASDAQ data, please explain the market trends and risk factors."

[1107] 2. "Generate appropriate answers to the question regarding the causes of recent market fluctuations."

[1108] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1109] Step 1: Data Collection

[1110] The server retrieves market data and economic indicator data from external data sources. Specifically, the server calls a market data API to obtain the latest market data in JSON format.

[1111] Input: Market Data API endpoint

[1112] Data processing: Send an API request and save the retrieved market data in JSON format.

[1113] Output: Acquired market data in JSON format

[1114] Step 2: Data Cleaning

[1115] The server cleans the acquired data. Specifically, it detects empty values, imputes them with the median, and detects and corrects outliers.

[1116] Input: Market data in JSON format

[1117] Data processing: Create a dataframe using the Pandas library, impute empty values ​​with the median, and detect and correct outliers.

[1118] Output: Cleaned data frame

[1119] Step 3: Data Normalization

[1120] The server performs data normalization. Specifically, it converts information from different data sources into a unified format.

[1121] Input: Cleaned dataframe

[1122] Data processing: Convert all price data to USD units.

[1123] Output: Normalized data frame

[1124] Step 4: Data Analysis

[1125] The server analyzes the data using generative artificial intelligence. Specifically, it sends a prompt message to the generative AI, and the AI ​​model begins the analysis.

[1126] Input: Normalized data frame, prompt: "Based on the latest NASDAQ data, describe market trends and risk factors."

[1127] Data processing: A prompt message is sent to a generative artificial intelligence (e.g., GPT-3), and the analysis results are received.

[1128] Output: Analysis results including market trends and risk factors

[1129] Step 5: Report Generation

[1130] The server generates a report based on the analysis results. Specifically, it selects a template for visual representation, inserts graphs and charts, and saves the report.

[1131] Input: Analysis results

[1132] Data processing: Generate an HTML report based on the analysis results and insert graphs and charts.

[1133] Output: Generated report (HTML format)

[1134] Step 6: Prepare the dashboard

[1135] The server prepares the generated report for display on the dashboard.

[1136] Input: Generated report (HTML format)

[1137] Data processing: Save reports to a database and make them accessible on the dashboard.

[1138] Output: Reports that can be displayed on the dashboard

[1139] Step 7: Accessing the Dashboard

[1140] Users access the dashboard from their own devices (PC, tablet, etc.).

[1141] Input: User authentication information

[1142] Data processing: The terminal receives report data sent from the server and displays it on the browser screen.

[1143] Output: Report displayed in the browser

[1144] Step 8: Real-time discussion support

[1145] Users enter questions and comments from their devices into a dashboard during the meeting. The server receives this input data and performs real-time analysis using generative artificial intelligence.

[1146] Input: User questions and comments

[1147] Data processing: The prompt "What are the causes of recent market fluctuations?" is sent to a generative AI system, and the answer is generated and displayed.

[1148] Output: Real-time responses generated

[1149] Step 9: Generate action items

[1150] The server analyzes the meeting's discussion content and automatically generates a concrete action plan. For example, it might send a prompt to the generative AI saying, "Please propose the next action plan."

[1151] Input: Discussion log data

[1152] Data processing: Generate specific action items based on generative artificial intelligence.

[1153] Output: Generated action items

[1154] Step 10: Generate and distribute meeting minutes.

[1155] After the meeting ends, the server automatically generates meeting minutes based on the meeting content and the generated action plan, and sends them to the user's terminal.

[1156] Input: Meeting content, action plan

[1157] Data processing: Convert meeting minutes to PDF format and send them to users via email.

[1158] Output: Meeting minutes sent to the user's device (PDF format)

[1159] (Application Example 1)

[1160] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1161] In today's markets, rapid and accurate decision-making is essential, but data collection, cleaning, and analysis are time-consuming and labor-intensive, making efficient operation difficult. Furthermore, the inability to provide timely and appropriate information and answers during meetings and discussions is a significant challenge.

[1162] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1163] In this invention, the server includes means for acquiring market data and economic indicator data from external data sources, means for cleaning and normalizing the acquired data, means for analyzing the data using generative AI to identify market trends and risk factors, means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start a roundtable discussion or crew meeting, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, means for analyzing meeting content and generating concrete action plans, means for distributing the generated action plans and meeting minutes to users, means for displaying graphs and charts that visually represent the analysis results, and means for collecting and analyzing market data, competitor information, and customer behavior data to support strategic planning for virtual store operations. This enables efficient and rapid decision-making and supports optimal strategic planning in real time for virtual store operations.

[1164] "External data sources" refer to external data providers or APIs that provide market data and economic indicator data.

[1165] "Market data" refers to data that includes information such as price, supply, and demand related to a specific market.

[1166] "Economic indicator data" refers to data that includes statistical information indicating the state of the economy, such as GDP, unemployment rate, and inflation rate.

[1167] "Cleaning" is the process of correcting or removing inappropriate or missing values ​​from data.

[1168] "Normalization" is the process of converting data obtained from different data sources into a unified format.

[1169] "Generative AI" is artificial intelligence that analyzes collected data and generates text to perform a specific task.

[1170] "Market trends" refer to information that indicates the fluctuation patterns of prices and demand in the market.

[1171] "Risk factors" refer to elements or events that could have a negative impact on the market or economy.

[1172] A "report" is a document that summarizes the results of an analysis and may include graphs and charts.

[1173] A "dashboard" is a web-based interface that allows users to access analysis results and reports.

[1174] A "roundtable discussion" refers to a small-scale discussion held in a meeting format.

[1175] A "crew meeting" refers to a meeting held to discuss a specific project or issue.

[1176] "Real-time" refers to data processing and information provision at the present moment.

[1177] An "action plan" is a specific plan of actions taken to achieve a particular challenge or objective.

[1178] "Meeting minutes" are documents that record the content discussed and decisions made during a meeting.

[1179] "Competitive information" refers to information about the activities and strategies of other competing companies in the market.

[1180] "Customer behavior data" refers to information about how customers used products and services.

[1181] This invention is a system that supports the operation of virtual stores by collecting market data and economic indicator data from external data sources and performing analysis using generative AI. A detailed embodiment for carrying out this invention is described below.

[1182] Data acquisition and preprocessing

[1183] server

[1184] The server collects market data, economic indicators, competitive information, and customer behavior data from external data sources. Specifically, the server retrieves this information using API requests. This data is received in formats such as JSON and XML. The server then cleans and normalizes the retrieved data. The cleaning process detects empty values ​​and outliers and corrects or removes them. The normalization process converts information from different data sources into a unified format.

[1185] Data analysis and report generation

[1186] server

[1187] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in a report format. This report is created in a visual format, including graphs and charts. The analysis results are stored on a server and prepared for display on a dashboard accessible to users. The dashboard is browser-based, and users can access it from PCs, tablets, smartphones, etc.

[1188] Roundtable discussion / crew meeting

[1189] User

[1190] Users access a web-based dashboard from their devices. The dashboard displays reports generated by the server, which users can use to initiate roundtables and crew meetings.

[1191] Real-time discussion support

[1192] server

[1193] During the meeting, users enter questions and comments from their devices into the dashboard. The server uses generative AI to analyze these inputs in real time and generate appropriate answers. The generated answers are immediately displayed on the dashboard, supporting the progress of the meeting.

[1194] Generating action items

[1195] server

[1196] By analyzing the content of the meeting discussion, the generative AI automatically generates specific action plans. For example, action plans such as "increase inventory" or "strengthen marketing campaigns" may be generated.

[1197] Minutes creation and distribution

[1198] server

[1199] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are then delivered to the user's device and shared with all meeting participants.

[1200] Specific example

[1201] The server calls an external API to retrieve market data in JSON format. The server imputes missing values ​​with averages and detects and corrects outliers. Generative AI identifies market trends and compiles them into a report. The user accesses a web-based dashboard from their terminal and starts a roundtable discussion. The server analyzes the user's questions, and the generative AI instantly generates and displays answers. During the meeting, the generative AI proposes the next action plan. After the meeting ends, the server automatically generates meeting minutes and sends them to the user's terminal.

[1202] Example of a prompt

[1203] Identify trends and risks from the following market data:

[1204] Data: [{'product': 'A', 'price': 100, 'demand': 200}, {'product': 'B', 'price': 150, 'demand': 180}]"

[1205] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1206] Step 1:

[1207] Data collection

[1208] The server retrieves market data, economic indicators, competitive information, and customer behavior data from external data sources via API requests. The server accesses a specified API endpoint and receives data in JSON or XML format. The input is the API request, and the output is the retrieved data in JSON or XML format as a response.

[1209] Step 2:

[1210] Data cleaning and normalization

[1211] The server cleans and normalizes the received data. Data cleaning detects empty values ​​and outliers and corrects or removes them based on statistical methods. Specifically, it imputes missing values ​​with the mean and detects and corrects outliers. The normalization process converts information from different data sources into a unified format. The input is the acquired data, and the output is the cleaned and normalized data.

[1212] Step 3:

[1213] Data Analysis

[1214] The server analyzes the cleaned and normalized data using generative AI (e.g., GPT-3 or BERT). Specifically, it generates prompt sentences suitable for analysis and inputs them into the generative AI. Based on these prompt sentences, the AI ​​identifies market trends and risk factors and returns the analysis results. The input consists of the cleaned and normalized data and prompt sentences, and the output is the analysis results.

[1215] Step 4:

[1216] Report generation

[1217] The server generates a report based on the analysis results. The report includes market trends and risk factors, as well as graphs and charts for visual clarity. The generated report is saved in formats such as HTML and PDF. The input is the analysis results, and the output is the generated report.

[1218] Step 5:

[1219] Dashboard display

[1220] Users access a web-based dashboard from their devices. The server displays the generated reports on the dashboard. Users can view the reports through the dashboard and start roundtables or crew meetings. The input is the generated reports, and the output is the dashboard displaying the reports.

[1221] Step 6:

[1222] Real-time Q&A

[1223] During a meeting, users input questions and comments from their devices into a dashboard. The server uses generative AI to analyze these inputs in real time and generate appropriate answers. The generated answers are displayed on the dashboard to support the progress of the meeting. The input consists of user questions and comments, and the output consists of the generated answers.

[1224] Step 7:

[1225] Action plan generation

[1226] The server analyzes the meeting discussions, and the generative AI automatically generates specific action plans. These plans may include concrete suggestions such as "increase inventory" or "strengthen marketing campaigns." The input is the meeting discussion content, and the output is the generated action plan.

[1227] Step 8:

[1228] Minutes generation and distribution

[1229] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are converted to PDF format or another format and delivered to the user's device. The input is the meeting discussion content and the generated action plan, and the output is the automatically generated meeting minutes.

[1230] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1231] This invention combines a system that collects market data and economic indicator data from external data sources, performs analysis using generative AI, and supports roundtable discussions and crew meetings based on the results, with an emotion engine that recognizes user emotions. The embodiments of this system are described in detail below.

[1232] Data acquisition and preprocessing

[1233] server

[1234] The server collects market and economic indicator data from external data sources. Specifically, the server retrieves information from data providers using API requests. This data is received in formats such as JSON and XML. The server then cleans and normalizes the retrieved data. The cleaning process detects empty values ​​and outliers and removes or fills them in. The normalization process converts information from different data sources into a unified format.

[1235] Data analysis and report generation

[1236] server

[1237] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in report format. This report is created in a visual format, including graphs and charts. The analysis results are stored on a server and prepared for display on a dashboard. This dashboard provides an interface for users to view reports and initiate roundtables and crew meetings.

[1238] Roundtable discussion / crew meeting

[1239] User

[1240] Users access a web-based dashboard from their own devices (PC, tablet, etc.). The dashboard displays reports generated by the server, which users use to initiate roundtables and crew meetings.

[1241] Emotion recognition and real-time discussion support

[1242] server

[1243] During the meeting, users enter questions and comments from their devices into a dashboard. In addition, an emotion engine operates to recognize emotions from user speech and text input. The server uses generative AI and the emotion engine to analyze these inputs in real time and generate appropriate responses. The generated responses are immediately displayed on the dashboard to support the progress of the meeting.

[1244] Analysis of discussion content and generation of action plans

[1245] server

[1246] By analyzing the content of discussions during meetings, the generative AI and emotion engine automatically generate specific action plans. For example, it proposes action plans that reflect emotional data, such as "If user anxiety is detected, review risk management measures."

[1247] Minutes creation and distribution

[1248] server

[1249] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes also include user sentiment data recognized by the sentiment engine. For example, changes in emotions during discussions and the tone of the meeting are reflected in the minutes. The generated minutes are delivered to the user's device and shared with all meeting participants.

[1250] Specific example

[1251] 1. Data Collection: The server calls an external API to retrieve market data in JSON format.

[1252] 2. Data Cleaning: The server imputes missing values ​​with the mean and detects and corrects outliers.

[1253] 3. Data Analysis: Generative AI identifies market trends and compiles them into reports.

[1254] 4. Dashboard Access: Users access the web-based dashboard from their devices and begin the discussion.

[1255] 5. Emotion Recognition: The emotion engine recognizes emotions from the user's speech and text input.

[1256] 6. Real-time response generation: The server analyzes the user's question, and the generative AI and emotion engine instantly generate and display the response.

[1257] 7. Action Plan Generation: During the meeting, generate a concrete action plan based on emotional expression.

[1258] 8. Distribution of meeting minutes: After the meeting ends, the server automatically generates meeting minutes, including sentiment data, and sends them to the user's device.

[1259] This invention makes it possible to conduct efficient meetings through real-time analysis, which was difficult to achieve with conventional methods, and to formulate flexible action plans that reflect user sentiment data.

[1260] The following describes the processing flow.

[1261] Step 1:

[1262] Calling an external API

[1263] The server retrieves the latest data by sending HTTP requests to external APIs that provide market and economic indicator data. Specifically, it makes requests using API endpoint URLs and receives data in JSON or XML format.

[1264] Step 2:

[1265] Receiving API Responses

[1266] The server receives a response from an external API and temporarily stores the retrieved data. The stored data is then used in the next processing step.

[1267] Step 3:

[1268] Data Cleaning

[1269] The server cleans the acquired data. Specifically, it detects empty values ​​and outliers in the data and removes or imputes them. For example, missing values ​​are imputed with the mean of past data, and outliers are replaced with appropriate values.

[1270] Step 4:

[1271] Data normalization

[1272] The server normalizes the cleaned data. Specifically, it converts data obtained from different data sources into a unified format to maintain consistency. For example, it converts data in different time formats into a common timestamp format.

[1273] Step 5:

[1274] Initialization of generative AI

[1275] The server initializes generative AI (such as GPT-3 or BERT). It loads the necessary models and parameters and prepares the data for analysis.

[1276] Step 6:

[1277] Data input and analysis

[1278] The server feeds the pre-processed data into the generative AI and begins data analysis. The generative AI identifies market trends and risk factors and generates analysis results based on them.

[1279] Step 7:

[1280] Report generation

[1281] The server generates a report based on the analysis results obtained from the generative AI. This report includes text explanations of the analysis results, as well as graphs and charts. The information is presented in a visually easy-to-understand format.

[1282] Step 8:

[1283] Saving reports and displaying dashboards

[1284] The server stores the generated reports in a database and displays them on a dashboard for user access. The dashboard is provided via a web-based interface.

[1285] Step 9:

[1286] Access to the dashboard

[1287] Users access the dashboard from their own devices (PC, tablet, etc.) and view the generated reports. Based on these reports, users can then initiate roundtable discussions or crew meetings.

[1288] Step 10:

[1289] emotion recognition

[1290] The server uses an emotion engine to recognize emotions from user statements and text input. It analyzes specific keywords and expressions to determine the user's emotional state.

[1291] Step 11:

[1292] Real-time analysis and response generation

[1293] The server analyzes user questions and comments in real time and generates appropriate responses using generative AI and an emotion engine. For example, if a user expresses anxiety, the server analyzes it and generates a reassuring response.

[1294] Step 12:

[1295] Display the answer

[1296] The server displays the generated responses on a dashboard and provides them to users in real time, ensuring a smooth flow of the meeting.

[1297] Step 13:

[1298] Analysis of discussion content and generation of action plans

[1299] The server uses an emotion engine and generative AI to analyze the content of discussions during meetings and automatically generates concrete action plans. For example, it proposes an action plan that reflects the emotions expressed by the user.

[1300] Step 14:

[1301] Minutes generation

[1302] The server automatically generates meeting minutes based on the meeting content, the generated action plan, and the user's emotional state as recognized by the emotion engine.

[1303] Step 15:

[1304] Distribution of meeting minutes

[1305] After the meeting ends, the server distributes the generated meeting minutes to each user's device. This ensures that all meeting participants receive the minutes, facilitating smooth information sharing.

[1306] This system enables efficient collection and analysis of precise information from external data sources, real-time meeting support that takes user sentiment into consideration, and the development of concrete action plans.

[1307] (Example 2)

[1308] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1309] Conventional meeting systems have made it difficult to perform real-time data analysis and generate flexible action plans that reflect user sentiment. Furthermore, efficient analysis of meeting content, automatic generation of concrete action plans based on that analysis, and rapid distribution of meeting minutes to all participants have been challenging. This invention aims to solve these problems and provide a system that streamlines and enhances meeting management.

[1310] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1311] In this invention, the server includes means for acquiring market data and economic indicator data from external data sources, means for cleaning and normalizing the acquired data, means for analyzing the data using generative AI to identify market trends and risk factors, means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start a roundtable discussion or crew meeting, means for recognizing emotions from user statements and text inputs, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, means for analyzing meeting content and generating concrete action plans that reflect user emotion data, and means for automatically generating meeting minutes based on the meeting content and generated action plans and distributing them to users. This enables the generation of flexible action plans through real-time data analysis and emotion recognition, as well as rapid analysis of meeting content and automatic generation and distribution of meeting minutes.

[1312] "External data sources" refer to external information providers, APIs, and other entities that provide market data and economic indicator data.

[1313] "Market data" refers to data related to financial markets, such as stock prices, exchange rates, and commodity prices.

[1314] "Economic indicator data" refers to statistical data that shows the state of the economy, such as GDP, unemployment rate, and consumer price index.

[1315] "Cleaning" refers to the process of detecting, correcting, or removing empty or outlier values ​​in data.

[1316] "Normalization" refers to the process of converting data obtained from different data sources into a unified format.

[1317] "Generative AI" refers to artificial intelligence models that perform tasks such as data analysis and natural language generation (e.g., GPT-3, BERT, etc.).

[1318] "Market trends" refer to the temporal movements and fluctuation patterns of market data.

[1319] "Risk factors" refer to elements that could have a negative impact on markets or economic activity.

[1320] A "report" refers to a document or report that summarizes the results of an analysis.

[1321] A "dashboard" refers to a web-based interface that allows users to access and interact with analytical results and reports.

[1322] A "roundtable discussion" refers to a type of meeting where participants freely exchange opinions on a specific topic.

[1323] A "crew meeting" refers to a meeting held within a specific team or organization.

[1324] "Means of recognizing emotions" refers to algorithms and engines that identify emotions from user statements and text input.

[1325] "Means of real-time analysis" refers to the ability to instantly analyze input data and immediately generate and display results.

[1326] An "action plan" refers to a specific plan of action or measures.

[1327] "Meeting minutes" refers to a document that records the content of a meeting, the matters discussed, the decisions made, and the action plan.

[1328] This invention combines a system that collects market data and economic indicator data from external data sources, performs analysis using generative AI, and supports roundtable discussions and crew meetings based on the results, with an emotion engine that recognizes user emotions. The embodiments of this system are described in detail below.

[1329] The server uses API requests to retrieve market data and economic indicator data from external data sources. Specifically, the server accesses a URL like "https: / / api.example.com / marketdata" and receives the data in JSON format.

[1330] Next, the server cleans and normalizes the received data. Data cleaning involves imputing missing values ​​with the mean and detecting and correcting outliers. This is done using libraries such as Python's pandas library.

[1331] Cleaned and normalized data is analyzed by generative AI models (e.g., GPT-3, BERT, etc.). The server inputs this data into the generative AI to identify market trends and risk factors. The information obtained from the analysis is generated and saved as a report in a visual format (graphs, charts, etc.).

[1332] The analysis results are displayed on a dashboard. This uses web frameworks such as Python's Flask or Django, and is provided as a web-based interface accessible to users. Users access this dashboard from their devices and start roundtables or crew meetings based on the generated reports.

[1333] During the meeting, users enter questions and comments from their devices onto the dashboard. The emotion engine recognizes emotions from the user's statements and text input. For example, if a user enters "What do you think about the current market?", the emotion engine recognizes "anxiety," and the generative AI immediately generates and displays the response, "The market is highly volatile, so caution is needed."

[1334] The meeting content is analyzed in real time, and specific action plans are generated that reflect the user's emotional data. For example, the emotional engine analyzes statements such as "the risk is too high," and the generative AI generates an action plan such as "propose reviewing risk management measures."

[1335] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes also include sentiment data recognized by the sentiment engine, detailing specific points such as "proposed a review of risk management measures." The generated minutes are then delivered to the user's device and shared with all meeting participants.

[1336] This invention enables efficient meeting management through real-time analysis, which was difficult to achieve with conventional methods, and the development of flexible action plans that reflect user sentiment data. An example of a prompt is "Please tell me about future market trends." By entering this prompt, a generative AI can analyze it and provide a specific answer in real time.

[1337] The above details the specific method of the present invention. This system not only dramatically improves the efficiency of business meetings and analysis, but also contributes to an improved user experience.

[1338] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1339] Step 1: Data Collection

[1340] server

[1341] The server sends API requests to external data sources to retrieve market data and economic indicator data. For example, the server accesses a URL like "https: / / api.example.com / marketdata" and receives data in JSON format.

[1342] Input-based action: Request to an external API.

[1343] Output: Acquired market data and economic indicator data.

[1344] Step 2: Data Preprocessing

[1345] server

[1346] The server cleans and normalizes the data it receives. Data cleaning involves imputing missing values ​​with the mean and detecting and correcting outliers. Normalization converts data obtained from different data sources into a unified format.

[1347] Input-based operation: Cleaning and normalizing incoming data.

[1348] Output: Cleaned and normalized data.

[1349] Step 3: Data Analysis

[1350] server

[1351] The cleaned and normalized data is input into a generative AI for analysis. For example, the server supplies data to a generative AI model (e.g., GPT-3) to identify market trends and risk factors.

[1352] Input-based operation: Data input to a generative AI model.

[1353] Output: Analysis results identifying market trends and risk factors.

[1354] Step 4: Prepare to generate reports and display dashboards.

[1355] server

[1356] Based on the analysis results, a visual report is generated. The server uses web frameworks such as Python's Flask or Django to prepare the report in HTML format for display on the dashboard.

[1357] Input-based operation: Generates visual reports and HTML using analysis results.

[1358] Output: HTML for visual reports and dashboards.

[1359] Step 5: Access the Dashboard

[1360] User

[1361] Users access a web-based dashboard from their devices and initiate roundtables or crew meetings based on the displayed analytics reports.

[1362] Input-based action: User accesses the dashboard via browser.

[1363] Output: Analysis report displayed on the dashboard.

[1364] Step 6: Emotion Recognition and Real-Time Discussion Support

[1365] server

[1366] During a meeting, users enter questions and comments from their devices onto a dashboard. The server uses an emotion engine to recognize the user's emotions from these inputs. It then works in conjunction with generative AI to generate and display appropriate answers in real time. For example, if a user enters "What do you think about the current market?", the server's emotion engine recognizes the user's anxiety, and the generative AI instantly generates an answer regarding market fluctuations.

[1367] Input-based operation: Sentiment recognition and response generation based on user input.

[1368] Output: Real-time responses displayed on the dashboard.

[1369] Step 7: Generate an action plan

[1370] server

[1371] The system analyzes meeting content in real time and generates concrete action plans that reflect user sentiment data. For example, the sentiment engine analyzes statements such as "the risk is too high," and the generative AI proposes a revision of risk management measures.

[1372] Input-based actions: Analysis of meeting content and sentiment data.

[1373] Output: A concrete action plan.

[1374] Step 8: Generate and distribute meeting minutes

[1375] server

[1376] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes, which include sentiment data, are delivered to the user's device.

[1377] Input-based operation: Generate meeting minutes based on meeting content and action plan.

[1378] Output: Meeting minutes distributed to users.

[1379] The above outlines the processing steps of this system and the specific operational details of each step. This enables efficient and flexible meeting management through real-time analysis and emotion recognition.

[1380] (Application Example 2)

[1381] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1382] Conventional meeting support systems do not adequately support real-time discussions using market and economic indicator data. Furthermore, they struggle to recognize user emotions and generate effective action plans based on them. In addition, there is a lack of means to conduct meetings and make decisions in a way that takes staff emotions into consideration in the operation of physical stores.

[1383] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for acquiring market data and economic indicator data from an external data source, means for cleaning and normalizing the acquired data, means for analyzing the data using generative AI to identify market trends and risk factors, means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start a roundtable discussion or crew meeting, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, means for analyzing meeting content and generating a concrete action plan, means for distributing the generated action plan and meeting minutes to the user, means for analyzing the emotional state of store staff using market data and sentiment data and proposing an appropriate action plan, and means for conducting a meeting based on emotional state and market data through generative AI. This enables efficient meeting management through real-time analysis and the formulation of flexible action plans that reflect sentiment data.

[1384] "External data sources" refer to sources of information used to collect market data and economic indicator data from outside the system, such as the internet or third-party APIs.

[1385] "Market data" refers to statistical information related to a specific market, such as product sales, price trends, and consumer demand.

[1386] "Economic indicator data" refers to statistical information such as unemployment rates, GDP growth rates, and inflation rates that show the overall trends of the economy.

[1387] "Cleaning" is the process of detecting empty or outlier values ​​from acquired data and correcting or removing them.

[1388] "Normalization" is the process of converting information obtained from different data sources into a unified format.

[1389] "Generative AI" is a type of artificial intelligence that automatically generates new information and content based on large datasets.

[1390] A "dashboard" is an interface that allows users to access analysis results and reports and view visualized information.

[1391] An "emotion engine" is an algorithm or system that recognizes and analyzes emotions from a user's speech or text input.

[1392] "Real-time analysis" is a processing method that performs analysis immediately on collected data or user input and provides the results.

[1393] An "action plan" is a plan that proposes specific action guidelines and countermeasures based on analysis results and sentiment data.

[1394] Meeting minutes are documents that record the content of a meeting, the decisions made, and the proposed action plans, so that they can be referenced later.

[1395] A "physical store" is a sales facility located in a physical place, a store that customers can visit in person.

[1396] This invention is a system that collects market data and economic indicator data and supports the operation of physical stores through analysis using generative AI. This system recognizes user emotions in real time and proposes appropriate action plans. The series of functions for this purpose operate as follows:

[1397] Data acquisition and preprocessing

[1398] The server collects market and economic indicator data from external data sources. Specifically, the server retrieves information using API requests. The retrieved data is often received in JSON format. The server then cleans and normalizes the data. The cleaning process detects empty values ​​and outliers and either fills them in or removes them. The normalization process converts information from different data sources into a unified format.

[1399] Data analysis and report generation

[1400] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, generating the results in a report format. This report is created in a visual format, including graphs and charts. The analysis results are stored on a server and prepared for display on a dashboard. This dashboard includes an interface for users to view the report and initiate discussions or meetings.

[1401] Emotion recognition and argument support

[1402] During the meeting, users access the dashboard from their devices (e.g., smartphones or tablets) to enter questions and comments. The emotion engine recognizes emotions from the user's statements and text input. This emotion recognition works in conjunction with generative AI to generate real-time analysis and responses that correspond to the user's emotional state. The generated responses are immediately displayed on the dashboard to support the progress of the meeting.

[1403] Action plan generation and meeting minutes distribution

[1404] During the meeting, the server analyzes the discussion content, and the generative AI and emotion engine automatically generate a concrete action plan. This action plan includes specific measures that reflect market data and emotion data. For example, if user anxiety is detected, it will suggest reviewing inventory or rearranging staff. After the meeting ends, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes, which also include emotion data, are distributed to the user's device.

[1405] Examples of specific cases and prompt statements

[1406] As a concrete example, suppose a server calls an external API and retrieves economic indicator data in JSON format. This data is cleaned, and missing values ​​are imputed with the mean. A generative AI (e.g., GPT-3) analyzes the data using the "market data" and "sentiment analysis" results as prompts. The following is an example of such prompts:

[1407] Market data: Sales increased by 10% compared to the previous month. Demand for flagship products is increasing.

[1408] Sentiment analysis: Currently, many of the staff are showing positive motivation.

[1409] Please generate a meeting proposal based on the above.

[1410] This process enables the system to efficiently manage meetings by combining real-time analysis and emotion recognition, and allows for the development of flexible action plans that reflect the user's emotions.

[1411] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1412] Step 1: Data Acquisition

[1413] The server sends API requests to external data sources to retrieve market data and economic indicator data. Specifically, the server accesses the API endpoint via the internet and receives data in JSON format. The input is the API request, and the output is the retrieved market data and economic indicator data.

[1414] Step 2: Cleaning

[1415] The server cleans the received market and economic indicator data. The cleaning process detects and removes or imputes empty or outlier values. The input is the acquired market and economic indicator data, and the output is the cleaned data. For example, missing values ​​are imputed with the mean, and outliers are corrected to appropriate values.

[1416] Step 3: Normalize the data

[1417] The server normalizes the cleaned data. The normalization process converts information from different data sources into a unified format. The input is cleaned data, and the output is normalized data. For example, it converts numbers expressed in different units to a unified unit.

[1418] Step 4: Data Analysis

[1419] The server analyzes normalized data using generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in report format. The input is normalized data, and the output is a report containing the analysis results.

[1420] Step 5: Generate and save the report

[1421] The server generates and saves a report based on the analysis results. The report includes graphs and charts for visual representation. The input is the analysis results, and the output is the generated report. The report is stored on the server and accessible via the dashboard.

[1422] Step 6: Access the Dashboard

[1423] Users access the dashboard from their own devices (e.g., smartphones or tablets) and view the generated reports. Based on these reports, users can start roundtables or crew meetings. The input is the user's login information, and the output is the report display screen.

[1424] Step 7: Emotion Recognition

[1425] During the meeting, users enter questions and comments from their terminals into the dashboard. The server receives this information and uses an emotion engine to recognize emotions from the user's statements and text input. The input is the user's text input, and the output is the emotion recognition result.

[1426] Step 8: Real-time response generation

[1427] The server uses generative AI and an emotion engine to analyze user input and generate appropriate responses. The generated responses are immediately displayed on the dashboard. Input consists of emotion recognition results and user text input, while output is the generated response.

[1428] Step 9: Generate an action plan

[1429] The server analyzes the discussion content during the meeting and generates a concrete action plan using an emotion engine and generative AI. The action plan reflects market data and emotion data. The input is the meeting content and emotion recognition results, and the output is the concrete action plan.

[1430] Step 10: Generate and distribute meeting minutes.

[1431] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are then distributed to the user's terminal. The input consists of the meeting content and the generated action plan, while the output is the generated meeting minutes.

[1432] Example of a prompt

[1433] Market data: Sales increased by 10% compared to the previous month. Demand for flagship products is increasing.

[1434] Sentiment analysis: Currently, many of the staff are showing positive motivation.

[1435] Please generate a meeting proposal based on the above.

[1436] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1437] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1438] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1439] [Fourth Embodiment]

[1440] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1441] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1442] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1443] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1444] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1445] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1446] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1447] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1448] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1449] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1450] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1451] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1452] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1453] This invention relates to a system that collects market data and economic indicator data from external data sources, performs analysis using generative AI, and supports roundtable discussions and crew meetings based on the results. Embodiments of this system are described in detail below.

[1454] Data acquisition and preprocessing

[1455] server

[1456] The server collects market and economic indicator data from external data sources. Specifically, the server uses API requests to retrieve information from data providers. This data is received in formats such as JSON and XML.

[1457] The server then cleans and normalizes the acquired data. The cleaning process detects empty values ​​and outliers and corrects or removes them. The normalization process converts information from different data sources into a unified format.

[1458] Data analysis and report generation

[1459] server

[1460] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in a report format. This report is presented in a visual format, including graphs and charts.

[1461] The analysis results are saved on the server and prepared for display on the dashboard. This dashboard provides an interface for users to view reports and start roundtables or crew meetings.

[1462] Roundtable discussion / crew meeting

[1463] User

[1464] Users access a web-based dashboard from their own devices (PC, tablet, etc.). The dashboard displays reports generated by the server, which users use to initiate roundtables and crew meetings.

[1465] Real-time discussion support

[1466] server

[1467] During the meeting, users enter questions and comments from their devices into the dashboard. The server uses generative AI to analyze these inputs in real time and generate appropriate answers. The generated answers are immediately displayed on the dashboard, supporting the progress of the meeting.

[1468] Generating action items

[1469] server

[1470] By analyzing the content of the meeting discussion, the generative AI automatically generates specific action plans. For example, action plans such as "increase inventory" or "strengthen marketing campaigns" may be generated.

[1471] Minutes creation and distribution

[1472] server

[1473] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are then delivered to the user's device and shared with all meeting participants.

[1474] Specific example

[1475] 1. Data Collection: The server calls an external API to retrieve market data in JSON format.

[1476] 2. Data Cleaning: The server imputes missing values ​​with the mean and detects and corrects outliers.

[1477] 3. Data Analysis: Generative AI identifies market trends and compiles them into reports.

[1478] 4. Dashboard Access: Users access the web-based dashboard from their devices and begin the discussion.

[1479] 5. Real-time answer generation: The server analyzes the user's question, and the generation AI instantly generates and displays the answer.

[1480] 6. Action Plan Generation: During the meeting, a generative AI proposes the next action plan.

[1481] 7. Distribution of meeting minutes: After the meeting ends, the server automatically generates the meeting minutes and sends them to the user's terminal.

[1482] This invention makes it possible to conduct efficient meetings through real-time analysis, which was difficult to achieve with conventional methods, and to formulate highly responsive action plans.

[1483] The following describes the processing flow.

[1484] Step 1:

[1485] Calling an external API

[1486] The server sends requests to external APIs that provide market and economic indicator data. For example, it makes HTTP requests specifying a particular endpoint URL to retrieve the latest data.

[1487] Step 2:

[1488] Receiving API Responses

[1489] The server waits for responses from external APIs and receives data in formats such as JSON and XML. The received data is temporarily stored so that it can be used directly for analysis.

[1490] Step 3:

[1491] Data Cleaning

[1492] The server performs a cleaning process on the acquired data. Specifically, it detects empty values ​​and outliers and removes or imputes them. For example, if there are missing values, it imputes them with the average value of past data. Also, if outliers are found, it replaces them with appropriate values.

[1493] Step 4:

[1494] Data normalization

[1495] The server normalizes the cleaned data. It converts data obtained from different data sources into a unified format to maintain consistency. For example, it converts data in different time formats into a unified timestamp format.

[1496] Step 5:

[1497] Initialization of generative AI

[1498] The server initializes generative AI (e.g., GPT-3 or BERT). It loads the necessary models and parameters and prepares them for analysis.

[1499] Step 6:

[1500] Data input and analysis

[1501] The server feeds pre-processed data into the generative AI and begins analysis. The generative AI identifies market trends and risk factors and retrieves the results.

[1502] Step 7:

[1503] Report generation

[1504] The server generates a report based on the analysis results output by the generative AI. This report includes graphs and charts to visually represent the analysis results. It also explains the analysis results in text format and provides insights into the data.

[1505] Step 8:

[1506] Saving reports and displaying dashboards

[1507] The server stores the generated reports and prepares them for display on a dashboard accessible to the user. The dashboard provides a web-based interface, allowing users to view the reports.

[1508] Step 9:

[1509] Access to the dashboard

[1510] Users access the dashboard from their own devices (PC, tablet, etc.). Users can view generated reports and start roundtables or crew meetings.

[1511] Step 10:

[1512] Enter your questions and comments

[1513] During the meeting, users enter questions and comments from their devices into the dashboard. These entries are then sent to the server.

[1514] Step 11:

[1515] Real-time analysis and response generation

[1516] The server uses generative AI to analyze user questions and comments in real time. The AI ​​generates appropriate answers, which are then displayed on the dashboard.

[1517] Step 12:

[1518] Analysis of discussion content and generation of action plans

[1519] The server analyzes the content of the discussion during the meeting, and a generative AI automatically generates a concrete action plan. For example, it might make specific suggestions such as "strengthen the marketing campaign."

[1520] Step 13:

[1521] Minutes generation

[1522] The server automatically generates meeting minutes based on the meeting content and the generated action plan. The minutes record important items and decisions discussed during the meeting.

[1523] Step 14:

[1524] Distribution of meeting minutes

[1525] After the meeting ends, the server distributes the generated meeting minutes to the users' terminals. This ensures that all meeting participants receive the minutes, facilitating smooth information sharing.

[1526] (Example 1)

[1527] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1528] There is a need for a system that efficiently collects and analyzes market data and economic indicator data, and then uses the results to support meetings in real time. Conventional systems struggled to provide necessary information immediately because cleaning and analyzing large amounts of data was time-consuming. Furthermore, they were unable to smoothly generate appropriate answers to real-time questions and comments during meetings, or automatically generate meeting minutes after meetings.

[1529] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1530] In this invention, the server includes means for acquiring market data and economic indicator data from external data sources; means for cleaning and normalizing the acquired data; means for detecting, correcting, or removing empty values ​​and outliers; means for analyzing the data using generative artificial intelligence to identify market trends and risk factors; means for generating reports based on the analysis results, selecting templates for visual representation, inserting graphs and charts, and saving them; means for users to access the generated reports via a terminal and start a roundtable discussion or meeting; means for analyzing user questions and comments in real time and generating and displaying appropriate answers; means for analyzing meeting content and generating concrete action plans; and means for distributing the generated action plans and meeting minutes to users. This makes it possible to streamline the entire process from data collection to analysis and meeting support.

[1531] "External data sources" refer to external sources of information that provide market data and economic indicator data.

[1532] "Market data" refers to data related to market trends, such as stock prices, trading volume, and exchange rates.

[1533] "Economic indicator data" refers to numerical values ​​that show the state of the economy, such as GDP, unemployment rate, and price index.

[1534] "Generative artificial intelligence" refers to AI models that perform data analysis and information generation in response to given input.

[1535] "Cleaning" refers to the process of detecting empty or outlier values ​​from acquired data and correcting or removing them.

[1536] "Normalization" is the process of converting information obtained from different data sources into a unified format.

[1537] A "prompt statement" is an input statement used to instruct a generative artificial intelligence system to perform analysis or generate information.

[1538] A "report" is a document that summarizes the results of an analysis.

[1539] A "visual representation template" is a template for representing a report in a visual format, such as graphs or charts.

[1540] A "dashboard" is an interface that allows users to view reports and start discussion groups or meetings.

[1541] "Real-time responses" refer to answers that are generated and displayed instantly in response to user questions and comments.

[1542] An "action plan" is a specific plan of action that is generated based on the discussions held at a meeting.

[1543] "Meeting minutes" are documents that record the content and decisions made at a meeting.

[1544] This invention relates to a system that collects market data and economic indicator data from external data sources, analyzes them using generative artificial intelligence, and supports roundtables and meetings based on the results. This system can be implemented using the following hardware and software.

[1545] Data acquisition and preprocessing

[1546] The server collects market data and economic indicator data from external data sources. Specifically, the server calls external APIs (e.g., market data APIs) to retrieve the latest market data in JSON format.

[1547] The server cleans the retrieved data by detecting empty values, imputing them with the median, and detecting and correcting outliers. The Pandas library (Python) is used for dataframe manipulation during the cleaning process.

[1548] The server normalizes the data, converting information from different data sources into a unified format. For example, it converts all price data to USD units.

[1549] Data analysis and report generation

[1550] The server uses the cleaned and normalized data to perform analysis using generative artificial intelligence (e.g., GPT-3 or BERT).

[1551] The server formats the input data for the generative artificial intelligence and generates prompt sentences. For example, it can generate a prompt sentence such as, "Based on the latest NASDAQ data, please explain the market trends and risk factors."

[1552] Generative artificial intelligence identifies market trends and potential risk factors and generates reports. These reports are presented in a visual format, including graphs and charts.

[1553] Report display and dashboard preparation

[1554] The server saves the generated report and prepares it for display on the dashboard. Specifically, it converts the report to HTML format and adds code to visually display graphs and charts.

[1555] The dashboard provides an interface for users to view reports and start roundtables and meetings.

[1556] Access to the dashboard

[1557] Users access the dashboard using a web browser from their own device (PC, tablet, etc.). The device performs user authentication and verifies the user's access permissions.

[1558] The terminal receives report data sent from the server and displays it on the browser screen.

[1559] Real-time discussion support

[1560] Users enter questions and comments on the dashboard from their devices during the meeting. The devices then send the user input data to the server.

[1561] The server receives this input data and uses generative artificial intelligence to analyze it in real time. For example, the server sends the prompt "What are the causes of recent market fluctuations?" to the generative AI and immediately generates an answer. The generative AI generates the answer "Recent market fluctuations are mainly due to the influence of economic conditions."

[1562] The server displays the generated responses on the dashboard.

[1563] Generating action items

[1564] The server analyzes the meeting discussions and uses generative artificial intelligence to automatically generate concrete action plans. For example, the server sends the prompt "Please propose the next action plan" to the generative AI. The generative AI then generates specific action items such as "Increase inventory" or "Develop a new marketing strategy."

[1565] The server displays the generated action items on the dashboard.

[1566] Minutes creation and distribution

[1567] After the meeting ends, the server automatically generates meeting minutes based on the meeting content and the generated action plan. The minutes are generated in text format and converted to PDF format.

[1568] The server sends the generated meeting minutes to the user's terminal. For example, the server might send the minutes as an email attachment or make them available for download on the dashboard.

[1569] Specific example

[1570] 1. Data Collection: The server calls an external API to retrieve NASDAQ market data in JSON format.

[1571] 2. Data Cleaning: The server imputes empty values ​​with the median and corrects outliers to within ±3 standard deviations.

[1572] 3. Data Analysis: Generative artificial intelligence (GPT-3) identifies the latest market trends and compiles them into a report.

[1573] 4. Dashboard Access: Users access the dashboard from their devices using a web browser (e.g., Google Chrome browser) and start a roundtable discussion.

[1574] 5. Real-time answer generation: The server analyzes the user's question, "What are the causes of recent market fluctuations?", and the generative artificial intelligence (BERT) instantly generates and displays the answer.

[1575] 6. Action Plan Generation: During the meeting, the generative artificial intelligence proposes an action plan such as "Strengthen the sales strategy for Q2."

[1576] 7. Distribution of meeting minutes: After the meeting, the server automatically generates meeting minutes and sends them to the user's device in PDF format. The minutes include the discussion content and action plan.

[1577] Example of a prompt:

[1578] 1. "Based on the latest NASDAQ data, please explain the market trends and risk factors."

[1579] 2. "Generate appropriate answers to the question regarding the causes of recent market fluctuations."

[1580] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1581] Step 1: Data Collection

[1582] The server retrieves market data and economic indicator data from external data sources. Specifically, the server calls a market data API to obtain the latest market data in JSON format.

[1583] Input: Market Data API endpoint

[1584] Data processing: Send an API request and save the retrieved market data in JSON format.

[1585] Output: Acquired market data in JSON format

[1586] Step 2: Data Cleaning

[1587] The server cleans the acquired data. Specifically, it detects empty values, imputes them with the median, and detects and corrects outliers.

[1588] Input: Market data in JSON format

[1589] Data processing: Create a dataframe using the Pandas library, impute empty values ​​with the median, and detect and correct outliers.

[1590] Output: Cleaned data frame

[1591] Step 3: Data Normalization

[1592] The server performs data normalization. Specifically, it converts information from different data sources into a unified format.

[1593] Input: Cleaned dataframe

[1594] Data processing: Convert all price data to USD units.

[1595] Output: Normalized data frame

[1596] Step 4: Data Analysis

[1597] The server analyzes the data using generative artificial intelligence. Specifically, it sends a prompt message to the generative AI, and the AI ​​model begins the analysis.

[1598] Input: Normalized data frame, prompt: "Based on the latest NASDAQ data, describe market trends and risk factors."

[1599] Data processing: A prompt message is sent to a generative artificial intelligence (e.g., GPT-3), and the analysis results are received.

[1600] Output: Analysis results including market trends and risk factors

[1601] Step 5: Report Generation

[1602] The server generates a report based on the analysis results. Specifically, it selects a template for visual representation, inserts graphs and charts, and saves the report.

[1603] Input: Analysis results

[1604] Data processing: Generate an HTML report based on the analysis results and insert graphs and charts.

[1605] Output: Generated report (HTML format)

[1606] Step 6: Prepare the dashboard

[1607] The server prepares the generated report for display on the dashboard.

[1608] Input: Generated report (HTML format)

[1609] Data processing: Save reports to a database and make them accessible on the dashboard.

[1610] Output: Reports that can be displayed on the dashboard

[1611] Step 7: Accessing the Dashboard

[1612] Users access the dashboard from their own devices (PC, tablet, etc.).

[1613] Input: User authentication information

[1614] Data processing: The terminal receives report data sent from the server and displays it on the browser screen.

[1615] Output: Report displayed in the browser

[1616] Step 8: Real-time discussion support

[1617] Users enter questions and comments from their devices into a dashboard during the meeting. The server receives this input data and performs real-time analysis using generative artificial intelligence.

[1618] Input: User questions and comments

[1619] Data processing: The prompt "What are the causes of recent market fluctuations?" is sent to a generative AI system, and the answer is generated and displayed.

[1620] Output: Real-time responses generated

[1621] Step 9: Generate action items

[1622] The server analyzes the meeting's discussion content and automatically generates a concrete action plan. For example, it might send a prompt to the generative AI saying, "Please propose the next action plan."

[1623] Input: Discussion log data

[1624] Data processing: Generate specific action items based on generative artificial intelligence.

[1625] Output: Generated action items

[1626] Step 10: Generate and distribute meeting minutes.

[1627] After the meeting ends, the server automatically generates meeting minutes based on the meeting content and the generated action plan, and sends them to the user's terminal.

[1628] Input: Meeting content, action plan

[1629] Data processing: Convert meeting minutes to PDF format and send them to users via email.

[1630] Output: Meeting minutes sent to the user's device (PDF format)

[1631] (Application Example 1)

[1632] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1633] In today's markets, rapid and accurate decision-making is essential, but data collection, cleaning, and analysis are time-consuming and labor-intensive, making efficient operation difficult. Furthermore, the inability to provide timely and appropriate information and answers during meetings and discussions is a significant challenge.

[1634] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1635] In this invention, the server includes means for acquiring market data and economic indicator data from external data sources, means for cleaning and normalizing the acquired data, means for analyzing the data using generative AI to identify market trends and risk factors, means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start a roundtable discussion or crew meeting, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, means for analyzing meeting content and generating concrete action plans, means for distributing the generated action plans and meeting minutes to users, means for displaying graphs and charts that visually represent the analysis results, and means for collecting and analyzing market data, competitor information, and customer behavior data to support strategic planning for virtual store operations. This enables efficient and rapid decision-making and supports optimal strategic planning in real time for virtual store operations.

[1636] "External data sources" refer to external data providers or APIs that provide market data and economic indicator data.

[1637] "Market data" refers to data that includes information such as price, supply, and demand related to a specific market.

[1638] "Economic indicator data" refers to data that includes statistical information indicating the state of the economy, such as GDP, unemployment rate, and inflation rate.

[1639] "Cleaning" is the process of correcting or removing inappropriate or missing values ​​from data.

[1640] "Normalization" is the process of converting data obtained from different data sources into a unified format.

[1641] "Generative AI" is artificial intelligence that analyzes collected data and generates text to perform a specific task.

[1642] "Market trends" refer to information that indicates the fluctuation patterns of prices and demand in the market.

[1643] "Risk factors" refer to elements or events that could have a negative impact on the market or economy.

[1644] A "report" is a document that summarizes the results of an analysis and may include graphs and charts.

[1645] A "dashboard" is a web-based interface that allows users to access analysis results and reports.

[1646] A "roundtable discussion" refers to a small-scale discussion held in a meeting format.

[1647] A "crew meeting" refers to a meeting held to discuss a specific project or issue.

[1648] "Real-time" refers to data processing and information provision at the present moment.

[1649] An "action plan" is a specific plan of actions taken to achieve a particular challenge or objective.

[1650] "Meeting minutes" are documents that record the content discussed and decisions made during a meeting.

[1651] "Competitive information" refers to information about the activities and strategies of other competing companies in the market.

[1652] "Customer behavior data" refers to information about how customers used products and services.

[1653] This invention is a system that supports the operation of virtual stores by collecting market data and economic indicator data from external data sources and performing analysis using generative AI. A detailed embodiment for carrying out this invention is described below.

[1654] Data acquisition and preprocessing

[1655] server

[1656] The server collects market data, economic indicators, competitive information, and customer behavior data from external data sources. Specifically, the server retrieves this information using API requests. This data is received in formats such as JSON and XML. The server then cleans and normalizes the retrieved data. The cleaning process detects empty values ​​and outliers and corrects or removes them. The normalization process converts information from different data sources into a unified format.

[1657] Data analysis and report generation

[1658] server

[1659] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in a report format. This report is created in a visual format, including graphs and charts. The analysis results are stored on a server and prepared for display on a dashboard accessible to users. The dashboard is browser-based, and users can access it from PCs, tablets, smartphones, etc.

[1660] Roundtable discussion / crew meeting

[1661] User

[1662] Users access a web-based dashboard from their devices. The dashboard displays reports generated by the server, which users can use to initiate roundtables and crew meetings.

[1663] Real-time discussion support

[1664] server

[1665] During the meeting, users enter questions and comments from their devices into the dashboard. The server uses generative AI to analyze these inputs in real time and generate appropriate answers. The generated answers are immediately displayed on the dashboard, supporting the progress of the meeting.

[1666] Generating action items

[1667] server

[1668] By analyzing the content of the meeting discussion, the generative AI automatically generates specific action plans. For example, action plans such as "increase inventory" or "strengthen marketing campaigns" may be generated.

[1669] Minutes creation and distribution

[1670] server

[1671] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are then delivered to the user's device and shared with all meeting participants.

[1672] Specific example

[1673] The server calls an external API to retrieve market data in JSON format. The server imputes missing values ​​with averages and detects and corrects outliers. Generative AI identifies market trends and compiles them into a report. The user accesses a web-based dashboard from their terminal and starts a roundtable discussion. The server analyzes the user's questions, and the generative AI instantly generates and displays answers. During the meeting, the generative AI proposes the next action plan. After the meeting ends, the server automatically generates meeting minutes and sends them to the user's terminal.

[1674] Example of a prompt

[1675] Identify trends and risks from the following market data:

[1676] Data: [{'product': 'A', 'price': 100, 'demand': 200}, {'product': 'B', 'price': 150, 'demand': 180}]"

[1677] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1678] Step 1:

[1679] Data collection

[1680] The server retrieves market data, economic indicators, competitive information, and customer behavior data from external data sources via API requests. The server accesses a specified API endpoint and receives data in JSON or XML format. The input is the API request, and the output is the retrieved data in JSON or XML format as a response.

[1681] Step 2:

[1682] Data cleaning and normalization

[1683] The server cleans and normalizes the received data. Data cleaning detects empty values ​​and outliers and corrects or removes them based on statistical methods. Specifically, it imputes missing values ​​with the mean and detects and corrects outliers. The normalization process converts information from different data sources into a unified format. The input is the acquired data, and the output is the cleaned and normalized data.

[1684] Step 3:

[1685] Data Analysis

[1686] The server analyzes the cleaned and normalized data using generative AI (e.g., GPT-3 or BERT). Specifically, it generates prompt sentences suitable for analysis and inputs them into the generative AI. Based on these prompt sentences, the AI ​​identifies market trends and risk factors and returns the analysis results. The input consists of the cleaned and normalized data and prompt sentences, and the output is the analysis results.

[1687] Step 4:

[1688] Report generation

[1689] The server generates a report based on the analysis results. The report includes market trends and risk factors, as well as graphs and charts for visual clarity. The generated report is saved in formats such as HTML and PDF. The input is the analysis results, and the output is the generated report.

[1690] Step 5:

[1691] Dashboard display

[1692] Users access a web-based dashboard from their devices. The server displays the generated reports on the dashboard. Users can view the reports through the dashboard and start roundtables or crew meetings. The input is the generated reports, and the output is the dashboard displaying the reports.

[1693] Step 6:

[1694] Real-time Q&A

[1695] During a meeting, users input questions and comments from their devices into a dashboard. The server uses generative AI to analyze these inputs in real time and generate appropriate answers. The generated answers are displayed on the dashboard to support the progress of the meeting. The input consists of user questions and comments, and the output consists of the generated answers.

[1696] Step 7:

[1697] Action plan generation

[1698] The server analyzes the meeting discussions, and the generative AI automatically generates specific action plans. These plans may include concrete suggestions such as "increase inventory" or "strengthen marketing campaigns." The input is the meeting discussion content, and the output is the generated action plan.

[1699] Step 8:

[1700] Minutes generation and distribution

[1701] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are converted to PDF format or another format and delivered to the user's device. The input is the meeting discussion content and the generated action plan, and the output is the automatically generated meeting minutes.

[1702] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1703] This invention combines a system that collects market data and economic indicator data from external data sources, performs analysis using generative AI, and supports roundtable discussions and crew meetings based on the results, with an emotion engine that recognizes user emotions. The embodiments of this system are described in detail below.

[1704] Data acquisition and preprocessing

[1705] server

[1706] The server collects market and economic indicator data from external data sources. Specifically, the server retrieves information from data providers using API requests. This data is received in formats such as JSON and XML. The server then cleans and normalizes the retrieved data. The cleaning process detects empty values ​​and outliers and removes or fills them in. The normalization process converts information from different data sources into a unified format.

[1707] Data analysis and report generation

[1708] server

[1709] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in report format. This report is created in a visual format, including graphs and charts. The analysis results are stored on a server and prepared for display on a dashboard. This dashboard provides an interface for users to view reports and initiate roundtables and crew meetings.

[1710] Roundtable discussion / crew meeting

[1711] User

[1712] Users access a web-based dashboard from their own devices (PC, tablet, etc.). The dashboard displays reports generated by the server, which users use to initiate roundtables and crew meetings.

[1713] Emotion recognition and real-time discussion support

[1714] server

[1715] During the meeting, users enter questions and comments from their devices into a dashboard. In addition, an emotion engine operates to recognize emotions from user speech and text input. The server uses generative AI and the emotion engine to analyze these inputs in real time and generate appropriate responses. The generated responses are immediately displayed on the dashboard to support the progress of the meeting.

[1716] Analysis of discussion content and generation of action plans

[1717] server

[1718] By analyzing the content of discussions during meetings, the generative AI and emotion engine automatically generate specific action plans. For example, it proposes action plans that reflect emotional data, such as "If user anxiety is detected, review risk management measures."

[1719] Minutes creation and distribution

[1720] server

[1721] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes also include user sentiment data recognized by the sentiment engine. For example, changes in emotions during discussions and the tone of the meeting are reflected in the minutes. The generated minutes are delivered to the user's device and shared with all meeting participants.

[1722] Specific example

[1723] 1. Data Collection: The server calls an external API to retrieve market data in JSON format.

[1724] 2. Data Cleaning: The server imputes missing values ​​with the mean and detects and corrects outliers.

[1725] 3. Data Analysis: Generative AI identifies market trends and compiles them into reports.

[1726] 4. Dashboard Access: Users access the web-based dashboard from their devices and begin the discussion.

[1727] 5. Emotion Recognition: The emotion engine recognizes emotions from the user's speech and text input.

[1728] 6. Real-time response generation: The server analyzes the user's question, and the generative AI and emotion engine instantly generate and display the response.

[1729] 7. Action Plan Generation: During the meeting, generate a concrete action plan based on emotional expression.

[1730] 8. Distribution of meeting minutes: After the meeting ends, the server automatically generates meeting minutes, including sentiment data, and sends them to the user's device.

[1731] This invention makes it possible to conduct efficient meetings through real-time analysis, which was difficult to achieve with conventional methods, and to formulate flexible action plans that reflect user sentiment data.

[1732] The following describes the processing flow.

[1733] Step 1:

[1734] Calling an external API

[1735] The server retrieves the latest data by sending HTTP requests to external APIs that provide market and economic indicator data. Specifically, it makes requests using API endpoint URLs and receives data in JSON or XML format.

[1736] Step 2:

[1737] Receiving API Responses

[1738] The server receives a response from an external API and temporarily stores the retrieved data. The stored data is then used in the next processing step.

[1739] Step 3:

[1740] Data Cleaning

[1741] The server cleans the acquired data. Specifically, it detects empty values ​​and outliers in the data and removes or imputes them. For example, missing values ​​are imputed with the mean of past data, and outliers are replaced with appropriate values.

[1742] Step 4:

[1743] Data normalization

[1744] The server normalizes the cleaned data. Specifically, it converts data obtained from different data sources into a unified format to maintain consistency. For example, it converts data in different time formats into a common timestamp format.

[1745] Step 5:

[1746] Initialization of generative AI

[1747] The server initializes generative AI (such as GPT-3 or BERT). It loads the necessary models and parameters and prepares the data for analysis.

[1748] Step 6:

[1749] Data input and analysis

[1750] The server feeds the pre-processed data into the generative AI and begins data analysis. The generative AI identifies market trends and risk factors and generates analysis results based on them.

[1751] Step 7:

[1752] Report generation

[1753] The server generates a report based on the analysis results obtained from the generative AI. This report includes text explanations of the analysis results, as well as graphs and charts. The information is presented in a visually easy-to-understand format.

[1754] Step 8:

[1755] Saving reports and displaying dashboards

[1756] The server stores the generated reports in a database and displays them on a dashboard for user access. The dashboard is provided via a web-based interface.

[1757] Step 9:

[1758] Access to the dashboard

[1759] Users access the dashboard from their own devices (PC, tablet, etc.) and view the generated reports. Based on these reports, users can then initiate roundtable discussions or crew meetings.

[1760] Step 10:

[1761] emotion recognition

[1762] The server uses an emotion engine to recognize emotions from user statements and text input. It analyzes specific keywords and expressions to determine the user's emotional state.

[1763] Step 11:

[1764] Real-time analysis and response generation

[1765] The server analyzes user questions and comments in real time and generates appropriate responses using generative AI and an emotion engine. For example, if a user expresses anxiety, the server analyzes it and generates a reassuring response.

[1766] Step 12:

[1767] Display the answer

[1768] The server displays the generated responses on a dashboard and provides them to users in real time, ensuring a smooth flow of the meeting.

[1769] Step 13:

[1770] Analysis of discussion content and generation of action plans

[1771] The server uses an emotion engine and generative AI to analyze the content of discussions during meetings and automatically generates concrete action plans. For example, it proposes an action plan that reflects the emotions expressed by the user.

[1772] Step 14:

[1773] Minutes generation

[1774] The server automatically generates meeting minutes based on the meeting content, the generated action plan, and the user's emotional state as recognized by the emotion engine.

[1775] Step 15:

[1776] Distribution of meeting minutes

[1777] After the meeting ends, the server distributes the generated meeting minutes to each user's device. This ensures that all meeting participants receive the minutes, facilitating smooth information sharing.

[1778] This system enables efficient collection and analysis of precise information from external data sources, real-time meeting support that takes user sentiment into consideration, and the development of concrete action plans.

[1779] (Example 2)

[1780] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1781] Conventional meeting systems have made it difficult to perform real-time data analysis and generate flexible action plans that reflect user sentiment. Furthermore, efficient analysis of meeting content, automatic generation of concrete action plans based on that analysis, and rapid distribution of meeting minutes to all participants have been challenging. This invention aims to solve these problems and provide a system that streamlines and enhances meeting management.

[1782] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1783] In this invention, the server includes means for acquiring market data and economic indicator data from external data sources, means for cleaning and normalizing the acquired data, means for analyzing the data using generative AI to identify market trends and risk factors, means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start a roundtable discussion or crew meeting, means for recognizing emotions from user statements and text inputs, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, means for analyzing meeting content and generating concrete action plans that reflect user emotion data, and means for automatically generating meeting minutes based on the meeting content and generated action plans and distributing them to users. This enables the generation of flexible action plans through real-time data analysis and emotion recognition, as well as rapid analysis of meeting content and automatic generation and distribution of meeting minutes.

[1784] "External data sources" refer to external information providers, APIs, and other entities that provide market data and economic indicator data.

[1785] "Market data" refers to data related to financial markets, such as stock prices, exchange rates, and commodity prices.

[1786] "Economic indicator data" refers to statistical data that shows the state of the economy, such as GDP, unemployment rate, and consumer price index.

[1787] "Cleaning" refers to the process of detecting, correcting, or removing empty or outlier values ​​in data.

[1788] "Normalization" refers to the process of converting data obtained from different data sources into a unified format.

[1789] "Generative AI" refers to artificial intelligence models that perform tasks such as data analysis and natural language generation (e.g., GPT-3, BERT, etc.).

[1790] "Market trends" refer to the temporal movements and fluctuation patterns of market data.

[1791] "Risk factors" refer to elements that could have a negative impact on markets or economic activity.

[1792] A "report" refers to a document or report that summarizes the results of an analysis.

[1793] A "dashboard" refers to a web-based interface that allows users to access and interact with analytical results and reports.

[1794] A "roundtable discussion" refers to a type of meeting where participants freely exchange opinions on a specific topic.

[1795] A "crew meeting" refers to a meeting held within a specific team or organization.

[1796] "Means of recognizing emotions" refers to algorithms and engines that identify emotions from user statements and text input.

[1797] "Means of real-time analysis" refers to the ability to instantly analyze input data and immediately generate and display results.

[1798] An "action plan" refers to a specific plan of action or measures.

[1799] "Meeting minutes" refers to a document that records the content of a meeting, the matters discussed, the decisions made, and the action plan.

[1800] This invention combines a system that collects market data and economic indicator data from external data sources, performs analysis using generative AI, and supports roundtable discussions and crew meetings based on the results, with an emotion engine that recognizes user emotions. The embodiments of this system are described in detail below.

[1801] The server uses API requests to retrieve market data and economic indicator data from external data sources. Specifically, the server accesses a URL like "https: / / api.example.com / marketdata" and receives the data in JSON format.

[1802] Next, the server cleans and normalizes the received data. Data cleaning involves imputing missing values ​​with the mean and detecting and correcting outliers. This is done using libraries such as Python's pandas library.

[1803] Cleaned and normalized data is analyzed by generative AI models (e.g., GPT-3, BERT, etc.). The server inputs this data into the generative AI to identify market trends and risk factors. The information obtained from the analysis is generated and saved as a report in a visual format (graphs, charts, etc.).

[1804] The analysis results are displayed on a dashboard. This uses web frameworks such as Python's Flask or Django, and is provided as a web-based interface accessible to users. Users access this dashboard from their devices and start roundtables or crew meetings based on the generated reports.

[1805] During the meeting, users enter questions and comments from their devices onto the dashboard. The emotion engine recognizes emotions from the user's statements and text input. For example, if a user enters "What do you think about the current market?", the emotion engine recognizes "anxiety," and the generative AI immediately generates and displays the response, "The market is highly volatile, so caution is needed."

[1806] The meeting content is analyzed in real time, and specific action plans are generated that reflect the user's emotional data. For example, the emotional engine analyzes statements such as "the risk is too high," and the generative AI generates an action plan such as "propose reviewing risk management measures."

[1807] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes also include sentiment data recognized by the sentiment engine, detailing specific points such as "proposed a review of risk management measures." The generated minutes are then delivered to the user's device and shared with all meeting participants.

[1808] This invention enables efficient meeting management through real-time analysis, which was difficult to achieve with conventional methods, and the development of flexible action plans that reflect user sentiment data. An example of a prompt is "Please tell me about future market trends." By entering this prompt, a generative AI can analyze it and provide a specific answer in real time.

[1809] The above details the specific method of the present invention. This system not only dramatically improves the efficiency of business meetings and analysis, but also contributes to an improved user experience.

[1810] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1811] Step 1: Data Collection

[1812] server

[1813] The server sends API requests to external data sources to retrieve market data and economic indicator data. For example, the server accesses a URL like "https: / / api.example.com / marketdata" and receives data in JSON format.

[1814] Input-based action: Request to an external API.

[1815] Output: Acquired market data and economic indicator data.

[1816] Step 2: Data Preprocessing

[1817] server

[1818] The server cleans and normalizes the data it receives. Data cleaning involves imputing missing values ​​with the mean and detecting and correcting outliers. Normalization converts data obtained from different data sources into a unified format.

[1819] Input-based operation: Cleaning and normalizing incoming data.

[1820] Output: Cleaned and normalized data.

[1821] Step 3: Data Analysis

[1822] server

[1823] The cleaned and normalized data is input into a generative AI for analysis. For example, the server supplies data to a generative AI model (e.g., GPT-3) to identify market trends and risk factors.

[1824] Input-based operation: Data input to a generative AI model.

[1825] Output: Analysis results identifying market trends and risk factors.

[1826] Step 4: Prepare to generate reports and display dashboards.

[1827] server

[1828] Based on the analysis results, a visual report is generated. The server uses web frameworks such as Python's Flask or Django to prepare the report in HTML format for display on the dashboard.

[1829] Input-based operation: Generates visual reports and HTML using analysis results.

[1830] Output: HTML for visual reports and dashboards.

[1831] Step 5: Access the Dashboard

[1832] User

[1833] Users access a web-based dashboard from their devices and initiate roundtables or crew meetings based on the displayed analytics reports.

[1834] Input-based action: User accesses the dashboard via browser.

[1835] Output: Analysis report displayed on the dashboard.

[1836] Step 6: Emotion Recognition and Real-Time Discussion Support

[1837] server

[1838] During a meeting, users enter questions and comments from their devices onto a dashboard. The server uses an emotion engine to recognize the user's emotions from these inputs. It then works in conjunction with generative AI to generate and display appropriate answers in real time. For example, if a user enters "What do you think about the current market?", the server's emotion engine recognizes the user's anxiety, and the generative AI instantly generates an answer regarding market fluctuations.

[1839] Input-based operation: Sentiment recognition and response generation based on user input.

[1840] Output: Real-time responses displayed on the dashboard.

[1841] Step 7: Generate an action plan

[1842] server

[1843] The system analyzes meeting content in real time and generates concrete action plans that reflect user sentiment data. For example, the sentiment engine analyzes statements such as "the risk is too high," and the generative AI proposes a revision of risk management measures.

[1844] Input-based actions: Analysis of meeting content and sentiment data.

[1845] Output: A concrete action plan.

[1846] Step 8: Generate and distribute meeting minutes

[1847] server

[1848] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes, which include sentiment data, are delivered to the user's device.

[1849] Input-based operation: Generate meeting minutes based on meeting content and action plan.

[1850] Output: Meeting minutes distributed to users.

[1851] The above outlines the processing steps of this system and the specific operational details of each step. This enables efficient and flexible meeting management through real-time analysis and emotion recognition.

[1852] (Application Example 2)

[1853] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1854] Conventional meeting support systems do not adequately support real-time discussions using market and economic indicator data. Furthermore, they struggle to recognize user emotions and generate effective action plans based on them. In addition, there is a lack of means to conduct meetings and make decisions in a way that takes staff emotions into consideration in the operation of physical stores.

[1855] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for acquiring market data and economic indicator data from an external data source, means for cleaning and normalizing the acquired data, means for analyzing the data using generative AI to identify market trends and risk factors, means for generating and saving reports based on the analysis results, means for users to access the generated reports via a dashboard and start a roundtable discussion or crew meeting, means for analyzing user questions and comments in real time and generating and displaying appropriate answers, means for analyzing meeting content and generating a concrete action plan, means for distributing the generated action plan and meeting minutes to the user, means for analyzing the emotional state of store staff using market data and sentiment data and proposing an appropriate action plan, and means for conducting a meeting based on emotional state and market data through generative AI. This enables efficient meeting management through real-time analysis and the formulation of flexible action plans that reflect sentiment data.

[1856] "External data sources" refer to sources of information used to collect market data and economic indicator data from outside the system, such as the internet or third-party APIs.

[1857] "Market data" refers to statistical information related to a specific market, such as product sales, price trends, and consumer demand.

[1858] "Economic indicator data" refers to statistical information such as unemployment rates, GDP growth rates, and inflation rates that show the overall trends of the economy.

[1859] "Cleaning" is the process of detecting empty or outlier values ​​from acquired data and correcting or removing them.

[1860] "Normalization" is the process of converting information obtained from different data sources into a unified format.

[1861] "Generative AI" is a type of artificial intelligence that automatically generates new information and content based on large datasets.

[1862] A "dashboard" is an interface that allows users to access analysis results and reports and view visualized information.

[1863] An "emotion engine" is an algorithm or system that recognizes and analyzes emotions from a user's speech or text input.

[1864] "Real-time analysis" is a processing method that performs analysis immediately on collected data or user input and provides the results.

[1865] An "action plan" is a plan that proposes specific action guidelines and countermeasures based on analysis results and sentiment data.

[1866] Meeting minutes are documents that record the content of a meeting, the decisions made, and the proposed action plans, so that they can be referenced later.

[1867] A "physical store" is a sales facility located in a physical place, a store that customers can visit in person.

[1868] This invention is a system that collects market data and economic indicator data and supports the operation of physical stores through analysis using generative AI. This system recognizes user emotions in real time and proposes appropriate action plans. The series of functions for this purpose operate as follows:

[1869] Data acquisition and preprocessing

[1870] The server collects market and economic indicator data from external data sources. Specifically, the server retrieves information using API requests. The retrieved data is often received in JSON format. The server then cleans and normalizes the data. The cleaning process detects empty values ​​and outliers and either fills them in or removes them. The normalization process converts information from different data sources into a unified format.

[1871] Data analysis and report generation

[1872] Cleaned and normalized data is analyzed by generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, generating the results in a report format. This report is created in a visual format, including graphs and charts. The analysis results are stored on a server and prepared for display on a dashboard. This dashboard includes an interface for users to view the report and initiate discussions or meetings.

[1873] Emotion recognition and argument support

[1874] During the meeting, users access the dashboard from their devices (e.g., smartphones or tablets) to enter questions and comments. The emotion engine recognizes emotions from the user's statements and text input. This emotion recognition works in conjunction with generative AI to generate real-time analysis and responses that correspond to the user's emotional state. The generated responses are immediately displayed on the dashboard to support the progress of the meeting.

[1875] Action plan generation and meeting minutes distribution

[1876] During the meeting, the server analyzes the discussion content, and the generative AI and emotion engine automatically generate a concrete action plan. This action plan includes specific measures that reflect market data and emotion data. For example, if user anxiety is detected, it will suggest reviewing inventory or rearranging staff. After the meeting ends, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes, which also include emotion data, are distributed to the user's device.

[1877] Examples of specific cases and prompt statements

[1878] As a concrete example, suppose a server calls an external API and retrieves economic indicator data in JSON format. This data is cleaned, and missing values ​​are imputed with the mean. A generative AI (e.g., GPT-3) analyzes the data using the "market data" and "sentiment analysis" results as prompts. The following is an example of such prompts:

[1879] Market data: Sales increased by 10% compared to the previous month. Demand for flagship products is increasing.

[1880] Sentiment analysis: Currently, many of the staff are showing positive motivation.

[1881] Please generate a meeting proposal based on the above.

[1882] This process enables the system to efficiently manage meetings by combining real-time analysis and emotion recognition, and allows for the development of flexible action plans that reflect the user's emotions.

[1883] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1884] Step 1: Data Acquisition

[1885] The server sends API requests to external data sources to retrieve market data and economic indicator data. Specifically, the server accesses the API endpoint via the internet and receives data in JSON format. The input is the API request, and the output is the retrieved market data and economic indicator data.

[1886] Step 2: Cleaning

[1887] The server cleans the received market and economic indicator data. The cleaning process detects and removes or imputes empty or outlier values. The input is the acquired market and economic indicator data, and the output is the cleaned data. For example, missing values ​​are imputed with the mean, and outliers are corrected to appropriate values.

[1888] Step 3: Normalize the data

[1889] The server normalizes the cleaned data. The normalization process converts information from different data sources into a unified format. The input is cleaned data, and the output is normalized data. For example, it converts numbers expressed in different units to a unified unit.

[1890] Step 4: Data Analysis

[1891] The server analyzes normalized data using generative AI (e.g., GPT-3 or BERT). The generative AI identifies market trends and potential risk factors, and generates the results in report format. The input is normalized data, and the output is a report containing the analysis results.

[1892] Step 5: Generate and save the report

[1893] The server generates and saves a report based on the analysis results. The report includes graphs and charts for visual representation. The input is the analysis results, and the output is the generated report. The report is stored on the server and accessible via the dashboard.

[1894] Step 6: Access the Dashboard

[1895] Users access the dashboard from their own devices (e.g., smartphones or tablets) and view the generated reports. Based on these reports, users can start roundtables or crew meetings. The input is the user's login information, and the output is the report display screen.

[1896] Step 7: Emotion Recognition

[1897] During the meeting, users enter questions and comments from their terminals into the dashboard. The server receives this information and uses an emotion engine to recognize emotions from the user's statements and text input. The input is the user's text input, and the output is the emotion recognition result.

[1898] Step 8: Real-time response generation

[1899] The server uses generative AI and an emotion engine to analyze user input and generate appropriate responses. The generated responses are immediately displayed on the dashboard. Input consists of emotion recognition results and user text input, while output is the generated response.

[1900] Step 9: Generate an action plan

[1901] The server analyzes the discussion content during the meeting and generates a concrete action plan using an emotion engine and generative AI. The action plan reflects market data and emotion data. The input is the meeting content and emotion recognition results, and the output is the concrete action plan.

[1902] Step 10: Generate and distribute meeting minutes.

[1903] Once the meeting concludes, the server automatically generates meeting minutes based on the meeting content and the generated action plan. These minutes are then distributed to the user's terminal. The input consists of the meeting content and the generated action plan, while the output is the generated meeting minutes.

[1904] Example of a prompt

[1905] Market data: Sales increased by 10% compared to the previous month. Demand for flagship products is increasing.

[1906] Sentiment analysis: Currently, many of the staff are showing positive motivation.

[1907] Please generate a meeting proposal based on the above.

[1908] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1909] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1910] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1911] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1912] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1913] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1914] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1915] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1916] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1917] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1918] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1919] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1920] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1921] 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.

[1922] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1923] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1924] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1925] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1926] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1927] The descriptions and illustrations presented above are detailed explanations of the technical aspects of thi...

Claims

1. Means for obtaining market data and economic indicator data from external data sources, A means for cleaning and normalizing the acquired data, Generative AI is used to analyze data and identify market trends and risk factors, A means for generating and saving reports based on analysis results, A means for users to access reports generated via the dashboard and initiate a roundtable discussion or crew meeting, A means for analyzing user questions and comments in real time and generating and displaying appropriate answers, A means to analyze meeting content and generate concrete action plans, A means of distributing the generated action plan and meeting minutes to users, A system that includes this.

2. The system according to claim 1, comprising means for detecting empty values ​​or outliers from acquired data, and correcting or removing them.

3. The system according to claim 1, comprising means for selecting a template to visually represent the analysis results using a generative AI and inserting graphs and charts.

Images