system

Abstract

Traditional stadiums had limitations in improving spectator engagement and the viewing experience, requiring manual processes for things like match commentary, statistics analysis, and player feedback. This resulted in information delays and human errors, making it difficult to provide the best possible experience for spectators and players. There was also a lack of features and technologies to maximize monetization opportunities. [Solution] A means for acquiring video feeds and real-time event data of the match, A means for analyzing acquired video feeds and event data in real time and automatically generating explanatory text, A means of sending the generated explanatory text to the user's terminal and displaying it, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including 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 conventional stadiums, there are limitations in improving spectator engagement and viewing experience, and manual work is required for game commentary, stats analysis, player feedback, etc., resulting in information delays and human errors, making it difficult to provide an optimal experience for spectators and players. There is also a problem of lack of functions and technologies for maximizing revenue opportunities. The present invention aims to solve these problems and improve spectator engagement, viewing experience, player feedback, and create new revenue opportunities.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for acquiring video feeds and real-time event data of a match, means for analyzing the acquired video feeds and event data in real time and automatically generating commentary, and means for transmitting and displaying the generated commentary on a user terminal. Furthermore, it includes means for collecting various data generated during the match in real time, means for analyzing the collected data and generating statistical information, and means for transmitting and displaying the generated statistical information on a user terminal. It also includes means for collecting player movement data and performance data during the match, means for analyzing the collected data and generating individualized feedback for each player, and means for transmitting and displaying the generated feedback on a user terminal. Such a system is expected to further enhance the appeal of watching sports, maximize stadium revenue, and contribute to the development of the entire sports industry.

[0006] A "match video feed" is video data that provides footage of a sports match in real time or in recorded format.

[0007] "Real-time event data" refers to data that records important events that occur during a match, such as goals, fouls, and player substitutions, in real time.

[0008] "Analyzing data in real time" means processing acquired data instantly and providing the results in an immediately usable format.

[0009] "Methods for automatically generating explanatory text" refers to technologies that use AI and natural language processing to automatically create explanatory texts about the progress of a match and important events.

[0010] "User terminal" is a general term for devices that users use to receive and display information, such as smartphones, tablets, and PCs.

[0011] "Generating statistical information" means visualizing performance and trends from collected data as numbers and graphs.

[0012] "Player feedback" refers to personalized advice and information that assesses a player's performance and identifies areas for improvement.

[0013] "Monetization opportunities" refer to business opportunities to increase revenue through advertising, sponsorships, ticket sales, and other means.

[0014] "Functions and technologies" refer to specific means and tools used to improve audience engagement, provide match information, manage facilities, and enhance security. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] Shows 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 Embodiment 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 Embodiment 2 when the 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 the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] 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.

[0017] First, the terms used in the following description will be described.

[0018] In the following embodiments, the numbered processor (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.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] 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.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] The following describes embodiments for carrying out the present invention. This system acquires and analyzes video feeds and real-time event data of matches and provides various information to spectators and players.

[0037] System Overview

[0038] This system consists of the following main components:

[0039] 1. Data acquisition module

[0040] 2. Data Analysis Module

[0041] 3. Natural Language Generation Module

[0042] 4. Data transmission module

[0043] 5. User Interface (Terminal)

[0044] 6. Feedback Generation Module

[0045] Data acquisition module

[0046] The server retrieves the match video feed and real-time event data. This data includes a video stream of the sports match and real-time recordings of important events such as goals and fouls.

[0047] The server uses APIs and WebSockets to retrieve video feeds and event data.

[0048] Data Analysis Module

[0049] The system analyzes video feeds and event data acquired by the server in real time. Machine learning algorithms and motion recognition technologies are used for the analysis.

[0050] For example, when a goal is scored during a match, the system automatically identifies the video footage of that exact moment.

[0051] Natural Language Generation Module

[0052] The server automatically generates explanatory text based on the results of data analysis. Natural language generation technology is used to create detailed explanations about the flow of the match and events.

[0053] For example, it generates a descriptive sentence such as, "Player A scored a magnificent goal!"

[0054] Data transmission module

[0055] The server sends the generated explanatory text and statistical information to the terminal.

[0056] The server uses WebSocket or an API to send data to the terminal in real time.

[0057] User interface (terminal)

[0058] The terminal displays the received explanatory text and statistical information on the user interface. This allows users (spectators) to understand the progress of the match and detailed information in real time.

[0059] For example, a smartphone app could display statistics such as "Player A's current distance covered: 10km".

[0060] Feedback generation module

[0061] The server collects and analyzes player movement and performance data during matches.

[0062] The server generates personalized feedback and provides it to players and coaches after the match ends.

[0063] For example, it can generate feedback such as "You should move a little more towards the center when defending" and send it to the player's device (smartphone).

[0064] Specific example

[0065] 1. Real-time commentary during the match

[0066] The server analyzes the match video feed and detects the event "Player B scored a goal."

[0067] The server generates a natural language explanation such as "Player B scored a goal with a brilliant dribble!" and sends it to the terminal.

[0068] Users can view this explanation in real time using a smartphone app.

[0069] 2. Real-time statistics provided

[0070] The server collects player distance data during the match and confirms that player C has reached a distance of 8km.

[0071] The server generates statistical information such as "Player C's current distance covered: 8km" and sends it to the terminal.

[0072] Users can view this statistical information on large screens inside the stadium or on their smartphones.

[0073] 3. Player feedback after the match

[0074] After the match ends, the server analyzes player D's performance data to identify areas for improvement in his defensive play.

[0075] The server generates feedback stating, "More lateral movement is needed during defense," and sends it to the terminal.

[0076] The user (player) receives this feedback on their smartphone and uses it to identify areas for improvement for the next match.

[0077] In this way, this system can be used to significantly improve audience engagement, provide players with personalized feedback, and enhance their performance.

[0078] The following describes the processing flow.

[0079] Processing steps for automatically generated explanations

[0080] Step 1:

[0081] The server retrieves the match video feed and real-time event data. The server uses an API to obtain the video feed URL, establishes a WebSocket connection, and receives the event data.

[0082] Step 2:

[0083] The server analyzes the acquired video feed. A machine learning model is used to detect player movements and important events (e.g., goals, fouls) within the video frames.

[0084] Step 3:

[0085] The server analyzes real-time event data and compares it with the analysis results of the video feed. It identifies important events that match the event data.

[0086] Step 4:

[0087] The server uses natural language generation technology to generate explanatory text based on identified events. Templates are used to instantly convert the analysis results into text.

[0088] Step 5:

[0089] The server generates an explanatory text and sends it to the terminal. The explanatory text is sent to the terminal in real time using a WebSocket connection.

[0090] Step 6:

[0091] The terminal displays the received explanatory text on the user interface. Users can check the explanation in real time on their smartphones, tablets, etc.

[0092] Processing steps for real-time statistics analysis

[0093] Step 1:

[0094] The server collects various data generated during a match in real time. Data is periodically polled using an API or received in real time via a WebSocket connection.

[0095] Step 2:

[0096] The server analyzes the collected data, calculating statistical data such as player distance covered and pass success rate.

[0097] Step 3:

[0098] The server generates visualized statistical information based on the analysis results. This information is then converted into graphs and charts to visualize the data.

[0099] Step 4:

[0100] The server sends generated statistics to the terminal. Statistics data is sent to the terminal using a WebSocket connection or API.

[0101] Step 5:

[0102] The system displays statistical information received by the device on the user interface. Users can check the statistical information on their smartphones or on large screens in the stadium.

[0103] Feedback generation processing steps

[0104] Step 1:

[0105] The server collects player movement and performance data during matches. An API is used to retrieve each player's position and performance data.

[0106] Step 2:

[0107] The server analyzes the collected data to evaluate the players' movements and performance. Machine learning models are used for the analysis.

[0108] Step 3:

[0109] The server generates personalized feedback based on the analysis results. Using evaluation data and templates, it creates specific areas for improvement and advice.

[0110] Step 4:

[0111] The server generates feedback and sends it to the device. Feedback is sent to the player's device via email or a dedicated app.

[0112] Step 5:

[0113] The device displays the feedback it receives on the user interface. Users (players) can review the feedback and identify areas for improvement for the next match.

[0114] Processing steps for providing generated content

[0115] Step 1:

[0116] The server collects past match data and player information. It queries the database to retrieve the necessary data.

[0117] Step 2:

[0118] Based on data collected by the server, engaging content (articles, highlight videos, etc.) is generated. Natural language generation tools and video editing tools are used to create the content.

[0119] Step 3:

[0120] Convert server-generated content into a format suitable for the user interface. Export videos and articles in the appropriate format.

[0121] Step 4:

[0122] The server sends the generated content to the device. Content is sent to the device using an API or WebSocket connection.

[0123] Step 5:

[0124] The device displays the received content to the user. The user can view the content on a smartphone, tablet, or other device.

[0125] These processing steps enable the system to significantly improve audience engagement and the viewing experience.

[0126] (Example 1)

[0127] 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."

[0128] Conventional sports viewing systems have struggled to analyze live video and statistical information during matches and automatically generate commentary. This has resulted in a lack of detailed and timely information for spectators and athletes, limiting opportunities for engagement and performance improvement. This invention aims to solve these problems and provide a more interactive and informative viewing experience.

[0129] 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.

[0130] In this invention, the server includes means for acquiring video feeds and real-time event data of a match; means for analyzing the acquired video feeds and event data in real time and identifying goals and player actions using machine learning algorithms; means for automatically generating explanatory text using natural language generation technology based on the analysis results; and means for transmitting and displaying the generated explanatory text on a user terminal. This makes it possible to provide important moments and detailed statistical information of the match in real time.

[0131] A "video feed" refers to the input data used to acquire and distribute real-time footage of a match.

[0132] "Real-time event data" refers to data used to record and transmit important events that occur during a match, such as goals and fouls, in real time.

[0133] A "machine learning algorithm" refers to a computational method that learns patterns in data and automates specific tasks.

[0134] "Natural language generation technology" refers to the technology that generates text in natural language that humans can understand, based on analyzed data.

[0135] "Explanatory text" refers to text that explains events and statistical information that occur during a match, and is intended to provide information to spectators and players.

[0136] A "user terminal" is an electronic device used to receive and display information, and includes smartphones, tablets, computers, and other electronic devices.

[0137] "Statistical information" refers to numerical data about the performance of players and teams during a match.

[0138] "Feedback" refers to information provided to players and coaches after a match, including areas for improvement and advice.

[0139] "Analysis results" refer to the final output after analyzing the collected data, and include explanatory text, statistical information, and feedback.

[0140] "Collection means" refers to the methods and devices used to acquire the necessary data.

[0141] System Overview

[0142] This invention relates to a system that acquires video feeds and real-time event data of a match, analyzes them to automatically generate commentary, and transmits and displays the commentary and statistical information to a user terminal. The system consists of a server, a terminal, and a user, and each component works in cooperation with each other.

[0143] Specific examples of hardware and software to be used

[0144] The server requires a high-performance data processing computer and a network interface. Data analysis utilizes software implementing machine learning algorithms such as TENSORFLOW® and OpenPose. Generative AI models such as GPT-3® are used for natural language generation. APIs and WebSockets are used for data transmission and reception.

[0145] The devices include smartphones, tablets, or large screens within the stadium. These devices receive data transmitted from the server in real time and display it to the user.

[0146] Users include spectators watching the game, as well as players and their coaches who want to improve their performance. Users receive game progress updates, statistics, and feedback through smartphones, tablets, and large screens in the stadium.

[0147] Specific example

[0148] 1. Real-time commentary during the match

[0149] The server analyzes the match video feed and detects an event such as "Player B scored a goal." The server generates a natural language commentary such as "Player B scored a goal with a brilliant dribble!" and sends it to the device. The user can view this commentary in real time on their smartphone app.

[0150] 2. Real-time statistics provided

[0151] The server collects player distance data during the match and confirms that player C has reached 8km. The server generates statistics such as "Player C's current distance: 8km" and sends them to the terminal. The user can view these statistics on a large screen in the stadium or on their smartphone.

[0152] 3. Player feedback after the match

[0153] After the match ends, the server analyzes player D's performance data to identify areas for improvement in defense. The server generates feedback such as "More lateral movement is needed during defense" and sends it to the device. The user (player) receives this feedback on their smartphone and reviews the areas for improvement for the next match.

[0154] Example of a prompt

[0155] "This system analyzes video feeds and real-time event data during matches to provide information to spectators and players in real time. For example, the moment player A scores a goal, it generates commentary and notifies a smartphone app. Player distance covered and performance data are also displayed in real time, and specific feedback is provided to players after the match ends."

[0156] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0157] Step 1:

[0158] The server retrieves the match video feed and real-time event data.

[0159] Specific operation: The server uses the official FIFA API to retrieve real-time video streams. Simultaneously, it receives event data such as goals and fouls during the match via WebSocket.

[0160] Input: FIFA official API endpoint and WebSocket connection information

[0161] Output: Real-time video feed and event data

[0162] Step 2:

[0163] The server analyzes acquired video feeds and event data in real time.

[0164] Specific operation: The server analyzes the video feed using TensorFlow and OpenPose to detect specific events (e.g., goal scenes). It also applies machine learning algorithms to recognize player actions (e.g., shots and dribbles).

[0165] Input: Video feed and real-time event data

[0166] Output: Analyzed event information and player motion data

[0167] Step 3:

[0168] The server generates a natural language explanation based on the analysis results.

[0169] Specific operation: The server uses a generative AI model such as GPT-3 to create explanatory text based on the analyzed event information. For example, it might generate an explanatory text such as, "Player A scored a magnificent goal!"

[0170] Input: Analysis results (event information and player movement data)

[0171] Output: Auto-generated natural language explanation

[0172] Step 4:

[0173] The server sends the generated explanatory text and statistical information to the terminal.

[0174] Specific operation: The server sends generated explanatory text and statistical information to the terminal in real time using WebSocket or a REST API.

[0175] Input: Automatically generated explanatory text and statistical information

[0176] Output: Explanatory text and statistical information sent to the user's terminal.

[0177] Step 5:

[0178] The data received by the terminal is displayed on the user interface.

[0179] Specific operation: The device displays explanatory text and statistical information on the screen, providing it visually to the user. For example, a smartphone app might display "Player A's current distance traveled: 10km" as a notification.

[0180] Input: Explanatory text and statistical information sent from the server

[0181] Output: Explanatory text and statistics displayed on the user interface

[0182] Step 6:

[0183] The server collects and analyzes player movement and performance data during the match.

[0184] Specific operation: The server collects and analyzes real-time player movement data (e.g., distance traveled, location information) during a match. This allows for a detailed understanding of each player's performance.

[0185] Input: Player movement data during the match

[0186] Output: Analyzed performance data for each player

[0187] Step 7:

[0188] The server generates personalized feedback based on the analysis results.

[0189] Specific operation: Based on the analysis results, the server creates feedback for each player, including specific areas for improvement and advice. For example, it might generate feedback such as, "You should move a little more towards the center when defending."

[0190] Input: Analyzed performance data for each player

[0191] Output: Individualized feedback

[0192] Step 8:

[0193] The server sends the generated feedback to the user's terminal for display.

[0194] Specific operation: The server sends the generated feedback to the device (e.g., the player's smartphone), and the device displays that feedback.

[0195] Input: Personalized feedback

[0196] Output: Feedback sent to the user terminal and displayed feedback

[0197] (Application Example 1)

[0198] 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."

[0199] In sports matches, it is difficult for spectators and players to obtain detailed information in real time. Furthermore, there are limited means for players to receive individual feedback after the match has ended. As a result, spectators have difficulty understanding the progress of the match, and players have difficulty finding concrete guidelines for improving their own performance.

[0200] 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.

[0201] In this invention, the server includes means for acquiring video feeds and real-time event data of a match; means for analyzing the acquired video feeds and event data in real time and automatically generating commentary; means for transmitting the generated commentary to a user terminal and displaying it in real time; means for analyzing motion data and performance data after the match and generating personalized feedback; and means for transmitting and displaying individual player feedback to a user terminal. As a result, spectators can grasp the progress of the match and detailed commentary in real time, and players can receive specific feedback after the match to help improve their performance.

[0202] A "match video feed" refers to a video stream of a sports match, and is video data acquired for the purpose of real-time viewing and analysis.

[0203] "Real-time event data" refers to data that records important events that occur during a sports match (e.g., goals, fouls, etc.) in real time.

[0204] "Methods for automatically generating explanatory text" refer to methods for analyzing acquired video feeds and event data and automatically creating explanatory text about the progress of the match and events using natural language generation technology.

[0205] A "user terminal" refers to a device, such as a smartphone, tablet, personal computer, or head-mounted display, that allows a user to receive and display information in real time.

[0206] "Motion data and performance data" refers to detailed data on individual players' movements and performance during matches, including distance covered, speed, and number of shots.

[0207] "Personalized feedback" refers to feedback that includes specific improvement guidelines and advice for each individual athlete, based on analyzed motion and performance data.

[0208] A "generative AI model" is an algorithm or system that uses machine learning techniques to automatically generate explanatory text and feedback based on analysis results.

[0209] A "prompt statement" is an input statement used to make specific analysis requests or initial settings for the generated AI model.

[0210] "Statistical information" refers to information compiled in the form of numbers, graphs, and other formats, by analyzing various data collected during a match.

[0211] The embodiments for carrying out this invention will be described in detail below.

[0212] System Overview

[0213] This system acquires match video feeds and real-time event data, analyzes and processes it, provides users with information in real time, and provides personalized feedback to players after the match. The system consists of the following main components:

[0214] 1. Data acquisition module

[0215] 2. Data Analysis Module

[0216] 3. Natural Language Generation Module

[0217] 4. Data transmission module

[0218] 5. User Interface

[0219] 6. Feedback Generation Module

[0220] 7. Generative AI Models

[0221] 8. Prompt Statement System

[0222] Data acquisition module

[0223] The server retrieves match video feeds and real-time event data using an API or WebSocket. This data records the video stream of the sports match and important events such as goals and fouls in real time.

[0224] Data Analysis Module

[0225] The server analyzes the acquired video feed and event data in real time. The analysis utilizes machine learning algorithms (e.g., TensorFlow, OpenCV) and motion recognition technology. For example, if a goal is detected, the server automatically identifies the video footage from that moment.

[0226] Natural Language Generation Module

[0227] The server automatically generates explanatory text based on the results of data analysis. For natural language generation, it uses generative AI models such as GPT-4(registered trademark). For example, it can generate explanatory text such as, "Player A made a fantastic shot!"

[0228] Data transmission module

[0229] The server sends generated explanatory text and statistical information to the user's terminal in real time. This transmission is done using WebSocket or an API.

[0230] User Interface

[0231] The device displays the received commentary and statistics. This allows users to understand the progress of the match and detailed information in real time. For example, the smartphone might display information such as "Player C's current distance covered: 8km".

[0232] Feedback generation module

[0233] The server analyzes player movement and performance data after the match and generates personalized feedback. This feedback is sent to the user's terminal and displayed. For example, one piece of feedback might say, "You should move a little more towards the center when defending."

[0234] Generative AI models and prompt sentence systems

[0235] The system uses a generative AI model to generate explanatory text and feedback. The prompt system is used to make specific analysis requests and initial settings for the generative AI model.

[0236] Example of a prompt

[0237] "Please generate explanatory text for when a player scores a goal during a soccer match."

[0238] "Player A scored a goal with a long-range shot from 50 meters."

[0239] This system allows spectators to follow the progress of the match and receive detailed commentary in real time, while players can receive specific feedback after the match to help improve their performance.

[0240] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0241] Step 1:

[0242] Data acquisition module

[0243] The server retrieves video feeds and real-time event data of sports matches using an API or WebSocket. Inputs are the match video stream and important event data. The server receives this data in real time and prepares it for analysis. Outputs are the retrieved video feeds and event data.

[0244] Step 2:

[0245] Data Analysis Module

[0246] The server analyzes the acquired video feed and event data in real time. The input is the video feed and event data acquired in step 1. The server automatically identifies specific scenes and events (e.g., goal scenes) using machine learning algorithms (e.g., TensorFlow, OpenCV) and motion recognition technology. The output is the analyzed event information and its details.

[0247] Step 3:

[0248] Natural Language Generation Module

[0249] The server automatically generates explanatory text based on the results of data analysis. The input is the event information analyzed in step 2. The server uses a generative AI model such as GPT-4 as a natural language generation technique to create explanatory text according to the analysis results. For example, the sentence "Player A made a great shot!" is generated. The output is the generated explanatory text.

[0250] Step 4:

[0251] Data transmission module

[0252] The server sends the generated explanatory text and statistics to the user terminal in real time. The input is the explanatory text and related statistics generated in step 3. WebSocket or API is used for transmission. The output is the explanatory text and statistics sent to the user terminal.

[0253] Step 5:

[0254] User Interface

[0255] The terminal displays the received explanatory text and statistical information. The input is the explanatory text and statistical information sent in step 4. The user terminal displays this information on the screen in real time, allowing the user to understand the progress of the match and detailed information. For example, the smartphone displays information such as "Player C's current distance covered: 8km". The output is information that the user can visually confirm.

[0256] Step 6:

[0257] Feedback generation module

[0258] The server analyzes player movement and performance data after the match and generates personalized feedback. The input is player movement and performance data collected during the match. The server analyzes this data and generates feedback that provides specific improvement guidelines for each player. For example, feedback such as "You should move a little more towards the center when defending" might be generated. The output is the personalized feedback.

[0259] Step 7:

[0260] Feedback transmission module

[0261] The server sends the generated feedback to the user's (player's) terminal for display. The input is the personalized feedback generated in step 6. The server sends the feedback using WebSocket or API. The output is the feedback sent to the user's terminal.

[0262] In this way, spectators can follow the progress of the match and receive detailed commentary in real time, and players can receive specific feedback after the match to help improve their performance.

[0263] 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.

[0264] The following describes embodiments for carrying out the present invention. This system acquires and analyzes video feeds and real-time event data of matches, provides various information to spectators and players, and recognizes the user's emotions to customize the experience.

[0265] System Overview

[0266] This system consists of the following main components:

[0267] 1. Data acquisition module

[0268] 2. Data Analysis Module

[0269] 3. Natural Language Generation Module

[0270] 4. Data transmission module

[0271] 5. User Interface (Terminal)

[0272] 6. Feedback Generation Module

[0273] 7. Emotional Engine

[0274] Data acquisition module

[0275] The server retrieves the match video feed and real-time event data. This data includes a video stream of the sports match and real-time recordings of important events such as goals and fouls.

[0276] The server uses APIs and WebSocket to obtain video feeds and event data.

[0277] Data analysis module

[0278] The server analyzes the video feeds and event data obtained in real time. Machine learning algorithms and motion recognition technologies are used for the analysis.

[0279] For example, when a goal is scored during a game, the video of that moment is automatically identified.

[0280] Natural language generation module

[0281] Based on the results of data analysis, the server automatically generates explanatory texts. Using natural language generation technology, detailed explanatory texts about the game flow and events are created.

[0282] For example, an explanatory text such as "Player A made a great shot!" is generated.

[0283] Emotion engine

[0284] The server recognizes the user's emotions in real time. The emotion engine recognizes emotions such as joy, surprise, and excitement from the user's expressions and voice tones.

[0285] Based on the recognized emotions, customize the explanatory texts, statistical information, and feedback content.

[0286] Data transmission module

[0287] The server transmits the generated explanatory texts, emotion-based customized information, and statistical information to the terminal.

[0288] The server uses WebSocket connections or APIs to transmit data to the terminal in real time.

[0289] User interface (terminal)

[0290] The terminal displays the received explanatory text, customized information, and statistics on the user interface. This allows users (spectators) to understand the progress of the match and detailed information in real time.

[0291] For example, within a smartphone app, statistical information such as "Player A's current distance covered: 10km" could be displayed, along with explanatory text that changes according to the user's emotions.

[0292] Feedback generation module

[0293] The server collects and analyzes player movement and performance data during matches.

[0294] The server generates personalized feedback and provides it to players and coaches after the match ends.

[0295] For example, it can generate feedback such as "You should move a little more towards the center when defending" and send it to the player's device (smartphone).

[0296] Specific example

[0297] 1. Real-time commentary during the match

[0298] The server analyzes the match video feed and detects the event "Player B scored a goal."

[0299] The server generates a natural language explanation such as "Player B scored a goal with a brilliant dribble!" and sends it to the terminal.

[0300] Users can view this explanation in real time using a smartphone app.

[0301] The emotion engine recognizes the user's feelings of joy and adds phrases such as "The audience is also very excited!" to the next comment.

[0302] 2. Real-time stats provision

[0303] The server collects the running distance data of the players during the game and confirms that the running distance of player C has reached 8 km.

[0304] The server generates statistical information "Current running distance of player C: 8 km" and sends it to the terminal.

[0305] <00​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​

[0313] The following describes the processing flow.

[0314] Processing steps for automatically generated explanations

[0315] Step 1:

[0316] The server retrieves the match video feed and real-time event data. The server uses an API to obtain the video feed URL, establishes a WebSocket connection, and receives the event data.

[0317] Step 2:

[0318] The server analyzes the acquired video feed. A machine learning model is used to detect player movements and important events (e.g., goals, fouls) within the video frames.

[0319] Step 3:

[0320] The server analyzes real-time event data and compares it with the analysis results of the video feed. It identifies important events that match the event data.

[0321] Step 4:

[0322] The server uses natural language generation technology to generate explanatory text based on identified events. Templates are used to instantly convert the analysis results into text.

[0323] Step 5:

[0324] The server uses an emotion engine to recognize the user's emotions. It grasps the user's emotions in real time through facial recognition and voice tone analysis.

[0325] Step 6:

[0326] The server customizes the generated commentary based on the emotions it recognizes. For example, if the user is excited, it adds phrases like "The audience is also very excited!" to the commentary.

[0327] Step 7:

[0328] The server sends generated and customized explanatory text to the terminal. The explanatory text is sent to the terminal in real time using a WebSocket connection.

[0329] Step 8:

[0330] The terminal displays the received explanatory text on the user interface. Users can check the explanation in real time on their smartphones, tablets, etc.

[0331] Processing steps for real-time statistics analysis

[0332] Step 1:

[0333] The server collects various data generated during a match in real time. This is done by periodically polling the data using an API or by receiving the data in real time using a WebSocket connection.

[0334] Step 2:

[0335] The server analyzes the collected data. It executes analysis algorithms to calculate statistical data such as player distance covered and pass success rate.

[0336] Step 3:

[0337] The server generates visualized statistical information based on the analysis results. This information is then converted into graphs and charts to visualize the data.

[0338] Step 4:

[0339] The server uses an emotion engine to recognize the user's emotions in real time. The analysis results are then integrated with the user's emotion data.

[0340] Step 5:

[0341] The server adjusts the display format of statistics based on the emotions it perceives. For example, if the user is surprised, it might add a comment such as, "Player C is showing incredible stamina!"

[0342] Step 6:

[0343] The server sends generated and customized statistics to the terminal. Statistics are sent to the terminal using a WebSocket connection or API.

[0344] Step 7:

[0345] The system displays statistical information received by the device on the user interface. Users can check the statistical information on their smartphones or on large screens in the stadium.

[0346] Feedback generation processing steps

[0347] Step 1:

[0348] The server collects player movement and performance data during matches. An API is used to retrieve each player's position and performance data.

[0349] Step 2:

[0350] The server analyzes the collected data to evaluate the players' movements and performance. Machine learning models are used for the analysis.

[0351] Step 3:

[0352] The server generates personalized feedback based on the analysis results. Using evaluation data and templates, it creates specific areas for improvement and advice.

[0353] Step 4:

[0354] The server uses an emotion engine to recognize the player's emotions. It observes how the player receives feedback and analyzes their facial expressions and tone of voice.

[0355] Step 5:

[0356] The server customizes the feedback based on the emotions it perceives. For example, if a player is feeling frustrated or impatient, the feedback will be reinforced with positive language.

[0357] Step 6:

[0358] The server sends generated and customized feedback to the player's device. Feedback is sent to the player's device via email or a dedicated app.

[0359] Step 7:

[0360] The device displays the received feedback on the user interface. The user (player) reviews the feedback and identifies areas for improvement for the next match.

[0361] Processing steps for providing generated content

[0362] Step 1:

[0363] The server collects past match data and player information. It queries the database to retrieve the necessary data.

[0364] Step 2:

[0365] Based on data collected by the server, engaging content (articles, highlight videos, etc.) is generated. Natural language generation tools and video editing tools are used to create the content.

[0366] Step 3:

[0367] Convert server-generated content into a format suitable for the user interface. Export videos and articles in the appropriate format.

[0368] Step 4:

[0369] The server uses an emotion engine to recognize the user's emotions. It observes the user's reactions in real time while content is being delivered.

[0370] Step 5:

[0371] The server adjusts content visualizations based on the emotions it perceives. For example, if a user is emotional, it might add a "Featured Article: The Inspiring Story of Player X."

[0372] Step 6:

[0373] The server sends generated and customized content to the device. Content is sent to the device using an API or WebSocket connection.

[0374] Step 7:

[0375] The device displays the received content to the user. The user can view the content on a smartphone, tablet, or other device.

[0376] These processing steps enable the system to significantly improve audience engagement and the viewing experience. Furthermore, by utilizing the emotion engine, the quality of information provided can be customized to match the user's emotions.

[0377] (Example 2)

[0378] 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".

[0379] Traditional match viewing systems did not provide real-time information on the progress of the match or the performance of the players, making it difficult for spectators and players to immediately grasp the details of the match. Furthermore, the lack of commentary and feedback tailored to the user's emotions resulted in insufficient audience engagement. Additionally, feedback was typically provided after the match, without real-time advice or suggestions for improvement. Therefore, there was a need for technology that would make the match experience more engaging and personalized.

[0380] 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.

[0381] In this invention, the server includes means for acquiring a video stream and real-time event data of a match; means for analyzing the acquired video stream and event data in real time and detecting specific events using a machine learning algorithm; means for automatically generating explanatory text using natural language generation technology based on the analysis results; means for transmitting and displaying the generated explanatory text and customized information to a user terminal; and means for analyzing the user's facial expressions and voice, recognizing emotions in real time, and generating feedback. This enables the provision of detailed commentary and statistical information in real time, as well as the provision of customized information tailored to the user's emotions. Furthermore, it is possible to improve performance by providing specific feedback to players and coaches after the match.

[0382] "Match video stream" refers to video data of a match that is acquired in real time.

[0383] "Real-time event data" refers to data that records important events that occur during a match (e.g., goals, fouls) in real time.

[0384] A "machine learning algorithm" is a general term for mathematical models and methods used to automatically learn and analyze specific patterns and information based on data.

[0385] "Natural language generation technology" is a technology that uses computer-generated data to create natural language sentences that humans can read.

[0386] "Explanatory text" refers to a document that includes detailed explanations of the progress of a match or specific events.

[0387] A "user terminal" refers to electronic devices such as smartphones, tablets, and personal computers used by users.

[0388] "Customized information" refers to information that has been specially tailored to the user's needs and circumstances.

[0389] An "emotion engine" is a technology and system that analyzes a user's facial expressions, tone of voice, and other factors to recognize their emotions.

[0390] "Feedback" refers to information used to provide areas for improvement and advice based on an athlete's movements and performance.

[0391] The following describes specific embodiments for carrying out this invention. This system acquires and analyzes video streams and real-time event data of matches, provides various information to spectators and players, and recognizes user emotions to customize the experience. The system consists of a data acquisition module, a data analysis module, a natural language generation module, an emotion engine, a data transmission module, a user interface, and a feedback generation module.

[0392] Data acquisition module

[0393] The server retrieves the match video stream and real-time event data. This data is retrieved via cameras, APIs, and WebSocket connections. For example, the server accesses cameras for the video feed, streams video data, and receives event data in real time via WebSocket.

[0394] Data Analysis Module

[0395] The server analyzes the acquired video stream and event data in real time. Machine learning algorithms (e.g., TensorFlow) and motion recognition technologies (e.g., OpenCV) are used for the analysis. For example, the server analyzes the video data frame by frame to detect the moment a specific event (e.g., a goal) occurs.

[0396] Natural Language Generation Module

[0397] The server automatically generates explanatory text using natural language generation technology based on the results of data analysis. For example, it can use a generative AI model such as GPT-3 to generate explanatory text such as, "Player A scored a magnificent goal!"

[0398] Emotional Engine

[0399] The server recognizes the user's emotions in real time. By analyzing the user's facial expressions and tone of voice, it determines their emotions and generates corresponding feedback. For example, it uses AWS® Rekognition to read the user's emotions such as joy and surprise.

[0400] Data transmission module

[0401] The server sends generated explanatory text, customized information, and statistics to the terminal. WebSocket connection or API is used for transmission. For example, the generated explanatory text and statistics are sent to the terminal in JSON format.

[0402] User Interface

[0403] The terminal displays explanatory text, customized information, and statistics on the user interface. This display is performed on devices such as smartphones, tablets, and PCs. For example, the smartphone app screen might display information such as "Player A's current distance traveled: 10km".

[0404] Feedback generation module

[0405] The server collects and analyzes player movement and performance data during the match. It generates individual feedback, which is then sent to players and coaches after the match. For example, feedback such as "You should move a little more towards the center when defending" might be generated.

[0406] Specific example

[0407] Specific examples are given below.

[0408] Real-time commentary during the match

[0409] The server analyzes the match video stream and detects the event "Player B scores a goal." The server uses a generative AI model to generate a commentary such as "Player B scores a goal with a brilliant dribble!" and sends it to the device. The user checks this commentary in real time on the smartphone app, and the emotion engine recognizes the user's excitement and adds phrases such as "The crowd is also very excited!" to the next comment.

[0410] Real-time statistics provided

[0411] The server collects player distances during the match and confirms that player C has reached 8km. The server generates statistics such as "Player C's current distance: 8km" and sends them to the user's device. The user checks these statistics on their smartphone or on a large screen in the stadium, and the emotion engine recognizes the user's surprise and adds the comment, "Player C is showing incredible stamina!"

[0412] Examples of prompts for generative AI models

[0413] "Please generate natural language commentary describing the moment a player scores a goal during a soccer match. Additionally, please add emotionally charged comments that reflect the user's feelings, such as joy."

[0414] This invention can improve audience engagement and provide players with personalized feedback to enhance their performance. By utilizing an emotion engine, the quality of information provided can be customized to match the user's emotions.

[0415] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0416] Step 1:

[0417] Data acquisition

[0418] The server acquires the match video stream and real-time event data. This process involves acquiring video and event data via cameras, APIs, and WebSocket connections.

[0419] (Input): Camera video data, event data API, WebSocket connection.

[0420] (Output): Video stream data and event data stored on the server.

[0421] Specific operation: The server accesses the camera for the video feed and obtains real-time stream data. Simultaneously, it receives event data in real time via API calls and WebSocket connections and stores it in the server's database.

[0422] Step 2:

[0423] Data Analysis

[0424] The server analyzes acquired video streams and event data in real time. Machine learning algorithms and motion recognition technologies are used for the analysis.

[0425] (Input): Video stream data, event data.

[0426] (Output): Analysis results (detection results for a specific event).

[0427] Specific operation: The server analyzes video data frame by frame and detects the moment a specific event (e.g., a goal) occurs. The technologies used include Python's OpenCV library and TensorFlow models, which enable real-time event detection.

[0428] Step 3:

[0429] natural language generation

[0430] The server automatically generates explanatory text using natural language generation technology based on the results of data analysis.

[0431] (Input): Analysis result.

[0432] (Output): The generated explanatory text.

[0433] Specific operation: The server takes the analysis results as input and uses a generation AI model (e.g., GPT-3) to generate explanatory text. For example, content such as "Player A scored a magnificent goal!" is automatically generated.

[0434] Step 4:

[0435] emotion recognition

[0436] The server recognizes the user's emotions in real time. It analyzes the user's facial expressions and tone of voice.

[0437] (Input): User's facial expression data, voice data.

[0438] (Output): Emotion recognition result (joy, surprise, excitement, etc.).

[0439] Specific operation: The server acquires data from the camera and microphone and uses facial recognition algorithms and voice analysis algorithms to classify the user's emotions in real time. For example, emotions can be recognized using AWS Rekognition.

[0440] Step 5:

[0441] Data transmission

[0442] The server sends generated explanatory text, customized information, and statistical data to the terminal.

[0443] (Input): Generated explanatory text, sentiment recognition results, and statistical information.

[0444] (Output): Explanatory text and statistical information sent to the terminal.

[0445] Specific operation: The server sends the generated data to the terminal in real time via a WebSocket connection or API. JSON is commonly used as the transmission format.

[0446] Step 6:

[0447] Data display

[0448] The terminal displays explanatory text, customized information, and statistics received on the user interface.

[0449] (Input): Explanatory text and statistical information sent to the terminal.

[0450] (Output): Explanatory text and statistical information displayed on the user's terminal.

[0451] Specific operation: The device analyzes the data it receives and displays it on the application screen of a smartphone or tablet. For example, information such as "Player A's current distance traveled: 10km" will be displayed in the smartphone app.

[0452] Step 7:

[0453] Feedback generation

[0454] The server collects and analyzes player movement and performance data during the match. It generates individual feedback and sends it to players and coaches after the match ends.

[0455] (Input): Player motion data, performance data.

[0456] (Output): Individualized feedback.

[0457] Specific operation: The server analyzes the data collected after the match ends and generates improvement suggestions and advice for each player. For example, specific advice such as "You should move a little more towards the center when defending" is generated and sent to the terminal.

[0458] (Application Example 2)

[0459] 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."

[0460] Traditional match viewing systems had the means to acquire video feeds and event data and provide users with information in real time, but they lacked the ability to recognize user emotions and customize information based on those emotions. As a result, the viewing experience was uniform, and information tailored to the needs of individual users was not provided. Furthermore, advertising displays were not personalized considering the user's emotions or level of excitement at that moment, and therefore did not sufficiently increase engagement.

[0461] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring video feeds and real-time event data of a match; means for analyzing the acquired video feeds and event data in real time and automatically generating explanatory text; means for transmitting and displaying the generated explanatory text to a user terminal; means for recognizing the user's emotions in real time and customizing information based on those emotions; and means for transmitting the customized information to the user terminal and displaying advertisements. This makes it possible to provide information and display advertisements that reflect the user's emotions.

[0462] A "video feed" refers to live video data of a match, which is real-time video information of the game.

[0463] "Real-time event data" refers to data that records important event information, such as goals and fouls, that occur during a match in real time.

[0464] "Explanatory text" refers to textual information that describes events during a match, including detailed explanations of the match's progress and important events.

[0465] A "user terminal" is an electronic device that a user carries or wears to receive and display information, such as a smartphone, smart glasses, or tablet.

[0466] "Emotion recognition" is a technology that analyzes and identifies a user's emotions at a given moment based on their facial expressions, voice, and other factors.

[0467] "Customized information" refers to information that is provided in an individualized manner according to the user's needs and circumstances, based on the results of the user's emotion recognition.

[0468] "Advertising" refers to information displayed by companies or individuals to users in order to promote their products or services, with the aim of increasing user interest and attention.

[0469] "Statistical information" refers to numerical data obtained as a result of analyzing various data generated during a match, and includes detailed information about the match, such as the distance players covered and the number of goals scored.

[0470] The system for carrying out this invention acquires video feeds and real-time event data of a match, generates commentary based on this data, and transmits it to the user's terminal. It also recognizes the user's emotions in real time and provides customized information based on those emotions.

[0471] Required hardware and software

[0472] Hardware:

[0473] Camera: Uses the camera on smart glasses or a smartphone to capture the user's facial expressions.

[0474] Server: A central computing unit that acquires, analyzes, and transmits data.

[0475] software:

[0476] OpenCV: A library for capturing video feeds and performing image analysis.

[0477] dlib: A machine learning model for recognizing user emotions.

[0478] Advertising APIs (e.g., AdAPI): Used to retrieve ads that are relevant to the user's emotions.

[0479] WebSocket or API: A communication protocol that enables real-time transmission of data.

[0480] System operation

[0481] The server first acquires the match video feed and real-time event data, and then analyzes it. Based on the analysis results, it automatically generates commentary and sends it to the user's device. User devices that display the commentary include smartphones and smart glasses, and users can view this information in real time.

[0482] Next, the system recognizes the user's emotions in real time. This is done by analyzing facial expression data captured by the camera using the dlib library. Based on the recognized emotions, the server customizes the explanatory text and the displayed advertisements. For example, if the user is excited, entertainment-related advertisements are displayed, and if they are calm, health-related advertisements are displayed.

[0483] The generated information and advertisements are sent to the user's device using WebSocket or an API and displayed in real time. This process personalizes the match-watching experience to each user's emotions, leading to higher engagement.

[0484] Specific example

[0485] While a user is watching a sports match, they may show a smile and an excited expression the moment a player scores a goal. At this moment, the smart glasses' camera captures the expression, and the server uses the dlib library to recognize the emotion as "joy." The server then retrieves an entertainment-related advertisement (for example, a trailer for a new movie) and sends it to the smart glasses, displaying it in the user's field of view.

[0486] Example of a prompt

[0487] The following are examples of prompt statements to input into a generative AI model.

[0488] Please describe the role and new user experience of a smart glasses application that uses emotion recognition technology to detect a user's joy and excitement while they are watching a sports match in real time, and then displays relevant advertisements. Please provide details, including specific functions and examples.

[0489] In this way, the invention enables the provision of information and display of advertisements tailored to the user's emotions, thereby improving the viewing experience.

[0490] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0491] Step 1:

[0492] The server retrieves the match video feed and real-time event data. This data is sent to the server via API or WebSocket.

[0493] Input: Video feed, real-time event data

[0494] Processing: Retrieve data using API or WebSocket.

[0495] Output: Video feeds and event data stored in the server's data storage.

[0496] Step 2:

[0497] The system analyzes video feeds and event data acquired by the server. Machine learning algorithms are used for the analysis to automatically identify important events during the match.

[0498] Input: Video feed, real-time event data

[0499] Processing: Data analysis using machine learning algorithms

[0500] Output: Event-specific information (e.g., goal, foul, etc.)

[0501] Step 3:

[0502] The server automatically generates explanatory text based on the analysis results. It uses natural language generation technology to create text about the progress of the match and important events.

[0503] Input: Event specific information

[0504] Processing: Text generation using natural language generation technology

[0505] Output: Explanatory text (Example: "Player A scored a magnificent goal!")

[0506] Step 4:

[0507] The server sends the generated explanatory text to the user's terminal. Data is transmitted in real time via WebSocket or API.

[0508] Input: Explanation

[0509] Processing: Send data using WebSocket or API

[0510] Output: Explanatory text sent to the user's terminal

[0511] Step 5:

[0512] The terminal displays the received explanatory text. The explanatory text is displayed on the user interface of a smartphone or smart glasses.

[0513] Input: Received explanatory text

[0514] Processing: Display via user interface

[0515] Output: Explanatory text presented visually to the user.

[0516] Step 6:

[0517] To enable the server to recognize user emotions in real time, a camera is used to capture the user's facial expressions. The dlib library is used to analyze and recognize these emotions.

[0518] Input: Captured facial expression data

[0519] Processing: Sentiment analysis using the dlib library

[0520] Output: Recognized emotion (e.g., joy, surprise, etc.)

[0521] Step 7:

[0522] The server customizes information based on recognized emotions. Appropriate ad information and explanatory text are modified according to the emotions.

[0523] Input: Recognized emotions

[0524] Processing: Information customization (retrieving ad information using the ad API, changing explanatory text)

[0525] Output: Customized information (e.g., entertainment-related advertisements)

[0526] Step 8:

[0527] The server sends customized information to the user's terminal. Customized advertisements and explanatory text are sent using WebSocket or an API.

[0528] Input: Customized information

[0529] Processing: Sending data using WebSocket or API

[0530] Output: Customization information sent to the user's terminal

[0531] Step 9:

[0532] The device displays customized information it has received. This customized information is displayed on the user interface of smartphones and smart glasses.

[0533] Input: Received customized information

[0534] Processing: Display via user interface

[0535] Output: Customized information presented visually to the user (e.g., advertisements, specific explanatory text)

[0536] 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.

[0537] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0538] 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.

[0539] [Second Embodiment]

[0540] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0541] 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.

[0542] 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).

[0543] 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.

[0544] 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.

[0545] 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).

[0546] 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.

[0547] 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.

[0548] 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.

[0549] 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.

[0550] 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.

[0551] 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".

[0552] The following describes embodiments for carrying out the present invention. This system acquires and analyzes video feeds and real-time event data of matches and provides various information to spectators and players.

[0553] System Overview

[0554] This system consists of the following main components:

[0555] 1. Data acquisition module

[0556] 2. Data Analysis Module

[0557] 3. Natural Language Generation Module

[0558] 4. Data transmission module

[0559] 5. User Interface (Terminal)

[0560] 6. Feedback Generation Module

[0561] Data acquisition module

[0562] The server retrieves the match video feed and real-time event data. This data includes a video stream of the sports match and real-time recordings of important events such as goals and fouls.

[0563] The server uses APIs and WebSockets to retrieve video feeds and event data.

[0564] Data Analysis Module

[0565] The system analyzes video feeds and event data acquired by the server in real time. Machine learning algorithms and motion recognition technologies are used for the analysis.

[0566] For example, when a goal is scored during a match, the system automatically identifies the video footage of that exact moment.

[0567] Natural Language Generation Module

[0568] The server automatically generates explanatory text based on the results of data analysis. Natural language generation technology is used to create detailed explanations about the flow of the match and events.

[0569] For example, it generates a descriptive sentence such as, "Player A scored a magnificent goal!"

[0570] Data transmission module

[0571] The server sends the generated explanatory text and statistical information to the terminal.

[0572] The server uses WebSocket or an API to send data to the terminal in real time.

[0573] User interface (terminal)

[0574] The terminal displays the received explanatory text and statistical information on the user interface. This allows users (spectators) to understand the progress of the match and detailed information in real time.

[0575] For example, a smartphone app could display statistics such as "Player A's current distance covered: 10km".

[0576] Feedback generation module

[0577] The server collects and analyzes player movement and performance data during matches.

[0578] The server generates personalized feedback and provides it to players and coaches after the match ends.

[0579] For example, it can generate feedback such as "You should move a little more towards the center when defending" and send it to the player's device (smartphone).

[0580] Specific example

[0581] 1. Real-time commentary during the match

[0582] The server analyzes the match video feed and detects the event "Player B scored a goal."

[0583] The server generates a natural language explanation such as "Player B scored a goal with a brilliant dribble!" and sends it to the terminal.

[0584] Users can view this explanation in real time using a smartphone app.

[0585] 2. Real-time statistics provided

[0586] The server collects player distance data during the match and confirms that player C has reached a distance of 8km.

[0587] The server generates statistical information such as "Player C's current distance covered: 8km" and sends it to the terminal.

[0588] Users can view this statistical information on large screens inside the stadium or on their smartphones.

[0589] 3. Player feedback after the match

[0590] After the match ends, the server analyzes player D's performance data to identify areas for improvement in his defensive play.

[0591] The server generates feedback stating, "More lateral movement is needed during defense," and sends it to the terminal.

[0592] The user (player) receives this feedback on their smartphone and uses it to identify areas for improvement for the next match.

[0593] Thus, by using this system, it is possible to significantly improve audience engagement and provide players with personalized feedback, thereby improving their performance.

[0594] The following describes the processing flow.

[0595] Processing steps for automatically generated explanations

[0596] Step 1:

[0597] The server retrieves the match video feed and real-time event data. The server uses an API to obtain the video feed URL, establishes a WebSocket connection, and receives the event data.

[0598] Step 2:

[0599] The server analyzes the acquired video feed. A machine learning model is used to detect player movements and important events (e.g., goals, fouls) within the video frames.

[0600] Step 3:

[0601] The server analyzes real-time event data and compares it with the analysis results of the video feed. It identifies important events that match the event data.

[0602] Step 4:

[0603] The server uses natural language generation technology to generate explanatory text based on identified events. Templates are used to instantly convert the analysis results into text.

[0604] Step 5:

[0605] The server generates an explanatory text and sends it to the terminal. The explanatory text is sent to the terminal in real time using a WebSocket connection.

[0606] Step 6:

[0607] The terminal displays the received explanatory text on the user interface. Users can check the explanation in real time on their smartphones, tablets, etc.

[0608] Processing steps for real-time statistics analysis

[0609] Step 1:

[0610] The server collects various data generated during a match in real time. Data is periodically polled using an API or received in real time via a WebSocket connection.

[0611] Step 2:

[0612] The server analyzes the collected data, calculating statistical data such as player distance covered and pass success rate.

[0613] Step 3:

[0614] The server generates visualized statistical information based on the analysis results. This information is then converted into graphs and charts to visualize the data.

[0615] Step 4:

[0616] The server sends generated statistics to the terminal. Statistics data is sent to the terminal using a WebSocket connection or API.

[0617] Step 5:

[0618] The system displays statistical information received by the device on the user interface. Users can check the statistical information on their smartphones or on large screens in the stadium.

[0619] Feedback generation processing steps

[0620] Step 1:

[0621] The server collects player movement and performance data during matches. An API is used to retrieve each player's position and performance data.

[0622] Step 2:

[0623] The server analyzes the collected data to evaluate the players' movements and performance. Machine learning models are used for the analysis.

[0624] Step 3:

[0625] The server generates personalized feedback based on the analysis results. Using evaluation data and templates, it creates specific areas for improvement and advice.

[0626] Step 4:

[0627] The server generates feedback and sends it to the device. Feedback is sent to the player's device via email or a dedicated app.

[0628] Step 5:

[0629] The device displays the feedback it receives on the user interface. Users (players) can review the feedback and identify areas for improvement for the next match.

[0630] Processing steps for providing generated content

[0631] Step 1:

[0632] The server collects past match data and player information. It queries the database to retrieve the necessary data.

[0633] Step 2:

[0634] Based on data collected by the server, engaging content (articles, highlight videos, etc.) is generated. Natural language generation tools and video editing tools are used to create the content.

[0635] Step 3:

[0636] Convert server-generated content into a format suitable for the user interface. Export videos and articles in the appropriate format.

[0637] Step 4:

[0638] The server sends the generated content to the device. Content is sent to the device using an API or WebSocket connection.

[0639] Step 5:

[0640] The device displays the received content to the user. The user can view the content on a smartphone, tablet, or other device.

[0641] These processing steps enable the system to significantly improve audience engagement and the viewing experience.

[0642] (Example 1)

[0643] 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."

[0644] Conventional sports viewing systems have struggled to analyze live video and statistical information during matches and automatically generate commentary. This has resulted in a lack of detailed and timely information for spectators and athletes, limiting opportunities for engagement and performance improvement. This invention aims to solve these problems and provide a more interactive and informative viewing experience.

[0645] 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.

[0646] In this invention, the server includes means for acquiring video feeds and real-time event data of a match; means for analyzing the acquired video feeds and event data in real time and identifying goals and player actions using machine learning algorithms; means for automatically generating explanatory text using natural language generation technology based on the analysis results; and means for transmitting and displaying the generated explanatory text on a user terminal. This makes it possible to provide important moments and detailed statistical information of the match in real time.

[0647] A "video feed" refers to the input data used to acquire and distribute real-time footage of a match.

[0648] "Real-time event data" refers to data used to record and transmit important events that occur during a match, such as goals and fouls, in real time.

[0649] A "machine learning algorithm" refers to a computational method that learns patterns in data and automates specific tasks.

[0650] "Natural language generation technology" refers to the technology that generates text in natural language that humans can understand, based on analyzed data.

[0651] "Explanatory text" refers to text that explains events and statistical information that occur during a match, and is intended to provide information to spectators and players.

[0652] A "user terminal" is an electronic device used to receive and display information, and includes smartphones, tablets, computers, and other electronic devices.

[0653] "Statistical information" refers to numerical data about the performance of players and teams during a match.

[0654] "Feedback" refers to information provided to players and coaches after a match, including areas for improvement and advice.

[0655] "Analysis results" refer to the final output after analyzing the collected data, and include explanatory text, statistical information, and feedback.

[0656] "Collection means" refers to the methods and devices used to acquire the necessary data.

[0657] System Overview

[0658] This invention relates to a system that acquires video feeds and real-time event data of a match, analyzes them to automatically generate commentary, and transmits and displays the commentary and statistical information to a user terminal. The system consists of a server, a terminal, and a user, and each component works in cooperation with the others.

[0659] Specific examples of hardware and software to be used

[0660] The server requires a high-performance data processing computer and a network interface. Data analysis utilizes software implementing machine learning algorithms such as TensorFlow and OpenPose. Generative AI models such as GPT-3 are used for natural language generation. APIs and WebSockets are used for data transmission and reception.

[0661] The devices include smartphones, tablets, or large screens within the stadium. These devices receive data transmitted from the server in real time and display it to the user.

[0662] Users include spectators watching the game, as well as players and their coaches who want to improve their performance. Users receive game progress updates, statistics, and feedback through smartphones, tablets, and large screens in the stadium.

[0663] Specific example

[0664] 1. Real-time commentary during the match

[0665] The server analyzes the match video feed and detects an event such as "Player B scored a goal." The server generates a natural language commentary such as "Player B scored a goal with a brilliant dribble!" and sends it to the device. The user can view this commentary in real time on their smartphone app.

[0666] 2. Real-time statistics provided

[0667] The server collects player distance data during the match and confirms that player C has reached 8km. The server generates statistics such as "Player C's current distance: 8km" and sends them to the terminal. The user can view these statistics on a large screen in the stadium or on their smartphone.

[0668] 3. Player feedback after the match

[0669] After the match ends, the server analyzes player D's performance data to identify areas for improvement in defense. The server generates feedback such as "More lateral movement is needed during defense" and sends it to the device. The user (player) receives this feedback on their smartphone and reviews the areas for improvement for the next match.

[0670] Example of a prompt

[0671] "This system analyzes video feeds and real-time event data during matches to provide information to spectators and players in real time. For example, the moment player A scores a goal, it generates commentary and notifies a smartphone app. Player distance covered and performance data are also displayed in real time, and specific feedback is provided to players after the match ends."

[0672] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0673] Step 1:

[0674] The server retrieves the match video feed and real-time event data.

[0675] Specific operation: The server uses the official FIFA API to retrieve real-time video streams. Simultaneously, it receives event data such as goals and fouls during the match via WebSocket.

[0676] Input: FIFA official API endpoint and WebSocket connection information

[0677] Output: Real-time video feed and event data

[0678] Step 2:

[0679] The server analyzes acquired video feeds and event data in real time.

[0680] Specific operation: The server analyzes the video feed using TensorFlow and OpenPose to detect specific events (e.g., goal scenes). It also applies machine learning algorithms to recognize player actions (e.g., shots and dribbles).

[0681] Input: Video feed and real-time event data

[0682] Output: Analyzed event information and player motion data

[0683] Step 3:

[0684] The server generates a natural language explanation based on the analysis results.

[0685] Specific operation: The server uses a generative AI model such as GPT-3 to create explanatory text based on the analyzed event information. For example, it might generate an explanatory text such as, "Player A scored a magnificent goal!"

[0686] Input: Analysis results (event information and player movement data)

[0687] Output: Auto-generated natural language explanation

[0688] Step 4:

[0689] The server sends the generated explanatory text and statistical information to the terminal.

[0690] Specific operation: The server sends generated explanatory text and statistical information to the terminal in real time using WebSocket or a REST API.

[0691] Input: Automatically generated explanatory text and statistical information

[0692] Output: Explanatory text and statistical information sent to the user's terminal.

[0693] Step 5:

[0694] The data received by the terminal is displayed on the user interface.

[0695] Specific operation: The device displays explanatory text and statistical information on the screen, providing it visually to the user. For example, a smartphone app might display "Player A's current distance traveled: 10km" as a notification.

[0696] Input: Explanatory text and statistical information sent from the server

[0697] Output: Explanatory text and statistics displayed on the user interface

[0698] Step 6:

[0699] The server collects and analyzes player movement and performance data during the match.

[0700] Specific operation: The server collects and analyzes player movement data (e.g., distance traveled, location information) in real time during the match. This allows for a detailed understanding of each player's performance.

[0701] Input: Player movement data during the match

[0702] Output: Analyzed performance data for each player

[0703] Step 7:

[0704] The server generates personalized feedback based on the analysis results.

[0705] Specific operation: Based on the analysis results, the server creates feedback for each player, including specific areas for improvement and advice. For example, it might generate feedback such as, "You should move a little more towards the center when defending."

[0706] Input: Analyzed performance data for each player

[0707] Output: Individualized feedback

[0708] Step 8:

[0709] The server sends the generated feedback to the user's terminal for display.

[0710] Specific operation: The server sends the generated feedback to the device (e.g., the player's smartphone), and the device displays that feedback.

[0711] Input: Personalized feedback

[0712] Output: Feedback sent to the user terminal and displayed feedback

[0713] (Application Example 1)

[0714] 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."

[0715] In sports matches, it is difficult for spectators and players to obtain detailed information in real time. Furthermore, there are limited means for players to receive individual feedback after the match has ended. As a result, spectators have difficulty understanding the progress of the match, and players have difficulty finding concrete guidelines for improving their own performance.

[0716] 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.

[0717] In this invention, the server includes means for acquiring video feeds and real-time event data of a match; means for analyzing the acquired video feeds and event data in real time and automatically generating commentary; means for transmitting the generated commentary to a user terminal and displaying it in real time; means for analyzing motion data and performance data after the match and generating personalized feedback; and means for transmitting and displaying individual player feedback to a user terminal. As a result, spectators can grasp the progress of the match and detailed commentary in real time, and players can receive specific feedback after the match to help improve their performance.

[0718] A "match video feed" refers to a video stream of a sports match, and is video data acquired for the purpose of real-time viewing and analysis.

[0719] "Real-time event data" refers to data that records important events that occur during a sports match (e.g., goals, fouls, etc.) in real time.

[0720] "Methods for automatically generating explanatory text" refer to methods for analyzing acquired video feeds and event data and automatically creating explanatory text about the progress of the match and events using natural language generation technology.

[0721] A "user terminal" refers to a device, such as a smartphone, tablet, personal computer, or head-mounted display, that allows a user to receive and display information in real time.

[0722] "Motion data and performance data" refers to detailed data on individual players' movements and performance during matches, including distance covered, speed, and number of shots.

[0723] "Personalized feedback" refers to feedback that includes specific improvement guidelines and advice for each individual athlete, based on analyzed motion and performance data.

[0724] A "generative AI model" is an algorithm or system that uses machine learning techniques to automatically generate explanatory text and feedback based on analysis results.

[0725] A "prompt statement" is an input statement used to make specific analysis requests or initial settings for the generated AI model.

[0726] "Statistical information" refers to information compiled in the form of numbers, graphs, and other formats, by analyzing various data collected during a match.

[0727] The embodiments for carrying out this invention will be described in detail below.

[0728] System Overview

[0729] This system acquires match video feeds and real-time event data, analyzes and processes it, provides users with information in real time, and provides personalized feedback to players after the match. The system consists of the following main components:

[0730] 1. Data acquisition module

[0731] 2. Data Analysis Module

[0732] 3. Natural Language Generation Module

[0733] 4. Data transmission module

[0734] 5. User Interface

[0735] 6. Feedback Generation Module

[0736] 7. Generative AI Models

[0737] 8. Prompt Statement System

[0738] Data acquisition module

[0739] The server retrieves match video feeds and real-time event data using an API or WebSocket. This data records the video stream of the sports match and important events such as goals and fouls in real time.

[0740] Data Analysis Module

[0741] The server analyzes the acquired video feed and event data in real time. The analysis utilizes machine learning algorithms (e.g., TensorFlow, OpenCV) and motion recognition technology. For example, if a goal is detected, the server automatically identifies the video footage from that moment.

[0742] Natural Language Generation Module

[0743] The server automatically generates explanatory text based on the results of data analysis. For natural language generation, it uses generative AI models such as GPT-4. For example, it might generate the explanatory text, "Player A scored a magnificent goal!"

[0744] Data transmission module

[0745] The server sends generated explanatory text and statistical information to the user's terminal in real time. This transmission is done using WebSocket or an API.

[0746] User Interface

[0747] The device displays the received commentary and statistics. This allows users to understand the progress of the match and detailed information in real time. For example, the smartphone might display information such as "Player C's current distance covered: 8km".

[0748] Feedback generation module

[0749] The server analyzes player movement and performance data after the match and generates personalized feedback. This feedback is sent to the user's terminal and displayed. For example, one piece of feedback might say, "You should move a little more towards the center when defending."

[0750] Generative AI models and prompt sentence systems

[0751] The system uses a generative AI model to generate explanatory text and feedback. The prompt system is used to make specific analysis requests and initial settings for the generative AI model.

[0752] Example of a prompt

[0753] "Please generate explanatory text for when a player scores a goal during a soccer match."

[0754] "Player A scored a goal with a long-range shot from 50 meters."

[0755] This system allows spectators to follow the progress of the match and receive detailed commentary in real time, while players can receive specific feedback after the match to help improve their performance.

[0756] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0757] Step 1:

[0758] Data acquisition module

[0759] The server retrieves video feeds and real-time event data of sports matches using an API or WebSocket. Inputs are the match video stream and important event data. The server receives this data in real time and prepares it for analysis. Outputs are the retrieved video feeds and event data.

[0760] Step 2:

[0761] Data Analysis Module

[0762] The server analyzes the acquired video feed and event data in real time. The input is the video feed and event data acquired in step 1. The server automatically identifies specific scenes and events (e.g., goal scenes) using machine learning algorithms (e.g., TensorFlow, OpenCV) and motion recognition technology. The output is the analyzed event information and its details.

[0763] Step 3:

[0764] Natural Language Generation Module

[0765] The server automatically generates explanatory text based on the results of data analysis. The input is the event information analyzed in step 2. The server uses a generative AI model such as GPT-4 as a natural language generation technique to create explanatory text according to the analysis results. For example, the sentence "Player A made a great shot!" is generated. The output is the generated explanatory text.

[0766] Step 4:

[0767] Data transmission module

[0768] The server sends the generated explanatory text and statistics to the user terminal in real time. The input is the explanatory text and related statistics generated in step 3. WebSocket or API is used for transmission. The output is the explanatory text and statistics sent to the user terminal.

[0769] Step 5:

[0770] User Interface

[0771] The terminal displays the received explanatory text and statistical information. The input is the explanatory text and statistical information sent in step 4. The user terminal displays this information on the screen in real time, allowing the user to understand the progress of the match and detailed information. For example, the smartphone displays information such as "Player C's current distance covered: 8km". The output is information that the user can visually confirm.

[0772] Step 6:

[0773] Feedback generation module

[0774] The server analyzes player movement and performance data after the match and generates personalized feedback. The input is player movement and performance data collected during the match. The server analyzes this data and generates feedback that provides specific improvement guidelines for each player. For example, feedback such as "You should move a little more towards the center when defending" might be generated. The output is the personalized feedback.

[0775] Step 7:

[0776] Feedback transmission module

[0777] The server sends the generated feedback to the user's (player's) terminal for display. The input is the personalized feedback generated in step 6. The server sends the feedback using WebSocket or API. The output is the feedback sent to the user's terminal.

[0778] In this way, spectators can follow the progress of the match and receive detailed commentary in real time, and players can receive specific feedback after the match to help improve their performance.

[0779] 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.

[0780] The following describes embodiments for carrying out the present invention. This system acquires and analyzes video feeds and real-time event data of matches, provides various information to spectators and players, and recognizes the user's emotions to customize the experience.

[0781] System Overview

[0782] This system consists of the following main components:

[0783] 1. Data acquisition module

[0784] 2. Data Analysis Module

[0785] 3. Natural Language Generation Module

[0786] 4. Data transmission module

[0787] 5. User Interface (Terminal)

[0788] 6. Feedback Generation Module

[0789] 7. Emotional Engine

[0790] Data acquisition module

[0791] The server retrieves the match video feed and real-time event data. This data includes a video stream of the sports match and real-time recordings of important events such as goals and fouls.

[0792] The server uses APIs and WebSockets to retrieve video feeds and event data.

[0793] Data Analysis Module

[0794] The system analyzes video feeds and event data acquired by the server in real time. Machine learning algorithms and motion recognition technologies are used for the analysis.

[0795] For example, when a goal is scored during a match, the system automatically identifies the video footage of that exact moment.

[0796] Natural Language Generation Module

[0797] The server automatically generates explanatory text based on the results of data analysis. Natural language generation technology is used to create detailed explanations about the flow of the match and events.

[0798] For example, it generates a descriptive sentence such as, "Player A scored a magnificent goal!"

[0799] Emotional Engine

[0800] The server recognizes the user's emotions in real time. The emotion engine recognizes emotions such as joy, surprise, and excitement from the user's facial expressions and tone of voice.

[0801] Based on the recognized emotions, the explanatory text, statistical information, and feedback content are customized.

[0802] Data transmission module

[0803] The server sends generated explanatory text, sentiment-based customized information, and statistical data to the terminal.

[0804] The server uses a WebSocket connection or API to send data to the terminal in real time.

[0805] User interface (terminal)

[0806] The terminal displays the received explanatory text, customized information, and statistics on the user interface. This allows users (spectators) to understand the progress of the match and detailed information in real time.

[0807] For example, within a smartphone app, statistical information such as "Player A's current distance covered: 10km" could be displayed, along with explanatory text that changes according to the user's emotions.

[0808] Feedback generation module

[0809] The server collects and analyzes player movement and performance data during matches.

[0810] The server generates personalized feedback and provides it to players and coaches after the match ends.

[0811] For example, it can generate feedback such as "You should move a little more towards the center when defending" and send it to the player's device (smartphone).

[0812] Specific example

[0813] 1. Real-time commentary during the match

[0814] The server analyzes the match video feed and detects the event "Player B scored a goal."

[0815] The server generates a natural language explanation such as "Player B scored a goal with a brilliant dribble!" and sends it to the terminal.

[0816] Users can view this explanation in real time using a smartphone app.

[0817] The emotion engine recognizes the user's feelings of joy and adds phrases such as "The audience is also very excited!" to the next comment.

[0818] 2. Real-time statistics provided

[0819] The server collects player distance data during the match and confirms that player C has reached a distance of 8km.

[0820] The server generates statistical information such as "Player C's current distance covered: 8km" and sends it to the terminal.

[0821] Users can check statistical information on large screens inside the stadium or on their smartphones.

[0822] The emotion engine recognizes the user's surprise and adds the comment, "Player C is showing incredible stamina!" to the displayed statistics.

[0823] 3. Player feedback after the match

[0824] After the match ends, the server analyzes player D's performance data to identify areas for improvement in his defensive play.

[0825] The server generates feedback stating, "More lateral movement is needed during defense," and sends it to the terminal.

[0826] The user (player) receives this feedback on their smartphone and uses it to identify areas for improvement for the next match.

[0827] The emotional engine recognizes the player's feelings of frustration and impatience, and reinforces the feedback with more positive language before providing it.

[0828] Thus, this system can significantly improve audience engagement, provide players with personalized feedback, and enhance their performance. Furthermore, by utilizing an emotion engine, the quality of information provided can be customized to match the user's emotions.

[0829] The following describes the processing flow.

[0830] Processing steps for automatically generated explanations

[0831] Step 1:

[0832] The server retrieves the match video feed and real-time event data. The server uses an API to obtain the video feed URL, establishes a WebSocket connection, and receives the event data.

[0833] Step 2:

[0834] The server analyzes the acquired video feed. A machine learning model is used to detect player movements and important events (e.g., goals, fouls) within the video frames.

[0835] Step 3:

[0836] The server analyzes real-time event data and compares it with the analysis results of the video feed. It identifies important events that match the event data.

[0837] Step 4:

[0838] The server uses natural language generation technology to generate explanatory text based on identified events. Templates are used to instantly convert the analysis results into text.

[0839] Step 5:

[0840] The server uses an emotion engine to recognize the user's emotions. It grasps the user's emotions in real time through facial recognition and voice tone analysis.

[0841] Step 6:

[0842] The server customizes the generated commentary based on the emotions it recognizes. For example, if the user is excited, it adds phrases like "The audience is also very excited!" to the commentary.

[0843] Step 7:

[0844] The server sends generated and customized explanatory text to the terminal. The explanatory text is sent to the terminal in real time using a WebSocket connection.

[0845] Step 8:

[0846] The terminal displays the received explanatory text on the user interface. Users can check the explanation in real time on their smartphones, tablets, etc.

[0847] Processing steps for real-time statistics analysis

[0848] Step 1:

[0849] The server collects various data generated during a match in real time. This is done by periodically polling the data using an API or by receiving the data in real time using a WebSocket connection.

[0850] Step 2:

[0851] The server analyzes the collected data. It executes analysis algorithms to calculate statistical data such as player distance covered and pass success rate.

[0852] Step 3:

[0853] The server generates visualized statistical information based on the analysis results. This information is then converted into graphs and charts to visualize the data.

[0854] Step 4:

[0855] The server uses an emotion engine to recognize the user's emotions in real time. The analysis results are then integrated with the user's emotion data.

[0856] Step 5:

[0857] The server adjusts the display format of statistics based on the emotions it perceives. For example, if the user is surprised, it might add a comment such as, "Player C is showing incredible stamina!"

[0858] Step 6:

[0859] The server sends generated and customized statistics to the terminal. Statistics are sent to the terminal using a WebSocket connection or API.

[0860] Step 7:

[0861] The system displays statistical information received by the device on the user interface. Users can check the statistical information on their smartphones or on large screens in the stadium.

[0862] Feedback generation processing steps

[0863] Step 1:

[0864] The server collects player movement and performance data during matches. An API is used to retrieve each player's position and performance data.

[0865] Step 2:

[0866] The server analyzes the collected data to evaluate the players' movements and performance. Machine learning models are used for the analysis.

[0867] Step 3:

[0868] The server generates personalized feedback based on the analysis results. Using evaluation data and templates, it creates specific areas for improvement and advice.

[0869] Step 4:

[0870] The server uses an emotion engine to recognize the player's emotions. It observes how feedback is received and analyzes the player's facial expressions and tone of voice.

[0871] Step 5:

[0872] The server customizes the feedback based on the emotions it perceives. For example, if a player is feeling frustrated or impatient, the feedback will be reinforced with positive language.

[0873] Step 6:

[0874] The server sends generated and customized feedback to the player's device. Feedback is sent to the player's device via email or a dedicated app.

[0875] Step 7:

[0876] The device displays the feedback it receives on the user interface. The user (player) reviews the feedback and identifies areas for improvement for the next match.

[0877] Processing steps for providing generated content

[0878] Step 1:

[0879] The server collects past match data and player information. It queries the database to retrieve the necessary data.

[0880] Step 2:

[0881] Based on data collected by the server, engaging content (articles, highlight videos, etc.) is generated. Natural language generation tools and video editing tools are used to create the content.

[0882] Step 3:

[0883] Convert server-generated content into a format suitable for the user interface. Export videos and articles in the appropriate format.

[0884] Step 4:

[0885] The server uses an emotion engine to recognize the user's emotions and observes the user's reactions in real time while content is being delivered.

[0886] Step 5:

[0887] The server adjusts content visualizations based on the emotions it perceives. For example, if a user is emotional, it might add a "Featured Article: The Inspiring Story of Player X."

[0888] Step 6:

[0889] The server sends generated and customized content to the device. Content is sent to the device using an API or WebSocket connection.

[0890] Step 7:

[0891] The device displays the received content to the user. The user can view the content on a smartphone, tablet, or other device.

[0892] These processing steps enable the system to significantly improve audience engagement and the viewing experience. Furthermore, by utilizing the emotion engine, the quality of information provided can be customized to match the user's emotions.

[0893] (Example 2)

[0894] 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".

[0895] Traditional match viewing systems did not provide real-time information on the progress of the match or the performance of the players, making it difficult for spectators and players to immediately grasp the details of the match. Furthermore, the lack of commentary and feedback tailored to the user's emotions resulted in insufficient audience engagement. Additionally, feedback was typically provided after the match, without real-time advice or suggestions for improvement. Therefore, there was a need for technology that would make the match experience more engaging and personalized.

[0896] 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.

[0897] In this invention, the server includes means for acquiring a video stream and real-time event data of a match; means for analyzing the acquired video stream and event data in real time and detecting specific events using a machine learning algorithm; means for automatically generating explanatory text using natural language generation technology based on the analysis results; means for transmitting and displaying the generated explanatory text and customized information to a user terminal; and means for analyzing the user's facial expressions and voice, recognizing emotions in real time, and generating feedback. This enables the provision of detailed commentary and statistical information in real time, as well as the provision of customized information tailored to the user's emotions. Furthermore, it is possible to improve performance by providing specific feedback to players and coaches after the match.

[0898] "Match video stream" refers to video data of a match that is acquired in real time.

[0899] "Real-time event data" refers to data that records important events that occur during a match (e.g., goals, fouls) in real time.

[0900] A "machine learning algorithm" is a general term for mathematical models and methods used to automatically learn and analyze specific patterns and information based on data.

[0901] "Natural language generation technology" is a technology that uses computer-generated data to create natural language sentences that humans can read.

[0902] "Explanatory text" refers to a document that includes detailed explanations of the progress of a match or specific events.

[0903] A "user terminal" refers to electronic devices such as smartphones, tablets, and personal computers used by users.

[0904] "Customized information" refers to information that has been specially tailored to the user's needs and circumstances.

[0905] An "emotion engine" is a technology and system that recognizes emotions by analyzing a user's facial expressions, tone of voice, and other factors.

[0906] "Feedback" refers to information used to provide areas for improvement and advice based on an athlete's movements and performance.

[0907] The following describes specific embodiments for carrying out this invention. This system acquires and analyzes video streams and real-time event data of matches, provides various information to spectators and players, and recognizes user emotions to customize the experience. The system consists of a data acquisition module, a data analysis module, a natural language generation module, an emotion engine, a data transmission module, a user interface, and a feedback generation module.

[0908] Data acquisition module

[0909] The server retrieves the match video stream and real-time event data. This data is retrieved via cameras, APIs, and WebSocket connections. For example, the server accesses cameras for the video feed, streams video data, and receives event data in real time via WebSocket.

[0910] Data Analysis Module

[0911] The server analyzes the acquired video stream and event data in real time. Machine learning algorithms (e.g., TensorFlow) and motion recognition technologies (e.g., OpenCV) are used for the analysis. For example, the server analyzes the video data frame by frame to detect the moment a specific event (e.g., a goal) occurs.

[0912] Natural Language Generation Module

[0913] The server automatically generates explanatory text using natural language generation technology based on the results of data analysis. For example, it can use a generative AI model such as GPT-3 to generate explanatory text such as, "Player A scored a magnificent goal!"

[0914] Emotional Engine

[0915] The server recognizes the user's emotions in real time. By analyzing the user's facial expressions and tone of voice, it determines their emotions and generates corresponding feedback. For example, it uses AWS Rekognition to read the user's emotions such as joy and surprise.

[0916] Data transmission module

[0917] The server sends generated explanatory text, customized information, and statistics to the terminal. WebSocket connection or API is used for transmission. For example, the generated explanatory text and statistics are sent to the terminal in JSON format.

[0918] User Interface

[0919] The terminal displays explanatory text, customized information, and statistics on the user interface. This display is performed on devices such as smartphones, tablets, and PCs. For example, the smartphone app screen might display information such as "Player A's current distance traveled: 10km".

[0920] Feedback generation module

[0921] The server collects and analyzes player movement and performance data during the match. It generates individual feedback, which is then sent to players and coaches after the match. For example, feedback such as "You should move a little more towards the center when defending" might be generated.

[0922] Specific example

[0923] Specific examples are given below.

[0924] Real-time commentary during the match

[0925] The server analyzes the match video stream and detects the event "Player B scores a goal." The server uses a generative AI model to generate a commentary such as "Player B scores a goal with a brilliant dribble!" and sends it to the device. The user checks this commentary in real time on the smartphone app, and the emotion engine recognizes the user's excitement and adds phrases such as "The crowd is also very excited!" to the next comment.

[0926] Real-time statistics provided

[0927] The server collects player distances during the match and confirms that player C has reached 8km. The server generates statistics such as "Player C's current distance: 8km" and sends them to the user's device. The user checks these statistics on their smartphone or on a large screen in the stadium, and the emotion engine recognizes the user's surprise and adds the comment, "Player C is showing incredible stamina!"

[0928] Examples of prompts for generative AI models

[0929] "Please generate natural language commentary describing the moment a player scores a goal during a soccer match. Additionally, please add emotionally charged comments that reflect the user's feelings, such as joy."

[0930] This invention can improve audience engagement and provide players with personalized feedback to enhance their performance. By utilizing an emotion engine, the quality of information provided can be customized to match the user's emotions.

[0931] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0932] Step 1:

[0933] Data acquisition

[0934] The server acquires the match video stream and real-time event data. This process involves acquiring video and event data via cameras, APIs, and WebSocket connections.

[0935] (Input): Camera video data, event data API, WebSocket connection.

[0936] (Output): Video stream data and event data stored on the server.

[0937] Specific operation: The server accesses the camera for the video feed and obtains real-time stream data. Simultaneously, it receives event data in real time via API calls and WebSocket connections and stores it in the server's database.

[0938] Step 2:

[0939] Data Analysis

[0940] The server analyzes acquired video streams and event data in real time. Machine learning algorithms and motion recognition technologies are used for the analysis.

[0941] (Input): Video stream data, event data.

[0942] (Output): Analysis results (detection results for a specific event).

[0943] Specific operation: The server analyzes video data frame by frame and detects the moment a specific event (e.g., a goal) occurs. The technologies used include Python's OpenCV library and TensorFlow models, which enable real-time event detection.

[0944] Step 3:

[0945] natural language generation

[0946] The server automatically generates explanatory text using natural language generation technology based on the results of data analysis.

[0947] (Input): Analysis result.

[0948] (Output): The generated explanatory text.

[0949] Specific operation: The server takes the analysis results as input and uses a generation AI model (e.g., GPT-3) to generate explanatory text. For example, content such as "Player A scored a magnificent goal!" is automatically generated.

[0950] Step 4:

[0951] emotion recognition

[0952] The server recognizes the user's emotions in real time. It analyzes the user's facial expressions and tone of voice.

[0953] (Input): User's facial expression data, voice data.

[0954] (Output): Emotion recognition result (joy, surprise, excitement, etc.).

[0955] Specific operation: The server acquires data from the camera and microphone and uses facial recognition algorithms and voice analysis algorithms to classify the user's emotions in real time. For example, emotions can be recognized using AWS Rekognition.

[0956] Step 5:

[0957] Data transmission

[0958] The server sends generated explanatory text, customized information, and statistical data to the terminal.

[0959] (Input): Generated explanatory text, sentiment recognition results, and statistical information.

[0960] (Output): Explanatory text and statistical information sent to the terminal.

[0961] Specific operation: The server sends the generated data to the terminal in real time via a WebSocket connection or API. JSON is commonly used as the transmission format.

[0962] Step 6:

[0963] Data display

[0964] The terminal displays explanatory text, customized information, and statistics on the user interface.

[0965] (Input): Explanatory text and statistical information sent to the terminal.

[0966] (Output): Explanatory text and statistical information displayed on the user's terminal.

[0967] Specific operation: The device analyzes the data it receives and displays it on the application screen of a smartphone or tablet. For example, information such as "Player A's current distance traveled: 10km" will be displayed in the smartphone app.

[0968] Step 7:

[0969] Feedback generation

[0970] The server collects and analyzes player movement and performance data during the match. It generates individual feedback and sends it to players and coaches after the match ends.

[0971] (Input): Player motion data, performance data.

[0972] (Output): Individualized feedback.

[0973] Specific operation: The server analyzes the data collected after the match ends and generates improvement suggestions and advice for each player. For example, specific advice such as "You should move a little more towards the center when defending" is generated and sent to the terminal.

[0974] (Application Example 2)

[0975] 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."

[0976] Traditional match viewing systems had the means to acquire video feeds and event data and provide users with information in real time, but they lacked the ability to recognize user emotions and customize information based on those emotions. As a result, the viewing experience was uniform, and information tailored to the needs of individual users was not provided. Furthermore, advertising displays were not personalized considering the user's emotions or level of excitement at that moment, and therefore did not sufficiently increase engagement.

[0977] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring video feeds and real-time event data of a match; means for analyzing the acquired video feeds and event data in real time and automatically generating explanatory text; means for transmitting and displaying the generated explanatory text to a user terminal; means for recognizing the user's emotions in real time and customizing information based on those emotions; and means for transmitting the customized information to the user terminal and displaying advertisements. This makes it possible to provide information and display advertisements that reflect the user's emotions.

[0978] A "video feed" refers to live video data of a match, which is real-time video information of the game.

[0979] "Real-time event data" refers to data that records important event information, such as goals and fouls, that occur during a match in real time.

[0980] "Explanatory text" refers to textual information that describes events during a match, including detailed explanations of the match's progress and important events.

[0981] A "user terminal" is an electronic device that a user carries or wears to receive and display information, such as a smartphone, smart glasses, or tablet.

[0982] "Emotion recognition" is a technology that analyzes and identifies a user's emotions at a given moment based on their facial expressions, voice, and other factors.

[0983] "Customized information" refers to information that is provided in an individualized manner according to the user's needs and circumstances, based on the results of the user's emotion recognition.

[0984] "Advertising" refers to information displayed by companies or individuals to users in order to promote their products or services, with the aim of increasing user interest and attention.

[0985] "Statistical information" refers to numerical data obtained as a result of analyzing various data generated during a match, and includes detailed information about the match, such as the distance players covered and the number of goals scored.

[0986] The system for carrying out this invention acquires video feeds and real-time event data of a match, generates commentary based on this data, and transmits it to the user's terminal. It also recognizes the user's emotions in real time and provides customized information based on those emotions.

[0987] Required hardware and software

[0988] Hardware:

[0989] Camera: Uses the camera on smart glasses or a smartphone to capture the user's facial expressions.

[0990] Server: A central computing unit that acquires, analyzes, and transmits data.

[0991] software:

[0992] OpenCV: A library for capturing video feeds and performing image analysis.

[0993] dlib: A machine learning model for recognizing user emotions.

[0994] Advertising APIs (e.g., AdAPI): Used to retrieve ads that are relevant to the user's emotions.

[0995] WebSocket or API: A communication protocol that enables real-time transmission of data.

[0996] System operation

[0997] The server first acquires the match video feed and real-time event data, and then analyzes it. Based on the analysis results, it automatically generates commentary and sends it to the user's device. User devices that display the commentary include smartphones and smart glasses, and users can view this information in real time.

[0998] Next, the system recognizes the user's emotions in real time. This is done by analyzing facial expression data captured by the camera using the dlib library. Based on the recognized emotions, the server customizes the explanatory text and the displayed advertisements. For example, if the user is excited, entertainment-related advertisements are displayed, and if they are calm, health-related advertisements are displayed.

[0999] The generated information and advertisements are sent to the user's device using WebSocket or an API and displayed in real time. This process personalizes the match-watching experience to each user's emotions, leading to higher engagement.

[1000] Specific example

[1001] While a user is watching a sports match, they may show a smile and an excited expression the moment a player scores a goal. At this moment, the smart glasses' camera captures the expression, and the server uses the dlib library to recognize the emotion as "joy." The server then retrieves an entertainment-related advertisement (for example, a trailer for a new movie) and sends it to the smart glasses, displaying it in the user's field of view.

[1002] Example of a prompt

[1003] The following are examples of prompt statements to input into a generative AI model.

[1004] Please describe the role and new user experience of a smart glasses application that uses emotion recognition technology to detect a user's joy and excitement while they are watching a sports match in real time, and then displays relevant advertisements. Please provide details, including specific functions and examples.

[1005] In this way, the invention enables the provision of information and display of advertisements tailored to the user's emotions, thereby improving the viewing experience.

[1006] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1007] Step 1:

[1008] The server retrieves the match video feed and real-time event data. This data is sent to the server via API or WebSocket.

[1009] Input: Video feed, real-time event data

[1010] Processing: Retrieve data using API or WebSocket.

[1011] Output: Video feeds and event data stored in the server's data storage.

[1012] Step 2:

[1013] The system analyzes video feeds and event data acquired by the server. Machine learning algorithms are used for the analysis to automatically identify important events during the match.

[1014] Input: Video feed, real-time event data

[1015] Processing: Data analysis using machine learning algorithms

[1016] Output: Event-specific information (e.g., goal, foul, etc.)

[1017] Step 3:

[1018] The server automatically generates explanatory text based on the analysis results. It uses natural language generation technology to create text about the progress of the match and important events.

[1019] Input: Event specific information

[1020] Processing: Text generation using natural language generation technology

[1021] Output: Explanatory text (Example: "Player A scored a magnificent goal!")

[1022] Step 4:

[1023] The server sends the generated explanatory text to the user's terminal. Data is transmitted in real time via WebSocket or API.

[1024] Input: Explanation

[1025] Processing: Send data using WebSocket or API

[1026] Output: Explanatory text sent to the user's terminal

[1027] Step 5:

[1028] The terminal displays the received explanatory text. The explanatory text is displayed on the user interface of a smartphone or smart glasses.

[1029] Input: Received explanatory text

[1030] Processing: Display via user interface

[1031] Output: Explanatory text presented visually to the user.

[1032] Step 6:

[1033] To enable the server to recognize user emotions in real time, a camera is used to capture the user's facial expressions. The dlib library is used to analyze and recognize these emotions.

[1034] Input: Captured facial expression data

[1035] Processing: Sentiment analysis using the dlib library

[1036] Output: Recognized emotion (e.g., joy, surprise, etc.)

[1037] Step 7:

[1038] The server customizes information based on recognized emotions. Appropriate ad information and explanatory text are modified according to the emotions.

[1039] Input: Recognized emotions

[1040] Processing: Information customization (retrieving ad information using the ad API, changing explanatory text)

[1041] Output: Customized information (e.g., entertainment-related advertisements)

[1042] Step 8:

[1043] The server sends customized information to the user's terminal. Customized advertisements and explanatory text are sent using WebSocket or an API.

[1044] Input: Customized information

[1045] Processing: Sending data using WebSocket or API

[1046] Output: Customization information sent to the user's terminal

[1047] Step 9:

[1048] The device displays customized information it has received. This customized information is displayed on the user interface of smartphones and smart glasses.

[1049] Input: Received customized information

[1050] Processing: Display via user interface

[1051] Output: Customized information presented visually to the user (e.g., advertisements, specific explanatory text)

[1052] 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.

[1053] 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.

[1054] 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.

[1055] [Third Embodiment]

[1056] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1057] 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.

[1058] 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).

[1059] 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.

[1060] 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.

[1061] 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).

[1062] 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.

[1063] 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.

[1064] 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.

[1065] 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.

[1066] 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.

[1067] 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".

[1068] The following describes embodiments for carrying out the present invention. This system acquires and analyzes video feeds and real-time event data of matches and provides various information to spectators and players.

[1069] System Overview

[1070] This system consists of the following main components:

[1071] 1. Data acquisition module

[1072] 2. Data Analysis Module

[1073] 3. Natural Language Generation Module

[1074] 4. Data transmission module

[1075] 5. User Interface (Terminal)

[1076] 6. Feedback Generation Module

[1077] Data acquisition module

[1078] The server retrieves the match video feed and real-time event data. This data includes a video stream of the sports match and real-time recordings of important events such as goals and fouls.

[1079] The server uses APIs and WebSockets to retrieve video feeds and event data.

[1080] Data Analysis Module

[1081] The system analyzes video feeds and event data acquired by the server in real time. Machine learning algorithms and motion recognition technologies are used for the analysis.

[1082] For example, when a goal is scored during a match, the system automatically identifies the video footage of that exact moment.

[1083] Natural Language Generation Module

[1084] The server automatically generates explanatory text based on the results of data analysis. Natural language generation technology is used to create detailed explanations about the flow of the match and events.

[1085] For example, it can generate a descriptive sentence such as, "Player A scored a magnificent goal!"

[1086] Data transmission module

[1087] The server sends the generated explanatory text and statistical information to the terminal.

[1088] The server uses WebSocket or an API to send data to the terminal in real time.

[1089] User interface (terminal)

[1090] The terminal displays the received explanatory text and statistical information on the user interface. This allows users (spectators) to understand the progress of the match and detailed information in real time.

[1091] For example, a smartphone app could display statistics such as "Player A's current distance covered: 10km".

[1092] Feedback generation module

[1093] The server collects and analyzes player movement and performance data during matches.

[1094] The server generates personalized feedback and provides it to players and coaches after the match ends.

[1095] For example, it can generate feedback such as "You should move a little more towards the center when defending" and send it to the player's device (smartphone).

[1096] Specific example

[1097] 1. Real-time commentary during the match

[1098] The server analyzes the match video feed and detects the event "Player B scored a goal."

[1099] The server generates a natural language explanation such as "Player B scored a goal with a brilliant dribble!" and sends it to the terminal.

[1100] Users can view this explanation in real time using a smartphone app.

[1101] 2. Real-time statistics provided

[1102] The server collects player distance data during the match and confirms that player C has reached a distance of 8km.

[1103] The server generates statistical information such as "Player C's current distance covered: 8km" and sends it to the terminal.

[1104] Users can view this statistical information on large screens inside the stadium or on their smartphones.

[1105] 3. Player feedback after the match

[1106] After the match ends, the server analyzes player D's performance data to identify areas for improvement in his defensive play.

[1107] The server generates feedback stating, "More lateral movement is needed during defense," and sends it to the terminal.

[1108] The user (player) receives this feedback on their smartphone and uses it to identify areas for improvement for the next match.

[1109] In this way, this system can be used to significantly improve audience engagement, provide players with personalized feedback, and enhance their performance.

[1110] The following describes the processing flow.

[1111] Processing steps for automatically generated explanations

[1112] Step 1:

[1113] The server retrieves the match video feed and real-time event data. The server uses an API to obtain the video feed URL, establishes a WebSocket connection, and receives the event data.

[1114] Step 2:

[1115] The server analyzes the acquired video feed. A machine learning model is used to detect player movements and important events (e.g., goals, fouls) within the video frames.

[1116] Step 3:

[1117] The server analyzes real-time event data and compares it with the analysis results of the video feed. It identifies important events that match the event data.

[1118] Step 4:

[1119] The server uses natural language generation technology to generate explanatory text based on identified events. Templates are used to instantly convert the analysis results into text.

[1120] Step 5:

[1121] The server generates an explanatory text and sends it to the terminal. The explanatory text is sent to the terminal in real time using a WebSocket connection.

[1122] Step 6:

[1123] The terminal displays the received explanatory text on the user interface. Users can check the explanation in real time on their smartphones, tablets, etc.

[1124] Processing steps for real-time statistics analysis

[1125] Step 1:

[1126] The server collects various data generated during a match in real time. Data is periodically polled using an API or received in real time via a WebSocket connection.

[1127] Step 2:

[1128] The server analyzes the collected data, calculating statistical data such as player distance covered and pass success rate.

[1129] Step 3:

[1130] The server generates visualized statistical information based on the analysis results. This information is then converted into graphs and charts to visualize the data.

[1131] Step 4:

[1132] The server sends generated statistics to the terminal. Statistics data is sent to the terminal using a WebSocket connection or API.

[1133] Step 5:

[1134] The system displays statistical information received by the device on the user interface. Users can check the statistical information on their smartphones or on large screens in the stadium.

[1135] Feedback generation processing steps

[1136] Step 1:

[1137] The server collects player movement and performance data during matches. An API is used to retrieve each player's position and performance data.

[1138] Step 2:

[1139] The server analyzes the collected data to evaluate the players' movements and performance. Machine learning models are used for the analysis.

[1140] Step 3:

[1141] The server generates personalized feedback based on the analysis results. Using evaluation data and templates, it creates specific areas for improvement and advice.

[1142] Step 4:

[1143] The server generates feedback and sends it to the device. Feedback is sent to the player's device via email or a dedicated app.

[1144] Step 5:

[1145] The device displays the feedback it receives on the user interface. Users (players) can review the feedback and identify areas for improvement for the next match.

[1146] Processing steps for providing generated content

[1147] Step 1:

[1148] The server collects past match data and player information. It queries the database to retrieve the necessary data.

[1149] Step 2:

[1150] Based on data collected by the server, engaging content (articles, highlight videos, etc.) is generated. Natural language generation tools and video editing tools are used to create the content.

[1151] Step 3:

[1152] Convert server-generated content into a format suitable for the user interface. Export videos and articles in the appropriate format.

[1153] Step 4:

[1154] The server sends the generated content to the device. Content is sent to the device using an API or WebSocket connection.

[1155] Step 5:

[1156] The device displays the received content to the user. The user can view the content on a smartphone, tablet, or other device.

[1157] These processing steps enable the system to significantly improve audience engagement and the viewing experience.

[1158] (Example 1)

[1159] 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."

[1160] Conventional sports viewing systems have struggled to analyze live video and statistical information during matches and automatically generate commentary. This has resulted in a lack of detailed and timely information for spectators and athletes, limiting opportunities for engagement and performance improvement. This invention aims to solve these problems and provide a more interactive and informative viewing experience.

[1161] 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.

[1162] In this invention, the server includes means for acquiring video feeds and real-time event data of a match; means for analyzing the acquired video feeds and event data in real time and identifying goals and player actions using machine learning algorithms; means for automatically generating explanatory text using natural language generation technology based on the analysis results; and means for transmitting and displaying the generated explanatory text on a user terminal. This makes it possible to provide important moments and detailed statistical information of the match in real time.

[1163] A "video feed" refers to the input data used to acquire and distribute real-time footage of a match.

[1164] "Real-time event data" refers to data used to record and transmit important events that occur during a match, such as goals and fouls, in real time.

[1165] A "machine learning algorithm" refers to a computational method that learns patterns in data and automates specific tasks.

[1166] "Natural language generation technology" refers to the technology that generates text in natural language that humans can understand, based on analyzed data.

[1167] "Explanatory text" refers to text that explains events and statistical information that occur during a match, and is intended to provide information to spectators and players.

[1168] A "user terminal" is an electronic device used to receive and display information, and includes smartphones, tablets, computers, and other electronic devices.

[1169] "Statistical information" refers to numerical data about the performance of players and teams during a match.

[1170] "Feedback" refers to information provided to players and coaches after a match, including areas for improvement and advice.

[1171] "Analysis results" refer to the final output after analyzing the collected data, and include explanatory text, statistical information, and feedback.

[1172] "Collection means" refers to the methods and devices used to acquire the necessary data.

[1173] System Overview

[1174] This invention relates to a system that acquires video feeds and real-time event data of a match, analyzes them to automatically generate commentary, and transmits and displays the commentary and statistical information to a user terminal. The system consists of a server, a terminal, and a user, and each component works in cooperation with the others.

[1175] Specific examples of hardware and software to be used

[1176] The server requires a high-performance data processing computer and a network interface. Data analysis utilizes software implementing machine learning algorithms such as TensorFlow and OpenPose. Generative AI models such as GPT-3 are used for natural language generation. APIs and WebSockets are used for data transmission and reception.

[1177] The devices include smartphones, tablets, or large screens within the stadium. These devices receive data transmitted from the server in real time and display it to the user.

[1178] Users include spectators watching the game, as well as players and their coaches who want to improve their performance. Users receive game progress updates, statistics, and feedback through smartphones, tablets, and large screens in the stadium.

[1179] Specific example

[1180] 1. Real-time commentary during the match

[1181] The server analyzes the match video feed and detects an event such as "Player B scored a goal." The server generates a natural language commentary such as "Player B scored a goal with a brilliant dribble!" and sends it to the device. The user can view this commentary in real time on their smartphone app.

[1182] 2. Real-time statistics provided

[1183] The server collects player distance data during the match and confirms that player C has reached 8km. The server generates statistics such as "Player C's current distance: 8km" and sends them to the terminal. The user can view these statistics on a large screen in the stadium or on their smartphone.

[1184] 3. Player feedback after the match

[1185] After the match ends, the server analyzes player D's performance data to identify areas for improvement in defense. The server generates feedback such as "More lateral movement is needed during defense" and sends it to the device. The user (player) receives this feedback on their smartphone and reviews the areas for improvement for the next match.

[1186] Example of a prompt

[1187] "This system analyzes video feeds and real-time event data during matches to provide information to spectators and players in real time. For example, the moment player A scores a goal, it generates commentary and notifies a smartphone app. Player distance covered and performance data are also displayed in real time, and specific feedback is provided to players after the match ends."

[1188] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1189] Step 1:

[1190] The server retrieves the match video feed and real-time event data.

[1191] Specific operation: The server uses the official FIFA API to retrieve real-time video streams. Simultaneously, it receives event data such as goals and fouls during the match via WebSocket.

[1192] Input: FIFA official API endpoint and WebSocket connection information

[1193] Output: Real-time video feed and event data

[1194] Step 2:

[1195] The server analyzes acquired video feeds and event data in real time.

[1196] Specific operation: The server analyzes the video feed using TensorFlow and OpenPose to detect specific events (e.g., goal scenes). It also applies machine learning algorithms to recognize player actions (e.g., shots and dribbles).

[1197] Input: Video feed and real-time event data

[1198] Output: Analyzed event information and player motion data

[1199] Step 3:

[1200] The server generates a natural language explanation based on the analysis results.

[1201] Specific operation: The server uses a generative AI model such as GPT-3 to create explanatory text based on the analyzed event information. For example, it might generate an explanatory text such as, "Player A scored a magnificent goal!"

[1202] Input: Analysis results (event information and player movement data)

[1203] Output: Auto-generated natural language explanation

[1204] Step 4:

[1205] The server sends the generated explanatory text and statistical information to the terminal.

[1206] Specific operation: The server sends generated explanatory text and statistical information to the terminal in real time using WebSocket or a REST API.

[1207] Input: Automatically generated explanatory text and statistical information

[1208] Output: Explanatory text and statistical information sent to the user's terminal.

[1209] Step 5:

[1210] The data received by the terminal is displayed on the user interface.

[1211] Specific operation: The device displays explanatory text and statistical information on the screen, providing it visually to the user. For example, a smartphone app might display "Player A's current distance traveled: 10km" as a notification.

[1212] Input: Explanatory text and statistical information sent from the server

[1213] Output: Explanatory text and statistics displayed on the user interface

[1214] Step 6:

[1215] The server collects and analyzes player movement and performance data during the match.

[1216] Specific operation: The server collects and analyzes player movement data (e.g., distance traveled, location information) in real time during the match. This allows for a detailed understanding of each player's performance.

[1217] Input: Player movement data during the match

[1218] Output: Analyzed performance data for each player

[1219] Step 7:

[1220] The server generates personalized feedback based on the analysis results.

[1221] Specific operation: Based on the analysis results, the server creates feedback for each player, including specific areas for improvement and advice. For example, it might generate feedback such as, "You should move a little more towards the center when defending."

[1222] Input: Analyzed performance data for each player

[1223] Output: Individualized feedback

[1224] Step 8:

[1225] The server sends the generated feedback to the user's terminal for display.

[1226] Specific operation: The server sends the generated feedback to the device (e.g., the player's smartphone), and the device displays that feedback.

[1227] Input: Personalized feedback

[1228] Output: Feedback sent to the user terminal and displayed feedback

[1229] (Application Example 1)

[1230] 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."

[1231] In sports matches, it is difficult for spectators and players to obtain detailed information in real time. Furthermore, there are limited means for players to receive individual feedback after the match has ended. As a result, spectators have difficulty understanding the progress of the match, and players have difficulty finding concrete guidelines for improving their own performance.

[1232] 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.

[1233] In this invention, the server includes means for acquiring video feeds and real-time event data of a match; means for analyzing the acquired video feeds and event data in real time and automatically generating commentary; means for transmitting the generated commentary to a user terminal and displaying it in real time; means for analyzing motion data and performance data after the match and generating personalized feedback; and means for transmitting and displaying individual player feedback to a user terminal. As a result, spectators can grasp the progress of the match and detailed commentary in real time, and players can receive specific feedback after the match to help improve their performance.

[1234] A "match video feed" refers to a video stream of a sports match, and is video data acquired for the purpose of real-time viewing and analysis.

[1235] "Real-time event data" refers to data that records important events that occur during a sports match (e.g., goals, fouls, etc.) in real time.

[1236] "Methods for automatically generating explanatory text" refer to methods for analyzing acquired video feeds and event data and automatically creating explanatory text about the progress of the match and events using natural language generation technology.

[1237] A "user terminal" refers to a device, such as a smartphone, tablet, personal computer, or head-mounted display, that allows a user to receive and display information in real time.

[1238] "Motion data and performance data" refers to detailed data on individual players' movements and performance during matches, including distance covered, speed, and number of shots.

[1239] "Personalized feedback" refers to feedback that includes specific improvement guidelines and advice for each individual athlete, based on analyzed motion and performance data.

[1240] A "generative AI model" is an algorithm or system that uses machine learning techniques to automatically generate explanatory text and feedback based on analysis results.

[1241] A "prompt statement" is an input statement used to make specific analysis requests or initial settings for the generated AI model.

[1242] "Statistical information" refers to information compiled in the form of numbers, graphs, and other formats, by analyzing various data collected during a match.

[1243] The embodiments for carrying out this invention will be described in detail below.

[1244] System Overview

[1245] This system acquires match video feeds and real-time event data, analyzes and processes it, provides users with information in real time, and provides personalized feedback to players after the match. The system consists of the following main components:

[1246] 1. Data acquisition module

[1247] 2. Data Analysis Module

[1248] 3. Natural Language Generation Module

[1249] 4. Data transmission module

[1250] 5. User Interface

[1251] 6. Feedback Generation Module

[1252] 7. Generative AI Models

[1253] 8. Prompt Statement System

[1254] Data acquisition module

[1255] The server retrieves match video feeds and real-time event data using an API or WebSocket. This data records the video stream of the sports match and important events such as goals and fouls in real time.

[1256] Data Analysis Module

[1257] The server analyzes the acquired video feed and event data in real time. The analysis utilizes machine learning algorithms (e.g., TensorFlow, OpenCV) and motion recognition technology. For example, if a goal is detected, the server automatically identifies the video footage from that moment.

[1258] Natural Language Generation Module

[1259] The server automatically generates explanatory text based on the results of data analysis. For natural language generation, it uses generative AI models such as GPT-4. For example, it might generate the explanatory text, "Player A made a fantastic shot!"

[1260] Data transmission module

[1261] The server sends generated explanatory text and statistical information to the user's terminal in real time. This transmission is done using WebSocket or an API.

[1262] User Interface

[1263] The device displays the received commentary and statistics. This allows users to understand the progress of the match and detailed information in real time. For example, the smartphone might display information such as "Player C's current distance covered: 8km".

[1264] Feedback generation module

[1265] The server analyzes player movement and performance data after the match and generates personalized feedback. This feedback is sent to the user's terminal and displayed. For example, one piece of feedback might say, "You should move a little more towards the center when defending."

[1266] Generative AI models and prompt sentence systems

[1267] The system uses a generative AI model to generate explanatory text and feedback. The prompt system is used to make specific analysis requests and initial settings for the generative AI model.

[1268] Example of a prompt

[1269] "Please generate explanatory text for when a player scores a goal during a soccer match."

[1270] "Player A scored a goal with a long-range shot from 50 meters."

[1271] This system allows spectators to follow the progress of the match and receive detailed commentary in real time, while players can receive specific feedback after the match to help improve their performance.

[1272] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1273] Step 1:

[1274] Data acquisition module

[1275] The server retrieves video feeds and real-time event data of sports matches using an API or WebSocket. Inputs are the match video stream and important event data. The server receives this data in real time and prepares it for analysis. Outputs are the retrieved video feeds and event data.

[1276] Step 2:

[1277] Data Analysis Module

[1278] The server analyzes the acquired video feed and event data in real time. The input is the video feed and event data acquired in step 1. The server automatically identifies specific scenes and events (e.g., goal scenes) using machine learning algorithms (e.g., TensorFlow, OpenCV) and motion recognition technology. The output is the analyzed event information and its details.

[1279] Step 3:

[1280] Natural Language Generation Module

[1281] The server automatically generates explanatory text based on the results of data analysis. The input is the event information analyzed in step 2. The server uses a generative AI model such as GPT-4 as a natural language generation technique to create explanatory text according to the analysis results. For example, the sentence "Player A made a great shot!" is generated. The output is the generated explanatory text.

[1282] Step 4:

[1283] Data transmission module

[1284] The server sends the generated explanatory text and statistics to the user terminal in real time. The input is the explanatory text and related statistics generated in step 3. WebSocket or API is used for transmission. The output is the explanatory text and statistics sent to the user terminal.

[1285] Step 5:

[1286] User Interface

[1287] The terminal displays the received explanatory text and statistical information. The input is the explanatory text and statistical information sent in step 4. The user terminal displays this information on the screen in real time, allowing the user to understand the progress of the match and detailed information. For example, the smartphone displays information such as "Player C's current distance covered: 8km". The output is information that the user can visually confirm.

[1288] Step 6:

[1289] Feedback generation module

[1290] The server analyzes player movement and performance data after the match and generates personalized feedback. The input is player movement and performance data collected during the match. The server analyzes this data and generates feedback that provides specific improvement guidelines for each player. For example, feedback such as "You should move a little more towards the center when defending" might be generated. The output is the personalized feedback.

[1291] Step 7:

[1292] Feedback transmission module

[1293] The server sends the generated feedback to the user's (player's) terminal for display. The input is the personalized feedback generated in step 6. The server sends the feedback using WebSocket or API. The output is the feedback sent to the user's terminal.

[1294] In this way, spectators can follow the progress of the match and receive detailed commentary in real time, and players can receive specific feedback after the match to help improve their performance.

[1295] 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.

[1296] The following describes embodiments for carrying out the present invention. This system acquires and analyzes video feeds and real-time event data of matches, provides various information to spectators and players, and recognizes the user's emotions to customize the experience.

[1297] System Overview

[1298] This system consists of the following main components:

[1299] 1. Data acquisition module

[1300] 2. Data Analysis Module

[1301] 3. Natural Language Generation Module

[1302] 4. Data transmission module

[1303] 5. User Interface (Terminal)

[1304] 6. Feedback Generation Module

[1305] 7. Emotional Engine

[1306] Data acquisition module

[1307] The server retrieves the match video feed and real-time event data. This data includes a video stream of the sports match and real-time recordings of important events such as goals and fouls.

[1308] The server uses APIs and WebSockets to retrieve video feeds and event data.

[1309] Data Analysis Module

[1310] The system analyzes video feeds and event data acquired by the server in real time. Machine learning algorithms and motion recognition technologies are used for the analysis.

[1311] For example, when a goal is scored during a match, the system automatically identifies the video footage of that exact moment.

[1312] Natural Language Generation Module

[1313] The server automatically generates explanatory text based on the results of data analysis. Natural language generation technology is used to create detailed explanations about the flow of the match and events.

[1314] For example, it can generate a descriptive sentence such as, "Player A scored a magnificent goal!"

[1315] Emotional Engine

[1316] The server recognizes the user's emotions in real time. The emotion engine recognizes emotions such as joy, surprise, and excitement from the user's facial expressions and tone of voice.

[1317] Based on the recognized emotions, the explanatory text, statistical information, and feedback content are customized.

[1318] Data transmission module

[1319] The server sends generated explanatory text, sentiment-based customized information, and statistical data to the terminal.

[1320] The server uses a WebSocket connection or API to send data to the terminal in real time.

[1321] User interface (terminal)

[1322] The terminal displays the received explanatory text, customized information, and statistics on the user interface. This allows users (spectators) to understand the progress of the match and detailed information in real time.

[1323] For example, within a smartphone app, statistical information such as "Player A's current distance covered: 10km" could be displayed, along with explanatory text that changes according to the user's emotions.

[1324] Feedback generation module

[1325] The server collects and analyzes player movement and performance data during matches.

[1326] The server generates personalized feedback and provides it to players and coaches after the match ends.

[1327] For example, it can generate feedback such as "You should move a little more towards the center when defending" and send it to the player's device (smartphone).

[1328] Specific example

[1329] 1. Real-time commentary during the match

[1330] The server analyzes the match video feed and detects the event "Player B scored a goal."

[1331] The server generates a natural language explanation such as "Player B scored a goal with a brilliant dribble!" and sends it to the terminal.

[1332] Users can view this explanation in real time using a smartphone app.

[1333] The emotion engine recognizes the user's feelings of joy and adds phrases such as "The audience is also very excited!" to the next comment.

[1334] 2. Real-time statistics provided

[1335] The server collects player distance data during the match and confirms that player C has reached a distance of 8km.

[1336] The server generates statistical information such as "Player C's current distance covered: 8km" and sends it to the terminal.

[1337] Users can check statistical information on large screens inside the stadium or on their smartphones.

[1338] The emotion engine recognizes the user's surprise and adds the comment, "Player C is showing incredible stamina!" to the displayed statistics.

[1339] 3. Player feedback after the match

[1340] After the match ends, the server analyzes player D's performance data to identify areas for improvement in his defensive play.

[1341] The server generates feedback stating, "More lateral movement is needed during defense," and sends it to the terminal.

[1342] The user (player) receives this feedback on their smartphone and uses it to identify areas for improvement for the next match.

[1343] The emotional engine recognizes the player's feelings of frustration and impatience, and reinforces the feedback with more positive language before providing it.

[1344] Thus, this system can significantly improve audience engagement, provide players with personalized feedback, and enhance their performance. Furthermore, by utilizing an emotion engine, the quality of information provided can be customized to match the user's emotions.

[1345] The following describes the processing flow.

[1346] Processing steps for automatically generated explanations

[1347] Step 1:

[1348] The server retrieves the match video feed and real-time event data. The server uses an API to obtain the video feed URL, establishes a WebSocket connection, and receives the event data.

[1349] Step 2:

[1350] The server analyzes the acquired video feed. A machine learning model is used to detect player movements and important events (e.g., goals, fouls) within the video frames.

[1351] Step 3:

[1352] The server analyzes real-time event data and compares it with the analysis results of the video feed. It identifies important events that match the event data.

[1353] Step 4:

[1354] The server uses natural language generation technology to generate explanatory text based on identified events. Templates are used to instantly convert the analysis results into text.

[1355] Step 5:

[1356] The server uses an emotion engine to recognize the user's emotions. It grasps the user's emotions in real time through facial recognition and voice tone analysis.

[1357] Step 6:

[1358] The server customizes the generated commentary based on the emotions it recognizes. For example, if the user is excited, it adds phrases like "The audience is also very excited!" to the commentary.

[1359] Step 7:

[1360] The server sends generated and customized explanatory text to the terminal. The explanatory text is sent to the terminal in real time using a WebSocket connection.

[1361] Step 8:

[1362] The terminal displays the received explanatory text on the user interface. Users can check the explanation in real time on their smartphones, tablets, etc.

[1363] Processing steps for real-time statistics analysis

[1364] Step 1:

[1365] The server collects various data generated during a match in real time. This is done by periodically polling the data using an API or by receiving the data in real time using a WebSocket connection.

[1366] Step 2:

[1367] The server analyzes the collected data. It executes analysis algorithms to calculate statistical data such as player distance covered and pass success rate.

[1368] Step 3:

[1369] The server generates visualized statistical information based on the analysis results. This information is then converted into graphs and charts to visualize the data.

[1370] Step 4:

[1371] The server uses an emotion engine to recognize the user's emotions in real time. The analysis results are then integrated with the user's emotion data.

[1372] Step 5:

[1373] The server adjusts the display format of statistics based on the emotions it perceives. For example, if the user is surprised, it might add a comment such as, "Player C is showing incredible stamina!"

[1374] Step 6:

[1375] The server sends generated and customized statistics to the terminal. Statistics are sent to the terminal using a WebSocket connection or API.

[1376] Step 7:

[1377] The system displays statistical information received by the device on the user interface. Users can check the statistical information on their smartphones or on large screens in the stadium.

[1378] Feedback generation processing steps

[1379] Step 1:

[1380] The server collects player movement and performance data during matches. An API is used to retrieve each player's position and performance data.

[1381] Step 2:

[1382] The server analyzes the collected data to evaluate the players' movements and performance. Machine learning models are used for the analysis.

[1383] Step 3:

[1384] The server generates personalized feedback based on the analysis results. Using evaluation data and templates, it creates specific areas for improvement and advice.

[1385] Step 4:

[1386] The server uses an emotion engine to recognize the player's emotions. It observes how feedback is received and analyzes the player's facial expressions and tone of voice.

[1387] Step 5:

[1388] The server customizes the feedback based on the emotions it perceives. For example, if a player is feeling frustrated or impatient, the feedback will be reinforced with positive language.

[1389] Step 6:

[1390] The server sends generated and customized feedback to the player's device. Feedback is sent to the player's device via email or a dedicated app.

[1391] Step 7:

[1392] The device displays the feedback it receives on the user interface. The user (player) reviews the feedback and identifies areas for improvement for the next match.

[1393] Processing steps for providing generated content

[1394] Step 1:

[1395] The server collects past match data and player information. It queries the database to retrieve the necessary data.

[1396] Step 2:

[1397] Based on data collected by the server, engaging content (articles, highlight videos, etc.) is generated. Natural language generation tools and video editing tools are used to create the content.

[1398] Step 3:

[1399] Convert server-generated content into a format suitable for the user interface. Export videos and articles in the appropriate format.

[1400] Step 4:

[1401] The server uses an emotion engine to recognize the user's emotions and observes the user's reactions in real time while content is being delivered.

[1402] Step 5:

[1403] The server adjusts content visualizations based on the emotions it perceives. For example, if a user is emotional, it might add a "Featured Article: The Inspiring Story of Player X."

[1404] Step 6:

[1405] The server sends generated and customized content to the device. Content is sent to the device using an API or WebSocket connection.

[1406] Step 7:

[1407] The device displays the received content to the user. The user can view the content on a smartphone, tablet, or other device.

[1408] These processing steps enable the system to significantly improve audience engagement and the viewing experience. Furthermore, by utilizing the emotion engine, the quality of information provided can be customized to match the user's emotions.

[1409] (Example 2)

[1410] 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."

[1411] Traditional match viewing systems did not provide real-time information on the progress of the match or the performance of the players, making it difficult for spectators and players to immediately grasp the details of the match. Furthermore, the lack of commentary and feedback tailored to the user's emotions resulted in insufficient audience engagement. Additionally, feedback was typically provided after the match, without real-time advice or suggestions for improvement. Therefore, there was a need for technology that would make the match experience more engaging and personalized.

[1412] 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.

[1413] In this invention, the server includes means for acquiring a video stream and real-time event data of a match; means for analyzing the acquired video stream and event data in real time and detecting specific events using a machine learning algorithm; means for automatically generating explanatory text using natural language generation technology based on the analysis results; means for transmitting and displaying the generated explanatory text and customized information to a user terminal; and means for analyzing the user's facial expressions and voice, recognizing emotions in real time, and generating feedback. This enables the provision of detailed commentary and statistical information in real time, as well as the provision of customized information tailored to the user's emotions. Furthermore, it is possible to improve performance by providing specific feedback to players and coaches after the match.

[1414] "Match video stream" refers to video data of a match that is acquired in real time.

[1415] "Real-time event data" refers to data that records important events that occur during a match (e.g., goals, fouls) in real time.

[1416] A "machine learning algorithm" is a general term for mathematical models and methods used to automatically learn and analyze specific patterns and information based on data.

[1417] "Natural language generation technology" is a technology that uses computer-generated data to create natural language sentences that humans can read.

[1418] "Explanatory text" refers to a document that includes detailed explanations of the progress of a match or specific events.

[1419] A "user terminal" refers to electronic devices such as smartphones, tablets, and personal computers used by users.

[1420] "Customized information" refers to information that has been specially tailored to the user's needs and circumstances.

[1421] An "emotion engine" is a technology and system that recognizes emotions by analyzing a user's facial expressions, tone of voice, and other factors.

[1422] "Feedback" refers to information used to provide areas for improvement and advice based on an athlete's movements and performance.

[1423] The following describes specific embodiments for carrying out this invention. This system acquires and analyzes video streams and real-time event data of matches, provides various information to spectators and players, and recognizes user emotions to customize the experience. The system consists of a data acquisition module, a data analysis module, a natural language generation module, an emotion engine, a data transmission module, a user interface, and a feedback generation module.

[1424] Data acquisition module

[1425] The server retrieves the match video stream and real-time event data. This data is retrieved via cameras, APIs, and WebSocket connections. For example, the server accesses cameras for the video feed, streams video data, and receives event data in real time via WebSocket.

[1426] Data Analysis Module

[1427] The server analyzes the acquired video stream and event data in real time. Machine learning algorithms (e.g., TensorFlow) and motion recognition technologies (e.g., OpenCV) are used for the analysis. For example, the server analyzes the video data frame by frame to detect the moment a specific event (e.g., a goal) occurs.

[1428] Natural Language Generation Module

[1429] The server automatically generates explanatory text using natural language generation technology based on the results of data analysis. For example, it can use a generative AI model such as GPT-3 to generate explanatory text such as, "Player A scored a magnificent goal!"

[1430] Emotional Engine

[1431] The server recognizes the user's emotions in real time. By analyzing the user's facial expressions and tone of voice, it determines their emotions and generates corresponding feedback. For example, it uses AWS Rekognition to read the user's emotions such as joy and surprise.

[1432] Data transmission module

[1433] The server sends generated explanatory text, customized information, and statistics to the terminal. WebSocket connection or API is used for transmission. For example, the generated explanatory text and statistics are sent to the terminal in JSON format.

[1434] User Interface

[1435] The terminal displays explanatory text, customized information, and statistics on the user interface. This display is performed on devices such as smartphones, tablets, and PCs. For example, the smartphone app screen might display information such as "Player A's current distance traveled: 10km".

[1436] Feedback generation module

[1437] The server collects and analyzes player movement and performance data during the match. It generates individual feedback, which is then sent to players and coaches after the match. For example, feedback such as "You should move a little more towards the center when defending" might be generated.

[1438] Specific example

[1439] Specific examples are given below.

[1440] Real-time commentary during the match

[1441] The server analyzes the match video stream and detects the event "Player B scores a goal." The server uses a generative AI model to generate a commentary such as "Player B scores a goal with a brilliant dribble!" and sends it to the device. The user checks this commentary in real time on the smartphone app, and the emotion engine recognizes the user's excitement and adds phrases such as "The crowd is also very excited!" to the next comment.

[1442] Real-time statistics provided

[1443] The server collects player distances during the match and confirms that player C has reached 8km. The server generates statistics such as "Player C's current distance: 8km" and sends them to the user's device. The user checks these statistics on their smartphone or on a large screen in the stadium, and the emotion engine recognizes the user's surprise and adds the comment, "Player C is showing incredible stamina!"

[1444] Examples of prompts for generative AI models

[1445] "Please generate natural language commentary describing the moment a player scores a goal during a soccer match. Additionally, please add emotionally charged comments that reflect the user's feelings, such as joy."

[1446] This invention can improve audience engagement and provide players with personalized feedback to enhance their performance. By utilizing an emotion engine, the quality of information provided can be customized to match the user's emotions.

[1447] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1448] Step 1:

[1449] Data acquisition

[1450] The server acquires the match video stream and real-time event data. This process involves acquiring video and event data via cameras, APIs, and WebSocket connections.

[1451] (Input): Camera video data, event data API, WebSocket connection.

[1452] (Output): Video stream data and event data stored on the server.

[1453] Specific operation: The server accesses the camera for the video feed and obtains real-time stream data. Simultaneously, it receives event data in real time via API calls and WebSocket connections and stores it in the server's database.

[1454] Step 2:

[1455] Data Analysis

[1456] The server analyzes acquired video streams and event data in real time. Machine learning algorithms and motion recognition technologies are used for the analysis.

[1457] (Input): Video stream data, event data.

[1458] (Output): Analysis results (detection results for a specific event).

[1459] Specific operation: The server analyzes video data frame by frame and detects the moment a specific event (e.g., a goal) occurs. The technologies used include Python's OpenCV library and TensorFlow models, which enable real-time event detection.

[1460] Step 3:

[1461] natural language generation

[1462] The server automatically generates explanatory text using natural language generation technology based on the results of data analysis.

[1463] (Input): Analysis result.

[1464] (Output): The generated explanatory text.

[1465] Specific operation: The server takes the analysis results as input and uses a generation AI model (e.g., GPT-3) to generate explanatory text. For example, content such as "Player A scored a magnificent goal!" is automatically generated.

[1466] Step 4:

[1467] emotion recognition

[1468] The server recognizes the user's emotions in real time. It analyzes the user's facial expressions and tone of voice.

[1469] (Input): User's facial expression data, voice data.

[1470] (Output): Emotion recognition result (joy, surprise, excitement, etc.).

[1471] Specific operation: The server acquires data from the camera and microphone and uses facial recognition algorithms and voice analysis algorithms to classify the user's emotions in real time. For example, emotions can be recognized using AWS Rekognition.

[1472] Step 5:

[1473] Data transmission

[1474] The server sends generated explanatory text, customized information, and statistical data to the terminal.

[1475] (Input): Generated explanatory text, sentiment recognition results, and statistical information.

[1476] (Output): Explanatory text and statistical information sent to the terminal.

[1477] Specific operation: The server sends the generated data to the terminal in real time via a WebSocket connection or API. JSON is commonly used as the transmission format.

[1478] Step 6:

[1479] Data display

[1480] The terminal displays explanatory text, customized information, and statistics on the user interface.

[1481] (Input): Explanatory text and statistical information sent to the terminal.

[1482] (Output): Explanatory text and statistical information displayed on the user's terminal.

[1483] Specific operation: The device analyzes the data it receives and displays it on the application screen of a smartphone or tablet. For example, information such as "Player A's current distance traveled: 10km" will be displayed in the smartphone app.

[1484] Step 7:

[1485] Feedback generation

[1486] The server collects and analyzes player movement and performance data during the match. It generates individual feedback and sends it to players and coaches after the match ends.

[1487] (Input): Player motion data, performance data.

[1488] (Output): Individualized feedback.

[1489] Specific operation: The server analyzes the data collected after the match ends and generates improvement suggestions and advice for each player. For example, specific advice such as "You should move a little more towards the center when defending" is generated and sent to the terminal.

[1490] (Application Example 2)

[1491] 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."

[1492] Traditional match viewing systems had the means to acquire video feeds and event data and provide users with information in real time, but they lacked the ability to recognize user emotions and customize information based on those emotions. As a result, the viewing experience was uniform, and information tailored to the needs of individual users was not provided. Furthermore, advertising displays were not personalized considering the user's emotions or level of excitement at that moment, and therefore did not sufficiently increase engagement.

[1493] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring video feeds and real-time event data of a match; means for analyzing the acquired video feeds and event data in real time and automatically generating explanatory text; means for transmitting and displaying the generated explanatory text to a user terminal; means for recognizing the user's emotions in real time and customizing information based on those emotions; and means for transmitting the customized information to the user terminal and displaying advertisements. This makes it possible to provide information and display advertisements that reflect the user's emotions.

[1494] A "video feed" refers to live video data of a match, which is real-time video information of the game.

[1495] "Real-time event data" refers to data that records important event information, such as goals and fouls, that occur during a match in real time.

[1496] "Explanatory text" refers to textual information that describes events during a match, including detailed explanations of the match's progress and important events.

[1497] A "user terminal" is an electronic device that a user carries or wears to receive and display information, such as a smartphone, smart glasses, or tablet.

[1498] "Emotion recognition" is a technology that analyzes and identifies a user's emotions at a given moment based on their facial expressions, voice, and other factors.

[1499] "Customized information" refers to information that is provided in an individualized manner according to the user's needs and circumstances, based on the results of the user's emotion recognition.

[1500] "Advertising" refers to information displayed by companies or individuals to users in order to promote their products or services, with the aim of increasing user interest and attention.

[1501] "Statistical information" refers to numerical data obtained as a result of analyzing various data generated during a match, and includes detailed information about the match, such as the distance players covered and the number of goals scored.

[1502] The system for carrying out this invention acquires video feeds and real-time event data of a match, generates commentary based on this data, and transmits it to the user's terminal. It also recognizes the user's emotions in real time and provides customized information based on those emotions.

[1503] Required hardware and software

[1504] Hardware:

[1505] Camera: Uses the camera on smart glasses or a smartphone to capture the user's facial expressions.

[1506] Server: A central computing unit that acquires, analyzes, and transmits data.

[1507] software:

[1508] OpenCV: A library for capturing video feeds and performing image analysis.

[1509] dlib: A machine learning model for recognizing user emotions.

[1510] Advertising APIs (e.g., AdAPI): Used to retrieve ads that are relevant to the user's emotions.

[1511] WebSocket or API: A communication protocol that enables real-time transmission of data.

[1512] System operation

[1513] The server first acquires the match video feed and real-time event data, and then analyzes it. Based on the analysis results, it automatically generates commentary and sends it to the user's device. User devices that display the commentary include smartphones and smart glasses, and users can view this information in real time.

[1514] Next, the system recognizes the user's emotions in real time. This is done by analyzing facial expression data captured by the camera using the dlib library. Based on the recognized emotions, the server customizes the explanatory text and the displayed advertisements. For example, if the user is excited, entertainment-related advertisements are displayed, and if they are calm, health-related advertisements are displayed.

[1515] The generated information and advertisements are sent to the user's device using WebSocket or an API and displayed in real time. This process personalizes the match-watching experience to each user's emotions, leading to higher engagement.

[1516] Specific example

[1517] While a user is watching a sports match, they may show a smile and an excited expression the moment a player scores a goal. At this moment, the smart glasses' camera captures the expression, and the server uses the dlib library to recognize the emotion as "joy." The server then retrieves an entertainment-related advertisement (for example, a trailer for a new movie) and sends it to the smart glasses, displaying it in the user's field of view.

[1518] Example of a prompt

[1519] The following are examples of prompt statements to input into a generative AI model.

[1520] Please describe the role and new user experience of a smart glasses application that uses emotion recognition technology to detect a user's joy and excitement while they are watching a sports match in real time, and then displays relevant advertisements. Please provide details, including specific functions and examples.

[1521] In this way, the invention enables the provision of information and display of advertisements tailored to the user's emotions, thereby improving the viewing experience.

[1522] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1523] Step 1:

[1524] The server retrieves the match video feed and real-time event data. This data is sent to the server via API or WebSocket.

[1525] Input: Video feed, real-time event data

[1526] Processing: Retrieve data using API or WebSocket.

[1527] Output: Video feeds and event data stored in the server's data storage.

[1528] Step 2:

[1529] The system analyzes video feeds and event data acquired by the server. Machine learning algorithms are used for the analysis to automatically identify important events during the match.

[1530] Input: Video feed, real-time event data

[1531] Processing: Data analysis using machine learning algorithms

[1532] Output: Event-specific information (e.g., goal, foul, etc.)

[1533] Step 3:

[1534] The server automatically generates explanatory text based on the analysis results. It uses natural language generation technology to create text about the progress of the match and important events.

[1535] Input: Event specific information

[1536] Processing: Text generation using natural language generation technology

[1537] Output: Explanatory text (Example: "Player A scored a magnificent goal!")

[1538] Step 4:

[1539] The server sends the generated explanatory text to the user's terminal. Data is transmitted in real time via WebSocket or API.

[1540] Input: Explanation

[1541] Processing: Send data using WebSocket or API

[1542] Output: Explanatory text sent to the user's terminal

[1543] Step 5:

[1544] The terminal displays the received explanatory text. The explanatory text is displayed on the user interface of a smartphone or smart glasses.

[1545] Input: Received explanatory text

[1546] Processing: Display via user interface

[1547] Output: Explanatory text presented visually to the user.

[1548] Step 6:

[1549] To enable the server to recognize user emotions in real time, a camera is used to capture the user's facial expressions. The dlib library is used to analyze and recognize these emotions.

[1550] Input: Captured facial expression data

[1551] Processing: Sentiment analysis using the dlib library

[1552] Output: Recognized emotion (e.g., joy, surprise, etc.)

[1553] Step 7:

[1554] The server customizes information based on recognized emotions. Appropriate ad information and explanatory text are modified according to the emotions.

[1555] Input: Recognized emotions

[1556] Processing: Information customization (retrieving ad information using the ad API, changing explanatory text)

[1557] Output: Customized information (e.g., entertainment-related advertisements)

[1558] Step 8:

[1559] The server sends customized information to the user's terminal. Customized advertisements and explanatory text are sent using WebSocket or an API.

[1560] Input: Customized information

[1561] Processing: Sending data using WebSocket or API

[1562] Output: Customization information sent to the user's terminal

[1563] Step 9:

[1564] The device displays customized information it has received. This customized information is displayed on the user interface of smartphones and smart glasses.

[1565] Input: Received customized information

[1566] Processing: Display via user interface

[1567] Output: Customized information presented visually to the user (e.g., advertisements, specific explanatory text)

[1568] 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.

[1569] 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.

[1570] 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.

[1571] [Fourth Embodiment]

[1572] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1573] 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.

[1574] 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).

[1575] 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.

[1576] 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.

[1577] 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).

[1578] 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.

[1579] 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.

[1580] 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.

[1581] 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.

[1582] 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.

[1583] 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.

[1584] 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".

[1585] The following describes embodiments for carrying out the present invention. This system acquires and analyzes video feeds and real-time event data of matches and provides various information to spectators and players.

[1586] System Overview

[1587] This system consists of the following main components:

[1588] 1. Data acquisition module

[1589] 2. Data Analysis Module

[1590] 3. Natural Language Generation Module

[1591] 4. Data transmission module

[1592] 5. User Interface (Terminal)

[1593] 6. Feedback Generation Module

[1594] Data acquisition module

[1595] The server retrieves the match video feed and real-time event data. This data includes a video stream of the sports match and real-time recordings of important events such as goals and fouls.

[1596] The server uses APIs and WebSockets to retrieve video feeds and event data.

[1597] Data Analysis Module

[1598] The system analyzes video feeds and event data acquired by the server in real time. Machine learning algorithms and motion recognition technologies are used for the analysis.

[1599] For example, when a goal is scored during a match, the system automatically identifies the video footage of that exact moment.

[1600] Natural Language Generation Module

[1601] The server automatically generates explanatory text based on the results of data analysis. Natural language generation technology is used to create detailed explanations about the flow of the match and events.

[1602] For example, it can generate a descriptive sentence such as, "Player A scored a magnificent goal!"

[1603] Data transmission module

[1604] The server sends the generated explanatory text and statistical information to the terminal.

[1605] The server uses WebSocket or an API to send data to the terminal in real time.

[1606] User interface (terminal)

[1607] The terminal displays the received explanatory text and statistical information on the user interface. This allows users (spectators) to understand the progress of the match and detailed information in real time.

[1608] For example, a smartphone app could display statistics such as "Player A's current distance covered: 10km".

[1609] Feedback generation module

[1610] The server collects and analyzes player movement and performance data during matches.

[1611] The server generates personalized feedback and provides it to players and coaches after the match ends.

[1612] For example, it can generate feedback such as "You should move a little more towards the center when defending" and send it to the player's device (smartphone).

[1613] Specific example

[1614] 1. Real-time commentary during the match

[1615] The server analyzes the match video feed and detects the event "Player B scored a goal."

[1616] The server generates a natural language explanation such as "Player B scored a goal with a brilliant dribble!" and sends it to the terminal.

[1617] Users can view this explanation in real time using a smartphone app.

[1618] 2. Real-time statistics provided

[1619] The server collects player distance data during the match and confirms that player C has reached a distance of 8km.

[1620] The server generates statistical information such as "Player C's current distance covered: 8km" and sends it to the terminal.

[1621] Users can view this statistical information on large screens inside the stadium or on their smartphones.

[1622] 3. Player feedback after the match

[1623] After the match ends, the server analyzes player D's performance data to identify areas for improvement in his defensive play.

[1624] The server generates feedback stating, "More lateral movement is needed during defense," and sends it to the terminal.

[1625] The user (player) receives this feedback on their smartphone and uses it to identify areas for improvement for the next match.

[1626] In this way, this system can be used to significantly improve audience engagement, provide players with personalized feedback, and enhance their performance.

[1627] The following describes the processing flow.

[1628] Processing steps for automatically generated explanations

[1629] Step 1:

[1630] The server retrieves the match video feed and real-time event data. The server uses an API to obtain the video feed URL, establishes a WebSocket connection, and receives the event data.

[1631] Step 2:

[1632] The server analyzes the acquired video feed. A machine learning model is used to detect player movements and important events (e.g., goals, fouls) within the video frames.

[1633] Step 3:

[1634] The server analyzes real-time event data and compares it with the analysis results of the video feed. It identifies important events that match the event data.

[1635] Step 4:

[1636] The server uses natural language generation technology to generate explanatory text based on identified events. Templates are used to instantly convert the analysis results into text.

[1637] Step 5:

[1638] The server generates an explanatory text and sends it to the terminal. The explanatory text is sent to the terminal in real time using a WebSocket connection.

[1639] Step 6:

[1640] The terminal displays the received explanatory text on the user interface. Users can check the explanation in real time on their smartphones, tablets, etc.

[1641] Processing steps for real-time statistics analysis

[1642] Step 1:

[1643] The server collects various data generated during a match in real time. Data is periodically polled using an API or received in real time via a WebSocket connection.

[1644] Step 2:

[1645] The server analyzes the collected data, calculating statistical data such as player distance covered and pass success rate.

[1646] Step 3:

[1647] The server generates visualized statistical information based on the analysis results. This information is then converted into graphs and charts to visualize the data.

[1648] Step 4:

[1649] The server sends generated statistics to the terminal. Statistics data is sent to the terminal using a WebSocket connection or API.

[1650] Step 5:

[1651] The system displays statistical information received by the device on the user interface. Users can check the statistical information on their smartphones or on large screens in the stadium.

[1652] Feedback generation processing steps

[1653] Step 1:

[1654] The server collects player movement and performance data during matches. An API is used to retrieve each player's position and performance data.

[1655] Step 2:

[1656] The server analyzes the collected data to evaluate the players' movements and performance. Machine learning models are used for the analysis.

[1657] Step 3:

[1658] The server generates personalized feedback based on the analysis results. Using evaluation data and templates, it creates specific areas for improvement and advice.

[1659] Step 4:

[1660] The server generates feedback and sends it to the device. Feedback is sent to the player's device via email or a dedicated app.

[1661] Step 5:

[1662] The device displays the feedback it receives on the user interface. Users (players) can review the feedback and identify areas for improvement for the next match.

[1663] Processing steps for providing generated content

[1664] Step 1:

[1665] The server collects past match data and player information. It queries the database to retrieve the necessary data.

[1666] Step 2:

[1667] Based on data collected by the server, engaging content (articles, highlight videos, etc.) is generated. Natural language generation tools and video editing tools are used to create the content.

[1668] Step 3:

[1669] Convert server-generated content into a format suitable for the user interface. Export videos and articles in the appropriate format.

[1670] Step 4:

[1671] The server sends the generated content to the device. Content is sent to the device using an API or WebSocket connection.

[1672] Step 5:

[1673] The device displays the received content to the user. The user can view the content on a smartphone, tablet, or other device.

[1674] These processing steps enable the system to significantly improve audience engagement and the viewing experience.

[1675] (Example 1)

[1676] 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".

[1677] Conventional sports viewing systems have struggled to analyze live video and statistical information during matches and automatically generate commentary. This has resulted in a lack of detailed and timely information for spectators and athletes, limiting opportunities for engagement and performance improvement. This invention aims to solve these problems and provide a more interactive and informative viewing experience.

[1678] 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.

[1679] In this invention, the server includes means for acquiring video feeds and real-time event data of a match; means for analyzing the acquired video feeds and event data in real time and identifying goals and player actions using machine learning algorithms; means for automatically generating explanatory text using natural language generation technology based on the analysis results; and means for transmitting and displaying the generated explanatory text on a user terminal. This makes it possible to provide important moments and detailed statistical information of the match in real time.

[1680] A "video feed" refers to the input data used to acquire and distribute real-time footage of a match.

[1681] "Real-time event data" refers to data used to record and transmit important events that occur during a match, such as goals and fouls, in real time.

[1682] A "machine learning algorithm" refers to a computational method that learns patterns in data and automates specific tasks.

[1683] "Natural language generation technology" refers to the technology that generates text in natural language that humans can understand, based on analyzed data.

[1684] "Explanatory text" refers to text that explains events and statistical information that occur during a match, and is intended to provide information to spectators and players.

[1685] A "user terminal" is an electronic device used to receive and display information, and includes smartphones, tablets, computers, and other electronic devices.

[1686] "Statistical information" refers to numerical data about the performance of players and teams during a match.

[1687] "Feedback" refers to information provided to players and coaches after a match, including areas for improvement and advice.

[1688] "Analysis results" refer to the final output after analyzing the collected data, and include explanatory text, statistical information, and feedback.

[1689] "Collection means" refers to the methods and devices used to acquire the necessary data.

[1690] System Overview

[1691] This invention relates to a system that acquires video feeds and real-time event data of a match, analyzes them to automatically generate commentary, and transmits and displays the commentary and statistical information to a user terminal. The system consists of a server, a terminal, and a user, and each component works in cooperation with the others.

[1692] Specific examples of hardware and software to be used

[1693] The server requires a high-performance data processing computer and a network interface. Data analysis utilizes software implementing machine learning algorithms such as TensorFlow and OpenPose. Generative AI models such as GPT-3 are used for natural language generation. APIs and WebSockets are used for data transmission and reception.

[1694] The devices include smartphones, tablets, or large screens within the stadium. These devices receive data transmitted from the server in real time and display it to the user.

[1695] Users include spectators watching the game, as well as players and their coaches who want to improve their performance. Users receive game progress updates, statistics, and feedback through smartphones, tablets, and large screens in the stadium.

[1696] Specific example

[1697] 1. Real-time commentary during the match

[1698] The server analyzes the match video feed and detects an event such as "Player B scored a goal." The server generates a natural language commentary such as "Player B scored a goal with a brilliant dribble!" and sends it to the device. The user can view this commentary in real time on their smartphone app.

[1699] 2. Real-time statistics provided

[1700] The server collects player distance data during the match and confirms that player C has reached 8km. The server generates statistics such as "Player C's current distance: 8km" and sends them to the terminal. The user can view these statistics on a large screen in the stadium or on their smartphone.

[1701] 3. Player feedback after the match

[1702] After the match ends, the server analyzes player D's performance data to identify areas for improvement in defense. The server generates feedback such as "More lateral movement is needed during defense" and sends it to the device. The user (player) receives this feedback on their smartphone and reviews the areas for improvement for the next match.

[1703] Example of a prompt

[1704] "This system analyzes video feeds and real-time event data during matches to provide information to spectators and players in real time. For example, the moment player A scores a goal, it generates commentary and notifies a smartphone app. Player distance covered and performance data are also displayed in real time, and specific feedback is provided to players after the match ends."

[1705] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1706] Step 1:

[1707] The server retrieves the match video feed and real-time event data.

[1708] Specific operation: The server uses the official FIFA API to retrieve real-time video streams. Simultaneously, it receives event data such as goals and fouls during the match via WebSocket.

[1709] Input: FIFA official API endpoint and WebSocket connection information

[1710] Output: Real-time video feed and event data

[1711] Step 2:

[1712] The server analyzes acquired video feeds and event data in real time.

[1713] Specific operation: The server analyzes the video feed using TensorFlow and OpenPose to detect specific events (e.g., goal scenes). It also applies machine learning algorithms to recognize player actions (e.g., shots and dribbles).

[1714] Input: Video feed and real-time event data

[1715] Output: Analyzed event information and player motion data

[1716] Step 3:

[1717] The server generates a natural language explanation based on the analysis results.

[1718] Specific operation: The server uses a generative AI model such as GPT-3 to create explanatory text based on the analyzed event information. For example, it might generate an explanatory text such as, "Player A scored a magnificent goal!"

[1719] Input: Analysis results (event information and player movement data)

[1720] Output: Auto-generated natural language explanation

[1721] Step 4:

[1722] The server sends the generated explanatory text and statistical information to the terminal.

[1723] Specific operation: The server sends generated explanatory text and statistical information to the terminal in real time using WebSocket or a REST API.

[1724] Input: Automatically generated explanatory text and statistical information

[1725] Output: Explanatory text and statistical information sent to the user's terminal.

[1726] Step 5:

[1727] The data received by the terminal is displayed on the user interface.

[1728] Specific operation: The device displays explanatory text and statistical information on the screen, providing it visually to the user. For example, a smartphone app might display "Player A's current distance traveled: 10km" as a notification.

[1729] Input: Explanatory text and statistical information sent from the server

[1730] Output: Explanatory text and statistics displayed on the user interface

[1731] Step 6:

[1732] The server collects and analyzes player movement and performance data during the match.

[1733] Specific operation: The server collects and analyzes player movement data (e.g., distance traveled, location information) in real time during the match. This allows for a detailed understanding of each player's performance.

[1734] Input: Player movement data during the match

[1735] Output: Analyzed performance data for each player

[1736] Step 7:

[1737] The server generates personalized feedback based on the analysis results.

[1738] Specific operation: Based on the analysis results, the server creates feedback for each player, including specific areas for improvement and advice. For example, it might generate feedback such as, "You should move a little more towards the center when defending."

[1739] Input: Analyzed performance data for each player

[1740] Output: Individualized feedback

[1741] Step 8:

[1742] The server sends the generated feedback to the user's terminal for display.

[1743] Specific operation: The server sends the generated feedback to the device (e.g., the player's smartphone), and the device displays that feedback.

[1744] Input: Personalized feedback

[1745] Output: Feedback sent to the user terminal and displayed feedback

[1746] (Application Example 1)

[1747] 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".

[1748] In sports matches, it is difficult for spectators and players to obtain detailed information in real time. Furthermore, there are limited means for players to receive individual feedback after the match has ended. As a result, spectators have difficulty understanding the progress of the match, and players have difficulty finding concrete guidelines for improving their own performance.

[1749] 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.

[1750] In this invention, the server includes means for acquiring video feeds and real-time event data of a match; means for analyzing the acquired video feeds and event data in real time and automatically generating commentary; means for transmitting the generated commentary to a user terminal and displaying it in real time; means for analyzing motion data and performance data after the match and generating personalized feedback; and means for transmitting and displaying individual player feedback to a user terminal. As a result, spectators can grasp the progress of the match and detailed commentary in real time, and players can receive specific feedback after the match to help improve their performance.

[1751] A "match video feed" refers to a video stream of a sports match, and is video data acquired for the purpose of real-time viewing and analysis.

[1752] "Real-time event data" refers to data that records important events that occur during a sports match (e.g., goals, fouls, etc.) in real time.

[1753] "Methods for automatically generating explanatory text" refer to methods for analyzing acquired video feeds and event data and automatically creating explanatory text about the progress of the match and events using natural language generation technology.

[1754] A "user terminal" refers to a device, such as a smartphone, tablet, personal computer, or head-mounted display, that allows a user to receive and display information in real time.

[1755] "Motion data and performance data" refers to detailed data on individual players' movements and performance during matches, including distance covered, speed, and number of shots.

[1756] "Personalized feedback" refers to feedback that includes specific improvement guidelines and advice for each individual athlete, based on analyzed motion and performance data.

[1757] A "generative AI model" is an algorithm or system that uses machine learning techniques to automatically generate explanatory text and feedback based on analysis results.

[1758] A "prompt statement" is an input statement used to make specific analysis requests or initial settings for the generated AI model.

[1759] "Statistical information" refers to information compiled in the form of numbers, graphs, and other formats, by analyzing various data collected during a match.

[1760] The embodiments for carrying out this invention will be described in detail below.

[1761] System Overview

[1762] This system acquires match video feeds and real-time event data, analyzes and processes it, provides users with information in real time, and provides personalized feedback to players after the match. The system consists of the following main components:

[1763] 1. Data acquisition module

[1764] 2. Data Analysis Module

[1765] 3. Natural Language Generation Module

[1766] 4. Data transmission module

[1767] 5. User Interface

[1768] 6. Feedback Generation Module

[1769] 7. Generative AI Models

[1770] 8. Prompt Statement System

[1771] Data acquisition module

[1772] The server retrieves match video feeds and real-time event data using an API or WebSocket. This data records the video stream of the sports match and important events such as goals and fouls in real time.

[1773] Data Analysis Module

[1774] The server analyzes the acquired video feed and event data in real time. The analysis utilizes machine learning algorithms (e.g., TensorFlow, OpenCV) and motion recognition technology. For example, if a goal is detected, the server automatically identifies the video footage from that moment.

[1775] Natural Language Generation Module

[1776] The server automatically generates explanatory text based on the results of data analysis. For natural language generation, it uses generative AI models such as GPT-4. For example, it might generate the explanatory text, "Player A made a fantastic shot!"

[1777] Data transmission module

[1778] The server sends generated explanatory text and statistical information to the user's terminal in real time. This transmission is done using WebSocket or an API.

[1779] User Interface

[1780] The device displays the received commentary and statistics. This allows users to understand the progress of the match and detailed information in real time. For example, the smartphone might display information such as "Player C's current distance covered: 8km".

[1781] Feedback generation module

[1782] The server analyzes player movement and performance data after the match and generates personalized feedback. This feedback is sent to the user's terminal and displayed. For example, one piece of feedback might say, "You should move a little more towards the center when defending."

[1783] Generative AI models and prompt sentence systems

[1784] The system uses a generative AI model to generate explanatory text and feedback. The prompt system is used to make specific analysis requests and initial settings for the generative AI model.

[1785] Example of a prompt

[1786] "Please generate explanatory text for when a player scores a goal during a soccer match."

[1787] "Player A scored a goal with a long-range shot from 50 meters."

[1788] This system allows spectators to follow the progress of the match and receive detailed commentary in real time, while players can receive specific feedback after the match to help improve their performance.

[1789] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1790] Step 1:

[1791] Data acquisition module

[1792] The server retrieves video feeds and real-time event data of sports matches using an API or WebSocket. Inputs are the match video stream and important event data. The server receives this data in real time and prepares it for analysis. Outputs are the retrieved video feeds and event data.

[1793] Step 2:

[1794] Data Analysis Module

[1795] The server analyzes the acquired video feed and event data in real time. The input is the video feed and event data acquired in step 1. The server automatically identifies specific scenes and events (e.g., goal scenes) using machine learning algorithms (e.g., TensorFlow, OpenCV) and motion recognition technology. The output is the analyzed event information and its details.

[1796] Step 3:

[1797] Natural Language Generation Module

[1798] The server automatically generates explanatory text based on the results of data analysis. The input is the event information analyzed in step 2. The server uses a generative AI model such as GPT-4 as a natural language generation technique to create explanatory text according to the analysis results. For example, the sentence "Player A made a great shot!" is generated. The output is the generated explanatory text.

[1799] Step 4:

[1800] Data transmission module

[1801] The server sends the generated explanatory text and statistics to the user terminal in real time. The input is the explanatory text and related statistics generated in step 3. WebSocket or API is used for transmission. The output is the explanatory text and statistics sent to the user terminal.

[1802] Step 5:

[1803] User Interface

[1804] The terminal displays the received explanatory text and statistical information. The input is the explanatory text and statistical information sent in step 4. The user terminal displays this information on the screen in real time, allowing the user to understand the progress of the match and detailed information. For example, the smartphone displays information such as "Player C's current distance covered: 8km". The output is information that the user can visually confirm.

[1805] Step 6:

[1806] Feedback generation module

[1807] The server analyzes player movement and performance data after the match and generates personalized feedback. The input is player movement and performance data collected during the match. The server analyzes this data and generates feedback that provides specific improvement guidelines for each player. For example, feedback such as "You should move a little more towards the center when defending" might be generated. The output is the personalized feedback.

[1808] Step 7:

[1809] Feedback transmission module

[1810] The server sends the generated feedback to the user's (player's) terminal for display. The input is the personalized feedback generated in step 6. The server sends the feedback using WebSocket or API. The output is the feedback sent to the user's terminal.

[1811] In this way, spectators can follow the progress of the match and receive detailed commentary in real time, and players can receive specific feedback after the match to help improve their performance.

[1812] 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.

[1813] The following describes embodiments for carrying out the present invention. This system acquires and analyzes video feeds and real-time event data of matches, provides various information to spectators and players, and recognizes the user's emotions to customize the experience.

[1814] System Overview

[1815] This system consists of the following main components:

[1816] 1. Data acquisition module

[1817] 2. Data Analysis Module

[1818] 3. Natural Language Generation Module

[1819] 4. Data transmission module

[1820] 5. User Interface (Terminal)

[1821] 6. Feedback Generation Module

[1822] 7. Emotional Engine

[1823] Data acquisition module

[1824] The server retrieves the match video feed and real-time event data. This data includes a video stream of the sports match and real-time recordings of important events such as goals and fouls.

[1825] The server uses APIs and WebSockets to retrieve video feeds and event data.

[1826] Data Analysis Module

[1827] The system analyzes video feeds and event data acquired by the server in real time. Machine learning algorithms and motion recognition technologies are used for the analysis.

[1828] For example, when a goal is scored during a match, the system automatically identifies the video footage of that exact moment.

[1829] Natural Language Generation Module

[1830] The server automatically generates explanatory text based on the results of data analysis. Natural language generation technology is used to create detailed explanations about the flow of the match and events.

[1831] For example, it can generate a descriptive sentence such as, "Player A scored a magnificent goal!"

[1832] Emotional Engine

[1833] The server recognizes the user's emotions in real time. The emotion engine recognizes emotions such as joy, surprise, and excitement from the user's facial expressions and tone of voice.

[1834] Based on the recognized emotions, the explanatory text, statistical information, and feedback content are customized.

[1835] Data transmission module

[1836] The server sends generated explanatory text, sentiment-based customized information, and statistical data to the terminal.

[1837] The server uses a WebSocket connection or API to send data to the terminal in real time.

[1838] User interface (terminal)

[1839] The terminal displays the received explanatory text, customized information, and statistics on the user interface. This allows users (spectators) to understand the progress of the match and detailed information in real time.

[1840] For example, within a smartphone app, statistical information such as "Player A's current distance covered: 10km" could be displayed, along with explanatory text that changes according to the user's emotions.

[1841] Feedback generation module

[1842] The server collects and analyzes player movement and performance data during matches.

[1843] The server generates personalized feedback and provides it to players and coaches after the match ends.

[1844] For example, it can generate feedback such as "You should move a little more towards the center when defending" and send it to the player's device (smartphone).

[1845] Specific example

[1846] 1. Real-time commentary during the match

[1847] The server analyzes the match video feed and detects the event "Player B scored a goal."

[1848] The server generates a natural language explanation such as "Player B scored a goal with a brilliant dribble!" and sends it to the terminal.

[1849] Users can view this explanation in real time using a smartphone app.

[1850] The emotion engine recognizes the user's feelings of joy and adds phrases such as "The audience is also very excited!" to the next comment.

[1851] 2. Real-time statistics provided

[1852] The server collects player distance data during the match and confirms that player C has reached a distance of 8km.

[1853] The server generates statistical information such as "Player C's current distance covered: 8km" and sends it to the terminal.

[1854] Users can check statistical information on large screens inside the stadium or on their smartphones.

[1855] The emotion engine recognizes the user's surprise and adds the comment, "Player C is showing incredible stamina!" to the displayed statistics.

[1856] 3. Player feedback after the match

[1857] After the match ends, the server analyzes player D's performance data to identify areas for improvement in his defensive play.

[1858] The server generates feedback stating, "More lateral movement is needed during defense," and sends it to the terminal.

[1859] The user (player) receives this feedback on their smartphone and uses it to identify areas for improvement for the next match.

[1860] The emotional engine recognizes the player's feelings of frustration and impatience, and reinforces the feedback with more positive language before providing it.

[1861] Thus, this system can significantly improve audience engagement, provide players with personalized feedback, and enhance their performance. Furthermore, by utilizing an emotion engine, the quality of information provided can be customized to match the user's emotions.

[1862] The following describes the processing flow.

[1863] Processing steps for automatically generated explanations

[1864] Step 1:

[1865] The server retrieves the match video feed and real-time event data. The server uses an API to obtain the video feed URL, establishes a WebSocket connection, and receives the event data.

[1866] Step 2:

[1867] The server analyzes the acquired video feed. A machine learning model is used to detect player movements and important events (e.g., goals, fouls) within the video frames.

[1868] Step 3:

[1869] The server analyzes real-time event data and compares it with the analysis results of the video feed. It identifies important events that match the event data.

[1870] Step 4:

[1871] The server uses natural language generation technology to generate explanatory text based on identified events. Templates are used to instantly convert the analysis results into text.

[1872] Step 5:

[1873] The server uses an emotion engine to recognize the user's emotions. It grasps the user's emotions in real time through facial recognition and voice tone analysis.

[1874] Step 6:

[1875] The server customizes the generated commentary based on the emotions it recognizes. For example, if the user is excited, it adds phrases like "The audience is also very excited!" to the commentary.

[1876] Step 7:

[1877] The server sends generated and customized explanatory text to the terminal. The explanatory text is sent to the terminal in real time using a WebSocket connection.

[1878] Step 8:

[1879] The terminal displays the received explanatory text on the user interface. Users can check the explanation in real time on their smartphones, tablets, etc.

[1880] Processing steps for real-time statistics analysis

[1881] Step 1:

[1882] The server collects various data generated during a match in real time. This is done by periodically polling the data using an API or by receiving the data in real time using a WebSocket connection.

[1883] Step 2:

[1884] The server analyzes the collected data. It executes analysis algorithms to calculate statistical data such as player distance covered and pass success rate.

[1885] Step 3:

[1886] The server generates visualized statistical information based on the analysis results. This information is then converted into graphs and charts to visualize the data.

[1887] Step 4:

[1888] The server uses an emotion engine to recognize the user's emotions in real time. The analysis results are then integrated with the user's emotion data.

[1889] Step 5:

[1890] The server adjusts the display format of statistics based on the emotions it perceives. For example, if the user is surprised, it might add a comment such as, "Player C is showing incredible stamina!"

[1891] Step 6:

[1892] The server sends generated and customized statistics to the terminal. Statistics are sent to the terminal using a WebSocket connection or API.

[1893] Step 7:

[1894] The system displays statistical information received by the device on the user interface. Users can check the statistical information on their smartphones or on large screens in the stadium.

[1895] Feedback generation processing steps

[1896] Step 1:

[1897] The server collects player movement and performance data during matches. An API is used to retrieve each player's position and performance data.

[1898] Step 2:

[1899] The server analyzes the collected data to evaluate the players' movements and performance. Machine learning models are used for the analysis.

[1900] Step 3:

[1901] The server generates personalized feedback based on the analysis results. Using evaluation data and templates, it creates specific areas for improvement and advice.

[1902] Step 4:

[1903] The server uses an emotion engine to recognize the player's emotions. It observes how the player receives feedback and analyzes their facial expressions and tone of voice.

[1904] Step 5:

[1905] The server customizes the feedback based on the emotions it perceives. For example, if a player is feeling frustrated or impatient, the feedback will be reinforced with positive language.

[1906] Step 6:

[1907] The server sends generated and customized feedback to the player's device. Feedback is sent to the player's device via email or a dedicated app.

[1908] Step 7:

[1909] The device displays the received feedback on the user interface. The user (player) reviews the feedback and identifies areas for improvement for the next match.

[1910] Processing steps for providing generated content

[1911] Step 1:

[1912] The server collects past match data and player information. It queries the database to retrieve the necessary data.

[1913] Step 2:

[1914] Based on data collected by the server, engaging content (articles, highlight videos, etc.) is generated. Natural language generation tools and video editing tools are used to create the content.

[1915] Step 3:

[1916] Convert server-generated content into a format suitable for the user interface. Export videos and articles in the appropriate format.

[1917] Step 4:

[1918] The server uses an emotion engine to recognize the user's emotions. It observes the user's reactions in real time while content is being delivered.

[1919] Step 5:

[1920] The server adjusts content visualizations based on the emotions it perceives. For example, if a user is emotional, it might add a "Featured Article: The Inspiring Story of Player X."

[1921] Step 6:

[1922] The server sends generated and customized content to the device. Content is sent to the device using an API or WebSocket connection.

[1923] Step 7:

[1924] The device displays the received content to the user. The user can view the content on a smartphone, tablet, or other device.

[1925] These processing steps enable the system to significantly improve audience engagement and the viewing experience. Furthermore, by utilizing the emotion engine, the quality of information provided can be customized to match the user's emotions.

[1926] (Example 2)

[1927] 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".

[1928] Traditional match viewing systems did not provide real-time information on the progress of the match or the performance of the players, making it difficult for spectators and players to immediately grasp the details of the match. Furthermore, the lack of commentary and feedback tailored to the user's emotions resulted in insufficient audience engagement. Additionally, feedback was typically provided after the match, without real-time advice or suggestions for improvement. Therefore, there was a need for technology that would make the match experience more engaging and personalized.

[1929] 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.

[1930] In this invention, the server includes means for acquiring a video stream and real-time event data of a match; means for analyzing the acquired video stream and event data in real time and detecting specific events using a machine learning algorithm; means for automatically generating explanatory text using natural language generation technology based on the analysis results; means for transmitting and displaying the generated explanatory text and customized information to a user terminal; and means for analyzing the user's facial expressions and voice, recognizing emotions in real time, and generating feedback. This enables the provision of detailed commentary and statistical information in real time, as well as the provision of customized information tailored to the user's emotions. Furthermore, it is possible to improve performance by providing specific feedback to players and coaches after the match.

[1931] "Match video stream" refers to video data of a match that is acquired in real time.

[1932] "Real-time event data" refers to data that records important events that occur during a match (e.g., goals, fouls) in real time.

[1933] A "machine learning algorithm" is a general term for mathematical models and methods used to automatically learn and analyze specific patterns and information based on data.

[1934] "Natural language generation technology" is a technology that uses computer-generated data to create natural language sentences that humans can read.

[1935] "Explanatory text" refers to a document that includes detailed explanations of the progress of a match or specific events.

[1936] A "user terminal" refers to electronic devices such as smartphones, tablets, and personal computers used by users.

[1937] "Customized information" refers to information that has been specially tailored to the user's needs and circumstances.

[1938] An "emotion engine" is a technology and system that analyzes a user's facial expressions, tone of voice, and other factors to recognize their emotions.

[1939] "Feedback" refers to information used to provide areas for improvement and advice based on an athlete's movements and performance.

[1940] The following describes specific embodiments for carrying out this invention. This system acquires and analyzes video streams and real-time event data of matches, provides various information to spectators and players, and recognizes user emotions to customize the experience. The system consists of a data acquisition module, a data analysis module, a natural language generation module, an emotion engine, a data transmission module, a user interface, and a feedback generation module.

[1941] Data acquisition module

[1942] The server retrieves the match video stream and real-time event data. This data is retrieved via cameras, APIs, and WebSocket connections. For example, the server accesses cameras for the video feed, streams video data, and receives event data in real time via WebSocket.

[1943] Data Analysis Module

[1944] The server analyzes the acquired video stream and event data in real time. Machine learning algorithms (e.g., TensorFlow) and motion recognition technologies (e.g., OpenCV) are used for the analysis. For example, the server analyzes the video data frame by frame to detect the moment a specific event (e.g., a goal) occurs.

[1945] Natural Language Generation Module

[1946] The server automatically generates explanatory text using natural language generation technology based on the results of data analysis. For example, it can use a generative AI model such as GPT-3 to generate explanatory text such as, "Player A scored a magnificent goal!"

[1947] Emotional Engine

[1948] The server recognizes the user's emotions in real time. By analyzing the user's facial expressions and tone of voice, it determines their emotions and generates corresponding feedback. For example, it uses AWS Rekognition to read the user's emotions such as joy and surprise.

[1949] Data transmission module

[1950] The server sends generated explanatory text, customized information, and statistics to the terminal. WebSocket connection or API is used for transmission. For example, the generated explanatory text and statistics are sent to the terminal in JSON format.

[1951] User Interface

[1952] The terminal displays explanatory text, customized information, and statistics on the user interface. This display is performed on devices such as smartphones, tablets, and PCs. For example, the smartphone app screen might display information such as "Player A's current distance traveled: 10km".

[1953] Feedback generation module

[1954] The server collects and analyzes player movement and performance data during the match. It generates individual feedback, which is then sent to players and coaches after the match. For example, feedback such as "You should move a little more towards the center when defending" might be generated.

[1955] Specific example

[1956] Specific examples are given below.

[1957] Real-time commentary during the match

[1958] The server analyzes the match video stream and detects the event "Player B scores a goal." The server uses a generative AI model to generate a commentary such as "Player B scores a goal with a brilliant dribble!" and sends it to the device. The user checks this commentary in real time on the smartphone app, and the emotion engine recognizes the user's excitement and adds phrases such as "The crowd is also very excited!" to the next comment.

[1959] Real-time statistics provided

[1960] The server collects player distances during the match and confirms that player C has reached 8km. The server generates statistics such as "Player C's current distance: 8km" and sends them to the user's device. The user checks these statistics on their smartphone or on a large screen in the stadium, and the emotion engine recognizes the user's surprise and adds the comment, "Player C is showing incredible stamina!"

[1961] Examples of prompts for generative AI models

[1962] "Please generate natural language commentary describing the moment a player scores a goal during a soccer match. Additionally, please add emotionally charged comments that reflect the user's feelings, such as joy."

[1963] This invention can improve audience engagement and provide players with personalized feedback to enhance their performance. By utilizing an emotion engine, the quality of information provided can be customized to match the user's emotions.

[1964] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1965] Step 1:

[1966] Data acquisition

[1967] The server acquires the match video stream and real-time event data. This process involves acquiring video and event data via cameras, APIs, and WebSocket connections.

[1968] (Input): Camera video data, event data API, WebSocket connection.

[1969] (Output): Video stream data and event data stored on the server.

[1970] Specific operation: The server accesses the camera for the video feed and obtains real-time stream data. Simultaneously, it receives event data in real time via API calls and WebSocket connections and stores it in the server's database.

[1971] Step 2:

[1972] Data Analysis

[1973] The server analyzes acquired video streams and event data in real time. Machine learning algorithms and motion recognition technologies are used for the analysis.

[1974] (Input): Video stream data, event data.

[1975] (Output): Analysis results (detection results for a specific event).

[1976] Specific operation: The server analyzes video data frame by frame and detects the moment a specific event (e.g., a goal) occurs. The technologies used include Python's OpenCV library and TensorFlow models, which enable real-time event detection.

[1977] Step 3:

[1978] natural language generation

[1979] The server automatically generates explanatory text using natural language generation technology based on the results of data analysis.

[1980] (Input): Analysis result.

[1981] (Output): The generated explanatory text.

[1982] Specific operation: The server takes the analysis results as input and uses a generation AI model (e.g., GPT-3) to generate explanatory text. For example, content such as "Player A scored a magnificent goal!" is automatically generated.

[1983] Step 4:

[1984] emotion recognition

[1985] The server recognizes the user's emotions in real time. It analyzes the user's facial expressions and tone of voice.

[1986] (Input): User's facial expression data, voice data.

[1987] (Output): Emotion recognition result (joy, surprise, excitement, etc.).

[1988] Specific operation: The server acquires data from the camera and microphone and uses facial recognition algorithms and voice analysis algorithms to classify the user's emotions in real time. For example, emotions can be recognized using AWS Rekognition.

[1989] Step 5:

[1990] Data transmission

[1991] The server sends generated explanatory text, customized information, and statistical data to the terminal.

[1992] (Input): Generated explanatory text, sentiment recognition results, and statistical information.

[1993] (Output): Explanatory text and statistical information sent to the terminal.

[1994] Specific operation: The server sends the generated data to the terminal in real time via a WebSocket connection or API. JSON is commonly used as the transmission format.

[1995] Step 6:

[1996] Data display

[1997] The terminal displays explanatory text, customized information, and statistics received on the user interface.

[1998] (Input): Explanatory text and statistical information sent to the terminal.

[1999] (Output): Explanatory text and statistical information displayed on the user's terminal.

[2000] Specific operation: The device analyzes the data it receives and displays it on the application screen of a smartphone or tablet. For example, information such as "Player A's current distance traveled: 10km" will be displayed in the smartphone app.

[2001] Step 7:

[2002] Feedback generation

[2003] The server collects and analyzes player movement and performance data during the match. It generates individual feedback and sends it to players and coaches after the match ends.

[2004] (Input): Player motion data, performance data.

[2005] (Output): Individualized feedback.

[2006] Specific operation: The server analyzes the data collected after the match ends and generates improvement suggestions and advice for each player. For example, specific advice such as "You should move a little more towards the center when defending" is generated and sent to the terminal.

[2007] (Application Example 2)

[2008] 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".

[2009] Traditional match viewing systems had the means to acquire video feeds and event data and provide users with information in real time, but they lacked the ability to recognize user emotions and customize information based on those emotions. As a result, the viewing experience was uniform, and information tailored to the needs of individual users was not provided. Furthermore, advertising displays were not personalized considering the user's emotions or level of excitement at that moment, and therefore did not sufficiently increase engagement.

[2010] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring video feeds and real-time event data of a match; means for analyzing the acquired video feeds and event data in real time and automatically generating explanatory text; means for transmitting and displaying the generated explanatory text to a user terminal; means for recognizing the user's emotions in real time and customizing information based on those emotions; and means for transmitting the customized information to the user terminal and displaying advertisements. This makes it possible to provide information and display advertisements that reflect the user's emotions.

[2011] A "video feed" refers to live video data of a match, which is real-time video information of the game.

[2012] "Real-time event data" refers to data that records important event information, such as goals and fouls, that occur during a match in real time.

[2013] "Explanatory text" refers to textual information that describes events during a match, including detailed explanations of the match's progress and important events.

[2014] A "user terminal" is an electronic device that a user carries or wears to receive and display information, such as a smartphone, smart glasses, or tablet.

[2015] "Emotion recognition" is a technology that analyzes and identifies a user's emotions at a given moment based on their facial expressions, voice, and other factors.

[2016] "Customized information" refers to information that is provided in an individualized manner according to the user's needs and circumstances, based on the results of the user's emotion recognition.

[2017] "Advertising" refers to information displayed by companies or individuals to users in order to promote their products or services, with the aim of increasing user interest and attention.

[2018] "Statistical information" refers to numerical data obtained as a result of analyzing various data generated during a match, and includes detailed information about the match, such as the distance players covered and the number of goals scored.

[2019] The system for carrying out this invention acquires video feeds and real-time event data of a match, generates commentary based on this data, and transmits it to the user's terminal. It also recognizes the user's emotions in real time and provides customized information based on those emotions.

[2020] Required hardware and software

[2021] Hardware:

[2022] Camera: Uses the camera on smart glasses or a smartphone to capture the user's facial expressions.

[2023] Server: A central computing unit that acquires, analyzes, and transmits data.

[2024] software:

[2025] OpenCV: A library for capturing video feeds and performing image analysis.

[2026] dlib: A machine learning model for recognizing user emotions.

[2027] Advertising APIs (e.g., AdAPI): Used to retrieve ads that are relevant to the user's emotions.

[2028] WebSocket or API: A communication protocol that enables real-time transmission of data.

[2029] System operation

[2030] The server first acquires the match video feed and real-time event data, and then analyzes it. Based on the analysis results, it automatically generates commentary and sends it to the user's device. User devices that display the commentary include smartphones and smart glasses, and users can view this information in real time.

[2031] Next, the system recognizes the user's emotions in real time. This is done by analyzing facial expression data captured by the camera using the dlib library. Based on the recognized emotions, the server customizes the explanatory text and the displayed advertisements. For example, if the user is excited, entertainment-related advertisements are displayed, and if they are calm, health-related advertisements are displayed.

[2032] The generated information and advertisements are sent to the user's device using WebSocket or an API and displayed in real time. This process personalizes the match-watching experience to each user's emotions, leading to higher engagement.

[2033] Specific example

[2034] While a user is watching a sports match, they may show a smile and an excited expression the moment a player scores a goal. At this moment, the smart glasses' camera captures the expression, and the server uses the dlib library to recognize the emotion as "joy." The server then retrieves an entertainment-related advertisement (for example, a trailer for a new movie) and sends it to the smart glasses, displaying it in the user's field of view.

[2035] Example of a prompt

[2036] The following are examples of prompt statements to input into a generative AI model.

[2037] Please describe the role and new user experience of a smart glasses application that uses emotion recognition technology to detect a user's joy and excitement while they are watching a sports match in real time, and then displays relevant advertisements. Please provide details, including specific functions and examples.

[2038] In this way, the invention enables the provision of information and display of advertisements tailored to the user's emotions, thereby improving the viewing experience.

[2039] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[2040] Step 1:

[2041] The server retrieves the match video feed and real-time event data. This data is sent to the server via API or WebSocket.

[2042] Input: Video feed, real-time event data

[2043] Processing: Retrieve data using API or WebSocket.

[2044] Output: Video feeds and event data stored in the server's data storage.

[2045] Step 2:

[2046] The system analyzes video feeds and event data acquired by the server. Machine learning algorithms are used for the analysis to automatically identify important events during the match.

[2047] Input: Video feed, real-time event data

[2048] Processing: Data analysis using machine learning algorithms

[2049] Output: Event-specific information (e.g., goal, foul, etc.)

[2050] Step 3:

[2051] The server automatically generates explanatory text based on the analysis results. It uses natural language generation technology to create text about the progress of the match and important events.

[2052] Input: Event specific information

[2053] Processing: Text generation using natural language generation technology

[2054] Output: Explanatory text (Example: "Player A scored a magnificent goal!")

[2055] Step 4:

[2056] The server sends the generated explanatory text to the user's terminal. Data is transmitted in real time via WebSocket or API.

[2057] Input: Explanation

[2058] Processing: Send data using WebSocket or API

[2059] Output: Explanatory text sent to the user's terminal

[2060] Step 5:

[2061] The terminal displays the received explanatory text. The explanatory text is displayed on the user interface of a smartphone or smart glasses.

[2062] Input: Received explanatory text

[2063] Processing: Display via user interface

[2064] Output: Explanatory text presented visually to the user.

[2065] Step 6:

[2066] To enable the server to recognize user emotions in real time, a camera is used to capture the user's facial expressions. The dlib library is used to analyze and recognize these emotions.

[2067] Input: Captured facial expression data

[2068] Processing: Sentiment analysis using the dlib library

[2069] Output: Recognized emotion (e.g., joy, surprise, etc.)

[2070] Step 7:

[2071] The server customizes information based on recognized emotions. Appropriate ad information and explanatory text are modified according to the emotions.

[2072] Input: Recognized emotions

[2073] Processing: Information customization (retrieving ad information using the ad API, changing explanatory text)

[2074] Output: Customized information (e.g., entertainment-related advertisements)

[2075] Step 8:

[2076] The server sends customized information to the user's terminal. Customized advertisements and explanatory text are sent using WebSocket or an API.

[2077] Input: Customized information

[2078] Processing: Sending data using WebSocket or API

[2079] Output: Customization information sent to the user's terminal

[2080] Step 9:

[2081] The device displays customized information it has received. This customized information is displayed on the user interface of smartphones and smart glasses.

[2082] Input: Received customized information

[2083] Processing: Display via user interface

[2084] Output: Customized information presented visually to the user (e.g., advertisements, specific explanatory text)

[2085] 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.

[2086] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2087] 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 robot 414.

[2088] 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.

[2089] 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.

[2090] 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.

[2091] 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.

[2092] 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 based, for example, 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.

[2093] 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."

[2094] 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.

[2095] 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.

[2096] 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.

[2097] 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.

[2098] 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.

[2099] 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.

[2100] 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.

[2101] 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.

[2102] 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.

[2103] 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.

[2104] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[2105] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[2106] The following is further disclosed regarding the embodiments described above.

[2107] (Claim 1)

[2108] A means of obtaining match video feeds and real-time event data,

[2109] A means for analyzing acquired video feeds and event data in real time and automatically generating explanatory text,

[2110] A means of sending the generated explanatory text to the user's terminal and displaying it,

[2111] A system that includes this.

[2112] (Claim 2)

[2113] A means of collecting various data generated during a match in real time,

[2114] A means for analyzing collected data and generating statistical information,

[2115] A means for sending and displaying the generated statistical information on the user's terminal,

[2116] The system according to claim 1, including the following:

[2117] (Claim 3)

[2118] A means for collecting player movement data and performance data during a match,

[2119] A means of analyzing collected data and generating personalized feedback for each player,

[2120] A means of sending and displaying the generated feedback on the user's terminal,

[2121] The system according to claim 1, including the following:

[2122] "Example 1"

[2123] (Claim 1)

[2124] A means of obtaining match video feeds and real-time event data,

[2125] A means of analyzing acquired video feeds and event data in real time and using machine learning algorithms to identify goals and player actions,

[2126] A means for automatically generating explanatory text using natural language generation technology based on the analysis results,

[2127] A means of sending the generated explanatory text to the user's terminal and displaying it,

[2128] A system that includes this.

[2129] (Claim 2)

[2130] A means of collecting various data generated during a match in real time,

[2131] A means for analyzing collected data and generating statistical information,

[2132] A means for sending and displaying the generated statistical information on the user's terminal,

[2133] The system according to claim 1, including the following:

[2134] (Claim 3)

[2135] A means for collecting player movement data and performance data during a match,

[2136] A means of analyzing collected data and generating personalized feedback for each player,

[2137] A means of sending and displaying the generated feedback on the user's terminal,

[2138] The system according to claim 1, including the following:

[2139] "Application Example 1"

[2140] (Claim 1)

[2141] A means of obtaining match video feeds and real-time event data,

[2142] A means for analyzing acquired video feeds and event data in real time and automatically generating explanatory text,

[2143] A means of sending the generated explanatory text to the user's terminal and displaying it in real time,

[2144] A means for analyzing motion data and performance data after the end of a match and generating personalized feedback,

[2145] A means of sending and displaying individual player feedback on the user's terminal,

[2146] A system that includes this.

[2147] (Claim 2)

[2148] A means of collecting various data generated during a match in real time,

[2149] A means for analyzing collected data and generating statistical information,

[2150] A means for sending and displaying the generated statistical information on the user's terminal,

[2151] A means of generating explanatory text and feedback using a generative AI model,

[2152] A means of accepting initial settings and specific analysis requests using prompt statements,

[2153] The system according to claim 1, including the following:

[2154] (Claim 3)

[2155] A means for collecting player movement data and performance data during a match,

[2156] A means of analyzing collected data and generating personalized feedback for each player,

[2157] A means of sending and displaying the generated feedback on the user's terminal,

[2158] A means of providing real-time commentary and statistical information to the user interface of a content distribution service,

[2159] The system according to claim 1, including the following:

[2160] "Example 2 of combining an emotion engine"

[2161] (Claim 1)

[2162] A means for acquiring match video streams and real-time event data,

[2163] A means for analyzing acquired video streams and event data in real time and detecting specific events using machine learning algorithms,

[2164] A means for automatically generating explanatory text using natural language generation technology based on the analysis results,

[2165] A means for sending and displaying the generated explanatory text and customized information on the user's terminal,

[2166] A means of analyzing the user's facial expressions and voice, recognizing emotions in real time, and generating feedback,

[2167] A system that includes this.

[2168] (Claim 2)

[2169] A means of collecting various data generated during a match in real time and generating statistical information using machine learning algorithms,

[2170] A means for generating customized statistical information using natural language generation technology based on collected data,

[2171] A means for sending and displaying the generated statistical information on the user's terminal,

[2172] A means of providing information that responds to the user's emotions using an emotion engine,

[2173] The system according to claim 1, including the following:

[2174] (Claim 3)

[2175] A means of collecting and analyzing player movement data and performance data during a match,

[2176] A means of creating personalized feedback using natural language generation technology based on collected data,

[2177] A means of sending and displaying the generated feedback on the user's terminal,

[2178] A means of adjusting the content of feedback according to the player's emotions using an emotion engine,

[2179] The system according to claim 1, including the following:

[2180] "Application example 2 when combining with an emotional engine"

[2181] (Claim 1)

[2182] A means of obtaining match video feeds and real-time event data,

[2183] A means for analyzing acquired video feeds and event data in real time and automatically generating explanatory text,

[2184] A means of sending the generated explanatory text to the user's terminal and displaying it,

[2185] A means of recognizing user emotions in real time and customizing information based on those emotions,

[2186] A means of sending customized information to the user's device and displaying advertisements,

[2187] A system that includes this.

[2188] (Claim 2)

[2189] A means of collecting various data generated during a match in real time,

[2190] A means for analyzing collected data and generating statistical information,

[2191] A means for sending and displaying the generated statistical information on the user's terminal,

[2192] A means of sensing user emotions and customizing statistical information according to those emotions,

[2193] The system according to claim 1, including the following:

[2194] (Claim 3)

[2195] A means for collecting player movement data and performance data during a match,

[2196] A means of analyzing collected data and generating personalized feedback for each player,

[2197] A means of sending and displaying the generated feedback on the user's terminal,

[2198] A means of customizing feedback based on the emotions of the user or player,

[2199] The system according to claim 1, including the...

Claims

1. A means of obtaining match video feeds and real-time event data, A means for analyzing acquired video feeds and event data in real time and automatically generating explanatory text, A means of sending the generated explanatory text to the user's terminal and displaying it, A system that includes this.

2. A means of collecting various data generated during a match in real time, A means for analyzing collected data and generating statistical information, A means for sending and displaying the generated statistical information on the user's terminal, The system according to claim 1, including the following:

3. A means for collecting player movement data and performance data during a match, A means of analyzing collected data and generating personalized feedback for each player, A means of sending and displaying the generated feedback on the user's terminal, The system according to claim 1, including the following:

Images