System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting historical game data; means for analyzing the collected data; means for simulating a future game; means for visualizing simulation results; and means for suggesting a tactical plan based on the results of the game.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] One of the challenges facing sports team managers, coaches, and sports lottery users is the difficulty of planning specific strategies for the next opponent. There is a need for a method that can accurately predict future matches using past match data and tactical data, and make the results easy to understand visually. In addition, there is a lack of systems that propose optimal tactical plans to improve the winning rate of the next match. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting past game data, a means for analyzing the collected data, a means for simulating future games, a means for visualizing the simulation results, and a means for proposing tactical plans based on the game results. Specifically, past game data is collected from an API or database, and the data is analyzed using a generative artificial intelligence model. Future games are then simulated, and the simulation results are visualized. This video is provided to managers and coaches, allowing them to intuitively understand the game's development. Furthermore, the generative artificial intelligence model evaluates tens of millions of tactical plans and proposes the strategy that will maximize the chance of winning. This allows managers and coaches to easily develop specific tactical plans for the next game.

[0006] "Past match data" refers to statistical information, tactical information, individual player data, etc. relating to matches played previously.

[0007] "Means of collection" refers to methods and devices for obtaining past match data from APIs, databases, etc.

[0008] "Means of analysis" refers to methods or artificial intelligence models for processing collected data and converting it into an understandable form.

[0009] "Means for simulating" refers to methods or systems for virtually recreating the development of a future match based on analyzed data.

[0010] "Visualization means" refers to a method or graphical user interface for visually displaying the simulation results.

[0011] "Means for proposing tactical plans" refers to methods or systems for evaluating and proposing optimal tactics based on the results of a match.

[0012] "Means for transmitting to the terminal" refers to a communication method or protocol for transmitting the generated video data to the terminal used by the user.

[0013] A "generative artificial intelligence model" refers to a program or algorithm that uses techniques such as machine learning and deep learning to analyze data and perform simulations and propose tactics. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention is a system that collects and analyzes data from past sports matches, simulates future matches, visualizes the results, and proposes tactical plans. A specific embodiment of this system is described below.

[0036] 1. Collection and analysis of past match data

[0037] (server)

[0038] 1. The server collects past match data using an external API. For example, it calls an API to obtain match data for a specific team or player, and stores the data obtained in response within the server.

[0039] 2. The server then extracts stored tactical data and player stats from the database, parses this data, and pre-processes it into a format that the generative AI model can understand.

[0040] 2. Simulating future matches

[0041] (server)

[0042] 1. The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model then predicts each player's movements based on past data and virtually recreates the flow and outcome of the match.

[0043] 2. The simulation results are organized in JSON format and passed to the subsequent visualization process.

[0044] 3. Visualization of simulation results

[0045] (server)

[0046] 1. The server builds data to visualize the movements of players and the ball based on the simulation results. This data includes the positions of players, the ball, and the passage of time.

[0047] 2. The obtained data is used by the image generation engine to generate a visual image of the match. This image realistically reproduces the action of the match and is output in a format that is easy for users to understand.

[0048] 4. Tactical suggestion function

[0049] (server)

[0050] 1. The server uses a generative AI model to generate tens of millions of tactical plans. The system evaluates these plans and selects the one with the highest probability of winning.

[0051] 2. The selected optimal tactical plan is proposed to the manager or coach as a specific tactical proposal.

[0052] 5. User Interface

[0053] (Terminal)

[0054] 1. The device receives the video data and tactical plan sent from the server. The video is played on the device screen, allowing the manager or coach to intuitively understand the progress of the game.

[0055] 2. The tactical plan is displayed with detailed explanations and serves as a reference for the user to decide on specific next moves.

[0056] Specific examples

[0057] For example, when a soccer team's manager is planning a strategy for the next match, he collects and analyzes past match data and tactical data via an API. The results are then input into a generative AI model to simulate future matches. The simulation results are visualized and provided to the manager via a device. The generative AI model then proposes an optimal tactical plan to improve the manager's chances of winning the next match. This allows the manager to intuitively understand the game's development and select the optimal tactical strategy.

[0058] In this way, this system will make it easier for managers and coaches to plan specific strategies for matches, which will have a positive impact on the outcome of the match.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] (server)

[0062] The server first calls an external API to collect past match data. This API retrieves match data for specific teams and players and stores it in a database within the server. For example, to retrieve soccer match data, an API endpoint such as https: / / sportsdata.api / teams / teamA / matches is called.

[0063] Step 2:

[0064] (server)

[0065] To analyze the collected data, the server extracts tactical data and player stats from the database. This data is obtained, for example, using SQL queries. Since the obtained data is difficult for the generative AI model to understand as it is, preprocessing involves cleaning, normalizing, and extracting features from the data.

[0066] Step 3:

[0067] (server)

[0068] The server inputs the preprocessed data into a generative AI model to simulate future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and the flow of the match. The simulation results are organized by each phase of the match and output in JSON format.

[0069] Step 4:

[0070] (server)

[0071] The server uses the simulation results to create data for visualizing the movements of players and the ball. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into a video generation engine. This video generation engine then creates frames that reproduce the action of the game in real time.

[0072] Step 5:

[0073] (server)

[0074] The generated video data is sent to the terminal. The server compresses the generated video data and sends it to the user's terminal via the Internet. At this time, an appropriate compression algorithm is used to avoid data loss.

[0075] Step 6:

[0076] (Terminal)

[0077] The device receives the video data sent from the server and displays it on the screen. By watching this video, users can intuitively understand the simulated game progress. The device also provides functions such as playing, pausing, and rewinding the video in response to user operations.

[0078] Step 7:

[0079] (server)

[0080] The server proposes tactical plans based on the results of the match. It uses a generative AI model to generate tens of millions of tactical plans and evaluates the success rate of each plan. The plan with the highest success rate is selected and provided as a concrete tactical proposal for the next match.

[0081] Step 8:

[0082] (Terminal)

[0083] The device receives the proposed tactical plan and displays it to the user along with a detailed explanation. Managers and coaches can use this information to develop specific strategies for the next game. The device also provides an interface for users to modify the tactical plan or add new plans.

[0084] Step 9:

[0085] (User)

[0086] Users watch the video and review the proposed tactical plan. They can then modify the plan as necessary and decide on the final strategy for the next match. Through this system, managers and coaches can intuitively understand the development of the game and plan the optimal tactical plan.

[0087] Through these steps, the system helps managers, coaches, and even sports lottery users to plan specific strategies for the next game.

[0088] Example 1

[0089] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0090] Conventional tactical planning support systems for sports games only allow users to view past game data, and are therefore inadequate in predicting future game results and proposing specific tactical plans. Furthermore, there is no way to provide simulation results in a visually easy-to-understand format, making it difficult for managers and coaches to intuitively understand and formulate countermeasures.

[0091] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0092] In this invention, the server includes means for collecting past game data, means for analyzing and preprocessing the collected data, means for simulating future games using the preprocessed data, means for formatting the simulation results in JSON format, means for generating images based on the formatted data, means for generating and evaluating tactical plans based on game results, and means for proposing the evaluated tactical plans. This enables managers and coaches to predict future game results in detail, intuitively and easily understand optimal tactical plans, and take countermeasures.

[0093] "Past match data" refers to past results of sports matches, player statistics, tactical data, etc.

[0094] "Means of collection" refers to the methods and systems used to obtain the necessary data from external APIs and databases.

[0095] "Analysis and preprocessing means" refers to methods and systems that remove outliers from collected data, normalize the data, and prepare the data in a format that can be used by generative AI models.

[0096] "Simulating means" refers to a method or system that uses a generative AI model based on pre-processed data to virtually predict the course and outcome of future matches.

[0097] "Means for formatting in JSON format" refers to a method or system for formatting simulation results into JSON (JavaScript Object Notation), a standardized data format, and passing them to the next processing step.

[0098] "Means for generating images" refers to a method or system that uses an image generation engine based on simulation results to visually reproduce a match.

[0099] "Means for generating and evaluating tactical plans" refers to a method or system that uses a generative AI model to generate multiple tactical plans, simulate the effects of each, and select the optimal plan.

[0100] "Means for proposing tactical plans" refers to a method or system for providing the manager or coach with the evaluated optimal tactical plan in a concrete and easily understandable format.

[0101] The present invention is a system that collects and analyzes data from past sports matches, simulates future matches, visualizes the results, and proposes tactical plans. A specific embodiment of this system is described below.

[0102] The server uses external APIs to collect past game data. Specifically, it obtains game data related to specific teams and players from external APIs such as sports data provider APIs. For example, to collect NBA game data, it obtains the data using the API request " / api / v1 / games?team_id=1234" and stores the JSON-formatted data obtained as a response in the database.

[0103] The server then analyzes and pre-processes the stored match data from the database, including data extraction, outlier removal, and data normalization, such as extracting player positions and stats (e.g., shots, passes, and ball possession time) and formatting them in a format that can be used by the generative AI model.

[0104] The server then inputs the preprocessed data into a generative AI model to simulate future matches. The generative AI model predicts player movements based on past data and virtually recreates the flow and outcome of the match. The simulation results are organized in JSON format and passed to the next process.

[0105] The server uses the simulation results to build data for visualizing player and ball movements. This data includes player positions, ball position, and time progression. It then uses a video generation engine (e.g., Unity or Unreal Engine) to generate a visual image of the match. This image realistically reproduces the action of the match and is output in a format that is easy for users to understand.

[0106] The server also uses a generative AI model to generate millions of tactical plans. These plans are evaluated and the plan with the highest potential for winning is selected. The optimal plan is then proposed to the manager or coach as a concrete tactical proposal.

[0107] The device receives the video data and tactical plan sent from the server. The video is played on the device screen, allowing managers and coaches to intuitively understand the game's progress. The tactical plan is also displayed with detailed explanations, providing reference information for users to specifically and efficiently decide their next move.

[0108] To give a specific example, when a soccer team's coach plans a strategy for the next match, the server collects and analyzes past match data and tactical data via an API. This data is input into a generative AI model to simulate future matches. The simulation results are organized into a primary JSON format and generated as realistic match footage using a video generation engine. The generative AI model then generates an optimal tactical plan to improve the team's chances of winning the next match and proposes it to the coach. The coach can then view the footage and tactical plan on their device and issue instructions to their players.

[0109] An example prompt is, "This system collects past match data, simulates and visualizes future matches, and proposes optimal tactical plans. Please propose effective tactics for a specific team for the next match."

[0110] In this way, this system will make it easier for managers and coaches to plan specific strategies for matches, which will have a positive impact on the outcome of the match.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Processing Steps:

[0113] Step 1: Collect past match data

[0114] server

[0115] The server sends a request to an external API (e.g., a sports data provider API). Specifically, it uses an API endpoint to retrieve past game data for a specific team or player. The input is the API request, and the output is the game data in JSON format. For example, the request " / api / v1 / games?team_id=1234" is sent, and the resulting data is stored in the database.

[0116] Specific behavior:

[0117] 1. The server sends an API request.

[0118] 2. The obtained JSON format match data is stored in a database.

[0119] Step 2: Analysis and preprocessing of match data

[0120] server

[0121] The server analyzes and preprocesses the match data stored in the database. The input is past match data, and the output is the preprocessed data. Specifically, it extracts player position information and stats, removes outliers, and normalizes the data. For example, it organizes stats such as the number of shots, number of passes, and ball possession time of players.

[0122] Specific behavior:

[0123] 1. The server extracts the match data from the database.

[0124] 2. Remove outliers and impute missing values.

[0125] 3. Normalize the data and convert it into a format suitable for generative AI models.

[0126] Step 3: Run the simulation

[0127] server

[0128] The server inputs the preprocessed data into a generative AI model to simulate future matches. The input is the preprocessed data, and the output is the simulation results in JSON format. The generative AI model predicts player movements based on past data and virtually recreates the flow and outcome of the match.

[0129] Specific behavior:

[0130] 1. The server inputs preprocessed data into the generative AI model.

[0131] 2. A generative AI model simulates the flow of the game.

[0132] 3. Output the simulation results in JSON format.

[0133] Step 4: Formatting the simulation results

[0134] server

[0135] The server formats the simulation results obtained from the generative AI model and extracts the data necessary for the next visualization process. The input is the JSON data of the simulation results, and the output is the data for video generation. For example, this includes information such as player positions, ball position, and time lapse.

[0136] Specific behavior:

[0137] 1. The server receives the simulation results.

[0138] 2. Organize the necessary data (e.g., player positions by time, ball position).

[0139] 3. Pass the formatted data to the next process.

[0140] Step 5: Visualization process

[0141] server

[0142] The server uses a video generation engine based on the formatted data to generate video of the match. The input is the formatted data, and the output is the match video. The video reproduces the movements of the players and the ball in real time.

[0143] Specific behavior:

[0144] 1. The server launches the video generation engine (e.g., Unity, Unreal Engine).

[0145] 2. Read the formatted data and render it as an image.

[0146] 3. Prepare the generated video in file storage or streaming format.

[0147] Step 6: Generate and evaluate a tactical plan

[0148] server

[0149] The server uses a generative AI model to generate multiple tactical plans and evaluates the effectiveness of each through simulation. The input is preprocessed data and simulation conditions, and the output is the optimal tactical plan. The system evaluates these tactical plans and selects the one with the highest probability of winning.

[0150] Specific behavior:

[0151] 1. The server inputs prompts to generate a tactical plan into the generative AI model.

[0152] 2. Evaluate the generated tactical plan.

[0153] 3. Select the most effective tactical plan and develop detailed information.

[0154] Step 7: Sending data to the user interface

[0155] Terminal

[0156] The terminal receives the video data and tactical plans sent from the server and provides them to the manager or coach. The input is the video data and tactical plans from the server, and the output is information displayed in a format that is easy for the user to understand.

[0157] Specific behavior:

[0158] 1. The device retrieves video data and tactical plans from the server.

[0159] 2. Play video in real time or on demand.

[0160] 3. Display details of the tactical plan to allow users (managers and coaches) to take countermeasures.

[0161] (Application example 1)

[0162] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0163] Conventional sports game analysis and tactical planning systems are limited in their ability to collect and analyze past game data, limiting their ability to predict future game developments and propose tactical plans. Furthermore, the visualization of game simulations and proposed tactical plans are not provided in an intuitively understandable format, making it difficult for users to understand and apply them. Therefore, there is a need for a system that can consistently provide more accurate game predictions, realistic and intuitive visualization, and optimal tactical plans.

[0164] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0165] In this invention, the server includes a means for collecting past match data, a means for analyzing the collected data, a means for evaluating tactical plans using a generative AI model and selecting an optimal plan, and a means for presenting images and tactical plans through a user interface, thereby making it possible to provide highly accurate simulation results and optimal tactical plans in an intuitively easy-to-understand format.

[0166] "Past match data" refers to information about past matches in a particular sport, including player movements, match results, tactical data, and the like.

[0167] "Means of collection" refers to the methods and systems for obtaining data from external APIs, etc. and storing it on a server.

[0168] "Means of analysis" refers to the algorithms and programs used to organize collected data and convert it into meaningful information.

[0169] "Means to simulate future matches" refers to systems and algorithms that use past match data and analysis results to predict how future matches will play out.

[0170] "Means for visualizing simulation results" refers to technologies and tools that visually represent the results of a simulation and output them in a form that is easy for users to understand.

[0171] "Means for proposing tactical plans" refers to a method for generating optimal strategies and tactics based on the results of a match simulation and presenting them to the user.

[0172] A "generative AI model" refers to an artificial intelligence model based on deep learning that is used for purposes such as prediction, analysis, and suggestions.

[0173] "User interface" refers to the parts that users directly touch, such as the screen and operation methods used to exchange information between the system and the user.

[0174] This invention is a system that collects and analyzes past match data, simulates and visualizes future matches, and proposes tactical plans. The main elements of this system and their functions are explained in detail below.

[0175] The server first uses external APIs to collect past match data, including match data for specific sports teams and players, which is then stored in the server's database. The stored data is then analyzed and preprocessed into a format that can be understood by the generative AI model. This analysis includes player movement and tactical data, and the data is then properly organized before proceeding to the next processing stage.

[0176] The server inputs the preprocessed data into a generative AI model (such as OpenAI GPT-4 or Stable Diffusion) and runs a simulation to predict future matches. The simulation predicts each player's movements based on past data and recreates the flow and results of the match. The simulation results are organized in JSON format and passed to the visualization process.

[0177] The visualization process, based on the simulation results, builds data such as player positions, ball positions, and time progression. This data is then used to generate visual images using a video generation engine such as Unity or Unreal Engine. This video realistically reproduces the action of the match and is provided to users.

[0178] The tactical suggestion feature uses a generative AI model to generate tens of millions of tactical plans, which the system then evaluates to select the plan with the highest potential for winning. The selected plan is then suggested to the manager or coach, along with a detailed explanation.

[0179] The user interface displays the video data and tactical plans sent from the server on the device, allowing managers and coaches to intuitively understand the progress of the game. The tactical plans are also displayed with detailed explanations, so users can use them as reference information to decide on specific next moves.

[0180] As a concrete example, when a soccer team's manager is planning a strategy for the next match, he collects and analyzes past match data and tactical data via API. The results are input into a generative AI model, which simulates future matches. The simulation results are visualized and provided to the manager via a device. The generative AI model also proposes an optimal tactical plan to improve the team's chances of winning the next match.

[0181] An example of a prompt might be:

[0182] "For a match between Team A and Team B, simulate future game developments based on past data and propose the optimal tactical plan."

[0183] In this way, the system makes it easier for managers and coaches to plan specific strategies for matches, which can have a positive impact on the outcome of the match.

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] The server uses an external API to collect past match data. The input is a request to the external API, and the output is the retrieved match data. Specifically, the server hits a specific URL or endpoint and retrieves past match data in response. This data includes player location information, scores, tactical data, and more. For example, data is returned in JSON format from a sports data provider API.

[0187] Step 2:

[0188] The server stores the collected data in a database. The input is the acquired match data, and the output is the data stored in the database. Specifically, to insert the data for each match into the appropriate table, an SQL statement is generated and executed on the database (for example, MySQL or PostgreSQL). The database stores the match ID, player ID, and details of each play.

[0189] Step 3:

[0190] The server extracts the data to be analyzed from the database and preprocesses it into a format that the generative AI model can understand. The input is the match data extracted from the database, and the output is the preprocessed data. Specific operations include data cleanup (missing value processing, normalization) and format conversion (for example, conversion to CSV format). This prepares the data in a format that is easy to input into the AI ​​model.

[0191] Step 4:

[0192] The server inputs the preprocessed data into a generative AI model to simulate future matches. The input is the preprocessed data, and the output is the simulation results. Specifically, the server supplies data to a generative AI model (e.g., OpenAI GPT-4) to predict how the match will play out. At this time, the server simulates the movements of players and the progress of the match. The simulation results are organized in JSON format.

[0193] Step 5:

[0194] The server executes a visualization process based on the simulation results. The input is the simulation results, and the output is the game footage. Specifically, a video generation engine such as Unity or Unreal Engine is used to visually reproduce the movements of players and the ball. Data such as player positions, ball position, and time passage are used during this process.

[0195] Step 6:

[0196] The server sends the generated video data and tactical plan to the terminal. The input is the video data and tactical plan, and the output is the data sent to the terminal. Specifically, the server sends the video data and tactical plan via HTTP protocol to the terminal (e.g., a smartphone or head-mounted display) so that the user can view them.

[0197] Step 7:

[0198] The terminal displays the received video data and tactical plan. The input is the transmitted video data and tactical plan, and the output is a visual display provided to the user. Specifically, the terminal plays the video on its display and displays the tactical plan in text and graph format. The user can view this to confirm the game development and tactical proposals.

[0199] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0200] The present invention is a system that collects and analyzes past match data, simulates future matches, visualizes the results, and proposes tactical plans. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it is possible to provide optimal images and tactical plans for each individual user. A specific embodiment of this system is described below.

[0201] 1. Collection and analysis of past match data

[0202] (server)

[0203] 1. The server collects past match data using an external API. This API retrieves match data for specific teams and players and stores it in a database within the server.

[0204] 2. Next, the server extracts stored tactical data and player stats from the database. The server then analyzes this data and preprocesses it into a format that can be understood by the generative AI model.

[0205] 2. Simulating future matches

[0206] (server)

[0207] 1. The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and virtually recreate the flow and outcome of the match.

[0208] 2. The simulation results are organized in JSON format and passed to the subsequent visualization process.

[0209] 3. Visualization of simulation results

[0210] (server)

[0211] 1. The server creates data to visualize the movements of players and the ball based on the simulation results. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into the image generation engine. The image generation engine then creates frames that reproduce the action of the game in real time.

[0212] 2. The generated video data is sent to the terminal. The server compresses the generated video data and sends it to the user's terminal via the Internet.

[0213] 4. Tactical suggestion function

[0214] (server)

[0215] 1. The server uses a generative AI model to generate tens of millions of tactical plans. The system evaluates these plans and selects the plan with the highest probability of winning.

[0216] 2. The selected optimal tactical plan is proposed to the manager or coach as a specific tactical proposal.

[0217] 5. Emotion recognition function

[0218] (Terminal)

[0219] 1. The device uses the user's camera and microphone to input the user's facial expressions and voice into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (happiness, surprise, excitement, etc.).

[0220] 2. The recognized emotion data is sent to the server, which then dynamically changes the video content and tactical plan based on this data.

[0221] Specific examples

[0222] For example, when a soccer team's manager is planning strategies for the next match, he collects and analyzes past match data and tactical data via API. The results are then input into a generative AI model to simulate future matches. The simulation results are visualized and provided to the manager via a device.

[0223] Furthermore, the emotion engine recognizes the manager's emotions, and if the manager is feeling very nervous, for example, it will make the simulation video more detailed and suggest more specific tactical plans, allowing the manager to intuitively understand the progress of the game and select the optimal tactics.

[0224] In addition, the emotion engine recognizes the player's reactions and adjusts the tactics it suggests to increase the player's motivation, resulting in a more effective tactical plan.

[0225] In this way, this system will make it easier for managers, coaches, and even sports lottery users to plan specific strategies for matches, which will have a positive impact on the outcome of the match.

[0226] The processing flow will be explained below.

[0227] Step 1:

[0228] (server)

[0229] Use an external API to collect past match data. The server calls this API endpoint (e.g., https: / / sportsdata.api / teams / teamA / matches) to retrieve match data for specific teams and players. The retrieved data is then stored in a database within the server.

[0230] Step 2:

[0231] (server)

[0232] The stored tactical data and player stats are extracted from the database. Specifically, SQL queries are used to extract the required data, which is then analyzed. During the analysis, pre-processing steps such as data cleaning, normalization, and feature extraction are performed.

[0233] Step 3:

[0234] (server)

[0235] The preprocessed data is input into a generative AI model to simulate future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and the flow of the match. The simulation results are organized by each phase of the match and output in JSON format.

[0236] Step 4:

[0237] (server)

[0238] Based on the simulation results, data is created to visualize the movements of players and the ball. Specifically, the position data of each player and the movement data of the ball are organized along a time axis and input into a video generation engine. The video generation engine then creates frames that reproduce the movements of the game in real time.

[0239] Step 5:

[0240] (server)

[0241] The generated video data is sent to the terminal. The server compresses the generated video data and sends it to the user's terminal via the Internet. At this time, an appropriate compression algorithm is used to avoid data loss.

[0242] Step 6:

[0243] (Terminal)

[0244] The device receives the video data sent from the server and displays it on the screen. By watching this video, users can intuitively understand the progress of the simulated game. The device also provides functions such as playing, pausing, and rewinding the video in response to user operations.

[0245] Step 7:

[0246] (server)

[0247] Tactical plans are proposed based on the results of the match. The server uses a generative AI model to generate tens of millions of tactical plans and evaluates the success rate of each plan. The plan with the highest success rate is selected and provided as a concrete tactical proposal for the next match.

[0248] Step 8:

[0249] (Terminal)

[0250] The proposed tactical plan is received and displayed to the user along with a detailed explanation. Managers and coaches can use this information to develop specific strategies for the next game. The device also provides an interface for users to modify tactical plans or add new plans.

[0251] Step 9:

[0252] (Terminal)

[0253] The device uses the user's camera and microphone to input the user's facial expressions and voice into the emotion engine, which then analyzes this data and recognizes the user's emotional state (happiness, surprise, excitement, etc.).

[0254] Step 10:

[0255] (server)

[0256] The server receives the recognized emotion data. Based on this data, the server dynamically changes the video content and tactical plan. For example, if the user is nervous, the simulation video will be more detailed and the tactical plan will be explained more carefully.

[0257] Step 11:

[0258] (Terminal)

[0259] The dynamically changed video and tactical plan are received again from the server and provided to the user, who can then use this information to more specifically determine the strategy for the next match.

[0260] Step 12:

[0261] (User)

[0262] Managers and coaches can view the footage, review the proposed tactical plan, and, if necessary, revise the plan to determine the optimal strategy. Through this system, managers and coaches can intuitively understand the development of the game and devise the optimal tactics.

[0263] Through these steps, the system will help managers, coaches, and even sports lottery users to plan specific strategies for the next game, which will have a positive impact on the outcome of the game.

[0264] Example 2

[0265] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0266] Conventional match analysis systems mainly perform simple statistical analysis based on past match data, and have limited functionality for simulating future matches in real time and visually displaying the results. Furthermore, they do not provide personalized tactical suggestions that take into account the user's emotions, limiting their efficiency and effectiveness in match preparation.

[0267] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0268] In this invention, the server includes means for collecting past match data, means for analyzing the collected data, means for preprocessing the analyzed data, means for inputting the preprocessed data into a generative AI model to simulate future matches, means for organizing the simulation results in JSON format, means for generating video based on the simulation results, means for recognizing user emotions, means for dynamically changing the video content and tactical plans based on the recognized emotion data, and means for proposing tactical plans based on the simulation results, thereby enabling specific and detailed match simulations and personalized tactical proposals.

[0269] "Past match data" refers to historical data such as match results, statistical information, and tactical data of players and teams in a particular sporting event.

[0270] "Means of collection" refers to the functions and methods for obtaining the necessary information from external APIs or databases and storing it in the system.

[0271] "Means of analysis" refers to the functions and methods of analyzing collected data using statistical or machine learning techniques and extracting useful information.

[0272] "Preprocessing means" refers to processes such as data cleaning and normalization to convert the analyzed data into a format that is easy for the generative AI model to understand.

[0273] A "generative AI model" is an artificial intelligence model that learns from past data and is used to predict future events and outcomes.

[0274] "Means to simulate" refers to functions and methods for virtually recreating future match situations and outcomes using generative AI models.

[0275] "JSON format" is an abbreviation for JavaScript Object Notation, and is a standard format for describing data structures flexibly and simply.

[0276] "Means for generating images" refers to a function or method for creating image data for visually displaying player movements and game situations based on simulation results.

[0277] "Means for recognizing user emotions" refers to a function or method for analyzing the user's facial expressions and voice data obtained from sensors such as cameras and microphones, and determining their emotional state.

[0278] "Means for dynamic change" refers to functions and methods for adjusting video content and tactical plans in real time based on the user's emotional data.

[0279] "Means for proposing tactical plans" refers to functions and methods for proposing optimal strategies and formations based on simulation and analysis results.

[0280] The present invention is a system that collects and analyzes past match data, simulates future matches, visualizes the results, and proposes tactical plans. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it is possible to provide optimal images and tactical plans for each individual user. Specific embodiments of this system are described below.

[0281] 1. Collection and analysis of past match data

[0282] (server)

[0283] The server uses external APIs to collect past game data, such as a sports league's API, to retrieve game data for specific teams and players. This data is stored in a database on the server in JSON or CSV format.

[0284] The server then retrieves the stored match data from the database and analyzes it. This analysis includes player movement patterns on the field, scoring patterns, and transitional behavior between offense and defense. The analyzed data is then preprocessed into a format suitable for the generative AI model. This preprocessing includes normalizing the numerical data and filling in missing data.

[0285] 2. Simulating future matches

[0286] (server)

[0287] The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past match data to predict the game's development and outcome. This prediction includes the movements of each player, ball movement, and goal timing. The simulation results are organized in JSON format and used for visualization at a later stage.

[0288] 3. Visualization of simulation results

[0289] (server)

[0290] The server uses the simulation results to create data for visualizing the movements of players and the ball. Specifically, it organizes each player's position data and ball movement data along a timeline and inputs it into a video generation engine (e.g., Unity or Unreal Engine). The video generation engine uses this data to create frames that reproduce the action of the game in real time. The generated video data is then further compressed and sent to the user's device.

[0291] 4. Tactical suggestion function

[0292] (server)

[0293] The server uses a generative AI model to generate tens of millions of tactical plans. These plans are evaluated based on simulation results, and the plan with the highest win rate is selected. The selected tactical plan is presented to the manager or coach as a specific tactical proposal. This proposal may include specific position changes, attacking patterns, defensive plans, etc.

[0294] 5. Emotion recognition function

[0295] (Terminal)

[0296] The device uses the user's camera and microphone to input the user's facial expressions and voice data into the emotion engine. The emotion engine analyzes this data in real time and recognizes the user's emotional state (happiness, surprise, excitement, etc.). The recognized emotion data is sent to the server, which dynamically changes the video content and tactical plan based on this data. For example, if the user is nervous, the server can provide detailed simulation video and change the tactical plan to be more specific.

[0297] Specific examples

[0298] For example, when a soccer team manager is planning a strategy for the next game, he or she will use the system in the following steps.

[0299] First, the server collects past match data and tactical data via an API, analyzes it, and inputs it into the generative AI model. Next, the server runs a simulation of a future match and visualizes the results. The visualized simulation results are then sent to the manager's device. Furthermore, the server recognizes the manager's emotions through the device's camera and microphone and adjusts the corresponding tactical plan. For example, if the manager is very nervous, the simulation video will be more detailed and specific tactical plans will be proposed, allowing the manager to select the optimal tactical strategy.

[0300] Here are some example prompts to input to a generative AI model:

[0301] "Using match data from the past three years for a specific team, simulate the optimal tactical plan for the next match. If the user is nervous, provide specific tactical suggestions to help them cope."

[0302] Using such prompts, the generative AI model can suggest specific and useful tactics.

[0303] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0304] A detailed explanation of the program processing of this system

[0305] Processing Steps

[0306] Step 1: Collect past match data

[0307] (server)

[0308] Input: The server sends an API request to an external data provider.

[0309] Data processing / calculation: Receive match data returned from the API and extract necessary items (e.g., player statistics, match results, tactical data). Convert the data format to JSON or CSV.

[0310] Output: Collected data is saved in a database on the server.

[0311] Specific operation: The server calls the sports league API and specifies parameters such as "team_id" and "match_date" to retrieve match data from the past three years.

[0312] Step 2: Data extraction and preprocessing

[0313] (server)

[0314] Input: Saved match data from database.

[0315] Data processing / calculation: Analyze the data and extract detailed information such as player movements, number of goals, and possession. Fill in missing data, normalize the data, and preprocess it into a format that can be input into a generative AI model.

[0316] Output: The preprocessed dataset.

[0317] Specific operation: The server processes the data using the Pandas library, filling in missing data and standardizing it.

[0318] Step 3: Generate data to input to the AI ​​model

[0319] (server)

[0320] Input: Preprocessed data.

[0321] Data processing / computation: Input data into a generative AI model (e.g., a PyTorch model) and run inference on the model, which results in simulated results for future matches.

[0322] Output: Predicted data as a simulation result.

[0323] How it works: The server reads the pre-processed data and feeds it into a generative AI model that makes predictions using the arrow method and regression analysis.

[0324] Step 4: Organizing the simulation results

[0325] (server)

[0326] Input: Simulation results from a generative AI model.

[0327] Data processing / calculation: Organize the simulation results along the time axis and convert them into JSON format.

[0328] Output: Simulation result data in JSON format.

[0329] Specific operation: The server reads the model output, organizes player position data and ball movement data in chronological order, and converts them into JSON format.

[0330] Step 5: Inputting data into the image generation engine

[0331] (server)

[0332] Input: Simulation result data in JSON format.

[0333] Data processing / calculation: Input data into a video generation engine (Unity or Unreal Engine) to generate video of the virtual match.

[0334] Output: Frame data that recreates the action of the match.

[0335] Specific operation: The server reads the JSON data and passes it to the image generation engine script to generate real-time images.

[0336] Step 6: Compress and transmit the video data

[0337] (server)

[0338] Input: The generated frame data.

[0339] Data processing / calculation: Data size is optimized using a compression algorithm and sent to the user's device.

[0340] Output: Compressed video data.

[0341] Specific operation: The server applies a compression algorithm such as H.264 and sends the data to the terminal via the Internet.

[0342] Step 7: Generate and evaluate a tactical plan

[0343] (server)

[0344] Input: Simulation results obtained from a generative AI model.

[0345] Data processing / calculation: Simulating different tactical plans, evaluating them and selecting the best plan.

[0346] Output: Optimal tactical plan.

[0347] What it does: The server simulates multiple tactical scenarios and applies algorithms to evaluate the success rate and effectiveness of each scenario.

[0348] Step 8: Recognizing User Emotions

[0349] (Terminal)

[0350] Input: Emotion data from the user's camera or microphone.

[0351] Data processing / calculation: The emotion engine analyzes this data and determines the user's emotional state from their facial expressions and voice.

[0352] Output: Recognized emotion data.

[0353] How it works: The device uses software to capture the user's facial expressions and voice through a camera and microphone and analyzes them in real time.

[0354] Step 9: Dynamically change the visuals and tactical plans with emotional data

[0355] (server)

[0356] Input: Recognized emotion data and simulation results.

[0357] Data processing / calculation: Apply algorithms that dynamically change video content and tactical plans based on emotional data.

[0358] Output: Dynamically modified footage and tactical plans.

[0359] Specific actions: The server analyzes the emotional data and adjusts the level of detail in the video or makes the tactical plan more specific depending on the user's level of tension.

[0360] The above is a specific description of each processing step in this system.

[0361] (Application example 2)

[0362] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0363] While conventional match data analysis systems can analyze past match data and simulate future matches, they are unable to propose tactical plans that take the user's emotions into account, making it difficult to provide optimal information to each individual user. Furthermore, users have difficulty visually grasping the flow of the match, making it difficult for them to intuitively understand the effectiveness of tactical plans.

[0364] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0365] In this invention, the server includes means for collecting past match data, means for analyzing the collected data, means for simulating future matches, means for visualizing the simulation results, means for proposing a tactical plan based on the match results, and means for recognizing the user's emotions and dynamically changing the images and tactical plan based on the emotion data, thereby enabling the proposal of an optimized tactical plan for each user and enabling the user to visually and intuitively grasp the flow of the match.

[0366] Key Word Definitions

[0367] "Past match data" is recorded data relating to matches played in the past, and includes details such as player movements, scores, and tactical patterns.

[0368] "Means of collection" refers to the technical methods and devices used to collect the required data through external APIs and databases.

[0369] "Means of analysis" refers to technical methods or devices that preprocess collected data, extract useful information from the data, and further analyze it using statistical techniques or machine learning models.

[0370] "Means for simulating" refers to technical methods or devices that virtually reproduce the development of a future match based on analyzed data.

[0371] "Visualization means" refers to technical methods and devices that visually display the simulation results and generate video data that reproduces the movements of the game.

[0372] The "means for proposing a tactical plan" refers to a technical method or device that generates an optimal tactical plan based on simulation results and past match data and presents it to the user.

[0373] "Means for recognizing emotions" refers to technical methods or devices that analyze a user's facial expressions and voice data to identify the user's emotional state.

[0374] "Dynamic modification means" refers to technical methods or devices that modify the content of video or tactical plans in real time based on recognized emotion data.

[0375] MODE FOR CARRYING OUT THE INVENTION

[0376] This system collects and analyzes past match data, simulates future matches, visualizes the results, and proposes tactical plans. Furthermore, by incorporating an emotion engine, it recognizes the user's emotions and provides optimal images and tactical plans for each individual user.

[0377] 1. Collection and analysis of past match data

[0378] (server)

[0379] The server uses an external API to collect past match data. This API retrieves match data for specific teams and players and stores it in a database within the server. The server then extracts the stored tactical data and player stats from the database. The server analyzes this data and preprocesses it into a format that can be understood by the generative AI model.

[0380] 2. Simulating future matches

[0381] (server)

[0382] The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past data to predict each player's movements and virtually recreate the flow and outcome of the match. The simulation results are organized in JSON format and passed to the subsequent visualization process.

[0383] 3. Visualization of simulation results

[0384] (server)

[0385] The server creates data to visualize the movements of players and the ball based on the simulation results. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into a video generation engine. The video generation engine creates frames that reproduce the action of the game in real time. To send the generated video data to the terminal, the server compresses the video data and sends it to the user's terminal via the Internet.

[0386] 4. Tactical suggestion function

[0387] (server)

[0388] The server uses a generative AI model to generate tens of millions of tactical plans. It then evaluates these plans and selects the one with the highest winning rate. The selected optimal tactical plan is then proposed to the manager or coach as a concrete tactical proposal.

[0389] 5. Emotion recognition function

[0390] (Terminal)

[0391] The device uses the user's camera and microphone to input the user's facial expressions and voice into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (happiness, surprise, excitement, etc.). The recognized emotion data is sent to the server, which then dynamically changes the video content and tactical plan based on this data.

[0392] Specific examples

[0393] For example, when a soccer team's coach plans a strategy for the next match, he collects and analyzes past match data and tactical data via an API. The results are then input into a generative AI model to simulate future matches. The simulation results are visualized and provided to the coach via a device. Furthermore, an emotion engine recognizes the coach's emotions. For example, if the coach is very nervous, the simulation video becomes more detailed and the proposed tactical plan becomes more specific. This allows the coach to intuitively understand the game's development and select the optimal tactical strategy. Furthermore, the emotion engine recognizes the players' reactions and adjusts the proposed tactics to increase players' motivation, resulting in a more effective tactical plan.

[0394] Prompt Sentence Examples

[0395] "Use a virtual tactical assistant to analyze past match data and simulate future matches. Use emotion recognition to suggest optimal tactical plans based on the user's emotions."

[0396] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0397] Program processing flow

[0398] Processing Steps

[0399] Step 1:

[0400] The server uses an external API to collect past match data. Specifically, it sends an API request to obtain match data for specific teams and players (e.g., player movements, scores, tactical patterns, etc.). This data is stored in a database within the server. The input is the response data from the API, and the output is the stored match data.

[0401] Step 2:

[0402] The server extracts stored tactical data and player stats from the database and analyzes them. Specifically, it preprocesses the data and converts it into a format that can be understood by the generative AI model. The input is the extracted data from the database, and the output is the preprocessed data.

[0403] Step 3:

[0404] The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and virtually recreate the flow and outcome of the match. The input is preprocessed data, and the output is the simulation results in JSON format.

[0405] Step 4:

[0406] The server creates data to visualize the movements of players and the ball based on the simulation results. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into the image generation engine. The image generation engine creates frames that reproduce the action of the game in real time. The input is the simulation result data, and the output is visualized match data.

[0407] Step 5:

[0408] The server transmits the generated video data to the terminal. Specifically, it compresses the video data and transmits it to the user's terminal via the Internet. The input is the visualized match data, and the output is the data delivered to the user's terminal.

[0409] Step 6:

[0410] The device uses the user's camera and microphone to input the user's facial expressions and voice data into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, surprise, excitement, etc.). The input is raw data obtained from the camera and microphone, and the output is analyzed emotion data.

[0411] Step 7:

[0412] The server dynamically changes the video content and tactical plan based on the recognized emotion data. Specifically, it generates an optimal tactical plan corresponding to the user's emotion and updates the video and plan content. The input is the emotion data and the initial video and tactical plan, and the output is the updated video and tactical plan.

[0413] Step 8:

[0414] The server uses a generative AI model to generate tens of millions of tactical plans, evaluates them, and selects the plan with the highest winning rate. The selected optimal tactical plan is then proposed to the manager or coach as a specific tactical proposal. The input is past match data and simulation results, and the output is the optimal tactical plan.

[0415] Prompt Sentence Examples

[0416] "Use a virtual tactical assistant to analyze past match data and simulate future matches. Use emotion recognition to suggest optimal tactical plans based on the user's emotions."

[0417] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0418] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0419] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0420] [Second embodiment]

[0421] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0422] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0423] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0424] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0425] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0426] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0427] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0428] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0429] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0430] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0431] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0432] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0433] The present invention is a system that collects and analyzes data from past sports matches, simulates future matches, visualizes the results, and proposes tactical plans. A specific embodiment of this system is described below.

[0434] 1. Collection and analysis of past match data

[0435] (server)

[0436] 1. The server collects past match data using an external API. For example, it calls an API to obtain match data for a specific team or player, and stores the data obtained in response within the server.

[0437] 2. The server then extracts stored tactical data and player stats from the database, parses this data, and pre-processes it into a format that the generative AI model can understand.

[0438] 2. Simulating future matches

[0439] (server)

[0440] 1. The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model then predicts each player's movements based on past data and virtually recreates the flow and outcome of the match.

[0441] 2. The simulation results are organized in JSON format and passed to the subsequent visualization process.

[0442] 3. Visualization of simulation results

[0443] (server)

[0444] 1. The server builds data to visualize the movements of players and the ball based on the simulation results. This data includes the positions of players, the ball, and the passage of time.

[0445] 2. The obtained data is used by the image generation engine to generate a visual image of the match. This image realistically reproduces the action of the match and is output in a format that is easy for users to understand.

[0446] 4. Tactical suggestion function

[0447] (server)

[0448] 1. The server uses a generative AI model to generate tens of millions of tactical plans. The system evaluates these plans and selects the one with the highest probability of winning.

[0449] 2. The selected optimal tactical plan is proposed to the manager or coach as a specific tactical proposal.

[0450] 5. User Interface

[0451] (Terminal)

[0452] 1. The device receives the video data and tactical plan sent from the server. The video is played on the device screen, allowing the manager or coach to intuitively understand the progress of the game.

[0453] 2. The tactical plan is displayed with detailed explanations and serves as a reference for the user to decide on specific next moves.

[0454] Specific examples

[0455] For example, when a soccer team's manager is planning a strategy for the next match, he collects and analyzes past match data and tactical data via an API. The results are then input into a generative AI model to simulate future matches. The simulation results are visualized and provided to the manager via a device. The generative AI model then proposes an optimal tactical plan to improve the manager's chances of winning the next match. This allows the manager to intuitively understand the game's development and select the optimal tactical strategy.

[0456] In this way, this system will make it easier for managers and coaches to plan specific strategies for matches, which will have a positive impact on the outcome of the match.

[0457] The processing flow will be explained below.

[0458] Step 1:

[0459] (server)

[0460] The server first calls an external API to collect past match data. This API retrieves match data for specific teams and players and stores it in a database within the server. For example, to retrieve soccer match data, an API endpoint such as https: / / sportsdata.api / teams / teamA / matches is called.

[0461] Step 2:

[0462] (server)

[0463] To analyze the collected data, the server extracts tactical data and player stats from the database. This data is obtained, for example, using SQL queries. Since the obtained data is difficult for the generative AI model to understand as it is, preprocessing involves cleaning, normalizing, and extracting features from the data.

[0464] Step 3:

[0465] (server)

[0466] The server inputs the preprocessed data into a generative AI model to simulate future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and the flow of the match. The simulation results are organized by each phase of the match and output in JSON format.

[0467] Step 4:

[0468] (server)

[0469] The server uses the simulation results to create data for visualizing the movements of players and the ball. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into a video generation engine. This video generation engine then creates frames that reproduce the action of the game in real time.

[0470] Step 5:

[0471] (server)

[0472] The generated video data is sent to the terminal. The server compresses the generated video data and sends it to the user's terminal via the Internet. At this time, an appropriate compression algorithm is used to avoid data loss.

[0473] Step 6:

[0474] (Terminal)

[0475] The device receives the video data sent from the server and displays it on the screen. By watching this video, users can intuitively understand the simulated game progress. The device also provides functions such as playing, pausing, and rewinding the video in response to user operations.

[0476] Step 7:

[0477] (server)

[0478] The server proposes tactical plans based on the results of the match. It uses a generative AI model to generate tens of millions of tactical plans and evaluates the success rate of each plan. The plan with the highest success rate is selected and provided as a concrete tactical proposal for the next match.

[0479] Step 8:

[0480] (Terminal)

[0481] The device receives the proposed tactical plan and displays it to the user along with a detailed explanation. Managers and coaches can use this information to develop specific strategies for the next game. The device also provides an interface for users to modify the tactical plan or add new plans.

[0482] Step 9:

[0483] (User)

[0484] Users watch the video and review the proposed tactical plan. They can then modify the plan as necessary and decide on the final strategy for the next match. Through this system, managers and coaches can intuitively understand the development of the game and plan the optimal tactical plan.

[0485] Through these steps, the system helps managers, coaches, and even sports lottery users to plan specific strategies for the next game.

[0486] Example 1

[0487] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0488] Conventional tactical planning support systems for sports games only allow users to view past game data, and are therefore inadequate in predicting future game results and proposing specific tactical plans. Furthermore, there is no way to provide simulation results in a visually easy-to-understand format, making it difficult for managers and coaches to intuitively understand and formulate countermeasures.

[0489] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0490] In this invention, the server includes means for collecting past game data, means for analyzing and preprocessing the collected data, means for simulating future games using the preprocessed data, means for formatting the simulation results in JSON format, means for generating images based on the formatted data, means for generating and evaluating tactical plans based on game results, and means for proposing the evaluated tactical plans. This enables managers and coaches to predict future game results in detail, intuitively and easily understand optimal tactical plans, and take countermeasures.

[0491] "Past match data" refers to past results of sports matches, player statistics, tactical data, etc.

[0492] "Means of collection" refers to the methods and systems used to obtain the necessary data from external APIs and databases.

[0493] "Analysis and preprocessing means" refers to methods and systems that remove outliers from collected data, normalize the data, and prepare the data in a format that can be used by generative AI models.

[0494] "Simulating means" refers to a method or system that uses a generative AI model based on pre-processed data to virtually predict the course and outcome of future matches.

[0495] "Means for formatting in JSON format" refers to a method or system for formatting simulation results into JSON (JavaScript Object Notation), a standardized data format, and passing them to the next processing step.

[0496] "Means for generating images" refers to a method or system that uses an image generation engine based on simulation results to visually reproduce a match.

[0497] "Means for generating and evaluating tactical plans" refers to a method or system that uses a generative AI model to generate multiple tactical plans, simulate the effects of each, and select the optimal plan.

[0498] "Means for proposing tactical plans" refers to a method or system for providing the manager or coach with the evaluated optimal tactical plan in a concrete and easily understandable format.

[0499] The present invention is a system that collects and analyzes data from past sports matches, simulates future matches, visualizes the results, and proposes tactical plans. A specific embodiment of this system is described below.

[0500] The server uses external APIs to collect past game data. Specifically, it obtains game data related to specific teams and players from external APIs such as sports data provider APIs. For example, to collect NBA game data, it obtains the data using the API request " / api / v1 / games?team_id=1234" and stores the JSON-formatted data obtained as a response in the database.

[0501] The server then analyzes and pre-processes the stored match data from the database, including data extraction, outlier removal, and data normalization, such as extracting player positions and stats (e.g., shots, passes, and ball possession time) and formatting them in a format that can be used by the generative AI model.

[0502] The server then inputs the preprocessed data into a generative AI model to simulate future matches. The generative AI model predicts player movements based on past data and virtually recreates the flow and outcome of the match. The simulation results are organized in JSON format and passed to the next process.

[0503] The server uses the simulation results to build data for visualizing player and ball movements. This data includes player positions, ball position, and time progression. It then uses a video generation engine (e.g., Unity or Unreal Engine) to generate a visual image of the match. This image realistically reproduces the action of the match and is output in a format that is easy for users to understand.

[0504] The server also uses a generative AI model to generate millions of tactical plans. These plans are evaluated and the plan with the highest potential for winning is selected. The optimal plan is then proposed to the manager or coach as a concrete tactical proposal.

[0505] The device receives the video data and tactical plan sent from the server. The video is played on the device screen, allowing managers and coaches to intuitively understand the game's progress. The tactical plan is also displayed with detailed explanations, providing reference information for users to specifically and efficiently decide their next move.

[0506] To give a specific example, when a soccer team's coach plans a strategy for the next match, the server collects and analyzes past match data and tactical data via an API. This data is input into a generative AI model to simulate future matches. The simulation results are organized into a primary JSON format and generated as realistic match footage using a video generation engine. The generative AI model then generates an optimal tactical plan to improve the team's chances of winning the next match and proposes it to the coach. The coach can then view the footage and tactical plan on their device and issue instructions to their players.

[0507] An example prompt is, "This system collects past match data, simulates and visualizes future matches, and proposes optimal tactical plans. Please propose effective tactics for a specific team for the next match."

[0508] In this way, this system will make it easier for managers and coaches to plan specific strategies for matches, which will have a positive impact on the outcome of the match.

[0509] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0510] Processing Steps:

[0511] Step 1: Collect past match data

[0512] server

[0513] The server sends a request to an external API (e.g., a sports data provider API). Specifically, it uses an API endpoint to retrieve past game data for a specific team or player. The input is the API request, and the output is the game data in JSON format. For example, the request " / api / v1 / games?team_id=1234" is sent, and the resulting data is stored in the database.

[0514] Specific behavior:

[0515] 1. The server sends an API request.

[0516] 2. The obtained JSON format match data is stored in a database.

[0517] Step 2: Analysis and preprocessing of match data

[0518] server

[0519] The server analyzes and preprocesses the match data stored in the database. The input is past match data, and the output is the preprocessed data. Specifically, it extracts player position information and stats, removes outliers, and normalizes the data. For example, it organizes stats such as the number of shots, number of passes, and ball possession time of players.

[0520] Specific behavior:

[0521] 1. The server extracts the match data from the database.

[0522] 2. Remove outliers and impute missing values.

[0523] 3. Normalize the data and convert it into a format suitable for generative AI models.

[0524] Step 3: Run the simulation

[0525] server

[0526] The server inputs the preprocessed data into a generative AI model to simulate future matches. The input is the preprocessed data, and the output is the simulation results in JSON format. The generative AI model predicts player movements based on past data and virtually recreates the flow and outcome of the match.

[0527] Specific behavior:

[0528] 1. The server inputs preprocessed data into the generative AI model.

[0529] 2. A generative AI model simulates the flow of the game.

[0530] 3. Output the simulation results in JSON format.

[0531] Step 4: Formatting the simulation results

[0532] server

[0533] The server formats the simulation results obtained from the generative AI model and extracts the data necessary for the next visualization process. The input is the JSON data of the simulation results, and the output is the data for video generation. For example, this includes information such as player positions, ball position, and time lapse.

[0534] Specific behavior:

[0535] 1. The server receives the simulation results.

[0536] 2. Organize the necessary data (e.g., player positions by time, ball position).

[0537] 3. Pass the formatted data to the next process.

[0538] Step 5: Visualization process

[0539] server

[0540] The server uses a video generation engine based on the formatted data to generate video of the match. The input is the formatted data, and the output is the match video. The video reproduces the movements of the players and the ball in real time.

[0541] Specific behavior:

[0542] 1. The server launches the video generation engine (e.g., Unity, Unreal Engine).

[0543] 2. Read the formatted data and render it as an image.

[0544] 3. Prepare the generated video in file storage or streaming format.

[0545] Step 6: Generate and evaluate a tactical plan

[0546] server

[0547] The server uses a generative AI model to generate multiple tactical plans and evaluates the effectiveness of each through simulation. The input is preprocessed data and simulation conditions, and the output is the optimal tactical plan. The system evaluates these tactical plans and selects the one with the highest probability of winning.

[0548] Specific behavior:

[0549] 1. The server inputs prompts to generate a tactical plan into the generative AI model.

[0550] 2. Evaluate the generated tactical plan.

[0551] 3. Select the most effective tactical plan and develop detailed information.

[0552] Step 7: Sending data to the user interface

[0553] Terminal

[0554] The terminal receives the video data and tactical plans sent from the server and provides them to the manager or coach. The input is the video data and tactical plans from the server, and the output is information displayed in a format that is easy for the user to understand.

[0555] Specific behavior:

[0556] 1. The device retrieves video data and tactical plans from the server.

[0557] 2. Play video in real time or on demand.

[0558] 3. Display details of the tactical plan to allow users (managers and coaches) to take countermeasures.

[0559] (Application example 1)

[0560] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0561] Conventional sports game analysis and tactical planning systems are limited in their ability to collect and analyze past game data, limiting their ability to predict future game developments and propose tactical plans. Furthermore, the visualization of game simulations and proposed tactical plans are not provided in an intuitively understandable format, making it difficult for users to understand and apply them. Therefore, there is a need for a system that can consistently provide more accurate game predictions, realistic and intuitive visualization, and optimal tactical plans.

[0562] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0563] In this invention, the server includes a means for collecting past match data, a means for analyzing the collected data, a means for evaluating tactical plans using a generative AI model and selecting an optimal plan, and a means for presenting images and tactical plans through a user interface, thereby making it possible to provide highly accurate simulation results and optimal tactical plans in an intuitively easy-to-understand format.

[0564] "Past match data" refers to information about past matches in a particular sport, including player movements, match results, tactical data, and the like.

[0565] "Means of collection" refers to the methods and systems for obtaining data from external APIs, etc. and storing it on a server.

[0566] "Means of analysis" refers to the algorithms and programs used to organize collected data and convert it into meaningful information.

[0567] "Means to simulate future matches" refers to systems and algorithms that use past match data and analysis results to predict how future matches will play out.

[0568] "Means for visualizing simulation results" refers to technologies and tools that visually represent the results of a simulation and output them in a form that is easy for users to understand.

[0569] "Means for proposing tactical plans" refers to a method for generating optimal strategies and tactics based on the results of a match simulation and presenting them to the user.

[0570] A "generative AI model" refers to an artificial intelligence model based on deep learning that is used for purposes such as prediction, analysis, and suggestions.

[0571] "User interface" refers to the parts that users directly touch, such as the screen and operation methods used to exchange information between the system and the user.

[0572] This invention is a system that collects and analyzes past match data, simulates and visualizes future matches, and proposes tactical plans. The main elements of this system and their functions are explained in detail below.

[0573] The server first uses external APIs to collect past match data, including match data for specific sports teams and players, which is then stored in the server's database. The stored data is then analyzed and preprocessed into a format that can be understood by the generative AI model. This analysis includes player movement and tactical data, and the data is then properly organized before proceeding to the next processing stage.

[0574] The server inputs the preprocessed data into a generative AI model (such as OpenAI GPT-4 or Stable Diffusion) and runs a simulation to predict future matches. The simulation predicts each player's movements based on past data and recreates the flow and results of the match. The simulation results are organized in JSON format and passed to the visualization process.

[0575] The visualization process, based on the simulation results, builds data such as player positions, ball positions, and time progression. This data is then used to generate visual images using a video generation engine such as Unity or Unreal Engine. This video realistically reproduces the action of the match and is provided to users.

[0576] The tactical suggestion feature uses a generative AI model to generate tens of millions of tactical plans, which the system then evaluates to select the plan with the highest potential for winning. The selected plan is then suggested to the manager or coach, along with a detailed explanation.

[0577] The user interface displays the video data and tactical plans sent from the server on the device, allowing managers and coaches to intuitively understand the progress of the game. The tactical plans are also displayed with detailed explanations, so users can use them as reference information to decide on specific next moves.

[0578] As a concrete example, when a soccer team's manager is planning a strategy for the next match, he collects and analyzes past match data and tactical data via API. The results are input into a generative AI model, which simulates future matches. The simulation results are visualized and provided to the manager via a device. The generative AI model also proposes an optimal tactical plan to improve the team's chances of winning the next match.

[0579] An example of a prompt might be:

[0580] "For a match between Team A and Team B, simulate future game developments based on past data and propose the optimal tactical plan."

[0581] In this way, the system makes it easier for managers and coaches to plan specific strategies for matches, which can have a positive impact on the outcome of the match.

[0582] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0583] Step 1:

[0584] The server uses an external API to collect past match data. The input is a request to the external API, and the output is the retrieved match data. Specifically, the server hits a specific URL or endpoint and retrieves past match data in response. This data includes player location information, scores, tactical data, and more. For example, data is returned in JSON format from a sports data provider API.

[0585] Step 2:

[0586] The server stores the collected data in a database. The input is the acquired match data, and the output is the data stored in the database. Specifically, to insert the data for each match into the appropriate table, an SQL statement is generated and executed on the database (for example, MySQL or PostgreSQL). The database stores the match ID, player ID, and details of each play.

[0587] Step 3:

[0588] The server extracts the data to be analyzed from the database and preprocesses it into a format that the generative AI model can understand. The input is the match data extracted from the database, and the output is the preprocessed data. Specific operations include data cleanup (missing value processing, normalization) and format conversion (for example, conversion to CSV format). This prepares the data in a format that is easy to input into the AI ​​model.

[0589] Step 4:

[0590] The server inputs the preprocessed data into a generative AI model to simulate future matches. The input is the preprocessed data, and the output is the simulation results. Specifically, the server supplies data to a generative AI model (e.g., OpenAI GPT-4) to predict how the match will play out. At this time, the server simulates the movements of players and the progress of the match. The simulation results are organized in JSON format.

[0591] Step 5:

[0592] The server executes a visualization process based on the simulation results. The input is the simulation results, and the output is the game footage. Specifically, a video generation engine such as Unity or Unreal Engine is used to visually reproduce the movements of players and the ball. Data such as player positions, ball position, and time passage are used during this process.

[0593] Step 6:

[0594] The server sends the generated video data and tactical plan to the terminal. The input is the video data and tactical plan, and the output is the data sent to the terminal. Specifically, the server sends the video data and tactical plan via HTTP protocol to the terminal (e.g., a smartphone or head-mounted display) so that the user can view them.

[0595] Step 7:

[0596] The terminal displays the received video data and tactical plan. The input is the transmitted video data and tactical plan, and the output is a visual display provided to the user. Specifically, the terminal plays the video on its display and displays the tactical plan in text and graph format. The user can view this to confirm the game development and tactical proposals.

[0597] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0598] The present invention is a system that collects and analyzes past match data, simulates future matches, visualizes the results, and proposes tactical plans. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it is possible to provide optimal images and tactical plans for each individual user. A specific embodiment of this system is described below.

[0599] 1. Collection and analysis of past match data

[0600] (server)

[0601] 1. The server collects past match data using an external API. This API retrieves match data for specific teams and players and stores it in a database within the server.

[0602] 2. Next, the server extracts stored tactical data and player stats from the database. The server then analyzes this data and preprocesses it into a format that can be understood by the generative AI model.

[0603] 2. Simulating future matches

[0604] (server)

[0605] 1. The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and virtually recreate the flow and outcome of the match.

[0606] 2. The simulation results are organized in JSON format and passed to the subsequent visualization process.

[0607] 3. Visualization of simulation results

[0608] (server)

[0609] 1. The server creates data to visualize the movements of players and the ball based on the simulation results. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into the image generation engine. The image generation engine then creates frames that reproduce the action of the game in real time.

[0610] 2. The generated video data is sent to the terminal. The server compresses the generated video data and sends it to the user's terminal via the Internet.

[0611] 4. Tactical suggestion function

[0612] (server)

[0613] 1. The server uses a generative AI model to generate tens of millions of tactical plans. The system evaluates these plans and selects the plan with the highest probability of winning.

[0614] 2. The selected optimal tactical plan is proposed to the manager or coach as a specific tactical proposal.

[0615] 5. Emotion recognition function

[0616] (Terminal)

[0617] 1. The device uses the user's camera and microphone to input the user's facial expressions and voice into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (happiness, surprise, excitement, etc.).

[0618] 2. The recognized emotion data is sent to the server, which then dynamically changes the video content and tactical plan based on this data.

[0619] Specific examples

[0620] For example, when a soccer team's manager is planning strategies for the next match, he collects and analyzes past match data and tactical data via API. The results are then input into a generative AI model to simulate future matches. The simulation results are visualized and provided to the manager via a device.

[0621] Furthermore, the emotion engine recognizes the manager's emotions, and if the manager is feeling very nervous, for example, it will make the simulation video more detailed and suggest more specific tactical plans, allowing the manager to intuitively understand the progress of the game and select the optimal tactics.

[0622] In addition, the emotion engine recognizes the player's reactions and adjusts the tactics it suggests to increase the player's motivation, resulting in a more effective tactical plan.

[0623] In this way, this system will make it easier for managers, coaches, and even sports lottery users to plan specific strategies for matches, which will have a positive impact on the outcome of the match.

[0624] The processing flow will be explained below.

[0625] Step 1:

[0626] (server)

[0627] Use an external API to collect past match data. The server calls this API endpoint (e.g., https: / / sportsdata.api / teams / teamA / matches) to retrieve match data for specific teams and players. The retrieved data is then stored in a database within the server.

[0628] Step 2:

[0629] (server)

[0630] The stored tactical data and player stats are extracted from the database. Specifically, SQL queries are used to extract the required data, which is then analyzed. During the analysis, pre-processing steps such as data cleaning, normalization, and feature extraction are performed.

[0631] Step 3:

[0632] (server)

[0633] The preprocessed data is input into a generative AI model to simulate future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and the flow of the match. The simulation results are organized by each phase of the match and output in JSON format.

[0634] Step 4:

[0635] (server)

[0636] Based on the simulation results, data is created to visualize the movements of players and the ball. Specifically, the position data of each player and the movement data of the ball are organized along a time axis and input into a video generation engine. The video generation engine then creates frames that reproduce the movements of the game in real time.

[0637] Step 5:

[0638] (server)

[0639] The generated video data is sent to the terminal. The server compresses the generated video data and sends it to the user's terminal via the Internet. At this time, an appropriate compression algorithm is used to avoid data loss.

[0640] Step 6:

[0641] (Terminal)

[0642] The device receives the video data sent from the server and displays it on the screen. By watching this video, users can intuitively understand the progress of the simulated game. The device also provides functions such as playing, pausing, and rewinding the video in response to user operations.

[0643] Step 7:

[0644] (server)

[0645] Tactical plans are proposed based on the results of the match. The server uses a generative AI model to generate tens of millions of tactical plans and evaluates the success rate of each plan. The plan with the highest success rate is selected and provided as a concrete tactical proposal for the next match.

[0646] Step 8:

[0647] (Terminal)

[0648] The proposed tactical plan is received and displayed to the user along with a detailed explanation. Managers and coaches can use this information to develop specific strategies for the next game. The device also provides an interface for users to modify tactical plans or add new plans.

[0649] Step 9:

[0650] (Terminal)

[0651] The device uses the user's camera and microphone to input the user's facial expressions and voice into the emotion engine, which then analyzes this data and recognizes the user's emotional state (happiness, surprise, excitement, etc.).

[0652] Step 10:

[0653] (server)

[0654] The server receives the recognized emotion data. Based on this data, the server dynamically changes the video content and tactical plan. For example, if the user is nervous, the simulation video will be more detailed and the tactical plan will be explained more carefully.

[0655] Step 11:

[0656] (Terminal)

[0657] The dynamically changed video and tactical plan are received again from the server and provided to the user, who can then use this information to more specifically determine the strategy for the next match.

[0658] Step 12:

[0659] (User)

[0660] Managers and coaches can view the footage, review the proposed tactical plan, and, if necessary, revise the plan to determine the optimal strategy. Through this system, managers and coaches can intuitively understand the development of the game and devise the optimal tactics.

[0661] Through these steps, the system will help managers, coaches, and even sports lottery users to plan specific strategies for the next game, which will have a positive impact on the outcome of the game.

[0662] Example 2

[0663] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0664] Conventional match analysis systems mainly perform simple statistical analysis based on past match data, and have limited functionality for simulating future matches in real time and visually displaying the results. Furthermore, they do not provide personalized tactical suggestions that take into account the user's emotions, limiting their efficiency and effectiveness in match preparation.

[0665] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0666] In this invention, the server includes means for collecting past match data, means for analyzing the collected data, means for preprocessing the analyzed data, means for inputting the preprocessed data into a generative AI model to simulate future matches, means for organizing the simulation results in JSON format, means for generating video based on the simulation results, means for recognizing user emotions, means for dynamically changing the video content and tactical plans based on the recognized emotion data, and means for proposing tactical plans based on the simulation results, thereby enabling specific and detailed match simulations and personalized tactical proposals.

[0667] "Past match data" refers to historical data such as match results, statistical information, and tactical data of players and teams in a particular sporting event.

[0668] "Means of collection" refers to the functions and methods for obtaining the necessary information from external APIs or databases and storing it in the system.

[0669] "Means of analysis" refers to the functions and methods of analyzing collected data using statistical or machine learning techniques and extracting useful information.

[0670] "Preprocessing means" refers to processes such as data cleaning and normalization to convert the analyzed data into a format that is easy for the generative AI model to understand.

[0671] A "generative AI model" is an artificial intelligence model that learns from past data and is used to predict future events and outcomes.

[0672] "Means to simulate" refers to functions and methods for virtually recreating future match situations and outcomes using generative AI models.

[0673] "JSON format" is an abbreviation for JavaScript Object Notation, and is a standard format for describing data structures flexibly and simply.

[0674] "Means for generating images" refers to a function or method for creating image data for visually displaying player movements and game situations based on simulation results.

[0675] "Means for recognizing user emotions" refers to a function or method for analyzing the user's facial expressions and voice data obtained from sensors such as cameras and microphones, and determining their emotional state.

[0676] "Means for dynamic change" refers to functions and methods for adjusting video content and tactical plans in real time based on the user's emotional data.

[0677] "Means for proposing tactical plans" refers to functions and methods for proposing optimal strategies and formations based on simulation and analysis results.

[0678] The present invention is a system that collects and analyzes past match data, simulates future matches, visualizes the results, and proposes tactical plans. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it is possible to provide optimal images and tactical plans for each individual user. Specific embodiments of this system are described below.

[0679] 1. Collection and analysis of past match data

[0680] (server)

[0681] The server uses external APIs to collect past game data, such as a sports league's API, to retrieve game data for specific teams and players. This data is stored in a database on the server in JSON or CSV format.

[0682] The server then retrieves the stored match data from the database and analyzes it. This analysis includes player movement patterns on the field, scoring patterns, and transitional behavior between offense and defense. The analyzed data is then preprocessed into a format suitable for the generative AI model. This preprocessing includes normalizing the numerical data and filling in missing data.

[0683] 2. Simulating future matches

[0684] (server)

[0685] The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past match data to predict the game's development and outcome. This prediction includes the movements of each player, ball movement, and goal timing. The simulation results are organized in JSON format and used for visualization at a later stage.

[0686] 3. Visualization of simulation results

[0687] (server)

[0688] The server uses the simulation results to create data for visualizing the movements of players and the ball. Specifically, it organizes each player's position data and ball movement data along a timeline and inputs it into a video generation engine (e.g., Unity or Unreal Engine). The video generation engine uses this data to create frames that reproduce the action of the game in real time. The generated video data is then further compressed and sent to the user's device.

[0689] 4. Tactical suggestion function

[0690] (server)

[0691] The server uses a generative AI model to generate tens of millions of tactical plans. These plans are evaluated based on simulation results, and the plan with the highest win rate is selected. The selected tactical plan is presented to the manager or coach as a specific tactical proposal. This proposal may include specific position changes, attacking patterns, defensive plans, etc.

[0692] 5. Emotion recognition function

[0693] (Terminal)

[0694] The device uses the user's camera and microphone to input the user's facial expressions and voice data into the emotion engine. The emotion engine analyzes this data in real time and recognizes the user's emotional state (happiness, surprise, excitement, etc.). The recognized emotion data is sent to the server, which dynamically changes the video content and tactical plan based on this data. For example, if the user is nervous, the server can provide detailed simulation video and change the tactical plan to be more specific.

[0695] Specific examples

[0696] For example, when a soccer team manager is planning a strategy for the next game, he or she will use the system in the following steps.

[0697] First, the server collects past match data and tactical data via an API, analyzes it, and inputs it into the generative AI model. Next, the server runs a simulation of a future match and visualizes the results. The visualized simulation results are then sent to the manager's device. Furthermore, the server recognizes the manager's emotions through the device's camera and microphone and adjusts the corresponding tactical plan. For example, if the manager is very nervous, the simulation video will be more detailed and specific tactical plans will be proposed, allowing the manager to select the optimal tactical strategy.

[0698] Here are some example prompts to input to a generative AI model:

[0699] "Using match data from the past three years for a specific team, simulate the optimal tactical plan for the next match. If the user is nervous, provide specific tactical suggestions to help them cope."

[0700] Using such prompts, the generative AI model can suggest specific and useful tactics.

[0701] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0702] A detailed explanation of the program processing of this system

[0703] Processing Steps

[0704] Step 1: Collect past match data

[0705] (server)

[0706] Input: The server sends an API request to an external data provider.

[0707] Data processing / calculation: Receive match data returned from the API and extract necessary items (e.g., player statistics, match results, tactical data). Convert the data format to JSON or CSV.

[0708] Output: Collected data is saved in a database on the server.

[0709] Specific operation: The server calls the sports league API and specifies parameters such as "team_id" and "match_date" to retrieve match data from the past three years.

[0710] Step 2: Data extraction and preprocessing

[0711] (server)

[0712] Input: Saved match data from database.

[0713] Data processing / calculation: Analyze the data and extract detailed information such as player movements, number of goals, and possession. Fill in missing data, normalize the data, and preprocess it into a format that can be input into a generative AI model.

[0714] Output: The preprocessed dataset.

[0715] Specific operation: The server processes the data using the Pandas library, filling in missing data and standardizing it.

[0716] Step 3: Generate data to input to the AI ​​model

[0717] (server)

[0718] Input: Preprocessed data.

[0719] Data processing / computation: Input data into a generative AI model (e.g., a PyTorch model) and run inference on the model, which results in simulated results for future matches.

[0720] Output: Predicted data as a simulation result.

[0721] How it works: The server reads the pre-processed data and feeds it into a generative AI model that makes predictions using the arrow method and regression analysis.

[0722] Step 4: Organizing the simulation results

[0723] (server)

[0724] Input: Simulation results from a generative AI model.

[0725] Data processing / calculation: Organize the simulation results along the time axis and convert them into JSON format.

[0726] Output: Simulation result data in JSON format.

[0727] Specific operation: The server reads the model output, organizes player position data and ball movement data in chronological order, and converts them into JSON format.

[0728] Step 5: Inputting data into the image generation engine

[0729] (server)

[0730] Input: Simulation result data in JSON format.

[0731] Data processing / calculation: Input data into a video generation engine (Unity or Unreal Engine) to generate video of the virtual match.

[0732] Output: Frame data that recreates the action of the match.

[0733] Specific operation: The server reads the JSON data and passes it to the image generation engine script to generate real-time images.

[0734] Step 6: Compress and transmit the video data

[0735] (server)

[0736] Input: The generated frame data.

[0737] Data processing / calculation: Data size is optimized using a compression algorithm and sent to the user's device.

[0738] Output: Compressed video data.

[0739] Specific operation: The server applies a compression algorithm such as H.264 and sends the data to the terminal via the Internet.

[0740] Step 7: Generate and evaluate a tactical plan

[0741] (server)

[0742] Input: Simulation results obtained from a generative AI model.

[0743] Data processing / calculation: Simulating different tactical plans, evaluating them and selecting the best plan.

[0744] Output: Optimal tactical plan.

[0745] What it does: The server simulates multiple tactical scenarios and applies algorithms to evaluate the success rate and effectiveness of each scenario.

[0746] Step 8: Recognizing User Emotions

[0747] (Terminal)

[0748] Input: Emotion data from the user's camera or microphone.

[0749] Data processing / calculation: The emotion engine analyzes this data and determines the user's emotional state from their facial expressions and voice.

[0750] Output: Recognized emotion data.

[0751] How it works: The device uses software to capture the user's facial expressions and voice through a camera and microphone and analyzes them in real time.

[0752] Step 9: Dynamically change the visuals and tactical plans with emotional data

[0753] (server)

[0754] Input: Recognized emotion data and simulation results.

[0755] Data processing / calculation: Apply algorithms that dynamically change video content and tactical plans based on emotional data.

[0756] Output: Dynamically modified footage and tactical plans.

[0757] Specific actions: The server analyzes the emotional data and adjusts the level of detail in the video or makes the tactical plan more specific depending on the user's level of tension.

[0758] The above is a specific description of each processing step in this system.

[0759] (Application example 2)

[0760] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0761] While conventional match data analysis systems can analyze past match data and simulate future matches, they are unable to propose tactical plans that take the user's emotions into account, making it difficult to provide optimal information to each individual user. Furthermore, users have difficulty visually grasping the flow of the match, making it difficult for them to intuitively understand the effectiveness of tactical plans.

[0762] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0763] In this invention, the server includes means for collecting past match data, means for analyzing the collected data, means for simulating future matches, means for visualizing the simulation results, means for proposing a tactical plan based on the match results, and means for recognizing the user's emotions and dynamically changing the images and tactical plan based on the emotion data, thereby enabling the proposal of an optimized tactical plan for each user and enabling the user to visually and intuitively grasp the flow of the match.

[0764] Key Word Definitions

[0765] "Past match data" is recorded data relating to matches played in the past, and includes details such as player movements, scores, and tactical patterns.

[0766] "Means of collection" refers to the technical methods and devices used to collect the required data through external APIs and databases.

[0767] "Means of analysis" refers to technical methods or devices that preprocess collected data, extract useful information from the data, and further analyze it using statistical techniques or machine learning models.

[0768] "Means for simulating" refers to technical methods or devices that virtually reproduce the development of a future match based on analyzed data.

[0769] "Visualization means" refers to technical methods and devices that visually display the simulation results and generate video data that reproduces the movements of the game.

[0770] The "means for proposing a tactical plan" refers to a technical method or device that generates an optimal tactical plan based on simulation results and past match data and presents it to the user.

[0771] "Means for recognizing emotions" refers to technical methods or devices that analyze a user's facial expressions and voice data to identify the user's emotional state.

[0772] "Dynamic modification means" refers to technical methods or devices that modify the content of video or tactical plans in real time based on recognized emotion data.

[0773] MODE FOR CARRYING OUT THE INVENTION

[0774] This system collects and analyzes past match data, simulates future matches, visualizes the results, and proposes tactical plans. Furthermore, by incorporating an emotion engine, it recognizes the user's emotions and provides optimal images and tactical plans for each individual user.

[0775] 1. Collection and analysis of past match data

[0776] (server)

[0777] The server uses an external API to collect past match data. This API retrieves match data for specific teams and players and stores it in a database within the server. The server then extracts the stored tactical data and player stats from the database. The server analyzes this data and preprocesses it into a format that can be understood by the generative AI model.

[0778] 2. Simulating future matches

[0779] (server)

[0780] The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past data to predict each player's movements and virtually recreate the flow and outcome of the match. The simulation results are organized in JSON format and passed to the subsequent visualization process.

[0781] 3. Visualization of simulation results

[0782] (server)

[0783] The server creates data to visualize the movements of players and the ball based on the simulation results. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into a video generation engine. The video generation engine creates frames that reproduce the action of the game in real time. To send the generated video data to the terminal, the server compresses the video data and sends it to the user's terminal via the Internet.

[0784] 4. Tactical suggestion function

[0785] (server)

[0786] The server uses a generative AI model to generate tens of millions of tactical plans. It then evaluates these plans and selects the one with the highest winning rate. The selected optimal tactical plan is then proposed to the manager or coach as a concrete tactical proposal.

[0787] 5. Emotion recognition function

[0788] (Terminal)

[0789] The device uses the user's camera and microphone to input the user's facial expressions and voice into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (happiness, surprise, excitement, etc.). The recognized emotion data is sent to the server, which then dynamically changes the video content and tactical plan based on this data.

[0790] Specific examples

[0791] For example, when a soccer team's coach plans a strategy for the next match, he collects and analyzes past match data and tactical data via an API. The results are then input into a generative AI model to simulate future matches. The simulation results are visualized and provided to the coach via a device. Furthermore, an emotion engine recognizes the coach's emotions. For example, if the coach is very nervous, the simulation video becomes more detailed and the proposed tactical plan becomes more specific. This allows the coach to intuitively understand the game's development and select the optimal tactical strategy. Furthermore, the emotion engine recognizes the players' reactions and adjusts the proposed tactics to increase players' motivation, resulting in a more effective tactical plan.

[0792] Prompt Sentence Examples

[0793] "Use a virtual tactical assistant to analyze past match data and simulate future matches. Use emotion recognition to suggest optimal tactical plans based on the user's emotions."

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

[0795] Program processing flow

[0796] Processing Steps

[0797] Step 1:

[0798] The server uses an external API to collect past match data. Specifically, it sends an API request to obtain match data for specific teams and players (e.g., player movements, scores, tactical patterns, etc.). This data is stored in a database within the server. The input is the response data from the API, and the output is the stored match data.

[0799] Step 2:

[0800] The server extracts stored tactical data and player stats from the database and analyzes them. Specifically, it preprocesses the data and converts it into a format that can be understood by the generative AI model. The input is the extracted data from the database, and the output is the preprocessed data.

[0801] Step 3:

[0802] The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and virtually recreate the flow and outcome of the match. The input is preprocessed data, and the output is the simulation results in JSON format.

[0803] Step 4:

[0804] The server creates data to visualize the movements of players and the ball based on the simulation results. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into the image generation engine. The image generation engine creates frames that reproduce the action of the game in real time. The input is the simulation result data, and the output is visualized match data.

[0805] Step 5:

[0806] The server transmits the generated video data to the terminal. Specifically, it compresses the video data and transmits it to the user's terminal via the Internet. The input is the visualized match data, and the output is the data delivered to the user's terminal.

[0807] Step 6:

[0808] The device uses the user's camera and microphone to input the user's facial expressions and voice data into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, surprise, excitement, etc.). The input is raw data obtained from the camera and microphone, and the output is analyzed emotion data.

[0809] Step 7:

[0810] The server dynamically changes the video content and tactical plan based on the recognized emotion data. Specifically, it generates an optimal tactical plan corresponding to the user's emotion and updates the video and plan content. The input is the emotion data and the initial video and tactical plan, and the output is the updated video and tactical plan.

[0811] Step 8:

[0812] The server uses a generative AI model to generate tens of millions of tactical plans, evaluates them, and selects the plan with the highest winning rate. The selected optimal tactical plan is then proposed to the manager or coach as a specific tactical proposal. The input is past match data and simulation results, and the output is the optimal tactical plan.

[0813] Prompt Sentence Examples

[0814] "Use a virtual tactical assistant to analyze past match data and simulate future matches. Use emotion recognition to suggest optimal tactical plans based on the user's emotions."

[0815] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0816] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0817] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0818] [Third embodiment]

[0819] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0820] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0821] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0822] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0823] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0824] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0825] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0826] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0827] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0828] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0829] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0830] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0831] The present invention is a system that collects and analyzes data from past sports matches, simulates future matches, visualizes the results, and proposes tactical plans. A specific embodiment of this system is described below.

[0832] 1. Collection and analysis of past match data

[0833] (server)

[0834] 1. The server collects past match data using an external API. For example, it calls an API to obtain match data for a specific team or player, and stores the data obtained in response within the server.

[0835] 2. The server then extracts stored tactical data and player stats from the database, parses this data, and pre-processes it into a format that the generative AI model can understand.

[0836] 2. Simulating future matches

[0837] (server)

[0838] 1. The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model then predicts each player's movements based on past data and virtually recreates the flow and outcome of the match.

[0839] 2. The simulation results are organized in JSON format and passed to the subsequent visualization process.

[0840] 3. Visualization of simulation results

[0841] (server)

[0842] 1. The server builds data to visualize the movements of players and the ball based on the simulation results. This data includes the positions of players, the ball, and the passage of time.

[0843] 2. The obtained data is used by the image generation engine to generate a visual image of the match. This image realistically reproduces the action of the match and is output in a format that is easy for users to understand.

[0844] 4. Tactical suggestion function

[0845] (server)

[0846] 1. The server uses a generative AI model to generate tens of millions of tactical plans. The system evaluates these plans and selects the one with the highest probability of winning.

[0847] 2. The selected optimal tactical plan is proposed to the manager or coach as a specific tactical proposal.

[0848] 5. User Interface

[0849] (Terminal)

[0850] 1. The device receives the video data and tactical plan sent from the server. The video is played on the device screen, allowing the manager or coach to intuitively understand the progress of the game.

[0851] 2. The tactical plan is displayed with detailed explanations and serves as a reference for the user to decide on specific next moves.

[0852] Specific examples

[0853] For example, when a soccer team's manager is planning a strategy for the next match, he collects and analyzes past match data and tactical data via an API. The results are then input into a generative AI model to simulate future matches. The simulation results are visualized and provided to the manager via a device. The generative AI model then proposes an optimal tactical plan to improve the manager's chances of winning the next match. This allows the manager to intuitively understand the game's development and select the optimal tactical strategy.

[0854] In this way, this system will make it easier for managers and coaches to plan specific strategies for matches, which will have a positive impact on the outcome of the match.

[0855] The processing flow will be explained below.

[0856] Step 1:

[0857] (server)

[0858] The server first calls an external API to collect past match data. This API retrieves match data for specific teams and players and stores it in a database within the server. For example, to retrieve soccer match data, an API endpoint such as https: / / sportsdata.api / teams / teamA / matches is called.

[0859] Step 2:

[0860] (server)

[0861] To analyze the collected data, the server extracts tactical data and player stats from the database. This data is obtained, for example, using SQL queries. Since the obtained data is difficult for the generative AI model to understand as it is, preprocessing involves cleaning, normalizing, and extracting features from the data.

[0862] Step 3:

[0863] (server)

[0864] The server inputs the preprocessed data into a generative AI model to simulate future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and the flow of the match. The simulation results are organized by each phase of the match and output in JSON format.

[0865] Step 4:

[0866] (server)

[0867] The server uses the simulation results to create data for visualizing the movements of players and the ball. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into a video generation engine. This video generation engine then creates frames that reproduce the action of the game in real time.

[0868] Step 5:

[0869] (server)

[0870] The generated video data is sent to the terminal. The server compresses the generated video data and sends it to the user's terminal via the Internet. At this time, an appropriate compression algorithm is used to avoid data loss.

[0871] Step 6:

[0872] (Terminal)

[0873] The device receives the video data sent from the server and displays it on the screen. By watching this video, users can intuitively understand the simulated game progress. The device also provides functions such as playing, pausing, and rewinding the video in response to user operations.

[0874] Step 7:

[0875] (server)

[0876] The server proposes tactical plans based on the results of the match. It uses a generative AI model to generate tens of millions of tactical plans and evaluates the success rate of each plan. The plan with the highest success rate is selected and provided as a concrete tactical proposal for the next match.

[0877] Step 8:

[0878] (Terminal)

[0879] The device receives the proposed tactical plan and displays it to the user along with a detailed explanation. Managers and coaches can use this information to develop specific strategies for the next game. The device also provides an interface for users to modify the tactical plan or add new plans.

[0880] Step 9:

[0881] (User)

[0882] Users watch the video and review the proposed tactical plan. They can then modify the plan as necessary and decide on the final strategy for the next match. Through this system, managers and coaches can intuitively understand the development of the game and plan the optimal tactical plan.

[0883] Through these steps, the system helps managers, coaches, and even sports lottery users to plan specific strategies for the next game.

[0884] Example 1

[0885] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0886] Conventional tactical planning support systems for sports games only allow users to view past game data, and are therefore inadequate in predicting future game results and proposing specific tactical plans. Furthermore, there is no way to provide simulation results in a visually easy-to-understand format, making it difficult for managers and coaches to intuitively understand and formulate countermeasures.

[0887] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0888] In this invention, the server includes means for collecting past game data, means for analyzing and preprocessing the collected data, means for simulating future games using the preprocessed data, means for formatting the simulation results in JSON format, means for generating images based on the formatted data, means for generating and evaluating tactical plans based on game results, and means for proposing the evaluated tactical plans. This enables managers and coaches to predict future game results in detail, intuitively and easily understand optimal tactical plans, and take countermeasures.

[0889] "Past match data" refers to past results of sports matches, player statistics, tactical data, etc.

[0890] "Means of collection" refers to the methods and systems used to obtain the necessary data from external APIs and databases.

[0891] "Analysis and preprocessing means" refers to methods and systems that remove outliers from collected data, normalize the data, and prepare the data in a format that can be used by generative AI models.

[0892] "Simulating means" refers to a method or system that uses a generative AI model based on pre-processed data to virtually predict the course and outcome of future matches.

[0893] "Means for formatting in JSON format" refers to a method or system for formatting simulation results into JSON (JavaScript Object Notation), a standardized data format, and passing them to the next processing step.

[0894] "Means for generating images" refers to a method or system that uses an image generation engine based on simulation results to visually reproduce a match.

[0895] "Means for generating and evaluating tactical plans" refers to a method or system that uses a generative AI model to generate multiple tactical plans, simulate the effects of each, and select the optimal plan.

[0896] "Means for proposing tactical plans" refers to a method or system for providing the manager or coach with the evaluated optimal tactical plan in a concrete and easily understandable format.

[0897] The present invention is a system that collects and analyzes data from past sports matches, simulates future matches, visualizes the results, and proposes tactical plans. A specific embodiment of this system is described below.

[0898] The server uses external APIs to collect past game data. Specifically, it obtains game data related to specific teams and players from external APIs such as sports data provider APIs. For example, to collect NBA game data, it obtains the data using the API request " / api / v1 / games?team_id=1234" and stores the JSON-formatted data obtained as a response in the database.

[0899] The server then analyzes and pre-processes the stored match data from the database, including data extraction, outlier removal, and data normalization, such as extracting player positions and stats (e.g., shots, passes, and ball possession time) and formatting them in a format that can be used by the generative AI model.

[0900] The server then inputs the preprocessed data into a generative AI model to simulate future matches. The generative AI model predicts player movements based on past data and virtually recreates the flow and outcome of the match. The simulation results are organized in JSON format and passed to the next process.

[0901] The server uses the simulation results to build data for visualizing player and ball movements. This data includes player positions, ball position, and time progression. It then uses a video generation engine (e.g., Unity or Unreal Engine) to generate a visual image of the match. This image realistically reproduces the action of the match and is output in a format that is easy for users to understand.

[0902] The server also uses a generative AI model to generate millions of tactical plans. These plans are evaluated and the plan with the highest potential for winning is selected. The optimal plan is then proposed to the manager or coach as a concrete tactical proposal.

[0903] The device receives the video data and tactical plan sent from the server. The video is played on the device screen, allowing managers and coaches to intuitively understand the game's progress. The tactical plan is also displayed with detailed explanations, providing reference information for users to specifically and efficiently decide their next move.

[0904] To give a specific example, when a soccer team's coach plans a strategy for the next match, the server collects and analyzes past match data and tactical data via an API. This data is input into a generative AI model to simulate future matches. The simulation results are organized into a primary JSON format and generated as realistic match footage using a video generation engine. The generative AI model then generates an optimal tactical plan to improve the team's chances of winning the next match and proposes it to the coach. The coach can then view the footage and tactical plan on their device and issue instructions to their players.

[0905] An example prompt is, "This system collects past match data, simulates and visualizes future matches, and proposes optimal tactical plans. Please propose effective tactics for a specific team for the next match."

[0906] In this way, this system will make it easier for managers and coaches to plan specific strategies for matches, which will have a positive impact on the outcome of the match.

[0907] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0908] Processing Steps:

[0909] Step 1: Collect past match data

[0910] server

[0911] The server sends a request to an external API (e.g., a sports data provider API). Specifically, it uses an API endpoint to retrieve past game data for a specific team or player. The input is the API request, and the output is the game data in JSON format. For example, the request " / api / v1 / games?team_id=1234" is sent, and the resulting data is stored in the database.

[0912] Specific behavior:

[0913] 1. The server sends an API request.

[0914] 2. The obtained JSON format match data is stored in a database.

[0915] Step 2: Analysis and preprocessing of match data

[0916] server

[0917] The server analyzes and preprocesses the match data stored in the database. The input is past match data, and the output is the preprocessed data. Specifically, it extracts player position information and stats, removes outliers, and normalizes the data. For example, it organizes stats such as the number of shots, number of passes, and ball possession time of players.

[0918] Specific behavior:

[0919] 1. The server extracts the match data from the database.

[0920] 2. Remove outliers and impute missing values.

[0921] 3. Normalize the data and convert it into a format suitable for generative AI models.

[0922] Step 3: Run the simulation

[0923] server

[0924] The server inputs the preprocessed data into a generative AI model to simulate future matches. The input is the preprocessed data, and the output is the simulation results in JSON format. The generative AI model predicts player movements based on past data and virtually recreates the flow and outcome of the match.

[0925] Specific behavior:

[0926] 1. The server inputs preprocessed data into the generative AI model.

[0927] 2. A generative AI model simulates the flow of the game.

[0928] 3. Output the simulation results in JSON format.

[0929] Step 4: Formatting the simulation results

[0930] server

[0931] The server formats the simulation results obtained from the generative AI model and extracts the data necessary for the next visualization process. The input is the JSON data of the simulation results, and the output is the data for video generation. For example, this includes information such as player positions, ball position, and time lapse.

[0932] Specific behavior:

[0933] 1. The server receives the simulation results.

[0934] 2. Organize the necessary data (e.g., player positions by time, ball position).

[0935] 3. Pass the formatted data to the next process.

[0936] Step 5: Visualization process

[0937] server

[0938] The server uses a video generation engine based on the formatted data to generate video of the match. The input is the formatted data, and the output is the match video. The video reproduces the movements of the players and the ball in real time.

[0939] Specific behavior:

[0940] 1. The server launches the video generation engine (e.g., Unity, Unreal Engine).

[0941] 2. Read the formatted data and render it as an image.

[0942] 3. Prepare the generated video in file storage or streaming format.

[0943] Step 6: Generate and evaluate a tactical plan

[0944] server

[0945] The server uses a generative AI model to generate multiple tactical plans and evaluates the effectiveness of each through simulation. The input is preprocessed data and simulation conditions, and the output is the optimal tactical plan. The system evaluates these tactical plans and selects the one with the highest probability of winning.

[0946] Specific behavior:

[0947] 1. The server inputs prompts to generate a tactical plan into the generative AI model.

[0948] 2. Evaluate the generated tactical plan.

[0949] 3. Select the most effective tactical plan and develop detailed information.

[0950] Step 7: Sending data to the user interface

[0951] Terminal

[0952] The terminal receives the video data and tactical plans sent from the server and provides them to the manager or coach. The input is the video data and tactical plans from the server, and the output is information displayed in a format that is easy for the user to understand.

[0953] Specific behavior:

[0954] 1. The device retrieves video data and tactical plans from the server.

[0955] 2. Play video in real time or on demand.

[0956] 3. Display details of the tactical plan to allow users (managers and coaches) to take countermeasures.

[0957] (Application example 1)

[0958] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0959] Conventional sports game analysis and tactical planning systems are limited in their ability to collect and analyze past game data, limiting their ability to predict future game developments and propose tactical plans. Furthermore, the visualization of game simulations and proposed tactical plans are not provided in an intuitively understandable format, making it difficult for users to understand and apply them. Therefore, there is a need for a system that can consistently provide more accurate game predictions, realistic and intuitive visualization, and optimal tactical plans.

[0960] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0961] In this invention, the server includes a means for collecting past match data, a means for analyzing the collected data, a means for evaluating tactical plans using a generative AI model and selecting an optimal plan, and a means for presenting images and tactical plans through a user interface, thereby making it possible to provide highly accurate simulation results and optimal tactical plans in an intuitively easy-to-understand format.

[0962] "Past match data" refers to information about past matches in a particular sport, including player movements, match results, tactical data, and the like.

[0963] "Means of collection" refers to the methods and systems for obtaining data from external APIs, etc. and storing it on a server.

[0964] "Means of analysis" refers to the algorithms and programs used to organize collected data and convert it into meaningful information.

[0965] "Means to simulate future matches" refers to systems and algorithms that use past match data and analysis results to predict how future matches will play out.

[0966] "Means for visualizing simulation results" refers to technologies and tools that visually represent the results of a simulation and output them in a form that is easy for users to understand.

[0967] "Means for proposing tactical plans" refers to a method for generating optimal strategies and tactics based on the results of a match simulation and presenting them to the user.

[0968] A "generative AI model" refers to an artificial intelligence model based on deep learning that is used for purposes such as prediction, analysis, and suggestions.

[0969] "User interface" refers to the parts that users directly touch, such as the screen and operation methods used to exchange information between the system and the user.

[0970] This invention is a system that collects and analyzes past match data, simulates and visualizes future matches, and proposes tactical plans. The main elements of this system and their functions are explained in detail below.

[0971] The server first uses external APIs to collect past match data, including match data for specific sports teams and players, which is then stored in the server's database. The stored data is then analyzed and preprocessed into a format that can be understood by the generative AI model. This analysis includes player movement and tactical data, and the data is then properly organized before proceeding to the next processing stage.

[0972] The server inputs the preprocessed data into a generative AI model (such as OpenAI GPT-4 or Stable Diffusion) and runs a simulation to predict future matches. The simulation predicts each player's movements based on past data and recreates the flow and results of the match. The simulation results are organized in JSON format and passed to the visualization process.

[0973] The visualization process, based on the simulation results, builds data such as player positions, ball positions, and time progression. This data is then used to generate visual images using a video generation engine such as Unity or Unreal Engine. This video realistically reproduces the action of the match and is provided to users.

[0974] The tactical suggestion feature uses a generative AI model to generate tens of millions of tactical plans, which the system then evaluates to select the plan with the highest potential for winning. The selected plan is then suggested to the manager or coach, along with a detailed explanation.

[0975] The user interface displays the video data and tactical plans sent from the server on the device, allowing managers and coaches to intuitively understand the progress of the game. The tactical plans are also displayed with detailed explanations, so users can use them as reference information to decide on specific next moves.

[0976] As a concrete example, when a soccer team's manager is planning a strategy for the next match, he collects and analyzes past match data and tactical data via API. The results are input into a generative AI model, which simulates future matches. The simulation results are visualized and provided to the manager via a device. The generative AI model also proposes an optimal tactical plan to improve the team's chances of winning the next match.

[0977] An example of a prompt might be:

[0978] "For a match between Team A and Team B, simulate future game developments based on past data and propose the optimal tactical plan."

[0979] In this way, the system makes it easier for managers and coaches to plan specific strategies for matches, which can have a positive impact on the outcome of the match.

[0980] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0981] Step 1:

[0982] The server uses an external API to collect past match data. The input is a request to the external API, and the output is the retrieved match data. Specifically, the server hits a specific URL or endpoint and retrieves past match data in response. This data includes player location information, scores, tactical data, and more. For example, data is returned in JSON format from a sports data provider API.

[0983] Step 2:

[0984] The server stores the collected data in a database. The input is the acquired match data, and the output is the data stored in the database. Specifically, to insert the data for each match into the appropriate table, an SQL statement is generated and executed on the database (for example, MySQL or PostgreSQL). The database stores the match ID, player ID, and details of each play.

[0985] Step 3:

[0986] The server extracts the data to be analyzed from the database and preprocesses it into a format that the generative AI model can understand. The input is the match data extracted from the database, and the output is the preprocessed data. Specific operations include data cleanup (missing value processing, normalization) and format conversion (for example, conversion to CSV format). This prepares the data in a format that is easy to input into the AI ​​model.

[0987] Step 4:

[0988] The server inputs the preprocessed data into a generative AI model to simulate future matches. The input is the preprocessed data, and the output is the simulation results. Specifically, the server supplies data to a generative AI model (e.g., OpenAI GPT-4) to predict how the match will play out. At this time, the server simulates the movements of players and the progress of the match. The simulation results are organized in JSON format.

[0989] Step 5:

[0990] The server executes a visualization process based on the simulation results. The input is the simulation results, and the output is the game footage. Specifically, a video generation engine such as Unity or Unreal Engine is used to visually reproduce the movements of players and the ball. Data such as player positions, ball position, and time passage are used during this process.

[0991] Step 6:

[0992] The server sends the generated video data and tactical plan to the terminal. The input is the video data and tactical plan, and the output is the data sent to the terminal. Specifically, the server sends the video data and tactical plan via HTTP protocol to the terminal (e.g., a smartphone or head-mounted display) so that the user can view them.

[0993] Step 7:

[0994] The terminal displays the received video data and tactical plan. The input is the transmitted video data and tactical plan, and the output is a visual display provided to the user. Specifically, the terminal plays the video on its display and displays the tactical plan in text and graph format. The user can view this to confirm the game development and tactical proposals.

[0995] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0996] The present invention is a system that collects and analyzes past match data, simulates future matches, visualizes the results, and proposes tactical plans. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it is possible to provide optimal images and tactical plans for each individual user. A specific embodiment of this system is described below.

[0997] 1. Collection and analysis of past match data

[0998] (server)

[0999] 1. The server collects past match data using an external API. This API retrieves match data for specific teams and players and stores it in a database within the server.

[1000] 2. Next, the server extracts stored tactical data and player stats from the database. The server then analyzes this data and preprocesses it into a format that can be understood by the generative AI model.

[1001] 2. Simulating future matches

[1002] (server)

[1003] 1. The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and virtually recreate the flow and outcome of the match.

[1004] 2. The simulation results are organized in JSON format and passed to the subsequent visualization process.

[1005] 3. Visualization of simulation results

[1006] (server)

[1007] 1. The server creates data to visualize the movements of players and the ball based on the simulation results. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into the image generation engine. The image generation engine then creates frames that reproduce the action of the game in real time.

[1008] 2. The generated video data is sent to the terminal. The server compresses the generated video data and sends it to the user's terminal via the Internet.

[1009] 4. Tactical suggestion function

[1010] (server)

[1011] 1. The server uses a generative AI model to generate tens of millions of tactical plans. The system evaluates these plans and selects the plan with the highest probability of winning.

[1012] 2. The selected optimal tactical plan is proposed to the manager or coach as a specific tactical proposal.

[1013] 5. Emotion recognition function

[1014] (Terminal)

[1015] 1. The device uses the user's camera and microphone to input the user's facial expressions and voice into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (happiness, surprise, excitement, etc.).

[1016] 2. The recognized emotion data is sent to the server, which then dynamically changes the video content and tactical plan based on this data.

[1017] Specific examples

[1018] For example, when a soccer team's manager is planning strategies for the next match, he collects and analyzes past match data and tactical data via API. The results are then input into a generative AI model to simulate future matches. The simulation results are visualized and provided to the manager via a device.

[1019] Furthermore, the emotion engine recognizes the manager's emotions, and if the manager is feeling very nervous, for example, it will make the simulation video more detailed and suggest more specific tactical plans, allowing the manager to intuitively understand the progress of the game and select the optimal tactics.

[1020] In addition, the emotion engine recognizes the player's reactions and adjusts the tactics it suggests to increase the player's motivation, resulting in a more effective tactical plan.

[1021] In this way, this system will make it easier for managers, coaches, and even sports lottery users to plan specific strategies for matches, which will have a positive impact on the outcome of the match.

[1022] The processing flow will be explained below.

[1023] Step 1:

[1024] (server)

[1025] Use an external API to collect past match data. The server calls this API endpoint (e.g., https: / / sportsdata.api / teams / teamA / matches) to retrieve match data for specific teams and players. The retrieved data is then stored in a database within the server.

[1026] Step 2:

[1027] (server)

[1028] The stored tactical data and player stats are extracted from the database. Specifically, SQL queries are used to extract the required data, which is then analyzed. During the analysis, pre-processing steps such as data cleaning, normalization, and feature extraction are performed.

[1029] Step 3:

[1030] (server)

[1031] The preprocessed data is input into a generative AI model to simulate future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and the flow of the match. The simulation results are organized by each phase of the match and output in JSON format.

[1032] Step 4:

[1033] (server)

[1034] Based on the simulation results, data is created to visualize the movements of players and the ball. Specifically, the position data of each player and the movement data of the ball are organized along a time axis and input into a video generation engine. The video generation engine then creates frames that reproduce the movements of the game in real time.

[1035] Step 5:

[1036] (server)

[1037] The generated video data is sent to the terminal. The server compresses the generated video data and sends it to the user's terminal via the Internet. At this time, an appropriate compression algorithm is used to avoid data loss.

[1038] Step 6:

[1039] (Terminal)

[1040] The device receives the video data sent from the server and displays it on the screen. By watching this video, users can intuitively understand the progress of the simulated game. The device also provides functions such as playing, pausing, and rewinding the video in response to user operations.

[1041] Step 7:

[1042] (server)

[1043] Tactical plans are proposed based on the results of the match. The server uses a generative AI model to generate tens of millions of tactical plans and evaluates the success rate of each plan. The plan with the highest success rate is selected and provided as a concrete tactical proposal for the next match.

[1044] Step 8:

[1045] (Terminal)

[1046] The proposed tactical plan is received and displayed to the user along with a detailed explanation. Managers and coaches can use this information to develop specific strategies for the next game. The device also provides an interface for users to modify tactical plans or add new plans.

[1047] Step 9:

[1048] (Terminal)

[1049] The device uses the user's camera and microphone to input the user's facial expressions and voice into the emotion engine, which then analyzes this data and recognizes the user's emotional state (happiness, surprise, excitement, etc.).

[1050] Step 10:

[1051] (server)

[1052] The server receives the recognized emotion data. Based on this data, the server dynamically changes the video content and tactical plan. For example, if the user is nervous, the simulation video will be more detailed and the tactical plan will be explained more carefully.

[1053] Step 11:

[1054] (Terminal)

[1055] The dynamically changed video and tactical plan are received again from the server and provided to the user, who can then use this information to more specifically determine the strategy for the next match.

[1056] Step 12:

[1057] (User)

[1058] Managers and coaches can view the footage, review the proposed tactical plan, and, if necessary, revise the plan to determine the optimal strategy. Through this system, managers and coaches can intuitively understand the development of the game and devise the optimal tactics.

[1059] Through these steps, the system will help managers, coaches, and even sports lottery users to plan specific strategies for the next game, which will have a positive impact on the outcome of the game.

[1060] Example 2

[1061] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1062] Conventional match analysis systems mainly perform simple statistical analysis based on past match data, and have limited functionality for simulating future matches in real time and visually displaying the results. Furthermore, they do not provide personalized tactical suggestions that take into account the user's emotions, limiting their efficiency and effectiveness in match preparation.

[1063] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1064] In this invention, the server includes means for collecting past match data, means for analyzing the collected data, means for preprocessing the analyzed data, means for inputting the preprocessed data into a generative AI model to simulate future matches, means for organizing the simulation results in JSON format, means for generating video based on the simulation results, means for recognizing user emotions, means for dynamically changing the video content and tactical plans based on the recognized emotion data, and means for proposing tactical plans based on the simulation results, thereby enabling specific and detailed match simulations and personalized tactical proposals.

[1065] "Past match data" refers to historical data such as match results, statistical information, and tactical data of players and teams in a particular sporting event.

[1066] "Means of collection" refers to the functions and methods for obtaining the necessary information from external APIs or databases and storing it in the system.

[1067] "Means of analysis" refers to the functions and methods of analyzing collected data using statistical or machine learning techniques and extracting useful information.

[1068] "Preprocessing means" refers to processes such as data cleaning and normalization to convert the analyzed data into a format that is easy for the generative AI model to understand.

[1069] A "generative AI model" is an artificial intelligence model that learns from past data and is used to predict future events and outcomes.

[1070] "Means to simulate" refers to functions and methods for virtually recreating future match situations and outcomes using generative AI models.

[1071] "JSON format" is an abbreviation for JavaScript Object Notation, and is a standard format for describing data structures flexibly and simply.

[1072] "Means for generating images" refers to a function or method for creating image data for visually displaying player movements and game situations based on simulation results.

[1073] "Means for recognizing user emotions" refers to a function or method for analyzing the user's facial expressions and voice data obtained from sensors such as cameras and microphones, and determining their emotional state.

[1074] "Means for dynamic change" refers to functions and methods for adjusting video content and tactical plans in real time based on the user's emotional data.

[1075] "Means for proposing tactical plans" refers to functions and methods for proposing optimal strategies and formations based on simulation and analysis results.

[1076] The present invention is a system that collects and analyzes past match data, simulates future matches, visualizes the results, and proposes tactical plans. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it is possible to provide optimal images and tactical plans for each individual user. Specific embodiments of this system are described below.

[1077] 1. Collection and analysis of past match data

[1078] (server)

[1079] The server uses external APIs to collect past game data, such as a sports league's API, to retrieve game data for specific teams and players. This data is stored in a database on the server in JSON or CSV format.

[1080] The server then retrieves the stored match data from the database and analyzes it. This analysis includes player movement patterns on the field, scoring patterns, and transitional behavior between offense and defense. The analyzed data is then preprocessed into a format suitable for the generative AI model. This preprocessing includes normalizing the numerical data and filling in missing data.

[1081] 2. Simulating future matches

[1082] (server)

[1083] The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past match data to predict the game's development and outcome. This prediction includes the movements of each player, ball movement, and goal timing. The simulation results are organized in JSON format and used for visualization at a later stage.

[1084] 3. Visualization of simulation results

[1085] (server)

[1086] The server uses the simulation results to create data for visualizing the movements of players and the ball. Specifically, it organizes each player's position data and ball movement data along a timeline and inputs it into a video generation engine (e.g., Unity or Unreal Engine). The video generation engine uses this data to create frames that reproduce the action of the game in real time. The generated video data is then further compressed and sent to the user's device.

[1087] 4. Tactical suggestion function

[1088] (server)

[1089] The server uses a generative AI model to generate tens of millions of tactical plans. These plans are evaluated based on simulation results, and the plan with the highest win rate is selected. The selected tactical plan is presented to the manager or coach as a specific tactical proposal. This proposal may include specific position changes, attacking patterns, defensive plans, etc.

[1090] 5. Emotion recognition function

[1091] (Terminal)

[1092] The device uses the user's camera and microphone to input the user's facial expressions and voice data into the emotion engine. The emotion engine analyzes this data in real time and recognizes the user's emotional state (happiness, surprise, excitement, etc.). The recognized emotion data is sent to the server, which dynamically changes the video content and tactical plan based on this data. For example, if the user is nervous, the server can provide detailed simulation video and change the tactical plan to be more specific.

[1093] Specific examples

[1094] For example, when a soccer team manager is planning a strategy for the next game, he or she will use the system in the following steps.

[1095] First, the server collects past match data and tactical data via an API, analyzes it, and inputs it into the generative AI model. Next, the server runs a simulation of a future match and visualizes the results. The visualized simulation results are then sent to the manager's device. Furthermore, the server recognizes the manager's emotions through the device's camera and microphone and adjusts the corresponding tactical plan. For example, if the manager is very nervous, the simulation video will be more detailed and specific tactical plans will be proposed, allowing the manager to select the optimal tactical strategy.

[1096] Here are some example prompts to input to a generative AI model:

[1097] "Using match data from the past three years for a specific team, simulate the optimal tactical plan for the next match. If the user is nervous, provide specific tactical suggestions to help them cope."

[1098] Using such prompts, the generative AI model can suggest specific and useful tactics.

[1099] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1100] A detailed explanation of the program processing of this system

[1101] Processing Steps

[1102] Step 1: Collect past match data

[1103] (server)

[1104] Input: The server sends an API request to an external data provider.

[1105] Data processing / calculation: Receive match data returned from the API and extract necessary items (e.g., player statistics, match results, tactical data). Convert the data format to JSON or CSV.

[1106] Output: Collected data is saved in a database on the server.

[1107] Specific operation: The server calls the sports league API and specifies parameters such as "team_id" and "match_date" to retrieve match data from the past three years.

[1108] Step 2: Data extraction and preprocessing

[1109] (server)

[1110] Input: Saved match data from database.

[1111] Data processing / calculation: Analyze the data and extract detailed information such as player movements, number of goals, and possession. Fill in missing data, normalize the data, and preprocess it into a format that can be input into a generative AI model.

[1112] Output: The preprocessed dataset.

[1113] Specific operation: The server processes the data using the Pandas library, filling in missing data and standardizing it.

[1114] Step 3: Generate data to input to the AI ​​model

[1115] (server)

[1116] Input: Preprocessed data.

[1117] Data processing / computation: Input data into a generative AI model (e.g., a PyTorch model) and run inference on the model, which results in simulated results for future matches.

[1118] Output: Predicted data as a simulation result.

[1119] How it works: The server reads the pre-processed data and feeds it into a generative AI model that makes predictions using the arrow method and regression analysis.

[1120] Step 4: Organizing the simulation results

[1121] (server)

[1122] Input: Simulation results from a generative AI model.

[1123] Data processing / calculation: Organize the simulation results along the time axis and convert them into JSON format.

[1124] Output: Simulation result data in JSON format.

[1125] Specific operation: The server reads the model output, organizes player position data and ball movement data in chronological order, and converts them into JSON format.

[1126] Step 5: Inputting data into the image generation engine

[1127] (server)

[1128] Input: Simulation result data in JSON format.

[1129] Data processing / calculation: Input data into a video generation engine (Unity or Unreal Engine) to generate video of the virtual match.

[1130] Output: Frame data that recreates the action of the match.

[1131] Specific operation: The server reads the JSON data and passes it to the image generation engine script to generate real-time images.

[1132] Step 6: Compress and transmit the video data

[1133] (server)

[1134] Input: The generated frame data.

[1135] Data processing / calculation: Data size is optimized using a compression algorithm and sent to the user's device.

[1136] Output: Compressed video data.

[1137] Specific operation: The server applies a compression algorithm such as H.264 and sends the data to the terminal via the Internet.

[1138] Step 7: Generate and evaluate a tactical plan

[1139] (server)

[1140] Input: Simulation results obtained from a generative AI model.

[1141] Data processing / calculation: Simulating different tactical plans, evaluating them and selecting the best plan.

[1142] Output: Optimal tactical plan.

[1143] What it does: The server simulates multiple tactical scenarios and applies algorithms to evaluate the success rate and effectiveness of each scenario.

[1144] Step 8: Recognizing User Emotions

[1145] (Terminal)

[1146] Input: Emotion data from the user's camera or microphone.

[1147] Data processing / calculation: The emotion engine analyzes this data and determines the user's emotional state from their facial expressions and voice.

[1148] Output: Recognized emotion data.

[1149] How it works: The device uses software to capture the user's facial expressions and voice through a camera and microphone and analyzes them in real time.

[1150] Step 9: Dynamically change the visuals and tactical plans with emotional data

[1151] (server)

[1152] Input: Recognized emotion data and simulation results.

[1153] Data processing / calculation: Apply algorithms that dynamically change video content and tactical plans based on emotional data.

[1154] Output: Dynamically modified footage and tactical plans.

[1155] Specific actions: The server analyzes the emotional data and adjusts the level of detail in the video or makes the tactical plan more specific depending on the user's level of tension.

[1156] The above is a specific description of each processing step in this system.

[1157] (Application example 2)

[1158] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1159] While conventional match data analysis systems can analyze past match data and simulate future matches, they are unable to propose tactical plans that take the user's emotions into account, making it difficult to provide optimal information to each individual user. Furthermore, users have difficulty visually grasping the flow of the match, making it difficult for them to intuitively understand the effectiveness of tactical plans.

[1160] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1161] In this invention, the server includes means for collecting past match data, means for analyzing the collected data, means for simulating future matches, means for visualizing the simulation results, means for proposing a tactical plan based on the match results, and means for recognizing the user's emotions and dynamically changing the images and tactical plan based on the emotion data, thereby enabling the proposal of an optimized tactical plan for each user and enabling the user to visually and intuitively grasp the flow of the match.

[1162] Key Word Definitions

[1163] "Past match data" is recorded data relating to matches played in the past, and includes details such as player movements, scores, and tactical patterns.

[1164] "Means of collection" refers to the technical methods and devices used to collect the required data through external APIs and databases.

[1165] "Means of analysis" refers to technical methods or devices that preprocess collected data, extract useful information from the data, and further analyze it using statistical techniques or machine learning models.

[1166] "Means for simulating" refers to technical methods or devices that virtually reproduce the development of a future match based on analyzed data.

[1167] "Visualization means" refers to technical methods and devices that visually display the simulation results and generate video data that reproduces the movements of the game.

[1168] The "means for proposing a tactical plan" refers to a technical method or device that generates an optimal tactical plan based on simulation results and past match data and presents it to the user.

[1169] "Means for recognizing emotions" refers to technical methods or devices that analyze a user's facial expressions and voice data to identify the user's emotional state.

[1170] "Dynamic modification means" refers to technical methods or devices that modify the content of video or tactical plans in real time based on recognized emotion data.

[1171] MODE FOR CARRYING OUT THE INVENTION

[1172] This system collects and analyzes past match data, simulates future matches, visualizes the results, and proposes tactical plans. Furthermore, by incorporating an emotion engine, it recognizes the user's emotions and provides optimal images and tactical plans for each individual user.

[1173] 1. Collection and analysis of past match data

[1174] (server)

[1175] The server uses an external API to collect past match data. This API retrieves match data for specific teams and players and stores it in a database within the server. The server then extracts the stored tactical data and player stats from the database. The server analyzes this data and preprocesses it into a format that can be understood by the generative AI model.

[1176] 2. Simulating future matches

[1177] (server)

[1178] The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past data to predict each player's movements and virtually recreate the flow and outcome of the match. The simulation results are organized in JSON format and passed to the subsequent visualization process.

[1179] 3. Visualization of simulation results

[1180] (server)

[1181] The server creates data to visualize the movements of players and the ball based on the simulation results. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into a video generation engine. The video generation engine creates frames that reproduce the action of the game in real time. To send the generated video data to the terminal, the server compresses the video data and sends it to the user's terminal via the Internet.

[1182] 4. Tactical suggestion function

[1183] (server)

[1184] The server uses a generative AI model to generate tens of millions of tactical plans. It then evaluates these plans and selects the one with the highest winning rate. The selected optimal tactical plan is then proposed to the manager or coach as a concrete tactical proposal.

[1185] 5. Emotion recognition function

[1186] (Terminal)

[1187] The device uses the user's camera and microphone to input the user's facial expressions and voice into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (happiness, surprise, excitement, etc.). The recognized emotion data is sent to the server, which then dynamically changes the video content and tactical plan based on this data.

[1188] Specific examples

[1189] For example, when a soccer team's coach plans a strategy for the next match, he collects and analyzes past match data and tactical data via an API. The results are then input into a generative AI model to simulate future matches. The simulation results are visualized and provided to the coach via a device. Furthermore, an emotion engine recognizes the coach's emotions. For example, if the coach is very nervous, the simulation video becomes more detailed and the proposed tactical plan becomes more specific. This allows the coach to intuitively understand the game's development and select the optimal tactical strategy. Furthermore, the emotion engine recognizes the players' reactions and adjusts the proposed tactics to increase players' motivation, resulting in a more effective tactical plan.

[1190] Prompt Sentence Examples

[1191] "Use a virtual tactical assistant to analyze past match data and simulate future matches. Use emotion recognition to suggest optimal tactical plans based on the user's emotions."

[1192] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1193] Program processing flow

[1194] Processing Steps

[1195] Step 1:

[1196] The server uses an external API to collect past match data. Specifically, it sends an API request to obtain match data for specific teams and players (e.g., player movements, scores, tactical patterns, etc.). This data is stored in a database within the server. The input is the response data from the API, and the output is the stored match data.

[1197] Step 2:

[1198] The server extracts stored tactical data and player stats from the database and analyzes them. Specifically, it preprocesses the data and converts it into a format that can be understood by the generative AI model. The input is the extracted data from the database, and the output is the preprocessed data.

[1199] Step 3:

[1200] The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and virtually recreate the flow and outcome of the match. The input is preprocessed data, and the output is the simulation results in JSON format.

[1201] Step 4:

[1202] The server creates data to visualize the movements of players and the ball based on the simulation results. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into the image generation engine. The image generation engine creates frames that reproduce the action of the game in real time. The input is the simulation result data, and the output is visualized match data.

[1203] Step 5:

[1204] The server transmits the generated video data to the terminal. Specifically, it compresses the video data and transmits it to the user's terminal via the Internet. The input is the visualized match data, and the output is the data delivered to the user's terminal.

[1205] Step 6:

[1206] The device uses the user's camera and microphone to input the user's facial expressions and voice data into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, surprise, excitement, etc.). The input is raw data obtained from the camera and microphone, and the output is analyzed emotion data.

[1207] Step 7:

[1208] The server dynamically changes the video content and tactical plan based on the recognized emotion data. Specifically, it generates an optimal tactical plan corresponding to the user's emotion and updates the video and plan content. The input is the emotion data and the initial video and tactical plan, and the output is the updated video and tactical plan.

[1209] Step 8:

[1210] The server uses a generative AI model to generate tens of millions of tactical plans, evaluates them, and selects the plan with the highest winning rate. The selected optimal tactical plan is then proposed to the manager or coach as a specific tactical proposal. The input is past match data and simulation results, and the output is the optimal tactical plan.

[1211] Prompt Sentence Examples

[1212] "Use a virtual tactical assistant to analyze past match data and simulate future matches. Use emotion recognition to suggest optimal tactical plans based on the user's emotions."

[1213] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1214] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1215] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1216] [Fourth embodiment]

[1217] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1218] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1219] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1220] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1221] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1222] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1223] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1224] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1225] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1226] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1227] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1228] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1229] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1230] The present invention is a system that collects and analyzes data from past sports matches, simulates future matches, visualizes the results, and proposes tactical plans. A specific embodiment of this system is described below.

[1231] 1. Collection and analysis of past match data

[1232] (server)

[1233] 1. The server collects past match data using an external API. For example, it calls an API to obtain match data for a specific team or player, and stores the data obtained in response within the server.

[1234] 2. The server then extracts stored tactical data and player stats from the database, parses this data, and pre-processes it into a format that the generative AI model can understand.

[1235] 2. Simulating future matches

[1236] (server)

[1237] 1. The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model then predicts each player's movements based on past data and virtually recreates the flow and outcome of the match.

[1238] 2. The simulation results are organized in JSON format and passed to the subsequent visualization process.

[1239] 3. Visualization of simulation results

[1240] (server)

[1241] 1. The server builds data to visualize the movements of players and the ball based on the simulation results. This data includes the positions of players, the ball, and the passage of time.

[1242] 2. The obtained data is used by the image generation engine to generate a visual image of the match. This image realistically reproduces the action of the match and is output in a format that is easy for users to understand.

[1243] 4. Tactical suggestion function

[1244] (server)

[1245] 1. The server uses a generative AI model to generate tens of millions of tactical plans. The system evaluates these plans and selects the one with the highest probability of winning.

[1246] 2. The selected optimal tactical plan is proposed to the manager or coach as a specific tactical proposal.

[1247] 5. User Interface

[1248] (Terminal)

[1249] 1. The device receives the video data and tactical plan sent from the server. The video is played on the device screen, allowing the manager or coach to intuitively understand the progress of the game.

[1250] 2. The tactical plan is displayed with detailed explanations and serves as a reference for the user to decide on specific next moves.

[1251] Specific examples

[1252] For example, when a soccer team's manager is planning a strategy for the next match, he collects and analyzes past match data and tactical data via an API. The results are then input into a generative AI model to simulate future matches. The simulation results are visualized and provided to the manager via a device. The generative AI model then proposes an optimal tactical plan to improve the manager's chances of winning the next match. This allows the manager to intuitively understand the game's development and select the optimal tactical strategy.

[1253] In this way, this system will make it easier for managers and coaches to plan specific strategies for matches, which will have a positive impact on the outcome of the match.

[1254] The processing flow will be explained below.

[1255] Step 1:

[1256] (server)

[1257] The server first calls an external API to collect past match data. This API retrieves match data for specific teams and players and stores it in a database within the server. For example, to retrieve soccer match data, an API endpoint such as https: / / sportsdata.api / teams / teamA / matches is called.

[1258] Step 2:

[1259] (server)

[1260] To analyze the collected data, the server extracts tactical data and player stats from the database. This data is obtained, for example, using SQL queries. Since the obtained data is difficult for the generative AI model to understand as it is, preprocessing involves cleaning, normalizing, and extracting features from the data.

[1261] Step 3:

[1262] (server)

[1263] The server inputs the preprocessed data into a generative AI model to simulate future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and the flow of the match. The simulation results are organized by each phase of the match and output in JSON format.

[1264] Step 4:

[1265] (server)

[1266] The server uses the simulation results to create data for visualizing the movements of players and the ball. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into a video generation engine. This video generation engine then creates frames that reproduce the action of the game in real time.

[1267] Step 5:

[1268] (server)

[1269] The generated video data is sent to the terminal. The server compresses the generated video data and sends it to the user's terminal via the Internet. At this time, an appropriate compression algorithm is used to avoid data loss.

[1270] Step 6:

[1271] (Terminal)

[1272] The device receives the video data sent from the server and displays it on the screen. By watching this video, users can intuitively understand the simulated game progress. The device also provides functions such as playing, pausing, and rewinding the video in response to user operations.

[1273] Step 7:

[1274] (server)

[1275] The server proposes tactical plans based on the results of the match. It uses a generative AI model to generate tens of millions of tactical plans and evaluates the success rate of each plan. The plan with the highest success rate is selected and provided as a concrete tactical proposal for the next match.

[1276] Step 8:

[1277] (Terminal)

[1278] The device receives the proposed tactical plan and displays it to the user along with a detailed explanation. Managers and coaches can use this information to develop specific strategies for the next game. The device also provides an interface for users to modify the tactical plan or add new plans.

[1279] Step 9:

[1280] (User)

[1281] Users watch the video and review the proposed tactical plan. They can then modify the plan as necessary and decide on the final strategy for the next match. Through this system, managers and coaches can intuitively understand the development of the game and plan the optimal tactical plan.

[1282] Through these steps, the system helps managers, coaches, and even sports lottery users to plan specific strategies for the next game.

[1283] Example 1

[1284] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1285] Conventional tactical planning support systems for sports games only allow users to view past game data, and are therefore inadequate in predicting future game results and proposing specific tactical plans. Furthermore, there is no way to provide simulation results in a visually easy-to-understand format, making it difficult for managers and coaches to intuitively understand and formulate countermeasures.

[1286] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1287] In this invention, the server includes means for collecting past game data, means for analyzing and preprocessing the collected data, means for simulating future games using the preprocessed data, means for formatting the simulation results in JSON format, means for generating images based on the formatted data, means for generating and evaluating tactical plans based on game results, and means for proposing the evaluated tactical plans. This enables managers and coaches to predict future game results in detail, intuitively and easily understand optimal tactical plans, and take countermeasures.

[1288] "Past match data" refers to past results of sports matches, player statistics, tactical data, etc.

[1289] "Means of collection" refers to the methods and systems used to obtain the necessary data from external APIs and databases.

[1290] "Analysis and preprocessing means" refers to methods and systems that remove outliers from collected data, normalize the data, and prepare the data in a format that can be used by generative AI models.

[1291] "Simulating means" refers to a method or system that uses a generative AI model based on pre-processed data to virtually predict the course and outcome of future matches.

[1292] "Means for formatting in JSON format" refers to a method or system for formatting simulation results into JSON (JavaScript Object Notation), a standardized data format, and passing them to the next processing step.

[1293] "Means for generating images" refers to a method or system that uses an image generation engine based on simulation results to visually reproduce a match.

[1294] "Means for generating and evaluating tactical plans" refers to a method or system that uses a generative AI model to generate multiple tactical plans, simulate the effects of each, and select the optimal plan.

[1295] "Means for proposing tactical plans" refers to a method or system for providing the manager or coach with the evaluated optimal tactical plan in a concrete and easily understandable format.

[1296] The present invention is a system that collects and analyzes data from past sports matches, simulates future matches, visualizes the results, and proposes tactical plans. A specific embodiment of this system is described below.

[1297] The server uses external APIs to collect past game data. Specifically, it obtains game data related to specific teams and players from external APIs such as sports data provider APIs. For example, to collect NBA game data, it obtains the data using the API request " / api / v1 / games?team_id=1234" and stores the JSON-formatted data obtained as a response in the database.

[1298] The server then analyzes and pre-processes the stored match data from the database, including data extraction, outlier removal, and data normalization, such as extracting player positions and stats (e.g., shots, passes, and ball possession time) and formatting them in a format that can be used by the generative AI model.

[1299] The server then inputs the preprocessed data into a generative AI model to simulate future matches. The generative AI model predicts player movements based on past data and virtually recreates the flow and outcome of the match. The simulation results are organized in JSON format and passed to the next process.

[1300] The server uses the simulation results to build data for visualizing player and ball movements. This data includes player positions, ball position, and time progression. It then uses a video generation engine (e.g., Unity or Unreal Engine) to generate a visual image of the match. This image realistically reproduces the action of the match and is output in a format that is easy for users to understand.

[1301] The server also uses a generative AI model to generate millions of tactical plans. These plans are evaluated and the plan with the highest potential for winning is selected. The optimal plan is then proposed to the manager or coach as a concrete tactical proposal.

[1302] The device receives the video data and tactical plan sent from the server. The video is played on the device screen, allowing managers and coaches to intuitively understand the game's progress. The tactical plan is also displayed with detailed explanations, providing reference information for users to specifically and efficiently decide their next move.

[1303] To give a specific example, when a soccer team's coach plans a strategy for the next match, the server collects and analyzes past match data and tactical data via an API. This data is input into a generative AI model to simulate future matches. The simulation results are organized into a primary JSON format and generated as realistic match footage using a video generation engine. The generative AI model then generates an optimal tactical plan to improve the team's chances of winning the next match and proposes it to the coach. The coach can then view the footage and tactical plan on their device and issue instructions to their players.

[1304] An example prompt is, "This system collects past match data, simulates and visualizes future matches, and proposes optimal tactical plans. Please propose effective tactics for a specific team for the next match."

[1305] In this way, this system will make it easier for managers and coaches to plan specific strategies for matches, which will have a positive impact on the outcome of the match.

[1306] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1307] Processing Steps:

[1308] Step 1: Collect past match data

[1309] server

[1310] The server sends a request to an external API (e.g., a sports data provider API). Specifically, it uses an API endpoint to retrieve past game data for a specific team or player. The input is the API request, and the output is the game data in JSON format. For example, the request " / api / v1 / games?team_id=1234" is sent, and the resulting data is stored in the database.

[1311] Specific behavior:

[1312] 1. The server sends an API request.

[1313] 2. The obtained JSON format match data is stored in a database.

[1314] Step 2: Analysis and preprocessing of match data

[1315] server

[1316] The server analyzes and preprocesses the match data stored in the database. The input is past match data, and the output is the preprocessed data. Specifically, it extracts player position information and stats, removes outliers, and normalizes the data. For example, it organizes stats such as the number of shots, number of passes, and ball possession time of players.

[1317] Specific behavior:

[1318] 1. The server extracts the match data from the database.

[1319] 2. Remove outliers and impute missing values.

[1320] 3. Normalize the data and convert it into a format suitable for generative AI models.

[1321] Step 3: Run the simulation

[1322] server

[1323] The server inputs the preprocessed data into a generative AI model to simulate future matches. The input is the preprocessed data, and the output is the simulation results in JSON format. The generative AI model predicts player movements based on past data and virtually recreates the flow and outcome of the match.

[1324] Specific behavior:

[1325] 1. The server inputs preprocessed data into the generative AI model.

[1326] 2. A generative AI model simulates the flow of the game.

[1327] 3. Output the simulation results in JSON format.

[1328] Step 4: Formatting the simulation results

[1329] server

[1330] The server formats the simulation results obtained from the generative AI model and extracts the data necessary for the next visualization process. The input is the JSON data of the simulation results, and the output is the data for video generation. For example, this includes information such as player positions, ball position, and time lapse.

[1331] Specific behavior:

[1332] 1. The server receives the simulation results.

[1333] 2. Organize the necessary data (e.g., player positions by time, ball position).

[1334] 3. Pass the formatted data to the next process.

[1335] Step 5: Visualization process

[1336] server

[1337] The server uses a video generation engine based on the formatted data to generate video of the match. The input is the formatted data, and the output is the match video. The video reproduces the movements of the players and the ball in real time.

[1338] Specific behavior:

[1339] 1. The server launches the video generation engine (e.g., Unity, Unreal Engine).

[1340] 2. Read the formatted data and render it as an image.

[1341] 3. Prepare the generated video in file storage or streaming format.

[1342] Step 6: Generate and evaluate a tactical plan

[1343] server

[1344] The server uses a generative AI model to generate multiple tactical plans and evaluates the effectiveness of each through simulation. The input is preprocessed data and simulation conditions, and the output is the optimal tactical plan. The system evaluates these tactical plans and selects the one with the highest probability of winning.

[1345] Specific behavior:

[1346] 1. The server inputs prompts to generate a tactical plan into the generative AI model.

[1347] 2. Evaluate the generated tactical plan.

[1348] 3. Select the most effective tactical plan and develop detailed information.

[1349] Step 7: Sending data to the user interface

[1350] Terminal

[1351] The terminal receives the video data and tactical plans sent from the server and provides them to the manager or coach. The input is the video data and tactical plans from the server, and the output is information displayed in a format that is easy for the user to understand.

[1352] Specific behavior:

[1353] 1. The device retrieves video data and tactical plans from the server.

[1354] 2. Play video in real time or on demand.

[1355] 3. Display details of the tactical plan to allow users (managers and coaches) to take countermeasures.

[1356] (Application example 1)

[1357] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1358] Conventional sports game analysis and tactical planning systems are limited in their ability to collect and analyze past game data, limiting their ability to predict future game developments and propose tactical plans. Furthermore, the visualization of game simulations and proposed tactical plans are not provided in an intuitively understandable format, making it difficult for users to understand and apply them. Therefore, there is a need for a system that can consistently provide more accurate game predictions, realistic and intuitive visualization, and optimal tactical plans.

[1359] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1360] In this invention, the server includes a means for collecting past match data, a means for analyzing the collected data, a means for evaluating tactical plans using a generative AI model and selecting an optimal plan, and a means for presenting images and tactical plans through a user interface, thereby making it possible to provide highly accurate simulation results and optimal tactical plans in an intuitively easy-to-understand format.

[1361] "Past match data" refers to information about past matches in a particular sport, including player movements, match results, tactical data, and the like.

[1362] "Means of collection" refers to the methods and systems for obtaining data from external APIs, etc. and storing it on a server.

[1363] "Means of analysis" refers to the algorithms and programs used to organize collected data and convert it into meaningful information.

[1364] "Means to simulate future matches" refers to systems and algorithms that use past match data and analysis results to predict how future matches will play out.

[1365] "Means for visualizing simulation results" refers to technologies and tools that visually represent the results of a simulation and output them in a form that is easy for users to understand.

[1366] "Means for proposing tactical plans" refers to a method for generating optimal strategies and tactics based on the results of a match simulation and presenting them to the user.

[1367] A "generative AI model" refers to an artificial intelligence model based on deep learning that is used for purposes such as prediction, analysis, and suggestions.

[1368] "User interface" refers to the parts that users directly touch, such as the screen and operation methods used to exchange information between the system and the user.

[1369] This invention is a system that collects and analyzes past match data, simulates and visualizes future matches, and proposes tactical plans. The main elements of this system and their functions are explained in detail below.

[1370] The server first uses external APIs to collect past match data, including match data for specific sports teams and players, which is then stored in the server's database. The stored data is then analyzed and preprocessed into a format that can be understood by the generative AI model. This analysis includes player movement and tactical data, and the data is then properly organized before proceeding to the next processing stage.

[1371] The server inputs the preprocessed data into a generative AI model (such as OpenAI GPT-4 or Stable Diffusion) and runs a simulation to predict future matches. The simulation predicts each player's movements based on past data and recreates the flow and results of the match. The simulation results are organized in JSON format and passed to the visualization process.

[1372] The visualization process, based on the simulation results, builds data such as player positions, ball positions, and time progression. This data is then used to generate visual images using a video generation engine such as Unity or Unreal Engine. This video realistically reproduces the action of the match and is provided to users.

[1373] The tactical suggestion feature uses a generative AI model to generate tens of millions of tactical plans, which the system then evaluates to select the plan with the highest potential for winning. The selected plan is then suggested to the manager or coach, along with a detailed explanation.

[1374] The user interface displays the video data and tactical plans sent from the server on the device, allowing managers and coaches to intuitively understand the progress of the game. The tactical plans are also displayed with detailed explanations, so users can use them as reference information to decide on specific next moves.

[1375] As a concrete example, when a soccer team's manager is planning a strategy for the next match, he collects and analyzes past match data and tactical data via API. The results are input into a generative AI model, which simulates future matches. The simulation results are visualized and provided to the manager via a device. The generative AI model also proposes an optimal tactical plan to improve the team's chances of winning the next match.

[1376] An example of a prompt might be:

[1377] "For a match between Team A and Team B, simulate future game developments based on past data and propose the optimal tactical plan."

[1378] In this way, the system makes it easier for managers and coaches to plan specific strategies for matches, which can have a positive impact on the outcome of the match.

[1379] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1380] Step 1:

[1381] The server uses an external API to collect past match data. The input is a request to the external API, and the output is the retrieved match data. Specifically, the server hits a specific URL or endpoint and retrieves past match data in response. This data includes player location information, scores, tactical data, and more. For example, data is returned in JSON format from a sports data provider API.

[1382] Step 2:

[1383] The server stores the collected data in a database. The input is the acquired match data, and the output is the data stored in the database. Specifically, to insert the data for each match into the appropriate table, an SQL statement is generated and executed on the database (for example, MySQL or PostgreSQL). The database stores the match ID, player ID, and details of each play.

[1384] Step 3:

[1385] The server extracts the data to be analyzed from the database and preprocesses it into a format that the generative AI model can understand. The input is the match data extracted from the database, and the output is the preprocessed data. Specific operations include data cleanup (missing value processing, normalization) and format conversion (for example, conversion to CSV format). This prepares the data in a format that is easy to input into the AI ​​model.

[1386] Step 4:

[1387] The server inputs the preprocessed data into a generative AI model to simulate future matches. The input is the preprocessed data, and the output is the simulation results. Specifically, the server supplies data to a generative AI model (e.g., OpenAI GPT-4) to predict how the match will play out. At this time, the server simulates the movements of players and the progress of the match. The simulation results are organized in JSON format.

[1388] Step 5:

[1389] The server executes a visualization process based on the simulation results. The input is the simulation results, and the output is the game footage. Specifically, a video generation engine such as Unity or Unreal Engine is used to visually reproduce the movements of players and the ball. Data such as player positions, ball position, and time passage are used during this process.

[1390] Step 6:

[1391] The server sends the generated video data and tactical plan to the terminal. The input is the video data and tactical plan, and the output is the data sent to the terminal. Specifically, the server sends the video data and tactical plan via HTTP protocol to the terminal (e.g., a smartphone or head-mounted display) so that the user can view them.

[1392] Step 7:

[1393] The terminal displays the received video data and tactical plan. The input is the transmitted video data and tactical plan, and the output is a visual display provided to the user. Specifically, the terminal plays the video on its display and displays the tactical plan in text and graph format. The user can view this to confirm the game development and tactical proposals.

[1394] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1395] The present invention is a system that collects and analyzes past match data, simulates future matches, visualizes the results, and proposes tactical plans. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it is possible to provide optimal images and tactical plans for each individual user. A specific embodiment of this system is described below.

[1396] 1. Collection and analysis of past match data

[1397] (server)

[1398] 1. The server collects past match data using an external API. This API retrieves match data for specific teams and players and stores it in a database within the server.

[1399] 2. Next, the server extracts stored tactical data and player stats from the database. The server then analyzes this data and preprocesses it into a format that can be understood by the generative AI model.

[1400] 2. Simulating future matches

[1401] (server)

[1402] 1. The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and virtually recreate the flow and outcome of the match.

[1403] 2. The simulation results are organized in JSON format and passed to the subsequent visualization process.

[1404] 3. Visualization of simulation results

[1405] (server)

[1406] 1. The server creates data to visualize the movements of players and the ball based on the simulation results. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into the image generation engine. The image generation engine then creates frames that reproduce the action of the game in real time.

[1407] 2. The generated video data is sent to the terminal. The server compresses the generated video data and sends it to the user's terminal via the Internet.

[1408] 4. Tactical suggestion function

[1409] (server)

[1410] 1. The server uses a generative AI model to generate tens of millions of tactical plans. The system evaluates these plans and selects the plan with the highest probability of winning.

[1411] 2. The selected optimal tactical plan is proposed to the manager or coach as a specific tactical proposal.

[1412] 5. Emotion recognition function

[1413] (Terminal)

[1414] 1. The device uses the user's camera and microphone to input the user's facial expressions and voice into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (happiness, surprise, excitement, etc.).

[1415] 2. The recognized emotion data is sent to the server, which then dynamically changes the video content and tactical plan based on this data.

[1416] Specific examples

[1417] For example, when a soccer team's manager is planning strategies for the next match, he collects and analyzes past match data and tactical data via API. The results are then input into a generative AI model to simulate future matches. The simulation results are visualized and provided to the manager via a device.

[1418] Furthermore, the emotion engine recognizes the manager's emotions, and if the manager is feeling very nervous, for example, it will make the simulation video more detailed and suggest more specific tactical plans, allowing the manager to intuitively understand the progress of the game and select the optimal tactics.

[1419] In addition, the emotion engine recognizes the player's reactions and adjusts the tactics it suggests to increase the player's motivation, resulting in a more effective tactical plan.

[1420] In this way, this system will make it easier for managers, coaches, and even sports lottery users to plan specific strategies for matches, which will have a positive impact on the outcome of the match.

[1421] The processing flow will be explained below.

[1422] Step 1:

[1423] (server)

[1424] Use an external API to collect past match data. The server calls this API endpoint (e.g., https: / / sportsdata.api / teams / teamA / matches) to retrieve match data for specific teams and players. The retrieved data is then stored in a database within the server.

[1425] Step 2:

[1426] (server)

[1427] The stored tactical data and player stats are extracted from the database. Specifically, SQL queries are used to extract the required data, which is then analyzed. During the analysis, pre-processing steps such as data cleaning, normalization, and feature extraction are performed.

[1428] Step 3:

[1429] (server)

[1430] The preprocessed data is input into a generative AI model to simulate future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and the flow of the match. The simulation results are organized by each phase of the match and output in JSON format.

[1431] Step 4:

[1432] (server)

[1433] Based on the simulation results, data is created to visualize the movements of players and the ball. Specifically, the position data of each player and the movement data of the ball are organized along a time axis and input into a video generation engine. The video generation engine then creates frames that reproduce the movements of the game in real time.

[1434] Step 5:

[1435] (server)

[1436] The generated video data is sent to the terminal. The server compresses the generated video data and sends it to the user's terminal via the Internet. At this time, an appropriate compression algorithm is used to avoid data loss.

[1437] Step 6:

[1438] (Terminal)

[1439] The device receives the video data sent from the server and displays it on the screen. By watching this video, users can intuitively understand the progress of the simulated game. The device also provides functions such as playing, pausing, and rewinding the video in response to user operations.

[1440] Step 7:

[1441] (server)

[1442] Tactical plans are proposed based on the results of the match. The server uses a generative AI model to generate tens of millions of tactical plans and evaluates the success rate of each plan. The plan with the highest success rate is selected and provided as a concrete tactical proposal for the next match.

[1443] Step 8:

[1444] (Terminal)

[1445] The proposed tactical plan is received and displayed to the user along with a detailed explanation. Managers and coaches can use this information to develop specific strategies for the next game. The device also provides an interface for users to modify tactical plans or add new plans.

[1446] Step 9:

[1447] (Terminal)

[1448] The device uses the user's camera and microphone to input the user's facial expressions and voice into the emotion engine, which then analyzes this data and recognizes the user's emotional state (happiness, surprise, excitement, etc.).

[1449] Step 10:

[1450] (server)

[1451] The server receives the recognized emotion data. Based on this data, the server dynamically changes the video content and tactical plan. For example, if the user is nervous, the simulation video will be more detailed and the tactical plan will be explained more carefully.

[1452] Step 11:

[1453] (Terminal)

[1454] The dynamically changed video and tactical plan are received again from the server and provided to the user, who can then use this information to more specifically determine the strategy for the next match.

[1455] Step 12:

[1456] (User)

[1457] Managers and coaches can view the footage, review the proposed tactical plan, and, if necessary, revise the plan to determine the optimal strategy. Through this system, managers and coaches can intuitively understand the development of the game and devise the optimal tactics.

[1458] Through these steps, the system will help managers, coaches, and even sports lottery users to plan specific strategies for the next game, which will have a positive impact on the outcome of the game.

[1459] Example 2

[1460] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1461] Conventional match analysis systems mainly perform simple statistical analysis based on past match data, and have limited functionality for simulating future matches in real time and visually displaying the results. Furthermore, they do not provide personalized tactical suggestions that take into account the user's emotions, limiting their efficiency and effectiveness in match preparation.

[1462] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1463] In this invention, the server includes means for collecting past match data, means for analyzing the collected data, means for preprocessing the analyzed data, means for inputting the preprocessed data into a generative AI model to simulate future matches, means for organizing the simulation results in JSON format, means for generating video based on the simulation results, means for recognizing user emotions, means for dynamically changing the video content and tactical plans based on the recognized emotion data, and means for proposing tactical plans based on the simulation results, thereby enabling specific and detailed match simulations and personalized tactical proposals.

[1464] "Past match data" refers to historical data such as match results, statistical information, and tactical data of players and teams in a particular sporting event.

[1465] "Means of collection" refers to the functions and methods for obtaining the necessary information from external APIs or databases and storing it in the system.

[1466] "Means of analysis" refers to the functions and methods of analyzing collected data using statistical or machine learning techniques and extracting useful information.

[1467] "Preprocessing means" refers to processes such as data cleaning and normalization to convert the analyzed data into a format that is easy for the generative AI model to understand.

[1468] A "generative AI model" is an artificial intelligence model that learns from past data and is used to predict future events and outcomes.

[1469] "Means to simulate" refers to functions and methods for virtually recreating future match situations and outcomes using generative AI models.

[1470] "JSON format" is an abbreviation for JavaScript Object Notation, and is a standard format for describing data structures flexibly and simply.

[1471] "Means for generating images" refers to a function or method for creating image data for visually displaying player movements and game situations based on simulation results.

[1472] "Means for recognizing user emotions" refers to a function or method for analyzing the user's facial expressions and voice data obtained from sensors such as cameras and microphones, and determining their emotional state.

[1473] "Means for dynamic change" refers to functions and methods for adjusting video content and tactical plans in real time based on the user's emotional data.

[1474] "Means for proposing tactical plans" refers to functions and methods for proposing optimal strategies and formations based on simulation and analysis results.

[1475] The present invention is a system that collects and analyzes past match data, simulates future matches, visualizes the results, and proposes tactical plans. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it is possible to provide optimal images and tactical plans for each individual user. Specific embodiments of this system are described below.

[1476] 1. Collection and analysis of past match data

[1477] (server)

[1478] The server uses external APIs to collect past game data, such as a sports league's API, to retrieve game data for specific teams and players. This data is stored in a database on the server in JSON or CSV format.

[1479] The server then retrieves the stored match data from the database and analyzes it. This analysis includes player movement patterns on the field, scoring patterns, and transitional behavior between offense and defense. The analyzed data is then preprocessed into a format suitable for the generative AI model. This preprocessing includes normalizing the numerical data and filling in missing data.

[1480] 2. Simulating future matches

[1481] (server)

[1482] The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past match data to predict the game's development and outcome. This prediction includes the movements of each player, ball movement, and goal timing. The simulation results are organized in JSON format and used for visualization at a later stage.

[1483] 3. Visualization of simulation results

[1484] (server)

[1485] The server uses the simulation results to create data for visualizing the movements of players and the ball. Specifically, it organizes each player's position data and ball movement data along a timeline and inputs it into a video generation engine (e.g., Unity or Unreal Engine). The video generation engine uses this data to create frames that reproduce the action of the game in real time. The generated video data is then further compressed and sent to the user's device.

[1486] 4. Tactical suggestion function

[1487] (server)

[1488] The server uses a generative AI model to generate tens of millions of tactical plans. These plans are evaluated based on simulation results, and the plan with the highest win rate is selected. The selected tactical plan is presented to the manager or coach as a specific tactical proposal. This proposal may include specific position changes, attacking patterns, defensive plans, etc.

[1489] 5. Emotion recognition function

[1490] (Terminal)

[1491] The device uses the user's camera and microphone to input the user's facial expressions and voice data into the emotion engine. The emotion engine analyzes this data in real time and recognizes the user's emotional state (happiness, surprise, excitement, etc.). The recognized emotion data is sent to the server, which dynamically changes the video content and tactical plan based on this data. For example, if the user is nervous, the server can provide detailed simulation video and change the tactical plan to be more specific.

[1492] Specific examples

[1493] For example, when a soccer team manager is planning a strategy for the next game, he or she will use the system in the following steps.

[1494] First, the server collects past match data and tactical data via an API, analyzes it, and inputs it into the generative AI model. Next, the server runs a simulation of a future match and visualizes the results. The visualized simulation results are then sent to the manager's device. Furthermore, the server recognizes the manager's emotions through the device's camera and microphone and adjusts the corresponding tactical plan. For example, if the manager is very nervous, the simulation video will be more detailed and specific tactical plans will be proposed, allowing the manager to select the optimal tactical strategy.

[1495] Here are some example prompts to input to a generative AI model:

[1496] "Using match data from the past three years for a specific team, simulate the optimal tactical plan for the next match. If the user is nervous, provide specific tactical suggestions to help them cope."

[1497] Using such prompts, the generative AI model can suggest specific and useful tactics.

[1498] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1499] A detailed explanation of the program processing of this system

[1500] Processing Steps

[1501] Step 1: Collect past match data

[1502] (server)

[1503] Input: The server sends an API request to an external data provider.

[1504] Data processing / calculation: Receive match data returned from the API and extract necessary items (e.g., player statistics, match results, tactical data). Convert the data format to JSON or CSV.

[1505] Output: Collected data is saved in a database on the server.

[1506] Specific operation: The server calls the sports league API and specifies parameters such as "team_id" and "match_date" to retrieve match data from the past three years.

[1507] Step 2: Data extraction and preprocessing

[1508] (server)

[1509] Input: Saved match data from database.

[1510] Data processing / calculation: Analyze the data and extract detailed information such as player movements, number of goals, and possession. Fill in missing data, normalize the data, and preprocess it into a format that can be input into a generative AI model.

[1511] Output: The preprocessed dataset.

[1512] Specific operation: The server processes the data using the Pandas library, filling in missing data and standardizing it.

[1513] Step 3: Generate data to input to the AI ​​model

[1514] (server)

[1515] Input: Preprocessed data.

[1516] Data processing / computation: Input data into a generative AI model (e.g., a PyTorch model) and run inference on the model, which results in simulated results for future matches.

[1517] Output: Predicted data as a simulation result.

[1518] How it works: The server reads the pre-processed data and feeds it into a generative AI model that makes predictions using the arrow method and regression analysis.

[1519] Step 4: Organizing the simulation results

[1520] (server)

[1521] Input: Simulation results from a generative AI model.

[1522] Data processing / calculation: Organize the simulation results along the time axis and convert them into JSON format.

[1523] Output: Simulation result data in JSON format.

[1524] Specific operation: The server reads the model output, organizes player position data and ball movement data in chronological order, and converts them into JSON format.

[1525] Step 5: Inputting data into the image generation engine

[1526] (server)

[1527] Input: Simulation result data in JSON format.

[1528] Data processing / calculation: Input data into a video generation engine (Unity or Unreal Engine) to generate video of the virtual match.

[1529] Output: Frame data that recreates the action of the match.

[1530] Specific operation: The server reads the JSON data and passes it to the image generation engine script to generate real-time images.

[1531] Step 6: Compress and transmit the video data

[1532] (server)

[1533] Input: The generated frame data.

[1534] Data processing / calculation: Data size is optimized using a compression algorithm and sent to the user's device.

[1535] Output: Compressed video data.

[1536] Specific operation: The server applies a compression algorithm such as H.264 and sends the data to the terminal via the Internet.

[1537] Step 7: Generate and evaluate a tactical plan

[1538] (server)

[1539] Input: Simulation results obtained from a generative AI model.

[1540] Data processing / calculation: Simulating different tactical plans, evaluating them and selecting the best plan.

[1541] Output: Optimal tactical plan.

[1542] What it does: The server simulates multiple tactical scenarios and applies algorithms to evaluate the success rate and effectiveness of each scenario.

[1543] Step 8: Recognizing User Emotions

[1544] (Terminal)

[1545] Input: Emotion data from the user's camera or microphone.

[1546] Data processing / calculation: The emotion engine analyzes this data and determines the user's emotional state from their facial expressions and voice.

[1547] Output: Recognized emotion data.

[1548] How it works: The device uses software to capture the user's facial expressions and voice through a camera and microphone and analyzes them in real time.

[1549] Step 9: Dynamically change the visuals and tactical plans with emotional data

[1550] (server)

[1551] Input: Recognized emotion data and simulation results.

[1552] Data processing / calculation: Apply algorithms that dynamically change video content and tactical plans based on emotional data.

[1553] Output: Dynamically modified footage and tactical plans.

[1554] Specific actions: The server analyzes the emotional data and adjusts the level of detail in the video or makes the tactical plan more specific depending on the user's level of tension.

[1555] The above is a specific description of each processing step in this system.

[1556] (Application example 2)

[1557] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1558] While conventional match data analysis systems can analyze past match data and simulate future matches, they are unable to propose tactical plans that take the user's emotions into account, making it difficult to provide optimal information to each individual user. Furthermore, users have difficulty visually grasping the flow of the match, making it difficult for them to intuitively understand the effectiveness of tactical plans.

[1559] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1560] In this invention, the server includes means for collecting past match data, means for analyzing the collected data, means for simulating future matches, means for visualizing the simulation results, means for proposing a tactical plan based on the match results, and means for recognizing the user's emotions and dynamically changing the images and tactical plan based on the emotion data, thereby enabling the proposal of an optimized tactical plan for each user and enabling the user to visually and intuitively grasp the flow of the match.

[1561] Key Word Definitions

[1562] "Past match data" is recorded data relating to matches played in the past, and includes details such as player movements, scores, and tactical patterns.

[1563] "Means of collection" refers to the technical methods and devices used to collect the required data through external APIs and databases.

[1564] "Means of analysis" refers to technical methods or devices that preprocess collected data, extract useful information from the data, and further analyze it using statistical techniques or machine learning models.

[1565] "Means for simulating" refers to technical methods or devices that virtually reproduce the development of a future match based on analyzed data.

[1566] "Visualization means" refers to technical methods and devices that visually display the simulation results and generate video data that reproduces the movements of the game.

[1567] The "means for proposing a tactical plan" refers to a technical method or device that generates an optimal tactical plan based on simulation results and past match data and presents it to the user.

[1568] "Means for recognizing emotions" refers to technical methods or devices that analyze a user's facial expressions and voice data to identify the user's emotional state.

[1569] "Dynamic modification means" refers to technical methods or devices that modify the content of video or tactical plans in real time based on recognized emotion data.

[1570] MODE FOR CARRYING OUT THE INVENTION

[1571] This system collects and analyzes past match data, simulates future matches, visualizes the results, and proposes tactical plans. Furthermore, by incorporating an emotion engine, it recognizes the user's emotions and provides optimal images and tactical plans for each individual user.

[1572] 1. Collection and analysis of past match data

[1573] (server)

[1574] The server uses an external API to collect past match data. This API retrieves match data for specific teams and players and stores it in a database within the server. The server then extracts the stored tactical data and player stats from the database. The server analyzes this data and preprocesses it into a format that can be understood by the generative AI model.

[1575] 2. Simulating future matches

[1576] (server)

[1577] The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past data to predict each player's movements and virtually recreate the flow and outcome of the match. The simulation results are organized in JSON format and passed to the subsequent visualization process.

[1578] 3. Visualization of simulation results

[1579] (server)

[1580] The server creates data to visualize the movements of players and the ball based on the simulation results. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into a video generation engine. The video generation engine creates frames that reproduce the action of the game in real time. To send the generated video data to the terminal, the server compresses the video data and sends it to the user's terminal via the Internet.

[1581] 4. Tactical suggestion function

[1582] (server)

[1583] The server uses a generative AI model to generate tens of millions of tactical plans. It then evaluates these plans and selects the one with the highest winning rate. The selected optimal tactical plan is then proposed to the manager or coach as a concrete tactical proposal.

[1584] 5. Emotion recognition function

[1585] (Terminal)

[1586] The device uses the user's camera and microphone to input the user's facial expressions and voice into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (happiness, surprise, excitement, etc.). The recognized emotion data is sent to the server, which then dynamically changes the video content and tactical plan based on this data.

[1587] Specific examples

[1588] For example, when a soccer team's coach plans a strategy for the next match, he collects and analyzes past match data and tactical data via an API. The results are then input into a generative AI model to simulate future matches. The simulation results are visualized and provided to the coach via a device. Furthermore, an emotion engine recognizes the coach's emotions. For example, if the coach is very nervous, the simulation video becomes more detailed and the proposed tactical plan becomes more specific. This allows the coach to intuitively understand the game's development and select the optimal tactical strategy. Furthermore, the emotion engine recognizes the players' reactions and adjusts the proposed tactics to increase players' motivation, resulting in a more effective tactical plan.

[1589] Prompt Sentence Examples

[1590] "Use a virtual tactical assistant to analyze past match data and simulate future matches. Use emotion recognition to suggest optimal tactical plans based on the user's emotions."

[1591] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1592] Program processing flow

[1593] Processing Steps

[1594] Step 1:

[1595] The server uses an external API to collect past match data. Specifically, it sends an API request to obtain match data for specific teams and players (e.g., player movements, scores, tactical patterns, etc.). This data is stored in a database within the server. The input is the response data from the API, and the output is the stored match data.

[1596] Step 2:

[1597] The server extracts stored tactical data and player stats from the database and analyzes them. Specifically, it preprocesses the data and converts it into a format that can be understood by the generative AI model. The input is the extracted data from the database, and the output is the preprocessed data.

[1598] Step 3:

[1599] The server inputs the preprocessed data into a generative AI model and runs a simulation to predict future matches. The generative AI model uses patterns learned from past data to predict the movements of each player and virtually recreate the flow and outcome of the match. The input is preprocessed data, and the output is the simulation results in JSON format.

[1600] Step 4:

[1601] The server creates data to visualize the movements of players and the ball based on the simulation results. Specifically, it organizes each player's position data and ball movement data along a time axis and inputs it into the image generation engine. The image generation engine creates frames that reproduce the action of the game in real time. The input is the simulation result data, and the output is visualized match data.

[1602] Step 5:

[1603] The server transmits the generated video data to the terminal. Specifically, it compresses the video data and transmits it to the user's terminal via the Internet. The input is the visualized match data, and the output is the data delivered to the user's terminal.

[1604] Step 6:

[1605] The device uses the user's camera and microphone to input the user's facial expressions and voice data into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, surprise, excitement, etc.). The input is raw data obtained from the camera and microphone, and the output is analyzed emotion data.

[1606] Step 7:

[1607] The server dynamically changes the video content and tactical plan based on the recognized emotion data. Specifically, it generates an optimal tactical plan corresponding to the user's emotion and updates the video and plan content. The input is the emotion data and the initial video and tactical plan, and the output is the updated video and tactical plan.

[1608] Step 8:

[1609] The server uses a generative AI model to generate tens of millions of tactical plans, evaluates them, and selects the plan with the highest winning rate. The selected optimal tactical plan is then proposed to the manager or coach as a specific tactical proposal. The input is past match data and simulation results, and the output is the optimal tactical plan.

[1610] Prompt Sentence Examples

[1611] "Use a virtual tactical assistant to analyze past match data and simulate future matches. Use emotion recognition to suggest optimal tactical plans based on the user's emotions."

[1612] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1613] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1614] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1615] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1616] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1617] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1618] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1619] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1620] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1621] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1622] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1623] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1624] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1625] 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.

[1626] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1627] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1628] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1629] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1630] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1631] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1632] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1633] The following is further disclosed regarding the above embodiment.

[1634] (Claim 1)

[1635] A means of collecting past match data;

[1636] a means for analyzing the collected data;

[1637] a means of simulating future matches;

[1638] a means for visualizing the simulation results;

[1639] A means of proposing tactical plans based on the results of the match;

[1640] A system including:

[1641] (Claim 2)

[1642] 10. The system of claim 1, further comprising: means for transmitting the generated video data to the terminal.

[1643] (Claim 3)

[1644] 10. The system of claim 1, further comprising means for inputting the analyzed data into a generative artificial intelligence model to predict the outcome of the match.

[1645] "Example 1"

[1646] (Claim 1)

[1647] A means of collecting past match data;

[1648] a means for analyzing and pre-processing the collected data;

[1649] means for simulating future matches using the preprocessed data;

[1650] A means to format the simulation results in JSON format,

[1651] A means for generating an image based on the formatted data;

[1652] means for generating and evaluating tactical plans based on the results of a match;

[1653] a means of proposing an evaluated tactical plan;

[1654] A system including:

[1655] (Claim 2)

[1656] 10. The system of claim 1, further comprising means for transmitting the generated video data and tactical plan to the terminal.

[1657] (Claim 3)

[1658] 10. The system of claim 1, further comprising means for inputting the analyzed and preprocessed data into a generative artificial intelligence model to simulate the outcome of a match.

[1659] "Application Example 1"

[1660] (Claim 1)

[1661] A means of collecting past match data;

[1662] a means for analyzing the collected data;

[1663] a means of simulating future matches;

[1664] a means for visualizing the simulation results;

[1665] A means of proposing tactical plans based on the results of the match;

[1666] A means for evaluating tactical plans using a generative AI model and selecting the optimal plan; and

[1667] A means of presenting visuals and tactical plans through a user interface;

[1668] A system including:

[1669] (Claim 2)

[1670] 10. The system of claim 1, further comprising means for transmitting the generated video data to a terminal for viewing by a user.

[1671] (Claim 3)

[1672] 10. The system of claim 1, further comprising means for inputting the analyzed data into a generative AI model to predict the outcome of the match.

[1673] "Example 2: Combining Emotion Engines"

[1674] (Claim 1)

[1675] A means of collecting past match data;

[1676] a means for analyzing the collected data;

[1677] means for preprocessing the analyzed data;

[1678] A means of feeding the pre-processed data into a generative AI model to simulate future matches; and

[1679] A means to organize simulation results in JSON format,

[1680] means for generating an image based on the simulation results;

[1681] means for recognizing a user's emotion;

[1682] A means for dynamically changing video content and tactical plans based on the recognized emotion data;

[1683] A means for proposing a tactical plan based on the simulation results;

[1684] A system including:

[1685] (Claim 2)

[1686] 10. The system of claim 1, further comprising: means for transmitting the generated video data to the terminal.

[1687] (Claim 3)

[1688] 10. The system of claim 1, further comprising means for inputting the analyzed data into a generative AI model to predict the outcome of the match.

[1689] "Application example 2 when combining emotion engines"

[1690] (Claim 1)

[1691] A means of collecting past match data;

[1692] a means for analyzing the collected data;

[1693] a means of simulating future matches;

[1694] a means for visualizing the simulation results;

[1695] A means of proposing tactical plans based on the results of the match;

[1696] means for recognizing a user's emotions and dynamically changing the video and tactical plan based on the emotion data;

[1697] A system including:

[1698] (Claim 2)

[1699] 10. The system of claim 1, further comprising: means for transmitting the generated video data to the terminal.

[1700] (Claim 3)

[1701] 10. The system of claim 1, further comprising means for inputting the analyzed data into a generative artificial intelligence model to predict the outcome of the match. [Explanation of symbols]

[1702] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting past match data; a means for analyzing the collected data; a means of simulating future matches; a means for visualizing the simulation results; A means of proposing tactical plans based on the results of the match; A system including:

2. The system of claim 1 , further comprising: means for transmitting the generated video data to a terminal.

3. 10. The system of claim 1, further comprising means for inputting the analyzed data into a generative artificial intelligence model to predict the outcome of the match.

Images