system

Abstract

We provide the system. [Solution] A system including means for uploading soccer match videos, means for collecting team and player-specific data from the match videos, means for analyzing performance and suggesting improvements based on the collected data, and means for providing customized training plans and nutritional advice according to the players' condition.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Currently, the coaching of junior soccer club teams and players is personal based on the experience and knowledge of coaches and guardians, and the coaching methods are not necessarily optimal. Also, it is difficult to provide customized training plans and nutritional advice according to the conditions of each player.

Means for Solving the Problems

[0005] This invention provides a system that collects team and individual player data simply by uploading soccer match videos, and then analyzes performance and suggests improvements. Furthermore, it also provides customized training plans and nutritional advice based on the players' condition. These processes are performed by AI, moving away from the subjective guidance based on the experience and knowledge of coaches and parents, and supporting growth with the most optimal guidance methods. [Brief explanation of the drawing]

[0006] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 1 of Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 of Embodiment 2. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Form Example 2. [Figure 15] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 3 of Example 3. [Figure 16] This is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Form Example 3. [Figure 17] This is a sequence diagram showing the processing flow of the data processing system in Example 1 of the Form 1 when an emotion engine is combined. [Figure 18] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] This is a sequence diagram showing the processing flow of a data processing system in another embodiment. [Modes for carrying out the invention]

[0007] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0008] First, let's explain the terminology used in the following explanation.

[0009] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)), etc.

[0010] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0011] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0012] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and antennas, 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), or Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0014] [First Embodiment]

[0015] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0016] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0019] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0022] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0024] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0026] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0027] "Example of form 1"

[0028] The system of the present invention includes means for uploading soccer match videos, means for collecting team and player-specific data from the match videos, means for analyzing performance and suggesting improvements based on the collected data, and means for providing customized training plans and nutritional advice according to the players' condition. These means are realized using AI technology. Specifically, the system analyzes players' movements and performance from match videos to understand each player's strengths and weaknesses. Furthermore, the AI ​​provides optimal training plans and nutritional advice according to the players' condition and performance. This moves away from subjective instruction based on the experience and knowledge of coaches and parents, and supports growth with the most optimal coaching methods. "Example Form 2"

[0029] As a concrete example, a junior soccer club team uploads match videos to the system of the present invention after a game. The system uses AI to analyze the videos and collect individual player performance data (e.g., distance covered, number of sprints, pass success rate, etc.). Furthermore, the AI ​​analyzes performance and suggests improvements based on the collected data. For example, if a particular player tends to have a decrease in the number of sprints in the second half of a match, the AI ​​will suggest a training plan to improve that player's stamina. The system also provides customized nutritional advice according to the player's condition (e.g., energy sources to consume before a match, nutrients needed for recovery after a match, etc.).

[0030] The following describes the processing flow for each example of the form.

[0031] "Example of form 1"

[0032] Step 1: A user (e.g., a coach or parent) uploads a video of a soccer match to the system of the present invention.

[0033] Step 2: The system uses AI to analyze the video and collect individual player performance data (e.g., distance covered, number of sprints, pass completion rate, etc.).

[0034] Step 3: The AI ​​analyzes performance and suggests improvements based on the collected data.

[0035] Step 4: Based on the player's condition, the AI ​​provides a customized training plan and nutritional advice.

[0036] "Example of form 2"

[0037] Step 1: A junior soccer club team uploads a video of the match to the system of the present invention after the match.

[0038] Step 2: The system uses AI to analyze the videos and collect individual player performance data.

[0039] Step 3: The AI ​​analyzes performance and suggests improvements based on the collected data. If a particular player tends to have fewer sprints in the second half of a match, the AI ​​will suggest a training plan to improve that player's stamina.

[0040] Step 4: Based on the player's condition, the AI ​​provides customized nutritional advice. For example, it suggests energy sources to consume before a match and nutrients needed for recovery after a match.

[0041] (Example 1)

[0042] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0043] Traditional soccer coaching relied heavily on the experience and knowledge of coaches and parents, resulting in a subjective approach that made it difficult to provide optimal coaching based on individual player performance and condition. Furthermore, data collection and analysis from match footage were often done manually, making efficient analysis challenging.

[0044] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0045] In this invention, the server includes means for transmitting match video, means for acquiring group and individual information from the match video, means for analyzing abilities and suggesting improvements based on the acquired information, means for providing training plans and nutritional guidance tailored to the individual's condition, and means for inputting prompt sentences using a generative AI model and generating specific suggestions based on the analysis results. This enables optimal guidance based on the individual performance of each player and efficient data analysis.

[0046] "Match footage" refers to video data that records the events of a soccer match, and is used to visually capture the movements of the players and teams.

[0047] "Means of transmission" refers to a device or software that has the function of transferring digital data to other devices or systems via a network.

[0048] "Group and individual information" refers to data about the entire team and each player extracted from match footage, including detailed information about performance and movement.

[0049] "Means of acquisition" refers to devices or software used to collect specific data or information and convert it into a format usable within the system.

[0050] "Performance analysis" is the process of evaluating the performance of players and teams based on collected data, and identifying their strengths and weaknesses.

[0051] "Suggestions for improvement" refers to providing specific advice and strategies to improve the performance of players and teams based on the analysis results.

[0052] "Individual condition" refers to information about each player's physical condition, such as their health, fitness level, and fatigue level.

[0053] A "tailored training plan" is a training menu customized according to the individual athlete's condition and goals, aiming for effective performance improvement.

[0054] "Nutritional guidance" refers to providing advice on diet and nutritional intake in order to optimize an athlete's health and performance.

[0055] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[0056] A "prompt statement" is a sentence containing instructions or questions that are input into a generative AI model, and it serves as a trigger for the model to generate appropriate output.

[0057] This invention is a system for analyzing soccer match footage to improve the performance of players and teams. Users upload match footage from their terminals to a server. The server analyzes the footage using video analysis software (e.g., OpenCV) and extracts player movement and position data. This allows for the acquisition of group and individual information.

[0058] The server inputs the acquired information into an AI model (e.g., TENSORFLOW® or PyTorch) to analyze the player's abilities. The AI ​​model evaluates the player's strengths and weaknesses and generates specific suggestions for improvement. This includes a training plan tailored to the player's condition and nutritional guidance.

[0059] As a concrete example, a user inputs a prompt into the AI ​​model stating, "I want you to analyze the distance covered and the number of sprints performed by players during a match and suggest a training plan to improve their stamina." The server then measures the distance covered and the number of sprints from the match footage and uses the AI ​​model to suggest an effective training plan to improve stamina. This suggestion includes specific running menus and nutritional advice.

[0060] This system allows users to receive optimal coaching based on their individual performance and enables efficient data analysis.

[0061] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0062] Step 1:

[0063] The user uploads soccer match footage from their device to the server. The input is a match video file, which the server receives and saves. Specifically, the user selects the file using a dedicated interface and clicks the upload button.

[0064] Step 2:

[0065] The server analyzes the saved match footage using video analysis software (e.g., OpenCV). The input is the saved video file, and the output is player movement and position data. The server identifies players in the video and extracts data such as the distance covered and the number of sprints for each player. Specifically, the server tracks the position of each player frame by frame and calculates the distance traveled.

[0066] Step 3:

[0067] The server inputs the extracted data into an AI model (e.g., TensorFlow or PyTorch) to analyze the players' abilities. The input is data on the players' movements and positions, and the output is an evaluation of the players' strengths and weaknesses. The AI ​​model analyzes the data to evaluate each player's performance and generates suggestions for improvement. Specifically, the AI ​​model passes the data through a pre-trained model and calculates an evaluation score.

[0068] Step 4:

[0069] The server generates a customized training plan and nutritional guidance tailored to the athlete's condition based on the analysis results. The input is the athlete's evaluation results, and the output is a specific training menu and nutritional advice. The server uses a generation AI model to receive prompt messages and generates specific suggestions based on the analysis results. Specifically, the server inputs prompt messages into the AI ​​model and generates customized advice.

[0070] Step 5:

[0071] The server sends the generated training plan and nutritional guidance to the user's terminal. The input is the generated suggestions, and the output is information in a format that the user can review. Specifically, the server converts the suggestions into text format and sends a notification to the user's terminal.

[0072] (Application Example 1)

[0073] Next, we will describe Application Example 1 of Form 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."

[0074] There is a need to improve the operational efficiency of robots in factories and optimize the timing and methods of maintenance. However, conventional methods have made it difficult to detect inefficiencies in operation in real time and propose efficient operation plans.

[0075] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0076] In this invention, the server includes means for recording operations, means for collecting individual data from the recorded operations, means for performing efficiency analysis and suggesting improvements based on the collected data, and means for providing customized optimization plans and maintenance advice according to the state of operation. This enables real-time optimization of robot operations within a factory, resulting in efficient operation.

[0077] "Means for recording motion" refers to a device or method for recording the motion of robots and machinery in a factory using video or sensors.

[0078] "Means for collecting individual data" refers to a device or method for extracting operational information of a specific robot or machine from recorded movements and collecting it as data.

[0079] "Means for analyzing efficiency and proposing improvements" refers to a device or method that evaluates the efficiency of operations based on collected operational data and makes specific suggestions for improvement.

[0080] "Means for providing customized optimization plans and maintenance advice according to the operating state" refers to a device or method that takes into account the current operating state of a robot or machine and individually provides the optimal operating plan and maintenance method.

[0081] The system for implementing this invention is designed to optimize the operation of robots within a factory. The server records the robot's movements in real time using surveillance cameras and sensors installed within the factory. The recorded video data is analyzed frame by frame using OpenCV, and the operation data of each robot is extracted.

[0082] The server inputs collected operational data into a generative AI model built using TensorFlow to evaluate the efficiency of the operations. The AI ​​model detects inefficiencies and errors in the operations and generates efficient operation plans. Furthermore, it provides customized optimization plans and maintenance advice based on the operational status.

[0083] As a concrete example, we can analyze the movements of a robotic arm used in a factory and propose a plan to reduce wasted motion. Based on the generated plan, the user can adjust the robot's movements to achieve efficient operation.

[0084] An example of a prompt would be, "Analyze the video of the robot arm's movements and propose an efficient movement plan." This prompt prompts the AI ​​model to analyze the movement data and generate the optimal plan.

[0085] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0086] Step 1:

[0087] The server records the robot's movements in real time from surveillance cameras and sensors installed within the factory. The input is video data from the cameras and sensors, and the output is the recorded video file. In this step, the video data is divided into frames in preparation for subsequent analysis.

[0088] Step 2:

[0089] The server analyzes the recorded video data using OpenCV and extracts robot motion data from each frame. The input is the video file obtained in step 1, and the output is the motion data. In this step, the characteristics of the motion are extracted and organized as data.

[0090] Step 3:

[0091] The server inputs the extracted motion data into a generative AI model built using TensorFlow and evaluates the efficiency of the motion. The input is the motion data obtained in step 2, and the output is the efficiency evaluation result. In this step, the AI ​​model detects inefficiencies and errors in the motion.

[0092] Step 4:

[0093] The server generates an efficient operation plan based on the evaluation results of the AI ​​model. The input is the evaluation results obtained in step 3, and the output is the optimized operation plan. In this step, areas for improvement in operation are identified, and a specific plan is formulated.

[0094] Step 5:

[0095] The user adjusts the robot's movements based on the optimization plan provided by the server. The input is the movement plan obtained in step 4, and the output is the adjusted robot's movements. In this step, the user modifies the robot's settings according to the plan to achieve efficient operation.

[0096] (Example 2)

[0097] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0098] In sports competitions, analyzing athletes' performance in detail and providing individualized improvement suggestions and nutritional guidance is time-consuming and labor-intensive using traditional methods, making it difficult to do efficiently and effectively. This is especially true for junior athletes, who require appropriate guidance tailored to their individual developmental stages, but there is a lack of systems to achieve this.

[0099] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0100] In this invention, the server includes means for transmitting match video, means for acquiring group and individual information from the match video, means for evaluating abilities and suggesting improvements based on the acquired information, means for providing exercise plans and nutritional guidance tailored to the individual's condition, and means for generating prompt sentences using a generative AI model. This makes it possible to efficiently analyze athlete performance and quickly provide individual improvement suggestions and nutritional guidance.

[0101] "Match footage" refers to video data that records the events of a sports competition, allowing viewers to visually perceive the movements of the players and the progress of the match.

[0102] "Means of transmission" refers to technical means for moving data from one point to another, and includes the function of transferring data over a network.

[0103] "Group and individual information" refers to data about the entire team and each individual player participating in the match, including detailed information about their performance and behavior.

[0104] "Means of acquisition" refers to technical means for collecting data and extracting necessary information, and includes functions that use sensors and analysis software to obtain information.

[0105] "Performance assessment" is the process of analyzing an athlete's performance and measuring their technical and physical abilities.

[0106] "Suggestions for improvement" involve providing specific advice and plans to improve a player's performance, including changes to training and tactics.

[0107] "Individual condition" refers to the physical and mental condition of the athlete, including their health status and fatigue level.

[0108] A "tailored exercise plan" is a training program customized to the individual needs and condition of the athlete, aiming for efficient performance improvement.

[0109] "Nutritional guidance" involves providing advice on diet and nutrient intake to optimize an athlete's health and performance.

[0110] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[0111] A "prompt statement" is an instruction given to a generative AI model, serving as a guideline for the AI ​​to generate appropriate output.

[0112] A description of embodiments for carrying out this invention will be given.

[0113] Users upload match footage they filmed after junior soccer matches to the system using their devices. The server uses OpenCV and TensorFlow as AI analysis software to analyze the received match footage. The server uses this software to identify players in the match footage and track each player's movements.

[0114] The server collects performance data for each player through video analysis, such as distance covered, number of sprints, and pass completion rate. For example, it might record that player A ran 5km during a match, performed 15 sprints, and had a pass completion rate of 80%.

[0115] The collected data is input into a generating AI model on the server to analyze each player's performance. The AI ​​model evaluates the players' physical and technical tendencies and identifies areas for improvement. For example, if player B's sprint count decreases in the second half of a match, the AI ​​will make specific suggestions such as, "We recommend interval training three times a week to improve stamina."

[0116] Furthermore, the server uses AI to generate customized nutritional advice based on the player's condition. For example, it might advise, "Eat a meal high in carbohydrates before a match, and a meal containing protein and vitamins after a match."

[0117] As an example of a prompt that the user inputs to the generated AI model, you can use a sentence such as, "Analyze the match video, collect performance data for each player, and provide suggestions for improvement."

[0118] This system allows coaches and players at junior soccer clubs to review their performance after matches and identify specific areas for improvement.

[0119] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0120] Step 1:

[0121] Users upload match footage they filmed after junior soccer matches to the system using a terminal. The input is the match video file, and the output is the transfer of video data to the server. Users select the file through the terminal interface and press the upload button to send the video data to the server.

[0122] Step 2:

[0123] The server passes the received match video to AI analysis software (e.g., OpenCV or TensorFlow). The input is the match video data, and the output is data ready for analysis. The server divides the video data into frames and performs preprocessing to identify the players in each frame.

[0124] Step 3:

[0125] The server uses an AI model to track players in match footage and analyze each player's movements. The input is pre-processed video data, and the output is movement data for each player. The server tracks players' positions and movements and collects performance data such as distance covered and number of sprints.

[0126] Step 4:

[0127] The server inputs the collected performance data into a generating AI model to analyze each player's performance. The input is data on each player's movements, and the output is the performance evaluation result. The AI ​​model evaluates the players' physical strength and technical tendencies and identifies areas for improvement.

[0128] Step 5:

[0129] The server generates specific improvement suggestions for each player based on the analysis results. The input is the performance evaluation results, and the output is the improvement suggestions. For example, the AI ​​might suggest, "We recommend interval training three times a week to improve stamina."

[0130] Step 6:

[0131] The server uses AI to generate customized nutritional advice based on the player's condition. The input is the player's performance data and condition information, and the output is nutritional advice. For example, it might provide advice such as, "It is recommended to eat a meal high in carbohydrates before a match, and a meal containing protein and vitamins after a match."

[0132] Step 7:

[0133] The server provides users with generated improvement suggestions and nutritional advice. The input consists of improvement suggestions and nutritional advice, while the output is information provided to the user. Users can view this information through their terminals and utilize it for athlete training and nutrition management.

[0134] (Application Example 2)

[0135] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0136] There is a need to improve the operational efficiency and safety of machinery and workers operating within factories. However, conventional methods often involve manual recording and analysis of operations, making it difficult to propose efficient improvements.

[0137] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0138] In this invention, the server includes means for recording operations, means for collecting machine and operator-specific data from the recorded operations, means for analyzing work efficiency and safety and proposing improvements based on the collected data, and means for providing customized maintenance plans and operational advice according to the machine's condition. This makes it possible to efficiently and safely improve the operation of machines and operators within a factory.

[0139] "Means for recording motion" refers to devices or methods for recording the movements of machines or workers as video or sensor data.

[0140] "Means of collecting data" refers to devices and methods for extracting and organizing specific information for each machine or worker from recorded actions.

[0141] "Means for analysis and improvement proposals" refer to devices and methods for evaluating work efficiency and safety based on collected data and generating specific proposals for improvement.

[0142] "Means of providing maintenance plans and operational advice" refers to devices or methods for presenting appropriate maintenance schedules and operating procedures according to the condition of the machine and the actions of the operator.

[0143] Artificial intelligence is a technology that enables computer systems to mimic human intellectual behavior and perform data analysis and decision-making.

[0144] A description of the embodiment for carrying out the invention will be provided.

[0145] The system that realizes this invention is intended to improve the efficiency and safety of the operation of machinery and workers in a factory. The server records the movements of machinery and workers using cameras and sensors as means of recording operations. The recorded data is transmitted to the server as a means of data collection, and specific information for each machine and worker is extracted.

[0146] The server uses artificial intelligence to evaluate work efficiency and safety based on collected data, as a means of analysis and suggesting improvements. This involves using Python, analyzing videos with OpenCV, and building AI models using TensorFlow and PyTorch. This generates efficient operation patterns and specific suggestions for improving safety.

[0147] Furthermore, the server provides maintenance plans and operational advice by suggesting appropriate maintenance schedules and operating methods tailored to the machine's condition and the operator's actions. This maximizes machine operating efficiency and ensures operator safety.

[0148] A concrete example is when a robot is assembling parts, and the AI ​​detects that a particular movement is slow and suggests a new movement pattern to improve that movement. An example of a prompt used in this case would be, "Analyze the robot's movement patterns in this video and suggest improvements to increase efficiency."

[0149] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0150] Step 1:

[0151] The server uses cameras and sensors installed within the factory to record the movements of machinery and workers in real time. The input is video data from the cameras and sensors, and the output is a recorded video file. This video file is stored on the server for subsequent analysis.

[0152] Step 2:

[0153] The server divides the recorded video file into frames and extracts feature data related to the movements of machines and workers from each frame. The input is a video file, and the output is feature data for each frame. Image processing is performed using OpenCV to extract information such as the speed and direction of the movements.

[0154] Step 3:

[0155] The server uses the extracted feature data to perform analysis using an artificial intelligence model. The input is feature data, and the output is an evaluation result regarding work efficiency and safety. The AI ​​model, built using TensorFlow or PyTorch, identifies efficient operating patterns and areas for improvement to enhance safety.

[0156] Step 4:

[0157] The server generates specific improvement suggestions for machines and workers based on the analysis results. The input is the evaluation results, and the output is a list of improvement suggestions. Using the generated AI model, concrete action plans are created to improve efficiency and ensure safety.

[0158] Step 5:

[0159] The server provides machine maintenance schedules and operator advice based on improvement suggestions. Input is a list of improvement suggestions, and output is a maintenance plan and operational advice. This maximizes machine operating efficiency and ensures operator safety.

[0160] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0161] "Example of form 1"

[0162] One embodiment of the present invention is a system that incorporates an emotion engine. This system includes means for uploading soccer match videos, means for collecting team and player-specific data from the match videos, means for analyzing performance and suggesting improvements based on the collected data, means for providing customized training plans and nutritional advice according to the players' condition, and an emotion engine that recognizes the user's emotions. The emotion engine collects the user's emotional data and analyzes performance and suggests improvements based on that emotional data. The emotion engine also provides customized training plans and nutritional advice based on the user's emotional data.

[0163] "Example of form 2"

[0164] As a concrete example, a junior soccer club team uploads match videos to the system of the present invention after a game. The system uses AI to analyze the videos and collect performance data for each player. At the same time, the emotion engine collects the user's emotional data. Based on the collected performance data and emotional data, the AI ​​analyzes performance and suggests improvements. For example, if a particular player tends to have fewer sprints in the second half of a match, and fatigue can be inferred from that player's emotional data, the AI ​​will provide that player with a training plan to improve stamina and nutritional advice effective for fatigue recovery.

[0165] The following describes the processing flow for each example of the form.

[0166] "Example of form 1"

[0167] Step 1: The user uploads a video of a soccer match to the system.

[0168] Step 2: The system uses AI to collect team and player-specific data from the video.

[0169] Step 3: The emotion engine collects user emotion data.

[0170] Step 4: The AI ​​analyzes performance and suggests improvements based on the collected performance and sentiment data.

[0171] Step 5: The AI ​​provides a customized training plan and nutritional advice based on the player's condition.

[0172] "Example of form 2"

[0173] Step 1: Junior soccer club teams upload match videos to the system after the game.

[0174] Step 2: The system uses AI to analyze the videos and collect individual player performance data.

[0175] Step 3: The emotion engine collects user emotion data.

[0176] Step 4: The AI ​​analyzes performance and suggests improvements based on the collected performance and sentiment data.

[0177] Step 5: If a particular player tends to have a decrease in sprints in the second half of a match, and fatigue can be inferred from that player's emotional data, the AI ​​will provide that player with a training plan to improve stamina and nutritional advice that will help with fatigue recovery.

[0178] (Example 1)

[0179] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0180] In soccer matches, objectively evaluating player performance and providing optimal training plans and nutritional guidance to individual players has been difficult with traditional methods. Furthermore, coaching that takes into account players' emotional states relies on subjective judgment and is not optimized. This presents a challenge in effectively supporting player development.

[0181] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0182] In this invention, the server includes means for transmitting match video, means for extracting group and individual information from the match video, means for evaluating abilities and suggesting improvements based on the extracted information, means for providing training plans and nutritional guidance tailored to the individual's condition, and means for collecting and analyzing emotional information. This makes it possible to objectively evaluate the performance of players, provide optimal training plans and nutritional guidance for each player, and provide guidance that takes into account the emotional state of the players.

[0183] "Means for transmitting match footage" refers to a function that allows users to upload soccer match footage to the system and for the server to receive that footage.

[0184] "Means for extracting group and individual information" refers to a function for analyzing and collecting movement and performance data for the entire team and each individual player from match footage.

[0185] "Means for evaluating abilities and proposing improvements" refers to a function that analyzes a player's performance based on extracted data, identifies their strengths and weaknesses, and makes specific suggestions for improvement.

[0186] "Means of providing training plans and nutritional guidance tailored to individual conditions" refers to a function that generates and provides individually optimized training plans and nutritional advice based on the athlete's condition and performance data.

[0187] "Means for collecting and analyzing emotional information" refers to a function that collects user emotional data, analyzes that data, and provides guidance and support based on the emotional state of the players.

[0188] A description of embodiments for carrying out this invention will be given.

[0189] Users upload soccer match footage from their devices to the system. The server receives this footage and stores it in a database. Next, the server analyzes the footage using AI technology. Specifically, it utilizes computer vision technology and software such as OpenCV and TensorFlow to detect player movements and the position of the ball. This analysis extracts motion data for the entire team and for each individual player.

[0190] The server evaluates player performance based on the extracted data. Using an AI model, it identifies players' strengths and weaknesses and reveals areas for improvement. For example, it quantifies players' running distance and shooting accuracy and performs comparative analysis.

[0191] Furthermore, the server generates individually optimized training plans and nutritional advice based on the athlete's condition. This involves AI analyzing the athlete's data and suggesting running menus to improve endurance and meal plans to enhance concentration.

[0192] The server also uses an emotion engine to collect and analyze user emotional data. Based on the user's emotional state, it makes suggestions for performance improvement. For example, if a user is feeling stressed after a match, it might suggest mental training to help them relax.

[0193] For example, if a player is analyzed to have low running distance and poor shooting accuracy during a match, the server will provide that player with a training plan to improve endurance and nutritional advice to enhance concentration. Also, if a player is feeling down after a match, the emotional engine will suggest mental training to help them relax.

[0194] An example of a prompt for a generative AI model is: "Analyze a soccer match video, identify player A's strengths and weaknesses based on their performance data, and generate a training plan and nutritional advice for improvement. Also, consider player A's emotional data and suggest mental support."

[0195] The flow of the specific processing in Example 1 will be explained using Figure 15.

[0196] Step 1:

[0197] Users upload soccer match footage from their devices to the system. The input is the match video file, and the output is the video data stored on the server. Using their devices, users select the video file through a designated interface and press the upload button to send the video to the server.

[0198] Step 2:

[0199] The server stores the received video data in a database. The input is video data sent by the user, and the output is video data stored in the database. When the server receives video data, it uses a database management system to save the data in the appropriate format.

[0200] Step 3:

[0201] The server analyzes stored video data. The input is video data stored in a database, and the output is analysis data regarding player movements and ball position. The server uses computer vision technology, utilizing libraries such as OpenCV and TensorFlow, to detect player movements and ball position from the video.

[0202] Step 4:

[0203] The server evaluates player performance based on the analyzed data. The input is analyzed data on player movements and ball position, and the output is performance evaluation data for each player. The server uses an AI model to identify players' strengths and weaknesses and generate a quantified evaluation.

[0204] Step 5:

[0205] The server generates training plans and nutritional advice tailored to each athlete's condition. The input is the athlete's performance evaluation data, and the output is an individually optimized training plan and nutritional advice. The server utilizes AI to analyze the athlete's data and proposes running menus to improve endurance and meal plans to enhance concentration.

[0206] Step 6:

[0207] The server collects and analyzes user emotional data. The input is the user's emotional data, and the output is an analysis result based on their emotional state. The server uses an emotion engine to analyze the user's emotions and evaluate their stress and motivation levels.

[0208] Step 7:

[0209] The server provides customized advice based on the user's emotional state. The input is an analysis of the emotional state, and the output is a suggestion for mental support tailored to that emotional state. The server considers the user's emotional state and provides mental training to help them relax and advice to boost their motivation.

[0210] (Application Example 1)

[0211] Next, we will describe Application Example 1 of Form 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."

[0212] There is a need to improve the operational efficiency of robots in factories and to improve the work environment based on the emotions of the operators. However, conventional systems do not adequately analyze robot movements or recognize operator emotions, making it difficult to propose efficient movements or improve the work environment.

[0213] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0214] In this invention, the server includes means for uploading soccer match videos, means for collecting collective and individual data from the match videos, means for analyzing movements and suggesting improvements based on the collected data, means for providing customized training plans and nutritional guidance according to the individual's condition, and means for recognizing emotions and suggesting improvements to the work environment. This makes it possible to improve the operational efficiency of robots in factories and to improve the work environment based on the emotions of operators.

[0215] "A means of uploading soccer match videos" refers to a function for transferring video data of soccer matches to a server.

[0216] "Means for collecting collective and individual data from match videos" refers to a function for extracting information about the entire team and individual players from uploaded match videos.

[0217] "Means for analyzing operations and proposing improvements based on collected data" refers to a function that analyzes collected data and presents measures to improve the efficiency of operations and suggest improvements.

[0218] "Means of providing customized training plans and nutritional guidance according to the individual's condition" refers to a function that provides optimal training programs and nutritional advice based on the condition of each individual athlete or robot.

[0219] "Means for recognizing emotions and proposing improvements to the work environment" refers to a function that analyzes the emotions of operators and users and proposes measures to improve the work environment based on those analyses.

[0220] In an embodiment of this invention, the server is configured as follows: The server includes means for uploading soccer match videos, thereby allowing users to transfer match video data to the server. Next, the server extracts information about the entire team and individual players using means for collecting collective and individual data from the match videos. This data collection is performed using video analysis with Python and OpenCV.

[0221] Based on the collected data, the server employs means to analyze its behavior and suggest improvements. This process utilizes an AI model based on TensorFlow to generate efficient behavior plans. Furthermore, it provides customized training plans and nutritional guidance tailored to the individual's condition, which are also implemented by AI.

[0222] Furthermore, the server is equipped with the means to recognize emotions and suggest improvements to the work environment. It uses an emotion recognition API to analyze the emotional data of operators and users. This makes it possible to suggest improvements to the work environment.

[0223] As a concrete example, when a robot assembles parts in a factory, it can reduce wasted motion and suggest more efficient movements. It can also suggest breaks if the operator is tired. An example of a prompt message would be, "Analyze the robot's motion data and generate an efficient motion plan. Also, suggest improvements to the work environment based on the operator's emotional data."

[0224] The flow of a specific process in Application Example 1 will be explained using Figure 16.

[0225] Step 1:

[0226] The user uploads soccer match videos from their device to the server. The input is the video data of the match, and the output is the video file stored on the server. In this step, the user selects the match video and presses the upload button, and the data is transferred to the server.

[0227] Step 2:

[0228] The server collects collective and individual data from uploaded videos. The input is video files stored on the server, and the output is data about the entire team and individual players. Python and OpenCV are used to analyze the videos and extract player movement and position information.

[0229] Step 3:

[0230] The server analyzes the collected data and suggests improvements to the player's movements. The input is the player's movements and position information, and the output is an efficient movement plan. An AI model using TensorFlow analyzes the data and generates the optimal movement plan.

[0231] Step 4:

[0232] The server provides customized training plans and nutritional guidance tailored to each individual's condition. Inputs are the athlete's movement data and condition information, while output is individually customized training plans and nutritional advice. AI evaluates the athlete's strengths and weaknesses and proposes the optimal plan.

[0233] Step 5:

[0234] The server recognizes emotions and provides suggestions for improving the work environment. Input is emotional data from operators and users, and output is suggestions for improving the work environment. An emotion recognition API is used to analyze the emotional data and evaluate stress and fatigue levels.

[0235] Step 6:

[0236] The server notifies the user of the generated operation plan and improvement suggestions. The input is an efficient operation plan and improvement suggestions, and the output is a notification message to the user. The user can check the suggestions on their terminal and take action.

[0237] (Example 2)

[0238] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0239] Conventional sports analysis systems have limited data available from match videos, making it difficult to comprehensively evaluate athlete performance. Furthermore, they are unable to provide individualized improvement suggestions that take into account athlete emotions and physical condition, thus failing to adequately contribute to athlete development and health management.

[0240] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0241] In this invention, the server includes means for uploading match videos, means for collecting individual athlete data from the match videos, means for analyzing the athlete's condition based on the collected data and making suggestions for improvement, means for providing customized training plans and nutritional guidance according to the athlete's condition, means for collecting emotional data and utilizing it for analyzing the athlete's condition, and means for generating suggestions using a generative AI model. This makes it possible to comprehensively evaluate the athlete's performance and make improvement suggestions that meet individual needs.

[0242] "Match videos" are video data that records the events of a sports competition, allowing viewers to visually capture the movements of the players and the progress of the match.

[0243] "Athlete data" refers to information about individual players extracted from match videos, including performance indicators such as distance covered, number of sprints, and pass completion rate.

[0244] "Athlete status" refers to the physical and mental condition of an athlete, and is assessed based on performance data and emotional data.

[0245] A "training plan" outlines the schedule and content of training aimed at improving an athlete's performance, and is customized according to individual needs.

[0246] "Nutritional guidance" refers to advice on diet and nutrient intake aimed at maintaining the health and improving the performance of athletes, and is provided according to the individual athlete's condition.

[0247] "Emotional data" refers to information that indicates an athlete's emotional state, and is obtained through the analysis of facial expressions and movements.

[0248] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to analyze data and generate suggestions or predictions.

[0249] This invention is a system for analyzing sports competition videos to evaluate and improve athlete performance. Users upload match videos to the system using a terminal after the match. The server utilizes computer vision technology to analyze the received videos. Specifically, it uses software libraries such as OpenCV and TensorFlow to track the movements of athletes and extract individual athlete data.

[0250] The server collects athlete data such as distance covered, number of sprints, and pass completion rate for each player from the analysis results. Furthermore, it uses an emotion engine to collect emotional data from the players and comprehensively evaluate their condition. This makes it possible to understand the players' physical and mental condition.

[0251] The server uses a generated AI model based on the collected data to analyze player performance and generate suggestions for improvement. For example, if a particular player tends to have a decrease in sprints in the second half of a match, the server will suggest a training plan to improve that player's stamina. It also provides customized nutritional guidance on energy sources to consume before a match and nutrients needed for post-match recovery.

[0252] As a concrete example, an example of a prompt sentence to be input to the generating AI model is: "Please suggest a stamina-improving training plan for a player whose sprint count decreases in the second half of a match. Also, please provide nutritional advice before and after the match."

[0253] This system allows users to comprehensively evaluate athlete performance and receive improvement suggestions tailored to their individual needs. This can contribute to athlete development and health management.

[0254] The flow of the specific processing in Example 2 will be explained using Figure 17.

[0255] Step 1:

[0256] After a match, the user uploads the match video to the system using a terminal. The input is the match video file, and the output is the transfer of the video data to the server. The terminal checks the format and size of the video file, converts it to the appropriate format, and sends it to the server.

[0257] Step 2:

[0258] The server uses computer vision technology to analyze the received match videos. The input is the uploaded video data, and the output is data tracking the players' movements. Specifically, it uses libraries such as OpenCV and TensorFlow to track the position and movement of players in the video in real time and record each player's actions in a database.

[0259] Step 3:

[0260] The server collects individual athlete data from the analysis results. The input is tracking data, and the output is performance indicators such as distance covered, number of sprints, and pass completion rate. The server aggregates this data and quantifies the performance of each athlete.

[0261] Step 4:

[0262] The server uses an emotion engine to collect emotional data from players. The input is video data of the players' facial expressions and movements, and the output is data indicating the players' emotional state. The server uses an AI model to infer emotions from the video and evaluate the players' mental condition.

[0263] Step 5:

[0264] The server integrates collected athlete and emotional data and analyzes athlete performance using a generative AI model. The input is the integrated dataset, and the output is the analysis results identifying the athlete's strengths and areas for improvement. The server uses the AI ​​model to analyze the data and comprehensively evaluate the athlete's performance.

[0265] Step 6:

[0266] The server generates improvement suggestions for each player based on the analysis results. The input is the analysis results, and the output is a customized training plan and nutritional guidance. The server uses a generative AI model to create prompt messages and generate the optimal training plan and nutritional advice for each player.

[0267] Step 7:

[0268] The server provides the user with the generated suggestions. The input is customized suggestions, and the output is information provided to the user. The user can review these suggestions through their terminal and use them for athlete training and nutrition management.

[0269] (Application Example 2)

[0270] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0271] There is a growing need to monitor the operational efficiency of machinery and the condition of workers in factories in real time, and to propose efficient work plans and break schedules. However, conventional methods make it difficult to efficiently collect and analyze this data and make appropriate improvement suggestions.

[0272] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0273] In this invention, the server includes means for uploading video data, means for collecting data for each machine and operator from the video data, means for analyzing operations and proposing improvements based on the collected data, and means for providing a customized work plan and rest advice according to the operator's condition. This enables efficient management and improvement proposals for machines and operators in the factory.

[0274] "Video data" refers to digital data including visual information acquired by cameras and other imaging devices.

[0275] "Means for uploading" refers to a method or device for transferring digital data to a server or cloud storage via a network.

[0276] "Data for each machine and operator" refers to information on the operation of individual machines in the factory and the working conditions and status of operators.

[0277] "Means for collecting" refers to a method or device for acquiring specific information and gathering it for storage or analysis.

[0278] "Analysis of operations" refers to a process for evaluating the operation data of machines and operators and identifying efficiency and problems.

[0279] "Means for proposing improvements" refers to a method or device for presenting a specific action plan for efficiency improvement and problem solving based on the analysis results.

[0280] The operator's condition" refers to information indicating the physical and mental condition of the operator.

[0281] "Customized work plan" refers to a work schedule and procedure optimized according to the condition and ability of each operator. ID=34]]

[0282] "Rest advice" is information that proposes appropriate rest timing and methods to reduce the fatigue and stress of workers.

[0283] The system for implementing this invention monitors the machines and the operations of workers in the factory and provides efficient management and improvement proposals. The server transfers the video data obtained from the surveillance cameras in the factory to cloud storage using means for uploading video data. Next, it obtains the operation information of individual machines and the working status of workers using means for collecting data for each machine and worker from the video data.

[0284] This data is processed with OpenCV using Python and the operation is analyzed by a generative AI model using TensorFlow. The server uses means for proposing improvements based on the analysis results and presents a specific action plan for efficiency improvement and problem solving. Furthermore, in order to provide a customized work plan and rest advice according to the state of the worker, emotion recognition APIs (e.g., Microsoft (registered trademark) Azure (registered trademark) Emotion API) are used to collect and comprehensively analyze the emotion data of the worker.

[0285] As a specific example, if it is found that the operating efficiency of a specific machine decreases in the afternoon, the server proposes regular maintenance for that machine. Also, if it is found from the emotion data of the worker that the stress is increasing, rest can be proposed.

[0286] An example of a prompt sentence is "Analyze the cause of the decrease in machine operating efficiency in the afternoon and propose improvement measures."

[0287] The flow of the specific process in Application Example 2 will be described using FIG. 18.

[0288] Step 1:

[0289] The server acquires video data from surveillance cameras within the factory and uploads it to cloud storage via the network. The input is real-time video data from the surveillance cameras, and the output is a video file stored in cloud storage. This step involves the transfer and storage of video data.

[0290] Step 2:

[0291] The server processes the uploaded video data using OpenCV with Python and extracts motion data for both the machine and the worker. The input is a video file stored in cloud storage, and the output is machine motion information and worker work status data. In this step, video data analysis and motion data extraction are performed.

[0292] Step 3:

[0293] The server analyzes the extracted motion data using a generative AI model based on TensorFlow to identify operational efficiency and problems. The input consists of machine motion information and worker work status data, while the output is the analysis results regarding operational efficiency and problems. In this step, data analysis is performed by the AI ​​model.

[0294] Step 4:

[0295] The server makes improvement suggestions based on the analysis results and generates concrete action plans for efficiency improvement and problem solving. The input is the analysis results regarding operational efficiency and problems, and the output is the action plan of improvement suggestions. In this step, improvement measures are generated and proposed.

[0296] Step 5:

[0297] The server uses an emotion recognition API to collect worker emotion data and evaluate the worker's state. The input is real-time video data of the worker, and the output is the worker's emotion data. In this step, emotion data is collected and evaluated.

[0298] Step 6:

[0299] The server integratively analyzes the operator's emotional data and motion data, and provides a customized work plan and rest advice. The input is the operator's emotional data and motion data, and the output is the customized work plan and rest advice. In this step, integrated data analysis and individual proposals are carried out.

[0300] (Other embodiments)

[0301] Next, other embodiments will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0302] In the conventional sports analysis system, there is a problem that it is difficult not only to collect the performance data of athletes, but also to provide specific improvement proposals and training plans based on the data. In addition, since analysis and proposals considering the emotional state of athletes have not been carried out, there is also a problem that the mental support for athletes is insufficient.

[0303] The specific processing by the specific processing unit 290 of the data processing device 12 in other embodiments is realized by the following means.

[0304] In this invention, the server includes means for uploading a game video, means for analyzing and collecting data from the uploaded video, and means for generating a prompt using a generated AI model and instructing to make an improvement proposal. Thereby, it becomes possible to analyze the performance of athletes in detail and provide individual improvement proposals and training plans.

[0305] The "game video" is video data that captures the state of a soccer game and records the movements of players and teams.

[0306] "Means for uploading" refers to the software or hardware functionality for sending match videos filmed by users to a server.

[0307] "Means of analyzing and collecting data" refers to the functions of software or hardware that extract information about the movements of players and teams from match videos and process it to store it in a database.

[0308] A "generative AI model" refers to an algorithm or program that uses artificial intelligence technology to perform analysis and make suggestions based on input data and prompts.

[0309] A "prompt" is an input sentence used to instruct a generative AI model to perform a specific analysis or make a suggestion, and it contains specific instructions.

[0310] "Means for instructing the AI ​​to make improvement suggestions" refers to a function that creates prompts to instruct the generative AI model to generate suggestions for improving the player's performance.

[0311] A description of the embodiment for carrying out the invention will be provided.

[0312] This invention is a system that analyzes soccer match videos and generates specific suggestions for improving player performance. The system mainly consists of three elements: a server, a terminal, and a user.

[0313] The server receives match videos uploaded from user terminals and saves them to a cloud storage service (e.g., Amazon S3). The saved videos are analyzed using video analysis software such as OpenCV. As a result of the analysis, data related to the movements of players and teams is extracted and saved to a MySQL® database.

[0314] The server analyzes the players' performance using a generative AI model (e.g., OpenAI® GPT-4®) based on the collected data. It generates prompts to provide specific improvement suggestions and inputs them into the generative AI model. Based on these prompts, the generative AI model generates specific suggestions for improving the players' performance and returns them to the server.

[0315] Furthermore, the server monitors the player's condition data and generates prompts using a generative AI model to provide customized training plans and nutritional advice. Based on the prompts, the generative AI model generates the optimal training plan and nutritional advice for the player and returns it to the server.

[0316] Users film soccer matches using their smartphones or cameras and upload the videos to a server via a dedicated application. The user's device receives analysis results and suggestions from the server and displays them within the application. Users then review the provided training plans and nutritional advice and use them in their actual training and nutrition management.

[0317] Example prompt: Based on player A's distance covered and pass success rate, please suggest areas for improvement.

[0318] The flow of a specific process in another embodiment will be explained using Figure 19.

[0319] Step 1:

[0320] Users film soccer matches using their smartphones or cameras. The filmed videos are uploaded to a server via a dedicated application. The input is the match video, and the output is a video file stored in cloud storage. The application sends the video to the server when the user selects the video file and presses the upload button.

[0321] Step 2:

[0322] The server receives uploaded match videos and saves them to cloud storage such as Amazon S3. The input is the video file sent by the user, and the output is the video file saved in the cloud storage. Once saving is complete, the server records the video's metadata (e.g., upload date and time, file size) in a database.

[0323] Step 3:

[0324] The server uses video analysis software such as OpenCV to analyze the stored match videos. The input is video files stored in cloud storage, and the output is data about the movements of players and teams. The analysis tracks player movements and ball positions and extracts data. The extracted data is stored in a MySQL database.

[0325] Step 4:

[0326] The server analyzes player performance using a generative AI model (e.g., OpenAI GPT-4) based on the collected data. The input is data about player movements stored in a database, and the output is suggestions for improving player performance. The server generates prompts for improvement suggestions and inputs them into the generative AI model.

[0327] Example prompt: Based on player A's distance covered and pass success rate, please suggest areas for improvement.

[0328] Step 5:

[0329] The generative AI model generates specific suggestions for improving a player's performance based on the input prompt sentence. The input is the prompt sentence, and the output is the generated suggestion. The generated suggestion is returned to the server.

[0330] Step 6:

[0331] The server monitors the player's condition data and generates prompts using a generative AI model to provide customized training plans and nutritional advice. The input is the player's condition data, and the output is the training plan and nutritional advice.

[0332] Example prompt: Create a training plan and nutritional advice for player B, taking into account their fatigue level and weight changes.

[0333] Step 7:

[0334] The user terminal receives analysis results and suggestions sent from the server and displays them on the application. The input is the analysis results and suggestions from the server, and the output is the information displayed on the user interface. The user reviews the provided training plan and nutritional advice and uses it in their actual training and nutrition management.

[0335] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0336] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0337] Other examples of generative AI include Gemini® (registered trademark) (Internet search). <url: https: gemini.google.com ?hl="ja">) are some examples.

[0338] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0339] [Second Embodiment]

[0340] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0341] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0342] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0343] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0344] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0345] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0346] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0347] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0348] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0349] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0350] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0351] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0352] "Example of form 1"

[0353] The system of the present invention includes means for uploading soccer match videos, means for collecting team and player-specific data from the match videos, means for analyzing performance and suggesting improvements based on the collected data, and means for providing customized training plans and nutritional advice according to the players' condition. These means are realized using AI technology. Specifically, the system analyzes players' movements and performance from match videos to understand each player's strengths and weaknesses. Furthermore, the AI ​​provides optimal training plans and nutritional advice according to the players' condition and performance. This moves away from subjective instruction based on the experience and knowledge of coaches and parents, and supports growth with the most optimal coaching methods. "Example Form 2"

[0354] As a concrete example, a junior soccer club team uploads match videos to the system of the present invention after a game. The system uses AI to analyze the videos and collect individual player performance data (e.g., distance covered, number of sprints, pass success rate, etc.). Furthermore, the AI ​​analyzes performance and suggests improvements based on the collected data. For example, if a particular player tends to have a decrease in the number of sprints in the second half of a match, the AI ​​will suggest a training plan to improve that player's stamina. The system also provides customized nutritional advice according to the player's condition (e.g., energy sources to consume before a match, nutrients needed for recovery after a match, etc.).

[0355] The following describes the processing flow for each example of the form.

[0356] "Example of form 1"

[0357] Step 1: A user (e.g., a coach or parent) uploads a video of a soccer match to the system of the present invention.

[0358] Step 2: The system uses AI to analyze the video and collect individual player performance data (e.g., distance covered, number of sprints, pass completion rate, etc.).

[0359] Step 3: The AI ​​analyzes performance and suggests improvements based on the collected data.

[0360] Step 4: Based on the player's condition, the AI ​​provides a customized training plan and nutritional advice.

[0361] "Example of form 2"

[0362] Step 1: A junior soccer club team uploads a video of the match to the system of the present invention after the match.

[0363] Step 2: The system uses AI to analyze the videos and collect individual player performance data.

[0364] Step 3: The AI ​​analyzes performance and suggests improvements based on the collected data. If a particular player tends to have fewer sprints in the second half of a match, the AI ​​will suggest a training plan to improve that player's stamina.

[0365] Step 4: Based on the player's condition, the AI ​​provides customized nutritional advice. For example, it suggests energy sources to consume before a match and nutrients needed for recovery after a match.

[0366] (Example 1)

[0367] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0368] Traditional soccer coaching relied heavily on the experience and knowledge of coaches and parents, resulting in a subjective approach that made it difficult to provide optimal coaching based on individual player performance and condition. Furthermore, data collection and analysis from match footage were often done manually, making efficient analysis challenging.

[0369] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0370] In this invention, the server includes means for transmitting match video, means for acquiring group and individual information from the match video, means for analyzing abilities and suggesting improvements based on the acquired information, means for providing training plans and nutritional guidance tailored to the individual's condition, and means for inputting prompt sentences using a generative AI model and generating specific suggestions based on the analysis results. This enables optimal guidance based on the individual performance of each player and efficient data analysis.

[0371] "Match footage" refers to video data that records the events of a soccer match, and is used to visually capture the movements of the players and teams.

[0372] "Means of transmission" refers to a device or software that has the function of transferring digital data to other devices or systems via a network.

[0373] "Group and individual information" refers to data about the entire team and each player extracted from match footage, including detailed information about performance and movement.

[0374] "Means of acquisition" refers to devices or software used to collect specific data or information and convert it into a format usable within the system.

[0375] "Performance analysis" is the process of evaluating the performance of players and teams based on collected data, and identifying their strengths and weaknesses.

[0376] "Suggestions for improvement" refers to providing specific advice and strategies to improve the performance of players and teams based on the analysis results.

[0377] "Individual condition" refers to information about each player's physical condition, such as their health, fitness level, and fatigue level.

[0378] A "tailored training plan" is a training menu customized according to the individual athlete's condition and goals, aiming for effective performance improvement.

[0379] "Nutritional guidance" refers to providing advice on diet and nutritional intake in order to optimize an athlete's health and performance.

[0380] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[0381] A "prompt statement" is a sentence containing instructions or questions that are input into a generative AI model, and it serves as a trigger for the model to generate appropriate output.

[0382] This invention is a system for analyzing soccer match footage to improve the performance of players and teams. Users upload match footage from their terminals to a server. The server analyzes the footage using video analysis software (e.g., OpenCV) and extracts player movement and position data. This allows for the acquisition of group and individual information.

[0383] The server inputs the acquired information into an AI model (e.g., TensorFlow or PyTorch) to analyze the player's abilities. The AI ​​model evaluates the player's strengths and weaknesses and generates specific suggestions for improvement. This includes a training plan tailored to the player's condition and nutritional guidance.

[0384] As a concrete example, a user inputs a prompt into the AI ​​model stating, "I want you to analyze the distance covered and the number of sprints performed by players during a match and suggest a training plan to improve their stamina." The server then measures the distance covered and the number of sprints from the match footage and uses the AI ​​model to suggest an effective training plan to improve stamina. This suggestion includes specific running menus and nutritional advice.

[0385] This system allows users to receive optimal coaching based on their individual performance and enables efficient data analysis.

[0386] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0387] Step 1:

[0388] The user uploads soccer match footage from their device to the server. The input is a match video file, which the server receives and saves. Specifically, the user selects the file using a dedicated interface and clicks the upload button.

[0389] Step 2:

[0390] The server analyzes the saved match footage using video analysis software (e.g., OpenCV). The input is the saved video file, and the output is player movement and position data. The server identifies players in the video and extracts data such as the distance covered and the number of sprints for each player. Specifically, the server tracks the position of each player frame by frame and calculates the distance traveled.

[0391] Step 3:

[0392] The server inputs the extracted data into an AI model (e.g., TensorFlow or PyTorch) to analyze the players' abilities. The input is data on the players' movements and positions, and the output is an evaluation of the players' strengths and weaknesses. The AI ​​model analyzes the data to evaluate each player's performance and generates suggestions for improvement. Specifically, the AI ​​model passes the data through a pre-trained model and calculates an evaluation score.

[0393] Step 4:

[0394] The server generates a customized training plan and nutritional guidance tailored to the athlete's condition based on the analysis results. The input is the athlete's evaluation results, and the output is a specific training menu and nutritional advice. The server uses a generation AI model to receive prompt messages and generates specific suggestions based on the analysis results. Specifically, the server inputs prompt messages into the AI ​​model and generates customized advice.

[0395] Step 5:

[0396] The server sends the generated training plan and nutritional guidance to the user's terminal. The input is the generated suggestions, and the output is information in a format that the user can review. Specifically, the server converts the suggestions into text format and sends a notification to the user's terminal.

[0397] (Application Example 1)

[0398] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0399] There is a need to improve the operational efficiency of robots in factories and optimize the timing and methods of maintenance. However, conventional methods have made it difficult to detect inefficiencies in operation in real time and propose efficient operation plans.

[0400] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0401] In this invention, the server includes means for recording operations, means for collecting individual data from the recorded operations, means for performing efficiency analysis and suggesting improvements based on the collected data, and means for providing customized optimization plans and maintenance advice according to the state of operation. This enables real-time optimization of robot operations within a factory, resulting in efficient operation.

[0402] "Means for recording motion" refers to a device or method for recording the motion of robots and machinery in a factory using video or sensors.

[0403] "Means for collecting individual data" refers to a device or method for extracting operational information of a specific robot or machine from recorded movements and collecting it as data.

[0404] "Means for analyzing efficiency and proposing improvements" refers to a device or method that evaluates the efficiency of operations based on collected operational data and makes specific suggestions for improvement.

[0405] "Means for providing customized optimization plans and maintenance advice according to the operating state" refers to a device or method that takes into account the current operating state of a robot or machine and individually provides the optimal operating plan and maintenance method.

[0406] The system for implementing this invention is designed to optimize the operation of robots within a factory. The server records the robot's movements in real time using surveillance cameras and sensors installed within the factory. The recorded video data is analyzed frame by frame using OpenCV, and the operation data of each robot is extracted.

[0407] The server inputs collected operational data into a generative AI model built using TensorFlow to evaluate the efficiency of the operations. The AI ​​model detects inefficiencies and errors in the operations and generates efficient operation plans. Furthermore, it provides customized optimization plans and maintenance advice based on the operational status.

[0408] As a concrete example, we can analyze the movements of a robotic arm used in a factory and propose a plan to reduce wasted motion. Based on the generated plan, the user can adjust the robot's movements to achieve efficient operation.

[0409] An example of a prompt would be, "Analyze the video of the robot arm's movements and propose an efficient movement plan." This prompt prompts the AI ​​model to analyze the movement data and generate the optimal plan.

[0410] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0411] Step 1:

[0412] The server records the robot's movements in real time from surveillance cameras and sensors installed within the factory. The input is video data from the cameras and sensors, and the output is the recorded video file. In this step, the video data is divided frame by frame in preparation for subsequent analysis.

[0413] Step 2:

[0414] The server analyzes the recorded video data using OpenCV and extracts robot motion data from each frame. The input is the video file obtained in step 1, and the output is motion data. In this step, the characteristics of the motion are extracted and organized as data.

[0415] Step 3:

[0416] The server inputs the extracted motion data into a generative AI model built using TensorFlow and evaluates the efficiency of the motion. The input is the motion data obtained in step 2, and the output is the efficiency evaluation result. In this step, the AI ​​model detects inefficiencies and errors in the motion.

[0417] Step 4:

[0418] The server generates an efficient operation plan based on the evaluation results of the AI ​​model. The input is the evaluation results obtained in step 3, and the output is the optimized operation plan. In this step, areas for improvement in operation are identified, and a specific plan is formulated.

[0419] Step 5:

[0420] The user adjusts the robot's movements based on the optimization plan provided by the server. The input is the movement plan obtained in step 4, and the output is the adjusted robot's movements. In this step, the user modifies the robot's settings according to the plan to achieve efficient operation.

[0421] (Example 2)

[0422] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0423] In sports competitions, analyzing athletes' performance in detail and providing individualized improvement suggestions and nutritional guidance is time-consuming and labor-intensive using traditional methods, making it difficult to do efficiently and effectively. This is especially true for junior athletes, who require appropriate guidance tailored to their individual developmental stages, but there is a lack of systems to achieve this.

[0424] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0425] In this invention, the server includes means for transmitting match video, means for acquiring group and individual information from the match video, means for evaluating abilities and suggesting improvements based on the acquired information, means for providing exercise plans and nutritional guidance tailored to the individual's condition, and means for generating prompt sentences using a generative AI model. This makes it possible to efficiently analyze athlete performance and quickly provide individual improvement suggestions and nutritional guidance.

[0426] "Match footage" refers to video data that records the events of a sports competition, allowing viewers to visually perceive the movements of the players and the progress of the match.

[0427] "Means of transmission" refers to technical means for moving data from one point to another, and includes the function of transferring data over a network.

[0428] "Group and individual information" refers to data about the entire team and each individual player participating in the match, including detailed information about their performance and behavior.

[0429] "Means of acquisition" refers to technical means for collecting data and extracting necessary information, and includes functions that use sensors and analysis software to obtain information.

[0430] "Performance assessment" is the process of analyzing an athlete's performance and measuring their technical and physical abilities.

[0431] "Suggestions for improvement" involve providing specific advice and plans to improve a player's performance, including changes to training and tactics.

[0432] "Individual condition" refers to the physical and mental condition of the athlete, including their health status and fatigue level.

[0433] A "tailored exercise plan" is a training program customized to the individual needs and condition of the athlete, aiming for efficient performance improvement.

[0434] "Nutritional guidance" involves providing advice on diet and nutrient intake to optimize an athlete's health and performance.

[0435] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[0436] A "prompt statement" is an instruction given to a generative AI model, serving as a guideline for the AI ​​to generate appropriate output.

[0437] A description of embodiments for carrying out this invention will be given.

[0438] Users upload match footage they filmed after junior soccer matches to the system using their devices. The server uses OpenCV and TensorFlow as AI analysis software to analyze the received match footage. The server uses this software to identify players in the match footage and track each player's movements.

[0439] The server collects performance data for each player through video analysis, such as distance covered, number of sprints, and pass completion rate. For example, it might record that player A ran 5km during a match, performed 15 sprints, and had a pass completion rate of 80%.

[0440] The collected data is input into a generating AI model on the server to analyze each player's performance. The AI ​​model evaluates the players' physical and technical tendencies and identifies areas for improvement. For example, if player B's sprint count decreases in the second half of a match, the AI ​​will make specific suggestions such as, "We recommend interval training three times a week to improve stamina."

[0441] Furthermore, the server uses AI to generate customized nutritional advice based on the player's condition. For example, it might advise, "Eat a meal high in carbohydrates before a match, and a meal containing protein and vitamins after a match."

[0442] As an example of a prompt that the user inputs to the generated AI model, you can use a sentence such as, "Analyze the match video, collect performance data for each player, and provide suggestions for improvement."

[0443] This system allows coaches and players at junior soccer clubs to review their performance after matches and identify specific areas for improvement.

[0444] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0445] Step 1:

[0446] Users upload match footage they filmed after junior soccer matches to the system using a terminal. The input is the match video file, and the output is the transfer of video data to the server. Users select the file through the terminal interface and press the upload button to send the video data to the server.

[0447] Step 2:

[0448] The server passes the received match video to AI analysis software (e.g., OpenCV or TensorFlow). The input is the match video data, and the output is data ready for analysis. The server divides the video data into frames and performs preprocessing to identify the players in each frame.

[0449] Step 3:

[0450] The server uses an AI model to track players in match footage and analyze each player's movements. The input is pre-processed video data, and the output is movement data for each player. The server tracks players' positions and movements and collects performance data such as distance covered and number of sprints.

[0451] Step 4:

[0452] The server inputs the collected performance data into a generating AI model to analyze each player's performance. The input is data on each player's movements, and the output is the performance evaluation result. The AI ​​model evaluates the players' physical strength and technical tendencies and identifies areas for improvement.

[0453] Step 5:

[0454] The server generates specific improvement suggestions for each player based on the analysis results. The input is the performance evaluation results, and the output is the improvement suggestions. For example, the AI ​​might suggest, "We recommend interval training three times a week to improve stamina."

[0455] Step 6:

[0456] The server uses AI to generate customized nutritional advice based on the player's condition. The input is the player's performance data and condition information, and the output is nutritional advice. For example, it might provide advice such as, "It is recommended to eat a meal high in carbohydrates before a match, and a meal containing protein and vitamins after a match."

[0457] Step 7:

[0458] The server provides users with generated improvement suggestions and nutritional advice. The input consists of improvement suggestions and nutritional advice, while the output is information provided to the user. Users can view this information through their terminals and utilize it for athlete training and nutrition management.

[0459] (Application Example 2)

[0460] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0461] There is a need to improve the operational efficiency and safety of machinery and workers operating within factories. However, conventional methods often involve manual recording and analysis of operations, making it difficult to propose efficient improvements.

[0462] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0463] In this invention, the server includes means for recording operations, means for collecting machine and operator-specific data from the recorded operations, means for analyzing work efficiency and safety and proposing improvements based on the collected data, and means for providing customized maintenance plans and operational advice according to the machine's condition. This makes it possible to efficiently and safely improve the operation of machines and operators within a factory.

[0464] "Means for recording motion" refers to devices or methods for recording the movements of machines or workers as video or sensor data.

[0465] "Means of collecting data" refers to devices and methods for extracting and organizing specific information for each machine or worker from recorded actions.

[0466] "Means for analysis and improvement proposals" refer to devices and methods for evaluating work efficiency and safety based on collected data and generating specific proposals for improvement.

[0467] "Means of providing maintenance plans and operational advice" refers to devices or methods for presenting appropriate maintenance schedules and operating procedures according to the condition of the machine and the actions of the operator.

[0468] Artificial intelligence is a technology that enables computer systems to mimic human intellectual behavior and perform data analysis and decision-making.

[0469] A description of the embodiment for carrying out the invention will be provided.

[0470] The system that realizes this invention is intended to improve the efficiency and safety of the operation of machinery and workers in a factory. The server records the movements of machinery and workers using cameras and sensors as means of recording operations. The recorded data is transmitted to the server as a means of data collection, and specific information for each machine and worker is extracted.

[0471] The server uses artificial intelligence to evaluate work efficiency and safety based on collected data, as a means of analysis and suggesting improvements. This involves using Python, analyzing videos with OpenCV, and building AI models using TensorFlow and PyTorch. This generates efficient operation patterns and specific suggestions for improving safety.

[0472] Furthermore, the server provides maintenance plans and operational advice by suggesting appropriate maintenance schedules and operating methods tailored to the machine's condition and the operator's actions. This maximizes machine operating efficiency and ensures operator safety.

[0473] A concrete example is when a robot is assembling parts, and the AI ​​detects that a particular movement is slow and suggests a new movement pattern to improve that movement. An example of a prompt used in this case would be, "Analyze the robot's movement patterns in this video and suggest improvements to increase efficiency."

[0474] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0475] Step 1:

[0476] The server uses cameras and sensors installed within the factory to record the movements of machinery and workers in real time. The input is video data from the cameras and sensors, and the output is a recorded video file. This video file is stored on the server for subsequent analysis.

[0477] Step 2:

[0478] The server divides the recorded video file into frames and extracts feature data related to the movements of the machine and the worker from each frame. The input is the video file, and the output is feature data for each frame. Image processing is performed using OpenCV to extract information such as the speed and direction of the movements.

[0479] Step 3:

[0480] The server uses the extracted feature data to perform analysis using an artificial intelligence model. The input is feature data, and the output is an evaluation result regarding work efficiency and safety. The AI ​​model, built using TensorFlow or PyTorch, identifies efficient operating patterns and areas for improvement to enhance safety.

[0481] Step 4:

[0482] The server generates specific improvement suggestions for machines and workers based on the analysis results. The input is the evaluation results, and the output is a list of improvement suggestions. Using the generated AI model, concrete action plans are created to improve efficiency and ensure safety.

[0483] Step 5:

[0484] The server provides machine maintenance schedules and operator advice based on improvement suggestions. Input is a list of improvement suggestions, and output is a maintenance plan and operational advice. This maximizes machine operating efficiency and ensures operator safety.

[0485] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0486] "Example of form 1"

[0487] One embodiment of the present invention is a system that incorporates an emotion engine. This system includes means for uploading soccer match videos, means for collecting team and player-specific data from the match videos, means for analyzing performance and suggesting improvements based on the collected data, means for providing customized training plans and nutritional advice according to the players' condition, and an emotion engine that recognizes the user's emotions. The emotion engine collects the user's emotional data and analyzes performance and suggests improvements based on that emotional data. The emotion engine also provides customized training plans and nutritional advice based on the user's emotional data.

[0488] "Example of form 2"

[0489] As a concrete example, a junior soccer club team uploads match videos to the system of the present invention after a game. The system uses AI to analyze the videos and collect performance data for each player. At the same time, the emotion engine collects the user's emotional data. Based on the collected performance data and emotional data, the AI ​​analyzes performance and suggests improvements. For example, if a particular player tends to have fewer sprints in the second half of a match, and fatigue can be inferred from that player's emotional data, the AI ​​will provide that player with a training plan to improve stamina and nutritional advice effective for fatigue recovery.

[0490] The following describes the processing flow for each example of the form.

[0491] "Example of form 1"

[0492] Step 1: The user uploads a video of a soccer match to the system.

[0493] Step 2: The system uses AI to collect team and player-specific data from the video.

[0494] Step 3: The emotion engine collects user emotion data.

[0495] Step 4: The AI ​​analyzes performance and suggests improvements based on the collected performance and sentiment data.

[0496] Step 5: The AI ​​provides a customized training plan and nutritional advice based on the player's condition.

[0497] "Example of form 2"

[0498] Step 1: Junior soccer club teams upload match videos to the system after the game.

[0499] Step 2: The system uses AI to analyze the videos and collect individual player performance data.

[0500] Step 3: The emotion engine collects user emotion data.

[0501] Step 4: The AI ​​analyzes performance and suggests improvements based on the collected performance and sentiment data.

[0502] Step 5: If a particular player tends to have a decrease in sprints in the second half of a match, and fatigue can be inferred from that player's emotional data, the AI ​​will provide that player with a training plan to improve stamina and nutritional advice that will help with fatigue recovery.

[0503] (Example 1)

[0504] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0505] In soccer matches, objectively evaluating player performance and providing optimal training plans and nutritional guidance to individual players has been difficult with traditional methods. Furthermore, coaching that takes into account players' emotional states relies on subjective judgment and is not optimized. This presents a challenge in effectively supporting player development.

[0506] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0507] In this invention, the server includes means for transmitting match video, means for extracting group and individual information from the match video, means for evaluating abilities and suggesting improvements based on the extracted information, means for providing training plans and nutritional guidance tailored to the individual's condition, and means for collecting and analyzing emotional information. This makes it possible to objectively evaluate the performance of players, provide optimal training plans and nutritional guidance for each player, and provide guidance that takes into account the emotional state of the players.

[0508] "Means for transmitting match footage" refers to a function that allows users to upload soccer match footage to the system and for the server to receive that footage.

[0509] "Means for extracting group and individual information" refers to a function for analyzing and collecting movement and performance data for the entire team and each individual player from match footage.

[0510] "Means for evaluating abilities and proposing improvements" refers to a function that analyzes a player's performance based on extracted data, identifies their strengths and weaknesses, and makes specific suggestions for improvement.

[0511] "Means of providing training plans and nutritional guidance tailored to individual conditions" refers to a function that generates and provides individually optimized training plans and nutritional advice based on the athlete's condition and performance data.

[0512] "Means for collecting and analyzing emotional information" refers to a function that collects user emotional data, analyzes that data, and provides guidance and support based on the emotional state of the players.

[0513] A description of embodiments for carrying out this invention will be given.

[0514] Users upload soccer match footage from their devices to the system. The server receives this footage and stores it in a database. Next, the server analyzes the footage using AI technology. Specifically, it utilizes computer vision technology and software such as OpenCV and TensorFlow to detect player movements and the position of the ball. This analysis extracts motion data for the entire team and for each individual player.

[0515] The server evaluates player performance based on the extracted data. Using an AI model, it identifies players' strengths and weaknesses and reveals areas for improvement. For example, it quantifies players' running distance and shooting accuracy and performs comparative analysis.

[0516] Furthermore, the server generates individually optimized training plans and nutritional advice based on the athlete's condition. This involves AI analyzing the athlete's data and suggesting running menus to improve endurance and meal plans to enhance concentration.

[0517] The server also uses an emotion engine to collect and analyze user emotional data. Based on the user's emotional state, it makes suggestions for performance improvement. For example, if a user is feeling stressed after a match, it might suggest mental training to help them relax.

[0518] For example, if a player is analyzed to have low running distance and poor shooting accuracy during a match, the server will provide that player with a training plan to improve endurance and nutritional advice to enhance concentration. Also, if a player is feeling down after a match, the emotional engine will suggest mental training to help them relax.

[0519] An example of a prompt for a generative AI model is: "Analyze a soccer match video, identify player A's strengths and weaknesses based on their performance data, and generate a training plan and nutritional advice for improvement. Also, consider player A's emotional data and suggest mental support."

[0520] The flow of the specific processing in Example 1 will be explained using Figure 15.

[0521] Step 1:

[0522] Users upload soccer match footage from their devices to the system. The input is the match video file, and the output is the video data stored on the server. Using their devices, users select the video file through a designated interface and press the upload button to send the video to the server.

[0523] Step 2:

[0524] The server stores the received video data in a database. The input is video data sent by the user, and the output is video data stored in the database. When the server receives video data, it uses a database management system to save the data in the appropriate format.

[0525] Step 3:

[0526] The server analyzes stored video data. The input is video data stored in a database, and the output is analysis data regarding player movements and ball position. The server uses computer vision technology, utilizing libraries such as OpenCV and TensorFlow, to detect player movements and ball position from the video.

[0527] Step 4:

[0528] The server evaluates player performance based on the analyzed data. The input is analyzed data on player movements and ball position, and the output is performance evaluation data for each player. The server uses an AI model to identify players' strengths and weaknesses and generate a quantified evaluation.

[0529] Step 5:

[0530] The server generates training plans and nutritional advice tailored to each athlete's condition. The input is the athlete's performance evaluation data, and the output is an individually optimized training plan and nutritional advice. The server utilizes AI to analyze the athlete's data and proposes running menus to improve endurance and meal plans to enhance concentration.

[0531] Step 6:

[0532] The server collects and analyzes user emotional data. The input is the user's emotional data, and the output is an analysis result based on their emotional state. The server uses an emotion engine to analyze the user's emotions and evaluate their stress and motivation levels.

[0533] Step 7:

[0534] The server provides customized advice based on the user's emotional state. The input is an analysis of the emotional state, and the output is a suggestion for mental support tailored to that emotional state. The server considers the user's emotional state and provides mental training to help them relax and advice to boost their motivation.

[0535] (Application Example 1)

[0536] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0537] There is a need to improve the operational efficiency of robots in factories and to improve the work environment based on the emotions of the operators. However, conventional systems do not adequately analyze robot movements or recognize operator emotions, making it difficult to propose efficient movements or improve the work environment.

[0538] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0539] In this invention, the server includes means for uploading soccer match videos, means for collecting collective and individual data from the match videos, means for analyzing movements and suggesting improvements based on the collected data, means for providing customized training plans and nutritional guidance according to the individual's condition, and means for recognizing emotions and suggesting improvements to the work environment. This makes it possible to improve the operational efficiency of robots in factories and to improve the work environment based on the emotions of operators.

[0540] "A means of uploading soccer match videos" refers to a function for transferring video data of soccer matches to a server.

[0541] "Means for collecting collective and individual data from match videos" refers to a function for extracting information about the entire team and individual players from uploaded match videos.

[0542] "Means for analyzing operations and proposing improvements based on collected data" refers to a function that analyzes collected data and presents measures to improve the efficiency of operations and suggest improvements.

[0543] "Means of providing customized training plans and nutritional guidance according to the individual's condition" refers to a function that provides optimal training programs and nutritional advice based on the condition of each individual athlete or robot.

[0544] "Means for recognizing emotions and proposing improvements to the work environment" refers to a function that analyzes the emotions of operators and users and proposes measures to improve the work environment based on those analyses.

[0545] In an embodiment of this invention, the server is configured as follows: The server includes means for uploading soccer match videos, thereby allowing users to transfer match video data to the server. Next, the server extracts information about the entire team and individual players using means for collecting collective and individual data from the match videos. This data collection is performed using video analysis with Python and OpenCV.

[0546] Based on the collected data, the server employs means to analyze its behavior and suggest improvements. This process utilizes an AI model based on TensorFlow to generate efficient behavior plans. Furthermore, it provides customized training plans and nutritional guidance tailored to the individual's condition, which are also implemented by AI.

[0547] Furthermore, the server is equipped with the means to recognize emotions and suggest improvements to the work environment. It uses an emotion recognition API to analyze the emotional data of operators and users. This makes it possible to suggest improvements to the work environment.

[0548] As a concrete example, when a robot assembles parts in a factory, it can reduce wasted motion and suggest more efficient movements. It can also suggest breaks if the operator is tired. An example of a prompt message would be, "Analyze the robot's motion data and generate an efficient motion plan. Also, suggest improvements to the work environment based on the operator's emotional data."

[0549] The flow of a specific process in Application Example 1 will be explained using Figure 16.

[0550] Step 1:

[0551] The user uploads soccer match videos from their device to the server. The input is the video data of the match, and the output is the video file stored on the server. In this step, the user selects the match video and presses the upload button, and the data is transferred to the server.

[0552] Step 2:

[0553] The server collects collective and individual data from uploaded videos. The input is video files stored on the server, and the output is data about the entire team and individual players. Python and OpenCV are used to analyze the videos and extract player movement and position information.

[0554] Step 3:

[0555] The server analyzes the collected data and suggests improvements to the player's movements. The input is the player's movements and position information, and the output is an efficient movement plan. An AI model using TensorFlow analyzes the data and generates the optimal movement plan.

[0556] Step 4:

[0557] The server provides customized training plans and nutritional guidance tailored to each individual's condition. Inputs are the athlete's movement data and condition information, while output is individually customized training plans and nutritional advice. AI evaluates the athlete's strengths and weaknesses and proposes the optimal plan.

[0558] Step 5:

[0559] The server recognizes emotions and provides suggestions for improving the work environment. Input is emotional data from operators and users, and output is suggestions for improving the work environment. An emotion recognition API is used to analyze the emotional data and evaluate stress and fatigue levels.

[0560] Step 6:

[0561] The server notifies the user of the generated operation plan and improvement suggestions. The input is an efficient operation plan or improvement suggestion, and the output is a notification message to the user. The user can check the suggestions on their terminal and put them into action.

[0562] (Example 2)

[0563] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0564] Conventional sports analysis systems have limited data available from match videos, making it difficult to comprehensively evaluate athlete performance. Furthermore, they are unable to provide individualized improvement suggestions that take into account athletes' emotions and physical condition, thus failing to adequately contribute to athlete development and health management.

[0565] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0566] In this invention, the server includes means for uploading match videos, means for collecting individual athlete data from the match videos, means for analyzing the athlete's condition based on the collected data and making suggestions for improvement, means for providing customized training plans and nutritional guidance according to the athlete's condition, means for collecting emotional data and utilizing it for analyzing the athlete's condition, and means for generating suggestions using a generative AI model. This makes it possible to comprehensively evaluate the athlete's performance and make improvement suggestions that meet individual needs.

[0567] "Match videos" are video data that records the events of a sports competition, allowing viewers to visually capture the movements of the players and the progress of the match.

[0568] "Athlete data" refers to information about individual players extracted from match videos, including performance indicators such as distance covered, number of sprints, and pass completion rate.

[0569] "Athlete status" refers to the physical and mental condition of an athlete, and is assessed based on performance data and emotional data.

[0570] A "training plan" outlines the schedule and content of training aimed at improving an athlete's performance, and is customized according to individual needs.

[0571] "Nutritional guidance" refers to advice on diet and nutrient intake aimed at maintaining the health and improving the performance of athletes, and is provided according to the individual athlete's condition.

[0572] "Emotional data" refers to information that indicates an athlete's emotional state, and is obtained through the analysis of facial expressions and movements.

[0573] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to analyze data and generate suggestions or predictions.

[0574] This invention is a system for analyzing sports competition videos to evaluate and improve athlete performance. Users upload match videos to the system using a terminal after the match. The server utilizes computer vision technology to analyze the received videos. Specifically, it uses software libraries such as OpenCV and TensorFlow to track the movements of athletes and extract individual athlete data.

[0575] The server collects athlete data such as distance covered, number of sprints, and pass completion rate for each player from the analysis results. Furthermore, it uses an emotion engine to collect emotional data from the players and comprehensively evaluate their condition. This makes it possible to understand the players' physical and mental condition.

[0576] The server uses a generated AI model based on the collected data to analyze player performance and generate suggestions for improvement. For example, if a particular player tends to have a decrease in sprints in the second half of a match, the server will suggest a training plan to improve that player's stamina. It also provides customized nutritional guidance on energy sources to consume before a match and nutrients needed for post-match recovery.

[0577] As a concrete example, an example of a prompt sentence to be input to the generating AI model is: "Please suggest a stamina-improving training plan for a player whose sprint count decreases in the second half of a match. Also, please provide nutritional advice before and after the match."

[0578] This system allows users to comprehensively evaluate athlete performance and receive improvement suggestions tailored to their individual needs. This can contribute to athlete development and health management.

[0579] The flow of the specific processing in Example 2 will be explained using Figure 17.

[0580] Step 1:

[0581] After a match, the user uploads the match video to the system using a terminal. The input is the match video file, and the output is the transfer of the video data to the server. The terminal checks the format and size of the video file, converts it to the appropriate format, and sends it to the server.

[0582] Step 2:

[0583] The server uses computer vision technology to analyze the received match videos. The input is the uploaded video data, and the output is data tracking the players' movements. Specifically, it uses libraries such as OpenCV and TensorFlow to track the position and movement of players in the video in real time and record each player's actions in a database.

[0584] Step 3:

[0585] The server collects individual athlete data from the analysis results. The input is tracking data, and the output is performance indicators such as distance covered, number of sprints, and pass completion rate. The server aggregates this data and quantifies the performance of each athlete.

[0586] Step 4:

[0587] The server uses an emotion engine to collect emotional data from players. The input is video data of the players' facial expressions and movements, and the output is data indicating the players' emotional state. The server uses an AI model to infer emotions from the video and evaluate the players' mental condition.

[0588] Step 5:

[0589] The server integrates collected athlete and emotional data and analyzes athlete performance using a generative AI model. The input is the integrated dataset, and the output is the analysis results identifying the athlete's strengths and areas for improvement. The server uses the AI ​​model to analyze the data and comprehensively evaluate the athlete's performance.

[0590] Step 6:

[0591] The server generates improvement suggestions for each player based on the analysis results. The input is the analysis results, and the output is a customized training plan and nutritional guidance. The server uses a generative AI model to create prompt messages and generate the optimal training plan and nutritional advice for each player.

[0592] Step 7:

[0593] The server provides the user with the generated suggestions. The input is customized suggestions, and the output is information provided to the user. The user can review these suggestions through their terminal and use them for athlete training and nutrition management.

[0594] (Application Example 2)

[0595] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0596] There is a growing need to understand the operational efficiency of machinery and the condition of workers in factories in real time, and to propose efficient work plans and break schedules. However, conventional methods make it difficult to efficiently collect and analyze this data and make appropriate improvement suggestions.

[0597] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0598] In this invention, the server includes means for uploading video data, means for collecting machine and worker-specific data from the video data, means for analyzing operations and suggesting improvements based on the collected data, and means for providing customized work plans and rest advice according to the worker's condition. This enables efficient management and improvement suggestions for machines and workers within the factory.

[0599] "Video data" refers to digital data containing visual information acquired by cameras and other imaging devices.

[0600] "Means of uploading" refers to a method or device for transferring digital data to a server or cloud storage via a network.

[0601] "Machine and worker-specific data" refers to operational information for individual machines within the factory, as well as information regarding the work status and condition of workers.

[0602] "Means of collection" refers to methods or apparatus for acquiring specific information and gathering it for storage or analysis.

[0603] "Action analysis" is the process of evaluating the motion data of machines and workers to identify efficiency issues and problems.

[0604] "Means of proposing improvements" refers to methods or devices that present specific action plans for improving efficiency or solving problems based on analysis results.

[0605] "Worker's condition" refers to information indicating the physical and mental state of the worker.

[0606] A "customized work plan" refers to a work schedule and procedures that are optimized according to the individual worker's condition and abilities.

[0607] "Break advice" refers to information that suggests appropriate timing and methods for breaks in order to reduce fatigue and stress among workers.

[0608] The system for implementing this invention monitors the operation of machinery and workers in a factory and provides efficient management and improvement suggestions. The server uses means for uploading video data to transfer video data acquired from surveillance cameras in the factory to cloud storage. Next, it uses means for collecting machine and worker-specific data from the video data to obtain operation information for individual machines and the work status of workers.

[0609] This data is processed using OpenCV with Python, and the behavior is analyzed by a generative AI model using TensorFlow. Based on the analysis results, the server provides suggestions for improvement and presents concrete action plans for efficiency improvement and problem solving. Furthermore, to provide customized work plans and break advice according to the worker's state, emotion recognition APIs (e.g., Microsoft Azure Emotion API) are used to collect and comprehensively analyze worker emotion data.

[0610] For example, if it is found that a particular machine's operational efficiency decreases in the afternoon, the server will suggest regular maintenance for that machine. Similarly, if worker emotional data indicates increased stress, it can suggest a break.

[0611] An example of a prompt message is, "Analyze the cause of the decrease in machine operation efficiency in the afternoon and propose solutions for improvement."

[0612] The flow of a specific process in Application Example 2 will be explained using Figure 18.

[0613] Step 1:

[0614] The server acquires video data from surveillance cameras within the factory and uploads it to cloud storage via the network. The input is real-time video data from the surveillance cameras, and the output is a video file stored in cloud storage. This step involves the transfer and storage of video data.

[0615] Step 2:

[0616] The server processes the uploaded video data using OpenCV with Python and extracts motion data for both the machine and the worker. The input is a video file stored in cloud storage, and the output is machine motion information and worker work status data. In this step, video data analysis and motion data extraction are performed.

[0617] Step 3:

[0618] The server analyzes the extracted motion data using a generative AI model based on TensorFlow to identify operational efficiency and problems. The input consists of machine motion information and worker work status data, while the output is the analysis results regarding operational efficiency and problems. In this step, data analysis is performed by the AI ​​model.

[0619] Step 4:

[0620] The server makes improvement suggestions based on the analysis results and generates concrete action plans for efficiency improvement and problem solving. The input is the analysis results regarding operational efficiency and problems, and the output is the action plan of improvement suggestions. In this step, improvement measures are generated and proposed.

[0621] Step 5:

[0622] The server uses an emotion recognition API to collect worker emotion data and evaluate the worker's state. The input is real-time video data of the worker, and the output is the worker's emotion data. In this step, emotion data is collected and evaluated.

[0623] Step 6:

[0624] The server integrates and analyzes worker emotional and behavioral data to provide customized work plans and break advice. The input is worker emotional and behavioral data, and the output is customized work plans and break advice. This step involves integrated data analysis and personalized recommendations.

[0625] (Other examples)

[0626] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[0627] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0628] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0629] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[0630] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0631] [Third Embodiment]

[0632] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0633] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0634] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0635] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0636] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0637] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0638] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0639] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0640] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0641] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0642] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0643] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0644] "Example of form 1"

[0645] The system of the present invention includes means for uploading soccer match videos, means for collecting team and player-specific data from the match videos, means for analyzing performance and suggesting improvements based on the collected data, and means for providing customized training plans and nutritional advice according to the players' condition. These means are realized using AI technology. Specifically, the system analyzes players' movements and performance from match videos to understand each player's strengths and weaknesses. Furthermore, the AI ​​provides optimal training plans and nutritional advice according to the players' condition and performance. This moves away from subjective instruction based on the experience and knowledge of coaches and parents, and supports growth with the most optimal coaching methods. "Example Form 2"

[0646] As a concrete example, a junior soccer club team uploads match videos to the system of the present invention after a game. The system uses AI to analyze the videos and collect individual player performance data (e.g., distance covered, number of sprints, pass success rate, etc.). Furthermore, the AI ​​analyzes performance and suggests improvements based on the collected data. For example, if a particular player tends to have a decrease in the number of sprints in the second half of a match, the AI ​​will suggest a training plan to improve that player's stamina. The system also provides customized nutritional advice according to the player's condition (e.g., energy sources to consume before a match, nutrients needed for recovery after a match, etc.).

[0647] The following describes the processing flow for each example of the form.

[0648] "Example of form 1"

[0649] Step 1: A user (e.g., a coach or parent) uploads a video of a soccer match to the system of the present invention.

[0650] Step 2: The system uses AI to analyze the video and collect individual player performance data (e.g., distance covered, number of sprints, pass completion rate, etc.).

[0651] Step 3: The AI ​​analyzes performance and suggests improvements based on the collected data.

[0652] Step 4: Based on the player's condition, the AI ​​provides a customized training plan and nutritional advice.

[0653] "Example of form 2"

[0654] Step 1: A junior soccer club team uploads a video of the match to the system of the present invention after the match.

[0655] Step 2: The system uses AI to analyze the videos and collect individual player performance data.

[0656] Step 3: The AI ​​analyzes performance and suggests improvements based on the collected data. If a particular player tends to have fewer sprints in the second half of a match, the AI ​​will suggest a training plan to improve that player's stamina.

[0657] Step 4: Based on the player's condition, the AI ​​provides customized nutritional advice. For example, it suggests energy sources to consume before a match and nutrients needed for recovery after a match.

[0658] (Example 1)

[0659] Next, we will describe Embodiment 1 of Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0660] Traditional soccer coaching relied heavily on the experience and knowledge of coaches and parents, resulting in a subjective approach that made it difficult to provide optimal coaching based on individual player performance and condition. Furthermore, data collection and analysis from match footage were often done manually, making efficient analysis challenging.

[0661] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0662] In this invention, the server includes means for transmitting match video, means for acquiring group and individual information from the match video, means for analyzing abilities and suggesting improvements based on the acquired information, means for providing training plans and nutritional guidance tailored to the individual's condition, and means for inputting prompt sentences using a generative AI model and generating specific suggestions based on the analysis results. This enables optimal guidance based on the individual performance of each player and efficient data analysis.

[0663] "Match footage" refers to video data that records the events of a soccer match, and is used to visually capture the movements of the players and teams.

[0664] "Means of transmission" refers to a device or software that has the function of transferring digital data to other devices or systems via a network.

[0665] "Group and individual information" refers to data about the entire team and each player extracted from match footage, including detailed information about performance and movement.

[0666] "Means of acquisition" refers to devices or software used to collect specific data or information and convert it into a format usable within the system.

[0667] "Performance analysis" is the process of evaluating the performance of players and teams based on collected data, and identifying their strengths and weaknesses.

[0668] "Suggestions for improvement" refers to providing specific advice and strategies to improve the performance of players and teams based on the analysis results.

[0669] "Individual condition" refers to information about each player's physical condition, such as their health, fitness level, and fatigue level.

[0670] A "tailored training plan" is a training menu customized according to the individual athlete's condition and goals, aiming for effective performance improvement.

[0671] "Nutritional guidance" refers to providing advice on diet and nutritional intake in order to optimize an athlete's health and performance.

[0672] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[0673] A "prompt statement" is a sentence containing instructions or questions that are input into a generative AI model, and it serves as a trigger for the model to generate appropriate output.

[0674] This invention is a system for analyzing soccer match footage to improve the performance of players and teams. Users upload match footage from their terminals to a server. The server analyzes the footage using video analysis software (e.g., OpenCV) and extracts player movement and position data. This allows for the acquisition of group and individual information.

[0675] The server inputs the acquired information into an AI model (e.g., TensorFlow or PyTorch) to analyze the player's abilities. The AI ​​model evaluates the player's strengths and weaknesses and generates specific suggestions for improvement. This includes a training plan tailored to the player's condition and nutritional guidance.

[0676] As a concrete example, a user inputs a prompt into the AI ​​model stating, "I want you to analyze the distance covered and the number of sprints performed by players during a match and suggest a training plan to improve their stamina." The server then measures the distance covered and the number of sprints from the match footage and uses the AI ​​model to suggest an effective training plan to improve stamina. This suggestion includes specific running menus and nutritional advice.

[0677] This system allows users to receive optimal coaching based on their individual performance and enables efficient data analysis.

[0678] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0679] Step 1:

[0680] The user uploads soccer match footage from their device to the server. The input is a match video file, which the server receives and saves. Specifically, the user selects the file using a dedicated interface and clicks the upload button.

[0681] Step 2:

[0682] The server analyzes the saved match footage using video analysis software (e.g., OpenCV). The input is the saved video file, and the output is player movement and position data. The server identifies players in the video and extracts data such as the distance covered and the number of sprints for each player. Specifically, the server tracks the position of each player frame by frame and calculates the distance traveled.

[0683] Step 3:

[0684] The server inputs the extracted data into an AI model (e.g., TensorFlow or PyTorch) to analyze the players' abilities. The input is data on the players' movements and positions, and the output is an evaluation of the players' strengths and weaknesses. The AI ​​model analyzes the data to evaluate each player's performance and generates suggestions for improvement. Specifically, the AI ​​model passes the data through a pre-trained model and calculates an evaluation score.

[0685] Step 4:

[0686] The server generates a customized training plan and nutritional guidance tailored to the athlete's condition based on the analysis results. The input is the athlete's evaluation results, and the output is a specific training menu and nutritional advice. The server uses a generation AI model to receive prompt messages and generates specific suggestions based on the analysis results. Specifically, the server inputs prompt messages into the AI ​​model and generates customized advice.

[0687] Step 5:

[0688] The server sends the generated training plan and nutritional guidance to the user's terminal. The input is the generated suggestions, and the output is information in a format that the user can review. Specifically, the server converts the suggestions into text format and sends a notification to the user's terminal.

[0689] (Application Example 1)

[0690] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0691] There is a need to improve the operational efficiency of robots in factories and optimize the timing and methods of maintenance. However, conventional methods have made it difficult to detect inefficiencies in operation in real time and propose efficient operation plans.

[0692] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0693] In this invention, the server includes means for recording operations, means for collecting individual data from the recorded operations, means for performing efficiency analysis and suggesting improvements based on the collected data, and means for providing customized optimization plans and maintenance advice according to the state of operation. This enables real-time optimization of robot operations within a factory, resulting in efficient operation.

[0694] "Means for recording motion" refers to a device or method for recording the motion of robots and machinery in a factory using video or sensors.

[0695] "Means for collecting individual data" refers to a device or method for extracting operational information of a specific robot or machine from recorded movements and collecting it as data.

[0696] "Means for analyzing efficiency and proposing improvements" refers to a device or method that evaluates the efficiency of operations based on collected operational data and makes specific suggestions for improvement.

[0697] "Means for providing customized optimization plans and maintenance advice according to the operating state" refers to a device or method that takes into account the current operating state of a robot or machine and individually provides the optimal operating plan and maintenance method.

[0698] The system for implementing this invention is designed to optimize the operation of robots within a factory. The server records the robot's movements in real time using surveillance cameras and sensors installed within the factory. The recorded video data is analyzed frame by frame using OpenCV, and the operation data of each robot is extracted.

[0699] The server inputs collected operational data into a generative AI model built using TensorFlow to evaluate the efficiency of the operations. The AI ​​model detects inefficiencies and errors in the operations and generates efficient operation plans. Furthermore, it provides customized optimization plans and maintenance advice based on the operational status.

[0700] As a concrete example, we can analyze the movements of a robotic arm used in a factory and propose a plan to reduce wasted motion. Based on the generated plan, the user can adjust the robot's movements to achieve efficient operation.

[0701] An example of a prompt would be, "Analyze the video of the robot arm's movements and propose an efficient movement plan." This prompt prompts the AI ​​model to analyze the movement data and generate the optimal plan.

[0702] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0703] Step 1:

[0704] The server records the robot's movements in real time from surveillance cameras and sensors installed within the factory. The input is video data from the cameras and sensors, and the output is the recorded video file. In this step, the video data is divided frame by frame in preparation for subsequent analysis.

[0705] Step 2:

[0706] The server analyzes the recorded video data using OpenCV and extracts robot motion data from each frame. The input is the video file obtained in step 1, and the output is motion data. In this step, the characteristics of the motion are extracted and organized as data.

[0707] Step 3:

[0708] The server inputs the extracted motion data into a generative AI model built using TensorFlow and evaluates the efficiency of the motion. The input is the motion data obtained in step 2, and the output is the efficiency evaluation result. In this step, the AI ​​model detects inefficiencies and errors in the motion.

[0709] Step 4:

[0710] The server generates an efficient operation plan based on the evaluation results of the AI ​​model. The input is the evaluation results obtained in step 3, and the output is the optimized operation plan. In this step, areas for improvement in operation are identified, and a specific plan is formulated.

[0711] Step 5:

[0712] The user adjusts the robot's movements based on the optimization plan provided by the server. The input is the movement plan obtained in step 4, and the output is the adjusted robot's movements. In this step, the user modifies the robot's settings according to the plan to achieve efficient operation.

[0713] (Example 2)

[0714] Next, we will describe Example 2 of the morphological example. 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."

[0715] In sports competitions, analyzing athletes' performance in detail and providing individualized improvement suggestions and nutritional guidance is time-consuming and labor-intensive using traditional methods, making it difficult to do efficiently and effectively. This is especially true for junior athletes, who require appropriate guidance tailored to their individual developmental stages, but there is a lack of systems to achieve this.

[0716] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0717] In this invention, the server includes means for transmitting match video, means for acquiring group and individual information from the match video, means for evaluating abilities and suggesting improvements based on the acquired information, means for providing exercise plans and nutritional guidance tailored to the individual's condition, and means for generating prompt sentences using a generative AI model. This makes it possible to efficiently analyze athlete performance and quickly provide individual improvement suggestions and nutritional guidance.

[0718] "Match footage" refers to video data that records the events of a sports competition, allowing viewers to visually capture the movements of the players and the progress of the match.

[0719] "Means of transmission" refers to technical means for moving data from one point to another, and includes the function of transferring data over a network.

[0720] "Group and individual information" refers to data about the entire team and each individual player participating in the match, including detailed information about their performance and behavior.

[0721] "Means of acquisition" refers to technical means for collecting data and extracting necessary information, and includes functions that use sensors and analysis software to obtain information.

[0722] "Performance assessment" is the process of analyzing an athlete's performance and measuring their technical and physical abilities.

[0723] "Suggestions for improvement" involve providing specific advice and plans to improve a player's performance, including changes to training and tactics.

[0724] "Individual condition" refers to the physical and mental condition of the athlete, including their health status and fatigue level.

[0725] A "tailored exercise plan" is a training program customized to the individual needs and condition of the athlete, aiming for efficient performance improvement.

[0726] "Nutritional guidance" involves providing advice on diet and nutrient intake to optimize an athlete's health and performance.

[0727] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[0728] A "prompt statement" is an instruction given to a generative AI model, serving as a guideline for the AI ​​to generate appropriate output.

[0729] A description of embodiments for carrying out this invention will be given.

[0730] Users upload match footage they filmed after junior soccer matches to the system using their devices. The server uses OpenCV and TensorFlow as AI analysis software to analyze the received match footage. The server uses this software to identify players in the match footage and track each player's movements.

[0731] The server collects performance data for each player through video analysis, such as distance covered, number of sprints, and pass completion rate. For example, it might record that player A ran 5km during a match, performed 15 sprints, and had a pass completion rate of 80%.

[0732] The collected data is input into a generating AI model on the server to analyze each player's performance. The AI ​​model evaluates the players' physical and technical tendencies and identifies areas for improvement. For example, if player B's sprint count decreases in the second half of a match, the AI ​​will make specific suggestions such as, "We recommend interval training three times a week to improve stamina."

[0733] Furthermore, the server uses AI to generate customized nutritional advice based on the player's condition. For example, it might advise, "Eat a meal high in carbohydrates before a match, and a meal containing protein and vitamins after a match."

[0734] As an example of a prompt that the user inputs to the generated AI model, you can use a sentence such as, "Analyze the match video, collect performance data for each player, and provide suggestions for improvement."

[0735] This system allows coaches and players at junior soccer clubs to review their performance after matches and identify specific areas for improvement.

[0736] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0737] Step 1:

[0738] Users upload match footage they filmed after junior soccer matches to the system using a terminal. The input is the match video file, and the output is the transfer of video data to the server. Users select the file through the terminal interface and press the upload button to send the video data to the server.

[0739] Step 2:

[0740] The server passes the received match video to AI analysis software (e.g., OpenCV or TensorFlow). The input is the match video data, and the output is data ready for analysis. The server divides the video data into frames and performs preprocessing to identify the players in each frame.

[0741] Step 3:

[0742] The server uses an AI model to track players in match footage and analyze each player's movements. The input is pre-processed video data, and the output is movement data for each player. The server tracks players' positions and movements and collects performance data such as distance covered and number of sprints.

[0743] Step 4:

[0744] The server inputs the collected performance data into a generating AI model to analyze each player's performance. The input is data on each player's movements, and the output is the performance evaluation result. The AI ​​model evaluates the players' physical strength and technical tendencies and identifies areas for improvement.

[0745] Step 5:

[0746] The server generates specific improvement suggestions for each player based on the analysis results. The input is the performance evaluation results, and the output is the improvement suggestions. For example, the AI ​​might suggest, "We recommend interval training three times a week to improve stamina."

[0747] Step 6:

[0748] The server uses AI to generate customized nutritional advice based on the player's condition. The input is the player's performance data and condition information, and the output is nutritional advice. For example, it might provide advice such as, "It is recommended to eat a meal high in carbohydrates before a match, and a meal containing protein and vitamins after a match."

[0749] Step 7:

[0750] The server provides users with generated improvement suggestions and nutritional advice. The input consists of improvement suggestions and nutritional advice, while the output is information provided to the user. Users can view this information through their terminals and utilize it for athlete training and nutrition management.

[0751] (Application Example 2)

[0752] Next, we will describe application example 2 of form 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."

[0753] There is a need to improve the operational efficiency and safety of machinery and workers operating within factories. However, conventional methods often involve manual recording and analysis of operations, making it difficult to propose efficient improvements.

[0754] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0755] In this invention, the server includes means for recording operations, means for collecting machine and operator-specific data from the recorded operations, means for analyzing work efficiency and safety and proposing improvements based on the collected data, and means for providing customized maintenance plans and operational advice according to the machine's condition. This makes it possible to efficiently and safely improve the operation of machines and operators within a factory.

[0756] "Means for recording motion" refers to devices or methods for recording the movements of machines or workers as video or sensor data.

[0757] "Means of collecting data" refers to devices and methods for extracting and organizing specific information for each machine or worker from recorded actions.

[0758] "Means for analysis and improvement proposals" refer to devices and methods for evaluating work efficiency and safety based on collected data and generating specific proposals for improvement.

[0759] "Means of providing maintenance plans and operational advice" refers to devices or methods for presenting appropriate maintenance schedules and operating procedures according to the condition of the machine and the actions of the operator.

[0760] Artificial intelligence is a technology that enables computer systems to mimic human intellectual behavior and perform data analysis and decision-making.

[0761] A description of the embodiment for carrying out the invention will be provided.

[0762] The system that realizes this invention is intended to improve the efficiency and safety of the operation of machinery and workers in a factory. The server records the movements of machinery and workers using cameras and sensors as means of recording operations. The recorded data is transmitted to the server as a means of data collection, and specific information for each machine and worker is extracted.

[0763] The server uses artificial intelligence to evaluate work efficiency and safety based on collected data, as a means of analysis and suggesting improvements. This involves using Python, analyzing videos with OpenCV, and building AI models using TensorFlow and PyTorch. This generates efficient operation patterns and specific suggestions for improving safety.

[0764] Furthermore, the server provides maintenance plans and operational advice by suggesting appropriate maintenance schedules and operating methods tailored to the machine's condition and the operator's actions. This maximizes machine operating efficiency and ensures operator safety.

[0765] A concrete example is when a robot is assembling parts, and the AI ​​detects that a particular movement is slow and suggests a new movement pattern to improve that movement. An example of a prompt used in this case would be, "Analyze the robot's movement patterns in this video and suggest improvements to increase efficiency."

[0766] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0767] Step 1:

[0768] The server uses cameras and sensors installed within the factory to record the movements of machinery and workers in real time. The input is video data from the cameras and sensors, and the output is a recorded video file. This video file is stored on the server for subsequent analysis.

[0769] Step 2:

[0770] The server divides the recorded video file into frames and extracts feature data related to the movements of the machine and the worker from each frame. The input is the video file, and the output is feature data for each frame. Image processing is performed using OpenCV to extract information such as the speed and direction of the movements.

[0771] Step 3:

[0772] The server uses the extracted feature data to perform analysis using an artificial intelligence model. The input is feature data, and the output is an evaluation result regarding work efficiency and safety. The AI ​​model, built using TensorFlow or PyTorch, identifies efficient operating patterns and areas for improvement to enhance safety.

[0773] Step 4:

[0774] The server generates specific improvement suggestions for machines and workers based on the analysis results. The input is the evaluation results, and the output is a list of improvement suggestions. Using the generated AI model, concrete action plans are created to improve efficiency and ensure safety.

[0775] Step 5:

[0776] The server provides machine maintenance schedules and operator advice based on improvement suggestions. Input is a list of improvement suggestions, and output is a maintenance plan and operational advice. This maximizes machine operating efficiency and ensures operator safety.

[0777] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0778] "Example of form 1"

[0779] One embodiment of the present invention is a system that incorporates an emotion engine. This system includes means for uploading soccer match videos, means for collecting team and player-specific data from the match videos, means for analyzing performance and suggesting improvements based on the collected data, means for providing customized training plans and nutritional advice according to the players' condition, and an emotion engine that recognizes the user's emotions. The emotion engine collects the user's emotional data and analyzes performance and suggests improvements based on that emotional data. The emotion engine also provides customized training plans and nutritional advice based on the user's emotional data.

[0780] "Example of form 2"

[0781] As a concrete example, a junior soccer club team uploads match videos to the system of the present invention after a game. The system uses AI to analyze the videos and collect performance data for each player. At the same time, the emotion engine collects the user's emotional data. Based on the collected performance data and emotional data, the AI ​​analyzes performance and suggests improvements. For example, if a particular player tends to have fewer sprints in the second half of a match, and fatigue can be inferred from that player's emotional data, the AI ​​will provide that player with a training plan to improve stamina and nutritional advice effective for fatigue recovery.

[0782] The following describes the processing flow for each example of the form.

[0783] "Example of form 1"

[0784] Step 1: The user uploads a video of a soccer match to the system.

[0785] Step 2: The system uses AI to collect team and player-specific data from the video.

[0786] Step 3: The emotion engine collects user emotion data.

[0787] Step 4: The AI ​​analyzes performance and suggests improvements based on the collected performance and sentiment data.

[0788] Step 5: The AI ​​provides a customized training plan and nutritional advice based on the player's condition.

[0789] "Example of form 2"

[0790] Step 1: Junior soccer club teams upload match videos to the system after the game.

[0791] Step 2: The system uses AI to analyze the videos and collect individual player performance data.

[0792] Step 3: The emotion engine collects user emotion data.

[0793] Step 4: The AI ​​analyzes performance and suggests improvements based on the collected performance and sentiment data.

[0794] Step 5: If a particular player tends to have a decrease in sprints in the second half of a match, and fatigue can be inferred from that player's emotional data, the AI ​​will provide that player with a training plan to improve stamina and nutritional advice that will help with fatigue recovery.

[0795] (Example 1)

[0796] Next, we will describe Embodiment 1 of Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0797] In soccer matches, objectively evaluating player performance and providing optimal training plans and nutritional guidance to individual players has been difficult with traditional methods. Furthermore, coaching that takes into account players' emotional states relies on subjective judgment and is not optimized. This presents a challenge in effectively supporting player development.

[0798] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0799] In this invention, the server includes means for transmitting match video, means for extracting group and individual information from the match video, means for evaluating abilities and suggesting improvements based on the extracted information, means for providing training plans and nutritional guidance tailored to the individual's condition, and means for collecting and analyzing emotional information. This makes it possible to objectively evaluate the performance of players, provide optimal training plans and nutritional guidance for each player, and provide guidance that takes into account the emotional state of the players.

[0800] "Means for transmitting match footage" refers to a function that allows users to upload soccer match footage to the system and for the server to receive that footage.

[0801] "Means for extracting group and individual information" refers to a function for analyzing and collecting movement and performance data for the entire team and each individual player from match footage.

[0802] "Means for evaluating abilities and proposing improvements" refers to a function that analyzes a player's performance based on extracted data, identifies their strengths and weaknesses, and makes specific suggestions for improvement.

[0803] "Means of providing training plans and nutritional guidance tailored to individual conditions" refers to a function that generates and provides individually optimized training plans and nutritional advice based on the athlete's condition and performance data.

[0804] "Means for collecting and analyzing emotional information" refers to a function that collects user emotional data, analyzes that data, and provides guidance and support based on the emotional state of the players.

[0805] A description of embodiments for carrying out this invention will be given.

[0806] Users upload soccer match footage from their devices to the system. The server receives this footage and stores it in a database. Next, the server analyzes the footage using AI technology. Specifically, it utilizes computer vision technology and software such as OpenCV and TensorFlow to detect player movements and the position of the ball. This analysis extracts motion data for the entire team and for each individual player.

[0807] The server evaluates player performance based on the extracted data. Using an AI model, it identifies players' strengths and weaknesses and reveals areas for improvement. For example, it quantifies players' running distance and shooting accuracy and performs comparative analysis.

[0808] Furthermore, the server generates individually optimized training plans and nutritional advice based on the athlete's condition. This involves AI analyzing the athlete's data and suggesting running menus to improve endurance and meal plans to enhance concentration.

[0809] The server also uses an emotion engine to collect and analyze user emotional data. Based on the user's emotional state, it makes suggestions for performance improvement. For example, if a user is feeling stressed after a match, it might suggest mental training to help them relax.

[0810] For example, if a player is analyzed to have low running distance and poor shooting accuracy during a match, the server will provide that player with a training plan to improve endurance and nutritional advice to enhance concentration. Also, if a player is feeling down after a match, the emotional engine will suggest mental training to help them relax.

[0811] An example of a prompt for a generative AI model is: "Analyze a soccer match video, identify player A's strengths and weaknesses based on their performance data, and generate a training plan and nutritional advice for improvement. Also, consider player A's emotional data and suggest mental support."

[0812] The flow of the specific processing in Example 1 will be explained using Figure 15.

[0813] Step 1:

[0814] Users upload soccer match footage from their devices to the system. The input is the match video file, and the output is the video data stored on the server. Using their devices, users select the video file through a designated interface and press the upload button to send the video to the server.

[0815] Step 2:

[0816] The server stores the received video data in a database. The input is video data sent by the user, and the output is video data stored in the database. When the server receives video data, it uses a database management system to save the data in the appropriate format.

[0817] Step 3:

[0818] The server analyzes stored video data. The input is video data stored in a database, and the output is analysis data regarding player movements and ball position. The server uses computer vision technology, utilizing libraries such as OpenCV and TensorFlow, to detect player movements and ball position from the video.

[0819] Step 4:

[0820] The server evaluates player performance based on the analyzed data. The input is analyzed data on player movements and ball position, and the output is performance evaluation data for each player. The server uses an AI model to identify players' strengths and weaknesses and generate a quantified evaluation.

[0821] Step 5:

[0822] The server generates training plans and nutritional advice tailored to each athlete's condition. The input is the athlete's performance evaluation data, and the output is an individually optimized training plan and nutritional advice. The server utilizes AI to analyze the athlete's data and proposes running menus to improve endurance and meal plans to enhance concentration.

[0823] Step 6:

[0824] The server collects and analyzes user emotional data. The input is the user's emotional data, and the output is an analysis result based on their emotional state. The server uses an emotion engine to analyze the user's emotions and evaluate their stress and motivation levels.

[0825] Step 7:

[0826] The server provides customized advice based on the user's emotional state. The input is an analysis of the emotional state, and the output is a suggestion for mental support tailored to that emotional state. The server considers the user's emotional state and provides mental training to help them relax and advice to boost their motivation.

[0827] (Application Example 1)

[0828] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0829] There is a need to improve the operational efficiency of robots in factories and to improve the work environment based on the emotions of the operators. However, conventional systems do not adequately analyze robot movements or recognize operator emotions, making it difficult to propose efficient movements or improve the work environment.

[0830] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0831] In this invention, the server includes means for uploading soccer match videos, means for collecting collective and individual data from the match videos, means for analyzing movements and suggesting improvements based on the collected data, means for providing customized training plans and nutritional guidance according to the individual's condition, and means for recognizing emotions and suggesting improvements to the work environment. This makes it possible to improve the operational efficiency of robots in factories and to improve the work environment based on the emotions of operators.

[0832] "A means of uploading soccer match videos" refers to a function for transferring video data of soccer matches to a server.

[0833] "Means for collecting collective and individual data from match videos" refers to a function for extracting information about the entire team and individual players from uploaded match videos.

[0834] "Means for analyzing operations and proposing improvements based on collected data" refers to a function that analyzes collected data and presents measures to improve the efficiency of operations and suggest improvements.

[0835] "Means of providing customized training plans and nutritional guidance according to the individual's condition" refers to a function that provides optimal training programs and nutritional advice based on the condition of each individual athlete or robot.

[0836] "Means for recognizing emotions and proposing improvements to the work environment" refers to a function that analyzes the emotions of operators and users and proposes measures to improve the work environment based on those analyses.

[0837] In an embodiment of this invention, the server is configured as follows: The server includes means for uploading soccer match videos, thereby allowing users to transfer match video data to the server. Next, the server extracts information about the entire team and individual players using means for collecting collective and individual data from the match videos. This data collection is performed using video analysis with Python and OpenCV.

[0838] Based on the collected data, the server employs means to analyze its behavior and suggest improvements. This process utilizes an AI model based on TensorFlow to generate efficient behavior plans. Furthermore, it provides customized training plans and nutritional guidance tailored to the individual's condition, which are also implemented by AI.

[0839] Furthermore, the server is equipped with the means to recognize emotions and suggest improvements to the work environment. It uses an emotion recognition API to analyze the emotional data of operators and users. This makes it possible to suggest improvements to the work environment.

[0840] As a concrete example, when a robot assembles parts in a factory, it can reduce wasted motion and suggest more efficient movements. It can also suggest breaks if the operator is tired. An example of a prompt message would be, "Analyze the robot's motion data and generate an efficient motion plan. Also, suggest improvements to the work environment based on the operator's emotional data."

[0841] The flow of a specific process in Application Example 1 will be explained using Figure 16.

[0842] Step 1:

[0843] The user uploads soccer match videos from their device to the server. The input is the video data of the match, and the output is the video file stored on the server. In this step, the user selects the match video and presses the upload button, and the data is transferred to the server.

[0844] Step 2:

[0845] The server collects collective and individual data from uploaded videos. The input is video files stored on the server, and the output is data about the entire team and individual players. Python and OpenCV are used to analyze the videos and extract player movement and position information.

[0846] Step 3:

[0847] The server analyzes the collected data and suggests improvements to the player's movements. The input is the player's movements and position information, and the output is an efficient movement plan. An AI model using TensorFlow analyzes the data and generates the optimal movement plan.

[0848] Step 4:

[0849] The server provides customized training plans and nutritional guidance tailored to each individual's condition. Inputs are the athlete's movement data and condition information, while output is individually customized training plans and nutritional advice. AI evaluates the athlete's strengths and weaknesses and proposes the optimal plan.

[0850] Step 5:

[0851] The server recognizes emotions and provides suggestions for improving the work environment. Input is emotional data from operators and users, and output is suggestions for improving the work environment. An emotion recognition API is used to analyze the emotional data and evaluate stress and fatigue levels.

[0852] Step 6:

[0853] The server notifies the user of the generated operation plan and improvement suggestions. The input is an efficient operation plan or improvement suggestion, and the output is a notification message to the user. The user can check the suggestions on their terminal and put them into action.

[0854] (Example 2)

[0855] Next, we will describe Example 2 of the Form Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0856] Conventional sports analysis systems have limited data available from match videos, making it difficult to comprehensively evaluate athlete performance. Furthermore, they are unable to provide individualized improvement suggestions that take into account athletes' emotions and physical condition, thus failing to adequately contribute to athlete development and health management.

[0857] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0858] In this invention, the server includes means for uploading match videos, means for collecting individual athlete data from the match videos, means for analyzing the athlete's condition based on the collected data and making suggestions for improvement, means for providing customized training plans and nutritional guidance according to the athlete's condition, means for collecting emotional data and utilizing it for analyzing the athlete's condition, and means for generating suggestions using a generative AI model. This makes it possible to comprehensively evaluate the athlete's performance and make improvement suggestions that meet individual needs.

[0859] "Match videos" are video data that records the events of a sports competition, allowing viewers to visually capture the movements of the players and the progress of the match.

[0860] "Athlete data" refers to information about individual players extracted from match videos, including performance indicators such as distance covered, number of sprints, and pass completion rate.

[0861] "Athlete status" refers to the physical and mental condition of an athlete, and is assessed based on performance data and emotional data.

[0862] A "training plan" outlines the schedule and content of training aimed at improving an athlete's performance, and is customized according to individual needs.

[0863] "Nutritional guidance" refers to advice on diet and nutrient intake aimed at maintaining the health and improving the performance of athletes, and is provided according to the individual athlete's condition.

[0864] "Emotional data" refers to information that indicates an athlete's emotional state, and is obtained through the analysis of facial expressions and movements.

[0865] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to analyze data and generate suggestions or predictions.

[0866] This invention is a system for analyzing sports competition videos to evaluate and improve athlete performance. Users upload match videos to the system using a terminal after the match. The server utilizes computer vision technology to analyze the received videos. Specifically, it uses software libraries such as OpenCV and TensorFlow to track the movements of athletes and extract individual athlete data.

[0867] The server collects athlete data such as distance covered, number of sprints, and pass completion rate for each player from the analysis results. Furthermore, it uses an emotion engine to collect emotional data from the players and comprehensively evaluate their condition. This makes it possible to understand the players' physical and mental condition.

[0868] The server uses a generated AI model based on the collected data to analyze player performance and generate suggestions for improvement. For example, if a particular player tends to have a decrease in sprints in the second half of a match, the server will suggest a training plan to improve that player's stamina. It also provides customized nutritional guidance on energy sources to consume before a match and nutrients needed for post-match recovery.

[0869] As a concrete example, an example of a prompt sentence to be input to the generating AI model is: "Please suggest a stamina-improving training plan for a player whose sprint count decreases in the second half of a match. Also, please provide nutritional advice before and after the match."

[0870] This system allows users to comprehensively evaluate athlete performance and receive improvement suggestions tailored to their individual needs. This can contribute to athlete development and health management.

[0871] The flow of the specific processing in Example 2 will be explained using Figure 17.

[0872] Step 1:

[0873] After a match, the user uploads the match video to the system using a terminal. The input is the match video file, and the output is the transfer of the video data to the server. The terminal checks the format and size of the video file, converts it to the appropriate format, and sends it to the server.

[0874] Step 2:

[0875] The server uses computer vision technology to analyze the received match videos. The input is the uploaded video data, and the output is data tracking the players' movements. Specifically, it uses libraries such as OpenCV and TensorFlow to track the position and movement of players in the video in real time and record each player's actions in a database.

[0876] Step 3:

[0877] The server collects individual athlete data from the analysis results. The input is tracking data, and the output is performance indicators such as distance covered, number of sprints, and pass completion rate. The server aggregates this data and quantifies the performance of each athlete.

[0878] Step 4:

[0879] The server uses an emotion engine to collect emotional data from players. The input is video data of the players' facial expressions and movements, and the output is data indicating the players' emotional state. The server uses an AI model to infer emotions from the video and evaluate the players' mental condition.

[0880] Step 5:

[0881] The server integrates collected athlete and emotional data and analyzes athlete performance using a generative AI model. The input is the integrated dataset, and the output is the analysis results identifying the athlete's strengths and areas for improvement. The server uses the AI ​​model to analyze the data and comprehensively evaluate the athlete's performance.

[0882] Step 6:

[0883] The server generates improvement suggestions for each player based on the analysis results. The input is the analysis results, and the output is a customized training plan and nutritional guidance. The server uses a generative AI model to create prompt messages and generate the optimal training plan and nutritional advice for each player.

[0884] Step 7:

[0885] The server provides the user with the generated suggestions. The input is customized suggestions, and the output is information provided to the user. The user can review these suggestions through their terminal and use them for athlete training and nutrition management.

[0886] (Application Example 2)

[0887] Next, we will describe application example 2 of form 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."

[0888] There is a growing need to understand the operational efficiency of machinery and the condition of workers in factories in real time, and to propose efficient work plans and break schedules. However, conventional methods make it difficult to efficiently collect and analyze this data and make appropriate improvement suggestions.

[0889] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0890] In this invention, the server includes means for uploading video data, means for collecting machine and worker-specific data from the video data, means for analyzing operations and suggesting improvements based on the collected data, and means for providing customized work plans and rest advice according to the worker's condition. This enables efficient management and improvement suggestions for machines and workers within the factory.

[0891] "Video data" refers to digital data containing visual information acquired by cameras and other imaging devices.

[0892] "Means of uploading" refers to a method or device for transferring digital data to a server or cloud storage via a network.

[0893] "Machine and worker-specific data" refers to operational information for individual machines within the factory, as well as information regarding the work status and condition of workers.

[0894] "Means of collection" refers to methods or apparatus for acquiring specific information and gathering it for storage or analysis.

[0895] "Action analysis" is the process of evaluating the motion data of machines and workers to identify efficiency issues and problems.

[0896] "Means of proposing improvements" refers to methods or devices that present specific action plans for improving efficiency or solving problems based on analysis results.

[0897] "Worker's condition" refers to information indicating the physical and mental state of the worker.

[0898] A "customized work plan" refers to a work schedule and procedures that are optimized according to the individual worker's condition and abilities.

[0899] "Break advice" refers to information that suggests appropriate timing and methods for breaks in order to reduce fatigue and stress among workers.

[0900] The system for implementing this invention monitors the operation of machinery and workers in a factory and provides efficient management and improvement suggestions. The server uses means for uploading video data to transfer video data acquired from surveillance cameras in the factory to cloud storage. Next, it uses means for collecting machine and worker-specific data from the video data to obtain operation information for individual machines and the work status of workers.

[0901] This data is processed using OpenCV with Python, and the behavior is analyzed by a generative AI model using TensorFlow. Based on the analysis results, the server provides suggestions for improvement and presents concrete action plans for efficiency improvement and problem solving. Furthermore, to provide customized work plans and break advice according to the worker's state, emotion recognition APIs (e.g., Microsoft Azure Emotion API) are used to collect and comprehensively analyze worker emotion data.

[0902] For example, if it is found that a particular machine's operational efficiency decreases in the afternoon, the server will suggest regular maintenance for that machine. Similarly, if worker emotional data indicates increased stress, it can suggest a break.

[0903] An example of a prompt message is, "Analyze the cause of the decrease in machine operation efficiency in the afternoon and propose solutions for improvement."

[0904] The flow of a specific process in Application Example 2 will be explained using Figure 18.

[0905] Step 1:

[0906] The server acquires video data from surveillance cameras within the factory and uploads it to cloud storage via the network. The input is real-time video data from the surveillance cameras, and the output is a video file stored in cloud storage. This step involves the transfer and storage of video data.

[0907] Step 2:

[0908] The server processes the uploaded video data using OpenCV with Python and extracts motion data for both the machine and the worker. The input is a video file stored in cloud storage, and the output is machine motion information and worker work status data. In this step, video data analysis and motion data extraction are performed.

[0909] Step 3:

[0910] The server analyzes the extracted motion data using a generative AI model based on TensorFlow to identify operational efficiency and problems. The input consists of machine motion information and worker work status data, while the output is the analysis results regarding operational efficiency and problems. In this step, data analysis is performed by the AI ​​model.

[0911] Step 4:

[0912] The server makes improvement suggestions based on the analysis results and generates concrete action plans for efficiency improvement and problem solving. The input is the analysis results regarding operational efficiency and problems, and the output is the action plan of improvement suggestions. In this step, improvement measures are generated and proposed.

[0913] Step 5:

[0914] The server uses an emotion recognition API to collect worker emotion data and evaluate the worker's state. The input is real-time video data of the worker, and the output is the worker's emotion data. In this step, emotion data is collected and evaluated.

[0915] Step 6:

[0916] The server integrates and analyzes worker emotional and behavioral data to provide customized work plans and break advice. The input is worker emotional and behavioral data, and the output is customized work plans and break advice. This step involves integrated data analysis and personalized recommendations.

[0917] (Other examples)

[0918] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[0919] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0920] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0921] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[0922] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0923] [Fourth Embodiment]

[0924] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0925] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0926] The data processing device 12 includes a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a “computer” related to the technology of this disclosure.

[0927] Computer 22 includes a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. A database 24 and a communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0928] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0929] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0930] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0931] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0932] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0933] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0934] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0935] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0936] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0937] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0938] "Example of form 1"

[0939] The system of the present invention includes means for uploading soccer match videos, means for collecting team and player-specific data from the match videos, means for analyzing performance and suggesting improvements based on the collected data, and means for providing customized training plans and nutritional advice according to the players' condition. These means are realized using AI technology. Specifically, the system analyzes players' movements and performance from match videos to understand each player's strengths and weaknesses. Furthermore, the AI ​​provides optimal training plans and nutritional advice according to the players' condition and performance. This moves away from subjective instruction based on the experience and knowledge of coaches and parents, and supports growth with the most optimal coaching methods. "Example Form 2"

[0940] As a concrete example, a junior soccer club team uploads match videos to the system of the present invention after a game. The system uses AI to analyze the videos and collect individual player performance data (e.g., distance covered, number of sprints, pass success rate, etc.). Furthermore, the AI ​​analyzes performance and suggests improvements based on the collected data. For example, if a particular player tends to have a decrease in the number of sprints in the second half of a match, the AI ​​will suggest a training plan to improve that player's stamina. The system also provides customized nutritional advice according to the player's condition (e.g., energy sources to consume before a match, nutrients needed for recovery after a match, etc.).

[0941] The following describes the processing flow for each example of the form.

[0942] "Example of form 1"

[0943] Step 1: A user (e.g., a coach or parent) uploads a video of a soccer match to the system of the present invention.

[0944] Step 2: The system uses AI to analyze the video and collect individual player performance data (e.g., distance covered, number of sprints, pass completion rate, etc.).

[0945] Step 3: The AI ​​analyzes performance and suggests improvements based on the collected data.

[0946] Step 4: Based on the player's condition, the AI ​​provides a customized training plan and nutritional advice.

[0947] "Example of form 2"

[0948] Step 1: A junior soccer club team uploads a video of the match to the system of the present invention after the match.

[0949] Step 2: The system uses AI to analyze the videos and collect individual player performance data.

[0950] Step 3: The AI ​​analyzes performance and suggests improvements based on the collected data. If a particular player tends to have fewer sprints in the second half of a match, the AI ​​will suggest a training plan to improve that player's stamina.

[0951] Step 4: Based on the player's condition, the AI ​​provides customized nutritional advice. For example, it suggests energy sources to consume before a match and nutrients needed for recovery after a match.

[0952] (Example 1)

[0953] Next, we will describe Embodiment 1 of Example Form 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0954] Traditional soccer coaching relied heavily on the experience and knowledge of coaches and parents, resulting in a subjective approach that made it difficult to provide optimal coaching based on individual player performance and condition. Furthermore, data collection and analysis from match footage were often done manually, making efficient analysis challenging.

[0955] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0956] In this invention, the server includes means for transmitting match video, means for acquiring group and individual information from the match video, means for analyzing abilities and suggesting improvements based on the acquired information, means for providing training plans and nutritional guidance tailored to the individual's condition, and means for inputting prompt sentences using a generative AI model and generating specific suggestions based on the analysis results. This enables optimal guidance based on the individual performance of each player and efficient data analysis.

[0957] "Match footage" refers to video data that records the events of a soccer match, and is used to visually capture the movements of the players and teams.

[0958] "Means of transmission" refers to a device or software that has the function of transferring digital data to other devices or systems via a network.

[0959] "Group and individual information" refers to data about the entire team and each player extracted from match footage, including detailed information about performance and movement.

[0960] "Means of acquisition" refers to devices or software used to collect specific data or information and convert it into a format usable within the system.

[0961] "Performance analysis" is the process of evaluating the performance of players and teams based on collected data, and identifying their strengths and weaknesses.

[0962] "Suggestions for improvement" refers to providing specific advice and strategies to improve the performance of players and teams based on the analysis results.

[0963] "Individual condition" refers to information about each player's physical condition, such as their health, fitness level, and fatigue level.

[0964] A "tailored training plan" is a training menu customized according to the individual athlete's condition and goals, aiming for effective performance improvement.

[0965] "Nutritional guidance" refers to providing advice on diet and nutritional intake in order to optimize an athlete's health and performance.

[0966] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[0967] A "prompt statement" is a sentence containing instructions or questions that are input into a generative AI model, and it serves as a trigger for the model to generate appropriate output.

[0968] This invention is a system for analyzing soccer match footage to improve the performance of players and teams. Users upload match footage from their terminals to a server. The server analyzes the footage using video analysis software (e.g., OpenCV) and extracts player movement and position data. This allows for the acquisition of group and individual information.

[0969] The server inputs the acquired information into an AI model (e.g., TensorFlow or PyTorch) to analyze the player's abilities. The AI ​​model evaluates the player's strengths and weaknesses and generates specific suggestions for improvement. This includes a training plan tailored to the player's condition and nutritional guidance.

[0970] As a concrete example, a user inputs a prompt into the AI ​​model stating, "I want you to analyze the distance covered and the number of sprints performed by players during a match and suggest a training plan to improve their stamina." The server then measures the distance covered and the number of sprints from the match footage and uses the AI ​​model to suggest an effective training plan to improve stamina. This suggestion includes specific running menus and nutritional advice.

[0971] This system allows users to receive optimal coaching based on their individual performance and enables efficient data analysis.

[0972] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0973] Step 1:

[0974] The user uploads soccer match footage from their device to the server. The input is a match video file, which the server receives and saves. Specifically, the user selects the file using a dedicated interface and clicks the upload button.

[0975] Step 2:

[0976] The server analyzes the saved match footage using video analysis software (e.g., OpenCV). The input is the saved video file, and the output is player movement and position data. The server identifies players in the video and extracts data such as the distance covered and the number of sprints for each player. Specifically, the server tracks the position of each player frame by frame and calculates the distance traveled.

[0977] Step 3:

[0978] The server inputs the extracted data into an AI model (e.g., TensorFlow or PyTorch) to analyze the players' abilities. The input is data on the players' movements and positions, and the output is an evaluation of the players' strengths and weaknesses. The AI ​​model analyzes the data to evaluate each player's performance and generates suggestions for improvement. Specifically, the AI ​​model passes the data through a pre-trained model and calculates an evaluation score.

[0979] Step 4:

[0980] The server generates a customized training plan and nutritional guidance tailored to the athlete's condition based on the analysis results. The input is the athlete's evaluation results, and the output is a specific training menu and nutritional advice. The server uses a generation AI model to receive prompt messages and generates specific suggestions based on the analysis results. Specifically, the server inputs prompt messages into the AI ​​model and generates customized advice.

[0981] Step 5:

[0982] The server sends the generated training plan and nutritional guidance to the user's terminal. The input is the generated suggestions, and the output is information in a format that the user can review. Specifically, the server converts the suggestions into text format and sends a notification to the user's terminal.

[0983] (Application Example 1)

[0984] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0985] There is a need to improve the operational efficiency of robots in factories and optimize the timing and methods of maintenance. However, conventional methods have made it difficult to detect inefficiencies in operation in real time and propose efficient operation plans.

[0986] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0987] In this invention, the server includes means for recording operations, means for collecting individual data from the recorded operations, means for performing efficiency analysis and suggesting improvements based on the collected data, and means for providing customized optimization plans and maintenance advice according to the state of operation. This enables real-time optimization of robot operations within a factory, resulting in efficient operation.

[0988] "Means for recording motion" refers to a device or method for recording the motion of robots and machinery in a factory using video or sensors.

[0989] "Means for collecting individual data" refers to a device or method for extracting operational information of a specific robot or machine from recorded movements and collecting it as data.

[0990] "Means for analyzing efficiency and proposing improvements" refers to a device or method that evaluates the efficiency of operations based on collected operational data and makes specific suggestions for improvement.

[0991] "Means for providing customized optimization plans and maintenance advice according to the operating state" refers to a device or method that takes into account the current operating state of a robot or machine and individually provides the optimal operating plan and maintenance method.

[0992] The system for implementing this invention is designed to optimize the operation of robots within a factory. The server records the robot's movements in real time using surveillance cameras and sensors installed within the factory. The recorded video data is analyzed frame by frame using OpenCV, and the operation data of each robot is extracted.

[0993] The server inputs collected operational data into a generative AI model built using TensorFlow to evaluate the efficiency of the operations. The AI ​​model detects inefficiencies and errors in the operations and generates efficient operation plans. Furthermore, it provides customized optimization plans and maintenance advice based on the operational status.

[0994] As a concrete example, we can analyze the movements of a robotic arm used in a factory and propose a plan to reduce wasted motion. Based on the generated plan, the user can adjust the robot's movements to achieve efficient operation.

[0995] An example of a prompt would be, "Analyze the video of the robot arm's movements and propose an efficient movement plan." This prompt prompts the AI ​​model to analyze the movement data and generate the optimal plan.

[0996] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0997] Step 1:

[0998] The server records the robot's movements in real time from surveillance cameras and sensors installed within the factory. The input is video data from the cameras and sensors, and the output is the recorded video file. In this step, the video data is divided into frames in preparation for subsequent analysis.

[0999] Step 2:

[1000] The server analyzes the recorded video data using OpenCV and extracts robot motion data from each frame. The input is the video file obtained in step 1, and the output is the motion data. In this step, the characteristics of the motion are extracted and organized as data.

[1001] Step 3:

[1002] The server inputs the extracted motion data into a generative AI model built using TensorFlow and evaluates the efficiency of the motion. The input is the motion data obtained in step 2, and the output is the efficiency evaluation result. In this step, the AI ​​model detects inefficiencies and errors in the motion.

[1003] Step 4:

[1004] The server generates an efficient operation plan based on the evaluation results of the AI ​​model. The input is the evaluation results obtained in step 3, and the output is the optimized operation plan. In this step, areas for improvement in operation are identified, and a specific plan is formulated.

[1005] Step 5:

[1006] The user adjusts the robot's movements based on the optimization plan provided by the server. The input is the movement plan obtained in step 4, and the output is the adjusted robot's movements. In this step, the user modifies the robot's settings according to the plan to achieve efficient operation.

[1007] (Example 2)

[1008] Next, we will describe Example 2 of the morphological example. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1009] In sports competitions, analyzing athletes' performance in detail and providing individualized improvement suggestions and nutritional guidance is time-consuming and labor-intensive using traditional methods, making it difficult to do efficiently and effectively. This is especially true for junior athletes, who require appropriate guidance tailored to their individual developmental stages, but there is a lack of systems to achieve this.

[1010] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1011] In this invention, the server includes means for transmitting match video, means for acquiring group and individual information from the match video, means for evaluating abilities and suggesting improvements based on the acquired information, means for providing exercise plans and nutritional guidance tailored to the individual's condition, and means for generating prompt sentences using a generative AI model. This makes it possible to efficiently analyze athlete performance and quickly provide individual improvement suggestions and nutritional guidance.

[1012] "Match footage" refers to video data that records the events of a sports competition, allowing viewers to visually perceive the movements of the players and the progress of the match.

[1013] "Means of transmission" refers to technical means for moving data from one point to another, and includes the function of transferring data over a network.

[1014] "Group and individual information" refers to data about the entire team and each individual player participating in the match, including detailed information about their performance and behavior.

[1015] "Means of acquisition" refers to technical means for collecting data and extracting necessary information, and includes functions that use sensors and analysis software to obtain information.

[1016] "Performance assessment" is the process of analyzing an athlete's performance and measuring their technical and physical abilities.

[1017] "Suggestions for improvement" involve providing specific advice and plans to improve a player's performance, including changes to training and tactics.

[1018] "Individual condition" refers to the physical and mental condition of the athlete, including their health status and fatigue level.

[1019] A "tailored exercise plan" is a training program customized to the individual needs and condition of the athlete, aiming for efficient performance improvement.

[1020] "Nutritional guidance" involves providing advice on diet and nutrient intake to optimize an athlete's health and performance.

[1021] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[1022] A "prompt statement" is an instruction given to a generative AI model, serving as a guideline for the AI ​​to generate appropriate output.

[1023] A description of embodiments for carrying out this invention will be given.

[1024] Users upload match footage they filmed after junior soccer matches to the system using their devices. The server uses OpenCV and TensorFlow as AI analysis software to analyze the received match footage. The server uses this software to identify players in the match footage and track each player's movements.

[1025] The server collects performance data for each player through video analysis, such as distance covered, number of sprints, and pass completion rate. For example, it might record that player A ran 5km during a match, performed 15 sprints, and had a pass completion rate of 80%.

[1026] The collected data is input into a generating AI model on the server to analyze each player's performance. The AI ​​model evaluates the players' physical and technical tendencies and identifies areas for improvement. For example, if player B's sprint count decreases in the second half of a match, the AI ​​will make specific suggestions such as, "We recommend interval training three times a week to improve stamina."

[1027] Furthermore, the server uses AI to generate customized nutritional advice based on the player's condition. For example, it might advise, "Eat a meal high in carbohydrates before a match, and a meal containing protein and vitamins after a match."

[1028] As an example of a prompt that the user inputs to the generated AI model, you can use a sentence such as, "Analyze the match video, collect performance data for each player, and provide suggestions for improvement."

[1029] This system allows coaches and players at junior soccer clubs to review their performance after matches and identify specific areas for improvement.

[1030] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1031] Step 1:

[1032] Users upload match footage they filmed after junior soccer matches to the system using a terminal. The input is the match video file, and the output is the transfer of video data to the server. Users select the file through the terminal interface and press the upload button to send the video data to the server.

[1033] Step 2:

[1034] The server passes the received match video to AI analysis software (e.g., OpenCV or TensorFlow). The input is the match video data, and the output is data ready for analysis. The server divides the video data into frames and performs preprocessing to identify the players in each frame.

[1035] Step 3:

[1036] The server uses an AI model to track players in match footage and analyze each player's movements. The input is pre-processed video data, and the output is movement data for each player. The server tracks players' positions and movements and collects performance data such as distance covered and number of sprints.

[1037] Step 4:

[1038] The server inputs the collected performance data into a generating AI model to analyze each player's performance. The input is data on each player's movements, and the output is the performance evaluation result. The AI ​​model evaluates the players' physical strength and technical tendencies and identifies areas for improvement.

[1039] Step 5:

[1040] The server generates specific improvement suggestions for each player based on the analysis results. The input is the performance evaluation results, and the output is the improvement suggestions. For example, the AI ​​might suggest, "We recommend interval training three times a week to improve stamina."

[1041] Step 6:

[1042] The server uses AI to generate customized nutritional advice based on the player's condition. The input is the player's performance data and condition information, and the output is nutritional advice. For example, it might provide advice such as, "It is recommended to eat a meal high in carbohydrates before a match, and a meal containing protein and vitamins after a match."

[1043] Step 7:

[1044] The server provides users with generated improvement suggestions and nutritional advice. The input consists of improvement suggestions and nutritional advice, while the output is information provided to the user. Users can view this information through their terminals and utilize it for athlete training and nutrition management.

[1045] (Application Example 2)

[1046] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1047] There is a need to improve the operational efficiency and safety of machinery and workers operating within factories. However, conventional methods often involve manual recording and analysis of operations, making it difficult to propose efficient improvements.

[1048] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1049] In this invention, the server includes means for recording operations, means for collecting machine and operator-specific data from the recorded operations, means for analyzing work efficiency and safety and proposing improvements based on the collected data, and means for providing customized maintenance plans and operational advice according to the machine's condition. This makes it possible to efficiently and safely improve the operation of machines and operators within a factory.

[1050] "Means for recording motion" refers to devices or methods for recording the movements of machines or workers as video or sensor data.

[1051] "Means of collecting data" refers to devices and methods for extracting and organizing specific information for each machine or worker from recorded actions.

[1052] "Means for analysis and improvement proposals" refer to devices and methods for evaluating work efficiency and safety based on collected data and generating specific proposals for improvement.

[1053] "Means of providing maintenance plans and operational advice" refers to devices or methods for presenting appropriate maintenance schedules and operating procedures according to the condition of the machine and the actions of the operator.

[1054] Artificial intelligence is a technology that enables computer systems to mimic human intellectual behavior and perform data analysis and decision-making.

[1055] A description of the embodiment for carrying out the invention will be provided.

[1056] The system that realizes this invention is intended to improve the efficiency and safety of the operation of machinery and workers in a factory. The server records the movements of machinery and workers using cameras and sensors as means of recording operations. The recorded data is transmitted to the server as a means of data collection, and specific information for each machine and worker is extracted.

[1057] The server uses artificial intelligence to evaluate work efficiency and safety based on collected data, as a means of analysis and suggesting improvements. This involves using Python, analyzing videos with OpenCV, and building AI models using TensorFlow and PyTorch. This generates efficient operation patterns and specific suggestions for improving safety.

[1058] Furthermore, the server provides maintenance plans and operational advice by suggesting appropriate maintenance schedules and operating methods tailored to the machine's condition and the operator's actions. This maximizes machine operating efficiency and ensures operator safety.

[1059] A concrete example is when a robot is assembling parts, and the AI ​​detects that a particular movement is slow and suggests a new movement pattern to improve that movement. An example of a prompt used in this case would be, "Analyze the robot's movement patterns in this video and suggest improvements to increase efficiency."

[1060] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1061] Step 1:

[1062] The server uses cameras and sensors installed within the factory to record the movements of machinery and workers in real time. The input is video data from the cameras and sensors, and the output is a recorded video file. This video file is stored on the server for subsequent analysis.

[1063] Step 2:

[1064] The server divides the recorded video file into frames and extracts feature data related to the movements of machines and workers from each frame. The input is a video file, and the output is feature data for each frame. Image processing is performed using OpenCV to extract information such as the speed and direction of the movements.

[1065] Step 3:

[1066] The server uses the extracted feature data to perform analysis using an artificial intelligence model. The input is feature data, and the output is an evaluation result regarding work efficiency and safety. The AI ​​model, built using TensorFlow or PyTorch, identifies efficient operating patterns and areas for improvement to enhance safety.

[1067] Step 4:

[1068] The server generates specific improvement suggestions for machines and workers based on the analysis results. The input is the evaluation results, and the output is a list of improvement suggestions. Using the generated AI model, concrete action plans are created to improve efficiency and ensure safety.

[1069] Step 5:

[1070] The server provides machine maintenance schedules and operator advice based on improvement suggestions. Input is a list of improvement suggestions, and output is a maintenance plan and operational advice. This maximizes machine operating efficiency and ensures operator safety.

[1071] Furthermore, an emotion engine that estimates the user's emotions may be combined. That is, the identification processing unit 290 estimates the user's emotions using the emotion identification model 59, and the user's emotions You may also perform specific processing using [this method].

[1072] "Example of form 1"

[1073] One embodiment of the present invention is a system that incorporates an emotion engine. This system includes means for uploading soccer match videos, means for collecting team and player-specific data from the match videos, means for analyzing performance and suggesting improvements based on the collected data, means for providing customized training plans and nutritional advice according to the players' condition, and an emotion engine that recognizes the user's emotions. The emotion engine collects the user's emotional data and analyzes performance and suggests improvements based on that emotional data. The emotion engine also provides customized training plans and nutritional advice based on the user's emotional data.

[1074] "Example of form 2"

[1075] As a concrete example, a junior soccer club team uploads match videos to the system of the present invention after a game. The system uses AI to analyze the videos and collect performance data for each player. At the same time, the emotion engine collects the user's emotional data. Based on the collected performance data and emotional data, the AI ​​analyzes performance and suggests improvements. For example, if a particular player tends to have fewer sprints in the second half of a match, and fatigue can be inferred from that player's emotional data, the AI ​​will provide that player with a training plan to improve stamina and nutritional advice effective for fatigue recovery.

[1076] The following describes the processing flow for each example of the form.

[1077] "Example of form 1"

[1078] Step 1: The user uploads a video of a soccer match to the system.

[1079] Step 2: The system uses AI to collect team and player-specific data from the video.

[1080] Step 3: The emotion engine collects user emotion data.

[1081] Step 4: The AI ​​analyzes performance and suggests improvements based on the collected performance and sentiment data.

[1082] Step 5: The AI ​​provides a customized training plan and nutritional advice based on the player's condition.

[1083] "Example of form 2"

[1084] Step 1: Junior soccer club teams upload match videos to the system after the game.

[1085] Step 2: The system uses AI to analyze the videos and collect individual player performance data.

[1086] Step 3: The emotion engine collects user emotion data.

[1087] Step 4: The AI ​​analyzes performance and suggests improvements based on the collected performance and sentiment data.

[1088] Step 5: If a particular player tends to have a decrease in sprints in the second half of a match, and fatigue can be inferred from that player's emotional data, the AI ​​will provide that player with a training plan to improve stamina and nutritional advice that will help with fatigue recovery.

[1089] (Example 1)

[1090] Next, we will describe Embodiment 1 of Example Form 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1091] In soccer matches, objectively evaluating player performance and providing optimal training plans and nutritional guidance to individual players has been difficult with traditional methods. Furthermore, coaching that takes into account players' emotional states relies on subjective judgment and is not optimized. This presents a challenge in effectively supporting player development.

[1092] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1093] In this invention, the server includes means for transmitting match video, means for extracting group and individual information from the match video, means for evaluating abilities and suggesting improvements based on the extracted information, means for providing training plans and nutritional guidance tailored to the individual's condition, and means for collecting and analyzing emotional information. This makes it possible to objectively evaluate the performance of players, provide optimal training plans and nutritional guidance for each player, and provide guidance that takes into account the emotional state of the players.

[1094] "Means for transmitting match footage" refers to a function that allows users to upload soccer match footage to the system and for the server to receive that footage.

[1095] "Means for extracting group and individual information" refers to a function for analyzing and collecting movement and performance data for the entire team and each individual player from match footage.

[1096] "Means for evaluating abilities and proposing improvements" refers to a function that analyzes a player's performance based on extracted data, identifies their strengths and weaknesses, and makes specific suggestions for improvement.

[1097] "Means of providing training plans and nutritional guidance tailored to individual conditions" refers to a function that generates and provides individually optimized training plans and nutritional advice based on the athlete's condition and performance data.

[1098] "Means for collecting and analyzing emotional information" refers to a function that collects user emotional data, analyzes that data, and provides guidance and support based on the emotional state of the players.

[1099] A description of embodiments for carrying out this invention will be given.

[1100] Users upload soccer match footage from their devices to the system. The server receives this footage and stores it in a database. Next, the server analyzes the footage using AI technology. Specifically, it utilizes computer vision technology and software such as OpenCV and TensorFlow to detect player movements and the position of the ball. This analysis extracts motion data for the entire team and for each individual player.

[1101] The server evaluates player performance based on the extracted data. Using an AI model, it identifies players' strengths and weaknesses and reveals areas for improvement. For example, it quantifies players' running distance and shooting accuracy and performs comparative analysis.

[1102] Furthermore, the server generates individually optimized training plans and nutritional advice based on the athlete's condition. This involves AI analyzing the athlete's data and suggesting running menus to improve endurance and meal plans to enhance concentration.

[1103] The server also uses an emotion engine to collect and analyze user emotional data. Based on the user's emotional state, it makes suggestions for performance improvement. For example, if a user is feeling stressed after a match, it might suggest mental training to help them relax.

[1104] For example, if a player is analyzed to have low running distance and poor shooting accuracy during a match, the server will provide that player with a training plan to improve endurance and nutritional advice to enhance concentration. Also, if a player is feeling down after a match, the emotional engine will suggest mental training to help them relax.

[1105] An example of a prompt for a generative AI model is: "Analyze a soccer match video, identify player A's strengths and weaknesses based on their performance data, and generate a training plan and nutritional advice for improvement. Also, consider player A's emotional data and suggest mental support."

[1106] The flow of the specific processing in Example 1 will be explained using Figure 15.

[1107] Step 1:

[1108] Users upload soccer match footage from their devices to the system. The input is the match video file, and the output is the video data stored on the server. Using their devices, users select the video file through a designated interface and press the upload button to send the video to the server.

[1109] Step 2:

[1110] The server stores the received video data in a database. The input is video data sent by the user, and the output is video data stored in the database. When the server receives video data, it uses a database management system to save the data in the appropriate format.

[1111] Step 3:

[1112] The server analyzes stored video data. The input is video data stored in a database, and the output is analysis data regarding player movements and ball position. The server uses computer vision technology, utilizing libraries such as OpenCV and TensorFlow, to detect player movements and ball position from the video.

[1113] Step 4:

[1114] The server evaluates player performance based on the analyzed data. The input is analyzed data on player movements and ball position, and the output is performance evaluation data for each player. The server uses an AI model to identify players' strengths and weaknesses and generate a quantified evaluation.

[1115] Step 5:

[1116] The server generates training plans and nutritional advice tailored to each athlete's condition. The input is the athlete's performance evaluation data, and the output is an individually optimized training plan and nutritional advice. The server utilizes AI to analyze the athlete's data and proposes running menus to improve endurance and meal plans to enhance concentration.

[1117] Step 6:

[1118] The server collects and analyzes user emotional data. The input is the user's emotional data, and the output is an analysis result based on their emotional state. The server uses an emotion engine to analyze the user's emotions and evaluate their stress and motivation levels.

[1119] Step 7:

[1120] The server provides customized advice based on the user's emotional state. The input is an analysis of the emotional state, and the output is a suggestion for mental support tailored to that emotional state. The server considers the user's emotional state and provides mental training to help them relax and advice to boost their motivation.

[1121] (Application Example 1)

[1122] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1123] There is a need to improve the operational efficiency of robots in factories and to improve the work environment based on the emotions of the operators. However, conventional systems do not adequately analyze robot movements or recognize operator emotions, making it difficult to propose efficient movements or improve the work environment.

[1124] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1125] In this invention, the server includes means for uploading soccer match videos, means for collecting collective and individual data from the match videos, means for analyzing movements and suggesting improvements based on the collected data, means for providing customized training plans and nutritional guidance according to the individual's condition, and means for recognizing emotions and suggesting improvements to the work environment. This makes it possible to improve the operational efficiency of robots in factories and to improve the work environment based on the emotions of operators.

[1126] "A means of uploading soccer match videos" refers to a function for transferring video data of soccer matches to a server.

[1127] "Means for collecting collective and individual data from match videos" refers to a function for extracting information about the entire team and individual players from uploaded match videos.

[1128] "Means for analyzing operations and proposing improvements based on collected data" refers to a function that analyzes collected data and presents measures to improve the efficiency of operations and suggest improvements.

[1129] "Means of providing customized training plans and nutritional guidance according to the individual's condition" refers to a function that provides optimal training programs and nutritional advice based on the condition of each individual athlete or robot.

[1130] "Means for recognizing emotions and proposing improvements to the work environment" refers to a function that analyzes the emotions of operators and users and proposes measures to improve the work environment based on those analyses.

[1131] In an embodiment of this invention, the server is configured as follows: The server includes means for uploading soccer match videos, thereby allowing users to transfer match video data to the server. Next, the server extracts information about the entire team and individual players using means for collecting collective and individual data from the match videos. This data collection is performed using video analysis with Python and OpenCV.

[1132] Based on the collected data, the server employs means to analyze its behavior and suggest improvements. This process utilizes an AI model based on TensorFlow to generate efficient behavior plans. Furthermore, it provides customized training plans and nutritional guidance tailored to the individual's condition, which are also implemented by AI.

[1133] Furthermore, the server is equipped with the means to recognize emotions and suggest improvements to the work environment. It uses an emotion recognition API to analyze the emotional data of operators and users. This makes it possible to suggest improvements to the work environment.

[1134] As a concrete example, when a robot assembles parts in a factory, it can reduce wasted motion and suggest more efficient movements. It can also suggest breaks if the operator is tired. An example of a prompt message would be, "Analyze the robot's motion data and generate an efficient motion plan. Also, suggest improvements to the work environment based on the operator's emotional data."

[1135] The flow of a specific process in Application Example 1 will be explained using Figure 16.

[1136] Step 1:

[1137] The user uploads soccer match videos from their device to the server. The input is the video data of the match, and the output is the video file stored on the server. In this step, the user selects the match video and presses the upload button, and the data is transferred to the server.

[1138] Step 2:

[1139] The server collects collective and individual data from uploaded videos. The input is video files stored on the server, and the output is data about the entire team and individual players. Python and OpenCV are used to analyze the videos and extract player movement and position information.

[1140] Step 3:

[1141] The server analyzes the collected data and suggests improvements to the player's movements. The input is the player's movements and position information, and the output is an efficient movement plan. An AI model using TensorFlow analyzes the data and generates the optimal movement plan.

[1142] Step 4:

[1143] The server provides customized training plans and nutritional guidance tailored to each individual's condition. Inputs are the athlete's movement data and condition information, while output is individually customized training plans and nutritional advice. AI evaluates the athlete's strengths and weaknesses and proposes the optimal plan.

[1144] Step 5:

[1145] The server recognizes emotions and provides suggestions for improving the work environment. Input is emotional data from operators and users, and output is suggestions for improving the work environment. An emotion recognition API is used to analyze the emotional data and evaluate stress and fatigue levels.

[1146] Step 6:

[1147] The server notifies the user of the generated operation plan and improvement suggestions. The input is an efficient operation plan and improvement suggestions, and the output is a notification message to the user. The user can check the suggestions on their terminal and take action.

[1148] (Example 2)

[1149] Next, we will describe Example 2 of the morphological example. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1150] Conventional sports analysis systems have limited data available from match videos, making it difficult to comprehensively evaluate athlete performance. Furthermore, they are unable to provide individualized improvement suggestions that take into account athlete emotions and physical condition, thus failing to adequately contribute to athlete development and health management.

[1151] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1152] In this invention, the server includes means for uploading match videos, means for collecting individual athlete data from the match videos, means for analyzing the athlete's condition based on the collected data and making suggestions for improvement, means for providing customized training plans and nutritional guidance according to the athlete's condition, means for collecting emotional data and utilizing it for analyzing the athlete's condition, and means for generating suggestions using a generative AI model. This makes it possible to comprehensively evaluate the athlete's performance and make improvement suggestions that meet individual needs.

[1153] "Match videos" are video data that records the events of a sports competition, allowing viewers to visually capture the movements of the players and the progress of the match.

[1154] "Athlete data" refers to information about individual players extracted from match videos, including performance indicators such as distance covered, number of sprints, and pass completion rate.

[1155] "Athlete status" refers to the physical and mental condition of an athlete, and is assessed based on performance data and emotional data.

[1156] A "training plan" outlines the schedule and content of training aimed at improving an athlete's performance, and is customized according to individual needs.

[1157] "Nutritional guidance" refers to advice on diet and nutrient intake aimed at maintaining the health and improving the performance of athletes, and is provided according to the individual athlete's condition.

[1158] "Emotional data" refers to information that indicates an athlete's emotional state, and is obtained through the analysis of facial expressions and movements.

[1159] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to analyze data and generate suggestions or predictions.

[1160] This invention is a system for analyzing sports competition videos to evaluate and improve athlete performance. Users upload match videos to the system using a terminal after the match. The server utilizes computer vision technology to analyze the received videos. Specifically, it uses software libraries such as OpenCV and TensorFlow to track the movements of athletes and extract individual athlete data.

[1161] The server collects athlete data such as distance covered, number of sprints, and pass completion rate for each player from the analysis results. Furthermore, it uses an emotion engine to collect emotional data from the players and comprehensively evaluate their condition. This makes it possible to understand the players' physical and mental condition.

[1162] The server uses a generated AI model based on the collected data to analyze player performance and generate suggestions for improvement. For example, if a particular player tends to have a decrease in sprints in the second half of a match, the server will suggest a training plan to improve that player's stamina. It also provides customized nutritional guidance on energy sources to consume before a match and nutrients needed for post-match recovery.

[1163] As a concrete example, an example of a prompt sentence to be input to the generating AI model is: "Please suggest a stamina-improving training plan for a player whose sprint count decreases in the second half of a match. Also, please provide nutritional advice before and after the match."

[1164] This system allows users to comprehensively evaluate athlete performance and receive improvement suggestions tailored to their individual needs. This can contribute to athlete development and health management.

[1165] The flow of the specific processing in Example 2 will be explained using Figure 17.

[1166] Step 1:

[1167] After a match, the user uploads the match video to the system using a terminal. The input is the match video file, and the output is the transfer of the video data to the server. The terminal checks the format and size of the video file, converts it to the appropriate format, and sends it to the server.

[1168] Step 2:

[1169] The server uses computer vision technology to analyze the received match videos. The input is the uploaded video data, and the output is data tracking the players' movements. Specifically, it uses libraries such as OpenCV and TensorFlow to track the position and movement of players in the video in real time and record each player's actions in a database.

[1170] Step 3:

[1171] The server collects individual athlete data from the analysis results. The input is tracking data, and the output is performance indicators such as distance covered, number of sprints, and pass completion rate. The server aggregates this data and quantifies the performance of each athlete.

[1172] Step 4:

[1173] The server uses an emotion engine to collect emotional data from players. The input is video data of the players' facial expressions and movements, and the output is data indicating the players' emotional state. The server uses an AI model to infer emotions from the video and evaluate the players' mental condition.

[1174] Step 5:

[1175] The server integrates collected athlete and emotional data and analyzes athlete performance using a generative AI model. The input is the integrated dataset, and the output is the analysis results identifying the athlete's strengths and areas for improvement. The server uses the AI ​​model to analyze the data and comprehensively evaluate the athlete's performance.

[1176] Step 6:

[1177] The server generates improvement suggestions for each player based on the analysis results. The input is the analysis results, and the output is a customized training plan and nutritional guidance. The server uses a generative AI model to create prompt messages and generate the optimal training plan and nutritional advice for each player.

[1178] Step 7:

[1179] The server provides the user with the generated suggestions. The input is customized suggestions, and the output is information provided to the user. The user can review these suggestions through their terminal and use them for athlete training and nutrition management.

[1180] (Application Example 2)

[1181] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1182] There is a growing need to monitor the operational efficiency of machinery and the condition of workers in factories in real time, and to propose efficient work plans and break schedules. However, conventional methods make it difficult to efficiently collect and analyze this data and make appropriate improvement suggestions.

[1183] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1184] In this invention, the server includes means for uploading video data, means for collecting machine and worker-specific data from the video data, means for analyzing operations and suggesting improvements based on the collected data, and means for providing customized work plans and rest advice according to the worker's condition. This enables efficient management and improvement suggestions for machines and workers within the factory.

[1185] "Video data" refers to digital data containing visual information acquired by cameras and other imaging devices.

[1186] "Means of uploading" refers to a method or device for transferring digital data to a server or cloud storage via a network.

[1187] "Machine and worker-specific data" refers to operational information for individual machines within the factory, as well as information regarding the work status and condition of workers.

[1188] "Means of collection" refers to methods or apparatus for acquiring specific information and gathering it for storage or analysis.

[1189] "Action analysis" is the process of evaluating the motion data of machines and workers to identify efficiency issues and problems.

[1190] "Means of proposing improvements" refers to methods or devices that present specific action plans for improving efficiency or solving problems based on analysis results.

[1191] "Worker's condition" refers to information indicating the physical and mental state of the worker.

[1192] A "customized work plan" refers to a work schedule and procedures that are optimized according to the individual worker's condition and abilities.

[1193] "Break advice" refers to information that suggests appropriate timing and methods for breaks in order to reduce fatigue and stress among workers.

[1194] The system for implementing this invention monitors the operation of machinery and workers in a factory and provides efficient management and improvement suggestions. The server uses means for uploading video data to transfer video data acquired from surveillance cameras in the factory to cloud storage. Next, it uses means for collecting machine and worker-specific data from the video data to obtain operation information for individual machines and the work status of workers.

[1195] This data is processed using OpenCV with Python, and the behavior is analyzed by a generative AI model using TensorFlow. Based on the analysis results, the server provides suggestions for improvement and presents concrete action plans for efficiency improvement and problem solving. Furthermore, to provide customized work plans and break advice according to the worker's state, emotion recognition APIs (e.g., Microsoft Azure Emotion API) are used to collect and comprehensively analyze worker emotion data.

[1196] For example, if it is found that a particular machine's operational efficiency decreases in the afternoon, the server will suggest regular maintenance for that machine. Similarly, if worker emotional data indicates increased stress, it can suggest a break.

[1197] An example of a prompt message is, "Analyze the cause of the decrease in machine operation efficiency in the afternoon and propose solutions for improvement."

[1198] The flow of a specific process in Application Example 2 will be explained using Figure 18.

[1199] Step 1:

[1200] The server acquires video data from surveillance cameras within the factory and uploads it to cloud storage via the network. The input is real-time video data from the surveillance cameras, and the output is a video file stored in cloud storage. This step involves the transfer and storage of video data.

[1201] Step 2:

[1202] The server processes the uploaded video data using OpenCV with Python and extracts motion data for both the machine and the worker. The input is a video file stored in cloud storage, and the output is machine motion information and worker work status data. In this step, video data analysis and motion data extraction are performed.

[1203] Step 3:

[1204] The server analyzes the extracted motion data using a generative AI model based on TensorFlow to identify operational efficiency and problems. The input consists of machine motion information and worker work status data, while the output is the analysis results regarding operational efficiency and problems. In this step, data analysis is performed by the AI ​​model.

[1205] Step 4:

[1206] The server makes improvement suggestions based on the analysis results and generates concrete action plans for efficiency improvement and problem solving. The input is the analysis results regarding operational efficiency and problems, and the output is the action plan of improvement suggestions. In this step, improvement measures are generated and proposed.

[1207] Step 5:

[1208] The server uses an emotion recognition API to collect worker emotion data and evaluate the worker's state. The input is real-time video data of the worker, and the output is the worker's emotion data. In this step, emotion data is collected and evaluated.

[1209] Step 6:

[1210] The server integrates and analyzes worker emotional and behavioral data to provide customized work plans and break advice. The input is worker emotional and behavioral data, and the output is customized work plans and break advice. This step involves integrated data analysis and personalized recommendations.

[1211] (Other examples)

[1212] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[1213] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1214] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1215] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[1216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1217] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1218] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1219] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1220] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1221] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1222] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1223] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1224] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[1225] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1226] 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.

[1227] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1228] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1229] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1230] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1231] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1232] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1233] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1234] The following is further disclosed regarding the embodiments described above.

[1235] (Claim 1)

[1236] A system that includes means for uploading soccer match videos, means for collecting team and player-specific data from match videos, means for analyzing performance and suggesting improvements based on the collected data, and means for providing customized training plans and nutritional advice according to the players' condition.

[1237] (Claim 2)

[1238] The system according to claim 1, wherein the means for analyzing the performance and proposing improvements is performed by AI.

[1239] (Claim 3)

[1240] The system according to claim 1, wherein AI is used to provide a customized training plan and nutritional advice according to the condition of the aforementioned athlete.

[1241] (Claim 4)

[1242] The system according to claim 1, further comprising an emotion engine that recognizes the user's emotions.

[1243] (Claim 5)

[1244] The system according to claim 4, wherein the emotion engine collects user emotion data and performs performance analysis and makes suggestions for improvement based on the emotion data.

[1245] (Claim 6)

[1246] The system according to claim 4, wherein the emotion engine provides a customized training plan and nutritional advice based on the user's emotional data.

[1247] "Example 1"

[1248] (Claim 1)

[1249] A means of transmitting match footage,

[1250] A means of obtaining collective and individual information from match footage,

[1251] A means of analyzing capabilities and proposing improvements based on acquired information,

[1252] Means of providing training plans and nutritional guidance tailored to individual conditions,

[1253] A system that includes a means for inputting prompt sentences using a generative AI model and generating specific suggestions based on the analysis results.

[1254] (Claim 2)

[1255] The system according to claim 1, wherein the means for analyzing the aforementioned capabilities and proposing improvements are performed by artificial intelligence.

[1256] (Claim 3)

[1257] The system according to claim 1, wherein the means of providing a training plan and nutritional guidance tailored to the individual's condition are performed by artificial intelligence.

[1258] "Application Example 1"

[1259] (Claim 1)

[1260] A means of recording the action,

[1261] A means of collecting individual data from recorded actions,

[1262] A means of analyzing efficiency and proposing improvements based on collected data,

[1263] A system that includes means of providing customized optimization plans and maintenance advice based on the operating status.

[1264] (Claim 2)

[1265] The system according to claim 1, wherein the means for analyzing efficiency and proposing improvements is performed by artificial intelligence.

[1266] (Claim 3)

[1267] The system according to claim 1, wherein the means for providing a customized optimization plan and maintenance advice according to the state of the operation is performed by artificial intelligence.

[1268] Example 2

[1269] (Claim 1)

[1270] A means of transmitting match footage,

[1271] A means of obtaining collective and individual information from match footage,

[1272] A means of evaluating and suggesting improvements to abilities based on acquired information,

[1273] A means of providing exercise plans and nutritional guidance tailored to the individual's condition,

[1274] A system that includes means for generating prompt sentences using a generative AI model.

[1275] (Claim 2)

[1276] The system according to claim 1, wherein the means for evaluating and suggesting improvements to the aforementioned capabilities is performed by artificial intelligence.

[1277] (Claim 3)

[1278] The system according to claim 1, wherein the means for providing an exercise plan and nutritional guidance tailored to the individual's condition is performed by artificial intelligence.

[1279] "Application Example 2"

[1280] (Claim 1)

[1281] A means of recording the action,

[1282] A means of collecting machine and operator-specific data from recorded movements,

[1283] A means of analyzing work efficiency and safety and proposing improvements based on collected data,

[1284] A system that includes means of providing customized maintenance plans and operational advice according to the condition of the machine.

[1285] (Claim 2)

[1286] The system according to claim 1, wherein the means for analyzing work efficiency and safety and proposing improvements is performed by artificial intelligence.

[1287] (Claim 3)

[1288] The system according to claim 1, wherein the means for providing customized maintenance plans and operational advice according to the condition of the machine is performed by artificial intelligence.

[1289] "Example 1 of combining an emotion engine"

[1290] (Claim 1)

[1291] A means of transmitting match footage,

[1292] A method for extracting group and individual information from match footage,

[1293] A means of evaluating and suggesting improvements to abilities based on extracted information,

[1294] Means of providing training plans and nutritional guidance tailored to individual conditions,

[1295] A means of collecting and analyzing emotional information,

[1296] A system that includes this.

[1297] (Claim 2)

[1298] The system according to claim 1, wherein the means for evaluating and suggesting improvements to the aforementioned capabilities is performed by artificial intelligence.

[1299] (Claim 3)

[1300] The system according to claim 1, wherein the means of providing a training plan and nutritional guidance tailored to the individual's condition are performed by artificial intelligence.

[1301] "Application example 1 of combining emotional engines"

[1302] (Claim 1)

[1303] How to upload soccer match videos,

[1304] Methods for collecting collective and individual data from match videos,

[1305] A means of analyzing operations and proposing improvements based on collected data,

[1306] Means of providing customized training plans and nutritional guidance according to the individual's condition,

[1307] A system that includes means for recognizing emotions and suggesting improvements to the work environment.

[1308] (Claim 2)

[1309] The system according to claim 1, wherein the means for analyzing the aforementioned operation and proposing improvements is performed by artificial intelligence.

[1310] (Claim 3)

[1311] The system according to claim 1, wherein the means for providing a customized training plan and nutritional guidance according to the condition of the individual is performed by artificial intelligence.

[1312] "Example 2 of combining an emotion engine"

[1313] (Claim 1)

[1314] How to upload match videos,

[1315] A method for collecting individual athlete data from match videos,

[1316] A means of analyzing the condition of athletes based on collected data and making suggestions for improvement,

[1317] A means of providing customized training plans and nutritional guidance according to the individual's condition,

[1318] A means of collecting emotional data and using it to analyze the state of athletes,

[1319] A means of generating proposals using a generative AI model,

[1320] A system that includes this.

[1321] (Claim 2)

[1322] The system according to claim 1, wherein the means for analyzing the condition of the person performing the exercise and making suggestions for improvement is performed by artificial intelligence.

[1323] (Claim 3)

[1324] The system according to claim 1, wherein the means of providing a customized training plan and nutritional guidance according to the condition of the athlete is performed by artificial intelligence.

[1325] "Application example 2 when combining with an emotional engine"

[1326] (Claim 1)

[1327] Methods for uploading video data,

[1328] A means of collecting data on machines and workers from video data,

[1329] A means of analyzing operations and proposing improvements based on collected data,

[1330] A system that includes means of providing customized work plans and rest advice according to the worker's condition.

[1331] (Claim 2)

[1332] The system according to claim 1, wherein the means for analyzing the aforementioned operation and proposing improvements is performed by artificial intelligence.

[1333] (Claim 3)

[1334] The system according to claim 1, wherein the means for providing a customized work plan and rest advice according to the worker's condition is performed by artificial intelligence. [Explanation of Symbols]

[1335] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Equipped with a processor, The aforementioned processor, Upload a video of a soccer match. The system automatically analyzes uploaded videos, extracts player movement and position data from the uploaded videos, and, based on the player movement and position data, collects data for each team and individual player, including at least the number of sprints for each player. Based on the collected data, the performance of each player, including the number of sprints, is analyzed, and if it is determined that a particular player tends to have a decrease in the number of sprints in the second half of a match, the generative AI model is used to generate a prompt instructing the system to propose an improved training plan for that particular player to enhance their stamina. system.

2. The system according to claim 1, wherein the processor monitors data including the player's physical condition, fitness level, and fatigue level as the player's condition data, and generates prompts to instruct the system to provide a customized training plan and nutritional advice including energy sources to be taken before a match or nutrients necessary for recovery after a match, using a generative AI model based on the player's condition data and the player's performance analyzed based on the collected data.

3. The system according to claim 1, wherein the processor collects emotional data using an emotion engine for recognizing the emotions of the athlete, and generates prompts to instruct the system to provide training plans, nutritional advice, and mental support suggestions to the athlete using a generative AI model based on the analysis results of the athlete's performance based on the collected data and the emotional data.

Images