System

Abstract

A system is provided.SOLUTION: A system comprising: a terminal including a plurality of sensors that collect movement and technical data of a player in real time; means for transmitting data collected from the terminal to a server; means for storing the data received by the server in a database; means for analyzing the data stored in the server using a generated AI and evaluating characteristics and abilities of each player; means for generating an instruction method suitable for each player based on an evaluation result by the server using the generated AI; and means for notifying a user terminal of the generated instruction method.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The shortage of coaches in the educational field, especially those who can provide high-quality instruction, is a serious problem. Many teachers with no athletic experience coach club activities, placing a heavy burden on each teacher. It is also difficult to provide detailed instruction tailored to the individual characteristics of each athlete, making it difficult to maximize each individual's potential. Furthermore, the standardization of teaching methods has led to problems with athletes not being able to fully realize their potential. There is a need to improve this situation, reduce the burden on coaches, and provide instruction tailored to the individual characteristics of each athlete. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes a terminal equipped with multiple sensors that collect player movement and technique data in real time, a means for transmitting the collected data from the terminal to a server, a means for the server to store the received data in a database, a means for the server to analyze the stored data using a generation AI and evaluate each player's characteristics and abilities, a means for the server to generate a coaching method appropriate for each player based on the evaluation results using the generation AI, and a means for notifying the user of the generated coaching method to the user's terminal. This system provides individualized instruction to each player, reducing the burden on coaches and improving players' abilities. In particular, the system can automatically suggest exercises to improve form and specific coaching methods to improve technique, enabling high-quality training.

[0006] A "terminal" is a device that includes multiple sensors for collecting player movement and technical data in real time.

[0007] "Sensors" are devices that detect and collect data on a player's physical movements and technical performance.

[0008] The "server" is a computer system that receives data sent from the terminal, stores it in a database, and then analyzes the data using generative AI.

[0009] "Data transmission means" is a mechanism for transmitting data collected by the terminal to a server via the Internet or the like.

[0010] "Data storage means" is a mechanism for storing data received by the server in a database.

[0011] The "data analysis means" is a system that uses a generation AI to analyze data stored on the server and evaluate the characteristics and abilities of each player.

[0012] "Generative AI" refers to artificial intelligence that uses machine learning and deep learning algorithms to analyze data and automatically generate teaching methods.

[0013] The "evaluation method" is a mechanism that uses generative AI to analyze data and determine the characteristics and abilities of players.

[0014] The "training method generation means" is a mechanism that generates training methods and exercise plans suitable for each player based on the evaluation results.

[0015] The "notification means" is a mechanism for notifying the user's terminal of the generated teaching method.

[0016] "User" refers to the players and coaches who receive and implement the analysis results and coaching methods generated using generative AI. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention relates to a system that collects player movement and technical data in real time, and automatically analyzes the data using a generation AI to propose coaching methods. The following configurations and operations are included as embodiments of the invention.

[0039] System configuration

[0040] 1. Terminal (IOT device)

[0041] It includes multiple sensors that collect player movement and technical data in real time, such as smart shoes, smart clothing, and smart balls.

[0042] 2. Data transmission method

[0043] Data collected from the devices is sent to a server via the internet using communication protocols such as HTTP, HTTPS, and MQTT.

[0044] 3. Server

[0045] The received data is saved in the database.

[0046] Generative AI is used to analyze data and evaluate each player's characteristics and abilities.

[0047] Based on the evaluation results, a coaching method appropriate for each player is generated.

[0048] 4. Means of notification

[0049] The generated training method is sent to the user's device, where the user can receive the notification and check the specific training method and training plan.

[0050] Program processing overview

[0051] Data collection

[0052] The device (for example, smart shoes) collects foot movement and load in real time while the athlete is running. The sensors collect highly accurate data and temporarily store it in memory.

[0053] Data transmission

[0054] The device sends the collected data to a server via an internet connection, where it is converted into an appropriate format (e.g., JSON) and sent using a communication protocol (e.g., HTTP).

[0055] Data storage

[0056] The server receives the data sent from the devices and stores it in a database, which is organized by player and used for later analysis.

[0057] Data analysis

[0058] The server retrieves data for each athlete from the database and begins analysis using generative AI. For example, it uses smart shoe data to evaluate Athlete A's running form and analyzes the load distribution and movement patterns of the feet.

[0059] Teaching method generation

[0060] Based on the analysis results, the generative AI generates the optimal coaching method for each athlete. For example, if it is determined that Athlete A's running form is imbalanced, it will suggest one-legged squats to train specific muscles.

[0061] Result notification

[0062] The training method generated by the server is sent to the user's (coach or player's) device. The notification includes the data analysis results and specific training methods. The user receives the notification and can check and implement the training methods on their device.

[0063] Specific examples

[0064] Example 1: Improving your running form

[0065] 1. Data Collection

[0066] The smart shoes collect Athlete A's running data (foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[0067] 2. Data Transmission

[0068] The data collected by the device is converted into JSON format and sent to a server via the Internet.

[0069] 3. Data storage

[0070] The server stores the received data in a database.

[0071] 4. Data Analysis

[0072] The server analyzes the stored data using generated AI and discovers an imbalanced load distribution in Athlete A's running form.

[0073] 5. Generating Instructional Methods

[0074] Based on the generated AI, the server suggests specific muscle training exercises to Player A, including single-leg squats.

[0075] 6. Result notification

[0076] The server generates a training method and notifies the device of Player A. Player A checks the notification and starts the recommended training.

[0077] Example 2: Improving shooting technique

[0078] 1. Data Collection

[0079] The smart ball collects shot data (angle, power, distance) from Player B. The sensors also measure wrist movement and ball rotation.

[0080] 2. Data Transmission

[0081] The data collected by the terminal is converted into XML format and sent to the server via the HTTPS protocol.

[0082] 3. Data storage

[0083] The server stores the received data in a database.

[0084] 4. Data Analysis

[0085] The server analyzes the saved data using a generative AI and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[0086] 5. Generating Instructional Methods

[0087] Based on the generated AI, the server suggests exercises to Player B to improve wrist flexibility and repeated shooting practice.

[0088] 6. Result notification

[0089] The server generates a training method and notifies the device of Player B. Player B checks the notification and performs the recommended exercises and training.

[0090] The above is one embodiment of the present invention, which can provide high-quality individual instruction and significantly reduce the burden on instructors.

[0091] The processing flow will be explained below.

[0092] Step 1:

[0093] The terminal begins operation. Specifically, IoT devices such as smart shoes and smart clothing collect player movement and technical data in real time. For example, in the case of smart shoes, pressure sensors and acceleration sensors measure foot movement and load.

[0094] Step 2:

[0095] The device temporarily stores the collected data. For example, the collected data is stored in the memory inside the smart shoes. During this process, the raw data is converted into an appropriate format (for example, JSON or CSV).

[0096] Step 3:

[0097] The device sends data to the server via an internet connection, using communication protocols such as HTTP, HTTPS, and MQTT. The data is encrypted before transmission to ensure security.

[0098] Step 4:

[0099] The server receives the data sent from the device, which is usually temporarily stored in a buffer or queue.

[0100] Step 5:

[0101] The server stores the received data in a database. The database organizes data by player and stores it in an easy-to-search format. For example, related data can be linked using a player ID as a key.

[0102] Step 6:

[0103] The server retrieves data for each player from the database, and the data is cleaned and normalized as preprocessing for data analysis, such as removing outliers and filling in missing data.

[0104] Step 7:

[0105] The server analyzes the stored data using a generation AI. The generation AI uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. For example, it analyzes foot load distribution and movement patterns from running data.

[0106] Step 8:

[0107] The server uses generative AI to generate specific training methods for each player, for example, suggesting one-leg squat training for a player with uneven leg load distribution.

[0108] Step 9:

[0109] The server sends the generated teaching methods to the user's device using communication protocols such as HTTP or WebSocket. The notification includes analysis results and training suggestions.

[0110] Step 10:

[0111] The user (coach or player) receives a notification on their device and checks the analysis results and coaching methods. For example, a player checks the recommended training method and implements it as recommended.

[0112] Through these steps, the system of the present invention can provide optimal instruction tailored to the characteristics of each player, significantly reducing the burden on the instructor.

[0113] Example 1

[0114] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0115] With conventional coaching methods, it is difficult to accurately grasp the characteristics and abilities of each player, making it difficult to provide efficient training methods. Furthermore, because data is not collected and analyzed in real time, it is not possible to provide appropriate feedback quickly. This has resulted in the problem of it taking a long time for players to improve their technique and form.

[0116] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0117] In this invention, the server includes a terminal including a plurality of sensors that collect player movement and technique data in real time, means for transmitting the data collected from the terminal to the server, means for the server to store the received data in a database, means for the server to analyze the stored data using a generation AI and evaluate the characteristics and abilities of each player, means for the server to generate a coaching method suitable for each player based on the evaluation results using the generation AI, and means for notifying the user's terminal of the generated coaching method and the results of data analysis. This makes it possible to provide appropriate coaching methods based on the characteristics and abilities of each player in real time, enabling efficient training.

[0118] A "terminal" is a device containing multiple sensors that collects player movement and technical data in real time.

[0119] The "server" is a central processing unit that receives and stores data sent from the terminal, analyzes and evaluates it using generation AI, and generates teaching methods based on the results.

[0120] A "sensor" is a device that measures and collects data on the movements and techniques performed by athletes in real time.

[0121] "Database" means a data management system that stores received data in an organized manner and makes it available for later analysis and evaluation.

[0122] "Generative AI" is an artificial intelligence technology that analyzes collected data, evaluates the characteristics and abilities of each player, and generates optimal coaching methods.

[0123] "Data transmission means" refers to a means including communication protocols and techniques for transmitting data collected by a terminal to a server.

[0124] The "data storage means" is a means for storing data received by the server in a database.

[0125] The "data analysis method" is a method for analyzing data stored in a database using generative AI to evaluate the characteristics and abilities of each player.

[0126] The "training method generation means" is a means for generating a training method suitable for each player based on the evaluation results by the generation AI.

[0127] The "notification means" is a means for notifying the user's terminal of the generated teaching method and the results of the data analysis.

[0128] This invention is a system that collects player movement and technical data in real time, and automatically analyzes it using a generation AI to propose coaching methods. This system is composed of a terminal, a data transmission means, a server, a data storage means, a data analysis means, a coaching method generation means, and a notification means.

[0129] System configuration

[0130] 1. Terminal (IOT device)

[0131] The devices include multiple sensors that collect player movement and technical data in real time. Examples include smart shoes, smart clothing, and smart balls. These devices are equipped with acceleration sensors, pressure sensors, and other sensors to collect highly accurate data.

[0132] 2. Data transmission method

[0133] The data collected by the device is sent to a server via the internet using a communication protocol such as HTTP, HTTPS, or MQTT, and the data is converted into an appropriate format such as JSON.

[0134] 3. Server

[0135] The server receives the data sent from the devices and stores it in a database. It also uses a generation AI to analyze the received data and evaluate the characteristics and abilities of each player. The server has the function of generating individual coaching methods based on the results of the data analysis.

[0136] 4. Data storage method

[0137] The data received by the server is stored in a database, organized by player, and used for later analysis.

[0138] 5. Data Analysis Methods

[0139] The server retrieves the data of a specific player from the database and begins analysis using the generation AI, which analyzes the stored data and evaluates the player's characteristics such as running form, throwing motion, and shooting technique.

[0140] 6. Instruction method generation means

[0141] The server generates the optimal coaching method for each player based on the evaluation results obtained by the AI ​​generation. The generated coaching method is provided as a specific training menu or exercise.

[0142] 7. Means of notification

[0143] The server then sends the generated training method and data analysis results to the user's device. The notification contains detailed information about the analysis results and training method. The user can then receive the notification and implement the specific training plan.

[0144] Specific examples

[0145] Example 1: Improving your running form

[0146] 1. Data Collection

[0147] The smart shoes collect Athlete A's running data (foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[0148] 2. Data Transmission

[0149] The data collected by the device is converted into JSON format and sent to a server via the Internet.

[0150] 3. Data storage

[0151] The server stores the received data in a database.

[0152] 4. Data Analysis

[0153] The server analyzes the stored data using generated AI and discovers an imbalanced load distribution in Athlete A's running form.

[0154] 5. Generating Instructional Methods

[0155] Based on the generated AI, the server suggests specific muscle training exercises to Player A, including single-leg squats.

[0156] 6. Result notification

[0157] The server generates a training method and notifies the device of Player A. Player A checks the notification and starts the recommended training.

[0158] Example 2: Improving shooting technique

[0159] 1. Data Collection

[0160] The smart ball collects shot data (angle, power, distance) from Player B. The sensors also measure wrist movement and ball rotation.

[0161] 2. Data Transmission

[0162] The data collected by the terminal is converted into XML format and sent to the server via the HTTPS protocol.

[0163] 3. Data storage

[0164] The server stores the received data in a database.

[0165] 4. Data Analysis

[0166] The server analyzes the saved data using a generative AI and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[0167] 5. Generating Instructional Methods

[0168] Based on the generated AI, the server suggests exercises to Player B to improve wrist flexibility and repeated shooting practice.

[0169] 6. Result notification

[0170] The server generates a training method and notifies the device of Player B. Player B checks the notification and performs the recommended exercises and training.

[0171] Example of input prompt for generative AI model

[0172] "Please analyze Athlete A's running form and suggest an appropriate training method."

[0173] "What exercises can Player B do to improve his shooting technique?"

[0174] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0175] Step 1:

[0176] Data collection

[0177] The device collects the player's movements and technical data in real time. Specifically, the acceleration and pressure sensors in the smart shoes measure the player's stride length, speed, foot contact time, and pressure when stepping on the ball. The player's movements are input, and measurement data is generated as output. This data is temporarily stored in the device's memory.

[0178] Specific actions

[0179] When the athlete starts running, sensors in the smart shoes collect data and temporarily store it in the device's memory.

[0180] Step 2:

[0181] Data transmission

[0182] The data collected by the device is converted into JSON format and sent to a server via the Internet. The HTTP protocol is used for communication. The input is the measurement data stored in the device, and the output is the JSON data sent to the server.

[0183] Specific actions

[0184] The device's microcontroller converts the measurement data into JSON format, and the Wi-Fi module transmits this data to a server over the Internet.

[0185] Step 3:

[0186] Data storage

[0187] The server receives the data sent from the device and stores it in a database. The input is JSON data that arrives at the server, and the output is structured data stored in the database.

[0188] Specific actions

[0189] The server receives the HTTP request, parses the JSON data, and inserts it into a database, organized by player.

[0190] Step 4:

[0191] Data analysis

[0192] The server retrieves the data of a specific player from the database and begins analysis using the generative AI. The input is the measurement data stored in the database, and the output is an evaluation of the player's characteristics and abilities.

[0193] Specific actions

[0194] The server executes a scheduled job, querying the database for the latest data on the specified athlete, and inputs the acquired data into a generative AI model to analyze running form and evaluate foot load distribution.

[0195] Step 5:

[0196] Teaching method generation

[0197] The server generates the optimal coaching method for each player based on the evaluation results obtained by the generation AI. The input is the evaluation results from the generation AI, and the output is a specific coaching method and training menu.

[0198] Specific actions

[0199] A generative AI compiles the analysis results and generates training plans (e.g., single-leg squats) that address specific problems. These plans are formatted in text format.

[0200] Step 6:

[0201] Result notification

[0202] The server notifies the user's device of the generated teaching method and the results of the data analysis. The input is the generated teaching plan, and the output is a notification message displayed on the user's device.

[0203] Users receive notifications and receive specific training instructions.

[0204] Specific actions

[0205] The server generates a notification message and sends it to the user's device as a push notification, which the user can receive and view detailed instruction methods.

[0206] (Application example 1)

[0207] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0208] The problem that this invention aims to solve is to provide optimal training methods for individual athletes by collecting player movement and technical data in real time, and automatically analyzing and proposing coaching methods using generation AI based on that data. Also, the problem that this invention aims to solve is to improve operational efficiency and reduce maintenance costs by monitoring operational data of industrial automation equipment used in factories in real time, automatically detecting abnormalities and inefficient operations, and proposing optimal operation and maintenance methods.

[0209] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0210] In this invention, the server includes a terminal including multiple sensors that collect player movement and technical data in real time, a means for transmitting the data collected from the terminal to the server, a means for storing the received data in a database, a means for analyzing the stored data using a generation AI to evaluate the characteristics and abilities of each player, a means for the server to generate a coaching method suitable for each player based on the evaluation results using the generation AI, a means for notifying the user of the generated coaching method, a means for generating motion patterns for detecting abnormalities and optimizing the operation of industrial automation equipment based on the data analysis results by the generation AI, and a means for using the generated motion patterns to maintain or optimize the operation of the industrial automation equipment. This makes it possible to provide the optimal coaching method for each player, detect abnormalities in industrial automation equipment in factories, and propose optimal maintenance methods.

[0211] An "athlete" is an individual who participates in a sport or competition and trains its skills and movements.

[0212] "Motion and technical data" refers to numbers and information related to the operation and performance of athletes and industrial automation equipment.

[0213] "Real-time" refers to processing and data collection occurring at the exact moment an event occurs.

[0214] A "sensor" is a device that detects physical movements or changes in the environment and outputs them as electrical signals.

[0215] A "terminal" is a device that includes sensors and is a device that collects and transmits data.

[0216] A "server" is a computer system that stores and processes data over a network.

[0217] "Generative AI" is an artificial intelligence technology that analyzes collected data and automatically creates optimal teaching methods and movement patterns based on the results.

[0218] A "database" is a system for efficiently storing and managing structured data.

[0219] "User" refers to a coach, player, or factory manager who uses the system.

[0220] "Industrial automation equipment" refers to machinery and robots used to automate manufacturing processes.

[0221] "Maintenance" refers to inspection and repair activities performed to keep equipment or systems in working order.

[0222] "Operational optimization" refers to activities that optimize operational methods to maximize the performance of equipment and systems.

[0223] System Configuration

[0224] This invention is a system that collects player movement and technical data in real time, and automatically analyzes it using a generation AI to propose coaching methods. It also monitors the operation data of industrial automation equipment in real time, generates operation patterns for abnormalities and optimization, and supports maintenance and operational optimization.

[0225] Hardware

[0226] 1. Terminal (IOT device)

[0227] These devices are equipped with multiple sensors and collect player movement and technical data in real time. Examples include smart shoes, smart clothing, and smart balls.

[0228] In the case of industrial automation equipment, it is a sensor that detects the operation of robot arms, processing equipment, etc.

[0229] 2. Server

[0230] This is a computer system that stores and analyzes data. Collected data is stored, analyzed using AI, and results are generated and notified.

[0231] 3. User Device

[0232] A device such as a smartphone or head-mounted display (HMD) through which the user receives analysis results and instructional methods.

[0233] software

[0234] 1. Generative AI Models

[0235] It is an artificial intelligence that analyzes collected data and automatically generates optimal teaching methods and movement patterns based on the results.

[0236] 2. Data transmission method

[0237] This software allows the device to send collected data to a server via an internet connection, using communication protocols such as HTTP, HTTPS, and MQTT.

[0238] 3. Database

[0239] It is a system that runs on a server and stores and manages received data.

[0240] 4. Means of notification

[0241] This software notifies the user's device of the teaching methods and behavior patterns generated by the server. Examples include push notifications and email notifications.

[0242] Overview of program processing

[0243] The terminal uses sensors installed in the device to collect real-time movement and technical data from athletes and industrial automation equipment. For example, when collecting an athlete's running data using smart shoes, the sensors measure stride length, speed, foot contact time, etc. The collected data is then converted into JSON format and sent to a server via the HTTP protocol. Similarly, motion data from industrial automation equipment is collected by sensors and sent to a server.

[0244] The server stores the received data in a database and uses generative AI to analyze the data and evaluate the characteristics and capabilities of each athlete and piece of equipment. For example, if the generative AI detects an uneven load distribution in an athlete's running form, it will suggest one-legged squats to train specific muscles. Similarly, it analyzes the movement data of a robotic arm to detect abnormal or inefficient movements, identify the cause, and suggest appropriate adjustments or maintenance methods.

[0245] The generated training methods and operation patterns are sent from the server to the user's device, where the user receives the notification and confirms and carries out the specific training methods and maintenance methods via their smartphone or HMD.

[0246] Examples of specific examples and prompts

[0247] Example 1: Improving your running form

[0248] 1. Smart shoes collect Athlete A's running data (foot movement, load) in real time.

[0249] 2. The device converts the collected data into JSON format and sends it to a server via the Internet.

[0250] 3. The server stores the data, and the generative AI analyzes your running form and detects imbalanced load distribution.

[0251] 4. The generative AI suggests specific muscle training exercises, including single-leg squats, and notifies Athlete A's device.

[0252] Example 2: Optimizing the operation of industrial automation equipment

[0253] 1. Sensors collect real-time motion data (angle, force, speed) from the robot arm.

[0254] 2. The device converts the collected data into JSON format and sends it to a server via the Internet.

[0255] 3. The server stores the data, and the generating AI analyzes the operational data to detect abnormalities and operational patterns for optimization.

[0256] 4. The generative AI proposes optimal maintenance methods and operation patterns and notifies the administrator's device.

[0257] Prompt Sentence Examples

[0258] An example of a prompt sentence to input to the generative AI model is as follows:

[0259] Analyze the robot arm's motion data and check the following:

[0260] Ingres' deviation from the standard

[0261] Abnormal operating speed

[0262] Excessive use of force

[0263] If any of these abnormalities occur, please suggest the cause and appropriate maintenance methods.

[0264] By following the above procedure, it is possible to develop a specific application of the present invention to a factory robot.

[0265] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0266] Step 1:

[0267] The device uses multiple sensors to collect real-time data on player movements and techniques. Specifically, smart shoes measure stride length, speed, and foot contact time. For industrial automation equipment, it collects motion data such as the angle, force, and speed of a robotic arm. The input is physical data from the sensors, and the output is a digital representation of the data.

[0268] Step 2:

[0269] The terminal sends the collected data to a server via the Internet. At this time, the collected data is converted into JSON format and sent using a communication protocol (e.g., HTTP). The input is the digital data collected in the previous step, and the output is the data to be sent to the server.

[0270] Step 3:

[0271] The server stores the received data in a database. A database management system (DBMS) is used to protect the data from loss and store it in a structured format. The input is the data sent to the server and the output is a new record added to the database.

[0272] Step 4:

[0273] The server retrieves the stored data from the database and analyzes the data using a generative AI model. A specific example is analyzing running data to detect imbalanced load distribution in an athlete's running form. The input is the data retrieved from the database, and the output is the analysis result. An example of data processing is applying a machine learning algorithm to cluster the data.

[0274] Step 5:

[0275] The server generates optimal training methods and movement patterns for each athlete and equipment based on the analysis results of the generative AI model. For example, if a running form is imbalanced, it will suggest single-leg squats to train specific muscles. The input is the analysis results, and the output is the generated training methods and movement patterns. Here, the generative AI model operates based on prompt statements.

[0276] Step 6:

[0277] The server notifies the user's device of the generated teaching methods and behavior patterns. Possible notification methods include push notifications and email notifications. The input is the generated teaching methods and behavior patterns, and the output is a notification message sent to the user's device.

[0278] Step 7:

[0279] The user receives a notification and checks the instruction method or operation procedure via a smartphone or head-mounted display (HMD). The user follows the notification to perform the specific instruction method or maintenance procedure. The input is the notification message, and the output is the user's action.

[0280] Through the above steps, training methods for athletes and operational optimization of industrial automation equipment are realized.

[0281] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0282] The present invention combines a system that collects player movement and technical data in real time, automatically analyzes it using a generation AI, and proposes coaching methods, with an emotion engine that recognizes the user's emotions. The following configurations and operations are included as modes for carrying out the invention.

[0283] System configuration

[0284] 1. Terminal (IOT device)

[0285] It includes multiple sensors that collect player movement and technical data in real time, such as smart shoes, smart clothing, and smart balls.

[0286] 2. Data transmission method

[0287] Data collected from the devices is sent to a server via the internet using communication protocols such as HTTP, HTTPS, and MQTT.

[0288] 3. Server

[0289] The received data is saved in the database.

[0290] Generative AI is used to analyze data and evaluate each player's characteristics and abilities.

[0291] Based on the evaluation results, a coaching method appropriate for each player is generated.

[0292] 4. Emotion Engine

[0293] The emotion engine is a system for recognizing the emotions of users (players and coaches). The emotion engine recognizes emotions by analyzing facial expressions, tone of voice, or biometric data.

[0294] 5. Means of notification

[0295] The generated training method is sent to the user's device, where the user can receive the notification and check the specific training method and training plan.

[0296] 6. Adjustment means

[0297] Based on the user's emotional data, the server adjusts the content of the instruction method and the method of suggestions.

[0298] Program processing overview

[0299] Data collection

[0300] The device (for example, smart shoes) collects foot movement and load in real time while the athlete is exercising. The sensor collects highly accurate data and temporarily stores it in memory.

[0301] Data transmission

[0302] The device temporarily stores the collected data and transmits it to a server via an internet connection, where it is converted into an appropriate format (e.g., JSON or CSV) and transmitted using a communication protocol (e.g., HTTP).

[0303] Data storage

[0304] The server receives the data sent from the devices and stores it in a database, which is organized by player and used for later analysis.

[0305] Data analysis

[0306] The server retrieves data for each player from the database and begins analysis using the Generative AI. The Generative AI uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. For example, it analyzes foot load distribution and movement patterns from running data.

[0307] emotion recognition

[0308] The emotion engine collects the user's facial expression, voice, or biometric data in real time to recognize emotions. For example, it captures the user's facial expression with a camera and uses image analysis technology to determine whether they are smiling.

[0309] Teaching method generation

[0310] Based on the analysis results, the generative AI generates the optimal training method for each player. For example, it will suggest single-leg squat training for a player with an imbalanced leg load distribution. Furthermore, it will adjust the training plan based on feedback from the emotion engine. For example, if the user is feeling stressed, it will add relaxation exercises to relieve stress.

[0311] Result notification

[0312] The server generates training methods and sends them to the user's device. HTTP or WebSocket is used as the communication protocol. The notification includes the results of the data analysis and training suggestions.

[0313] User reception and execution

[0314] The user (coach or player) receives a notification on their device and checks the analysis results and coaching methods. For example, the player checks the recommended training method and implements it as recommended.

[0315] Specific examples

[0316] Example 1: Improving your running form

[0317] 1. Data Collection

[0318] The smart shoes collect Athlete A's running data (foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[0319] 2. Data Transmission

[0320] The data collected by the device is converted into JSON format and sent to a server via the Internet.

[0321] 3. Data storage

[0322] The server stores the received data in a database.

[0323] 4. Data Analysis

[0324] The server analyzes the stored data using generated AI and discovers an imbalanced load distribution in Athlete A's running form.

[0325] 5. Emotion recognition

[0326] The emotion engine collects facial expression data from Athlete A and recognizes his / her emotional state during exercise. For example, it determines that Athlete A looks tired.

[0327] 6. Generating Instructional Methods

[0328] Based on the generative AI, the server suggests specific muscle training exercises, including one-legged squats, to Player A. Additionally, it adds relaxation exercises based on feedback from the emotion engine.

[0329] 7. Result notification

[0330] The server generates a training method and notifies the device of Player A. Player A checks the notification and starts the recommended training.

[0331] Example 2: Improving shooting technique

[0332] 1. Data Collection

[0333] The smart ball collects shot data (angle, power, distance) from Player B. The sensors also measure wrist movement and ball rotation.

[0334] 2. Data Transmission

[0335] The data collected by the terminal is converted into XML format and sent to the server via the HTTPS protocol.

[0336] 3. Data storage

[0337] The server stores the received data in a database.

[0338] 4. Data Analysis

[0339] The server analyzes the saved data using a generative AI and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[0340] 5. Emotion recognition

[0341] The emotion engine analyzes Player B's tone of voice in real time to recognize his emotions, for example, determining whether he is relaxed or nervous.

[0342] 6. Generating Instructional Methods

[0343] Based on the generated AI, the server suggests wrist flexibility exercises and repeated shooting practice for Player B. Based on the emotional data, if Player B is nervous, it also adds relaxation techniques.

[0344] 7. Result notification

[0345] The server generates a training method and notifies the device of Player B. Player B checks the notification and performs wrist exercises and shooting practice.

[0346] The above is one embodiment of the present invention, which allows high-quality individual instruction to be provided, and also makes it possible to provide optimal instruction according to the emotional state of the player and coach.

[0347] The processing flow will be explained below.

[0348] Step 1:

[0349] The terminal begins operation. Specifically, IoT devices such as smart shoes and smart clothing collect player movement and technical data in real time. For example, in the case of smart shoes, pressure sensors and acceleration sensors measure foot movement and load.

[0350] Step 2:

[0351] The device temporarily stores the collected data. For example, the collected data is stored in the memory inside the smart shoes. During this process, the raw data is converted into an appropriate format (for example, JSON or CSV).

[0352] Step 3:

[0353] The device sends data to the server via an internet connection, using communication protocols such as HTTP, HTTPS, and MQTT. The data is encrypted before transmission to ensure security.

[0354] Step 4:

[0355] The server receives the data sent from the device, which is usually temporarily stored in a buffer or queue.

[0356] Step 5:

[0357] The server stores the received data in a database. The database organizes data by player and stores it in an easy-to-search format. For example, related data can be linked using a player ID as a key.

[0358] Step 6:

[0359] The server retrieves data for each player from the database, and the data is cleaned and normalized as preprocessing for data analysis, such as removing outliers and filling in missing data.

[0360] Step 7:

[0361] The server analyzes the stored data using a generation AI. The generation AI uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. For example, it analyzes foot load distribution and movement patterns from running data.

[0362] Step 8:

[0363] The emotion engine collects the user's facial expression, voice, or biometric data in real time to recognize emotions. For example, it captures the user's facial expression with a camera and uses image analysis technology to determine whether they are smiling.

[0364] Step 9:

[0365] The server receives data from the emotion engine and combines it with the analysis results of the generative AI to generate specific coaching methods for each player. For example, if a player has an imbalanced load distribution on their legs, it will suggest single-leg squat training, and if they are feeling stressed, it will add relaxation exercises.

[0366] Step 10:

[0367] The server then sends the generated training method to the user's device using a communication protocol such as HTTP or WebSocket. The notification includes the results of the data analysis and training suggestions.

[0368] Step 11:

[0369] The user (coach or player) receives a notification on their device and checks the analysis results and coaching methods. For example, a player checks the recommended training method and implements it as recommended.

[0370] Through these steps, the system of the present invention can provide optimal instruction tailored to the characteristics of each player, significantly reducing the burden on the coach. In addition, the introduction of an emotion engine enables detailed feedback tailored to the user's emotional state.

[0371] Example 2

[0372] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0373] In modern sports coaching, it is extremely important to collect real-time data on athletes' movements and techniques and provide appropriate instruction based on that data. However, currently, the entire process of data collection, analysis, and the creation of coaching methods requires a lot of manual work, making efficient training instruction difficult. Furthermore, the emotional state of athletes and coaches also has a significant impact on training effectiveness, but there are few systems that take this into account. The purpose of this project is to solve these issues.

[0374] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a terminal including multiple sensors that collect player movement and technique data in real time, means for transmitting the data collected from the terminal to the server via the Internet, means for storing the data received by the server in a database, means for analyzing the stored data by using a generation AI and evaluating the characteristics and abilities of each player, means for the server to generate a coaching method suitable for each player based on the evaluation results using the generation AI, means including an emotion engine that recognizes emotions by analyzing the user's facial expression, tone of voice, or biometric data, and means for adjusting the generated coaching method based on the recognized emotion data and notifying the user's terminal. This makes it possible to comprehensively improve player performance based on both scientific and emotional factors.

[0375] A "terminal" is a device containing multiple sensors that collects player movement and technical data in real time.

[0376] The "Internet" is a network infrastructure that allows information to be exchanged around the world.

[0377] A "server" is a computer system that receives, stores, and analyzes data sent from a terminal.

[0378] A "database" is a system for organizing and storing data received by a server.

[0379] "Generative AI" is an artificial intelligence system that uses machine learning algorithms to analyze data and evaluate each player's characteristics and abilities.

[0380] An "emotion engine" is a system that recognizes emotions by analyzing a user's facial expressions, tone of voice, or biometric data.

[0381] A "user terminal" is a device that receives and displays the generated teaching methods and analysis results.

[0382] "Instruction method" refers to the training plan and exercises that the generative AI will instruct each player on based on the analysis results.

[0383] This invention combines a system that collects player movement and technical data in real time, automatically analyzes it using a generation AI, and proposes coaching methods, with an emotion engine that recognizes the user's emotions. The system configuration and operation are as follows.

[0384] System configuration

[0385] 1. Terminal (IOT device)

[0386] Examples include smart shoes, smart clothing, smart balls, etc. These devices contain numerous sensors to collect player movement and technical data in real time.

[0387] 2. Data transmission method

[0388] The collected data is sent to a server via the internet using communication protocols such as HTTP, HTTPS, and MQTT.

[0389] 3. Server

[0390] The server stores the received data in a database, which can be, for example, MySQL or MongoDB.

[0391] The server analyzes the data using a generative AI, which uses machine learning algorithms (e.g., random forests and neural networks) to evaluate players' characteristics and abilities.

[0392] Based on the evaluation results, a coaching method appropriate for each player is generated.

[0393] 4. Emotion Engine

[0394] The emotion engine is a system that recognizes the emotions of users (players and coaches). For example, it uses a camera to capture facial expressions and uses image analysis technology to determine emotions. It also has the ability to analyze voice tone using audio analysis to recognize emotions.

[0395] 5. Means of notification

[0396] The generated teaching method is sent from the server to the user's device using HTTP or WebSocket as the communication protocol.

[0397] 6. Adjustment means

[0398] Based on the recognized emotion data, the server adjusts the content of the instruction method and the method of suggestions.

[0399] Specific examples

[0400] Example 1: Improving your running form

[0401] 1. Data Collection

[0402] The smart shoes collect Athlete A's running data (e.g., foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[0403] 2. Data Transmission

[0404] The collected data is converted into JSON format and sent to the server via the HTTP protocol.

[0405] 3. Data storage

[0406] The server stores the received data in a database.

[0407] 4. Data Analysis

[0408] The generative AI analyzes the saved data and discovers an imbalanced load distribution in Athlete A's running form.

[0409] 5. Emotion recognition

[0410] The emotion engine collects facial expression data of Athlete A and checks his emotional state during exercise. For example, it determines that Athlete A looks tired.

[0411] 6. Generating Instructional Methods

[0412] The generative AI suggests specific strength exercises, including single-leg squats, and also adds relaxation exercises based on feedback from the emotion engine.

[0413] 7. Result notification

[0414] A training method is generated and notified to the device of Player A. Player A checks the notification and starts the recommended training.

[0415] Example 2: Improving shooting technique

[0416] 1. Data Collection

[0417] The smart ball collects shot data (e.g., angle, power, and distance) from Player B. The sensors also measure wrist movement and ball rotation.

[0418] 2. Data Transmission

[0419] The collected data is converted into XML format and sent to the server via the HTTPS protocol.

[0420] 3. Data storage

[0421] The server stores the received data in a database.

[0422] 4. Data Analysis

[0423] The generative AI analyzes the saved data and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[0424] 5. Emotion recognition

[0425] The emotion engine analyzes Player B's tone of voice in real time to recognize his emotions, for example, determining whether he is relaxed or nervous.

[0426] 6. Generating Instructional Methods

[0427] The generative AI suggests wrist flexibility exercises and repeated shooting practice. Based on emotional data, if Player B is nervous, it will also add relaxation techniques.

[0428] 7. Result notification

[0429] A training method is generated and notified to the device of Player B. Player B checks the notification and performs wrist exercises and shooting practice.

[0430] Prompt Sentence Examples

[0431] Here is an example of a prompt to input to a generative AI model:

[0432] "Please suggest a training method to improve Athlete A's running form. Athlete A has an uneven load distribution on his feet. He also looks tired during exercise."

[0433] Using this prompt, the generative AI model can generate appropriate teaching methods and follow-up suggestions based on emotion.

[0434] As a result, the present invention provides a system for scientifically and comprehensively improving the performance of athletes.

[0435] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0436] Step 1:

[0437] Data collection

[0438] The devices (e.g., smart shoes, smart clothing, smart balls) collect data on players' movements and techniques in real time. Specifically, sensors collect data such as the player's stride length, speed, foot contact time, load, shot angle, power, and distance, and temporarily store this data in the device's memory.

[0439] Input: Player movements and technical data

[0440] Output: Temporarily saved data in the device memory

[0441] Example: When an athlete starts running, the sensors in the smart shoes are automatically activated and the collected data is written to memory.

[0442] Step 2:

[0443] Data transmission

[0444] The device converts the collected data into an appropriate format (e.g., JSON format) and sends it to a server via an internet connection using HTTP or HTTPS as the communication protocol. The data is sent in real time or at regular intervals.

[0445] Input: Temporarily saved data in the device memory

[0446] Output: Data sent to the server

[0447] Specific operation: The device sends the collected data in streaming format as a POST request to the specified server URL via Wi-Fi or mobile network.

[0448] Step 3:

[0449] Data storage

[0450] The server receives the data sent from the devices and stores it securely in a database, organizing it by player and indexing it for easy retrieval later.

[0451] Input: Data sent to the server

[0452] Output: Data stored in the database

[0453] What happens: A server endpoint receives the data and the program inserts it into a database, often MySQL or MongoDB.

[0454] Step 4:

[0455] Data analysis

[0456] The server retrieves data for each player from the database and analyzes it using a generative AI, which uses machine learning algorithms (e.g., random forests, neural networks) to evaluate the player's characteristics and abilities.

[0457] Input: Player data stored in the database

[0458] Output: Analysis results (player characteristics and ability evaluation)

[0459] Specific operation: The server periodically performs batch processing and streaming processing, inputting athlete data into the generative AI model for analysis. For example, it analyzes foot load distribution and movement patterns based on running data, and re-stores the results in the database.

[0460] Step 5:

[0461] emotion recognition

[0462] The emotion engine collects the user's facial expressions, tone of voice, biometric data, etc. in real time to recognize emotions. Specifically, it analyzes facial expression data captured by a camera and voice data to determine emotions.

[0463] Input: User facial expression data and voice data collected by camera and microphone

[0464] Output: Analysis results (user's emotional state)

[0465] Specific operation: Image data captured by the camera is input into a deep learning model to recognize the user's emotions. Voice data collected by the microphone is also recognized using voice analysis technology.

[0466] Step 6:

[0467] Teaching method generation

[0468] The server generates the optimal coaching method for each player based on the analysis results of the generative AI, and further adjusts the training plan based on feedback from the emotion engine.

[0469] Input: Analysis results and emotional state

[0470] Output: Optimized teaching methods and training plans

[0471] Specific movements: The generative AI combines running data and other exercise data with emotion recognition results to automatically generate training methods tailored to the athlete, such as one-legged squats and relaxation exercises.

[0472] Step 7:

[0473] Result notification

[0474] The server notifies the user's device of the generated teaching methods and training plans, using HTTP and WebSocket as communication protocols.

[0475] Input: Optimized teaching methods and training plans

[0476] Output: Instructions and training plans sent to the user's device

[0477] Specific operation: The server generates a notification message and sends an HTTP request to the IP address of the specified terminal. The user's terminal receives this notification and displays the content.

[0478] Step 8:

[0479] User reception and execution

[0480] The user receives a notification on their device, checks the analysis results and provides instructions, and then performs the training according to the instructions.

[0481] Input: Notification message from the server

[0482] Output: Training performed

[0483] Specific operation: After checking the notification on the device, the user performs actual training according to the displayed instruction method and training plan. The user's actions are again collected by the device's sensors and used in the next data collection phase.

[0484] (Application example 2)

[0485] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0486] While conventional sports coaching systems can collect and analyze athletes' movements and technical data in real time, they have difficulty providing coaching methods that take into account the emotional state of athletes and coaches. Furthermore, there is a lack of systems that collect movement data from factory workers to suggest efficient work procedures, or systems that recognize emotions and provide breaks and relaxation methods to reduce stress. This has made it difficult to provide optimal coaching to improve athletes' skills, increase worker efficiency, and reduce stress.

[0487] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0488] In this invention, the server includes a terminal including multiple sensors that collect player movement and technical data in real time, means for transmitting the data collected from the terminal to the server, means for storing the data received by the server in a database, an emotion engine that recognizes emotions by analyzing the user's facial expressions, voice, or biometric data, means for adjusting the content of the instruction method and the method of proposal based on the recognition results of the emotion engine, and means for notifying the user's terminal of the generated instruction method. This makes it possible to propose optimal instruction methods and work procedures that take into account the movements and emotional states of players and workers.

[0489] "Athlete" means an individual who performs an action or skill in a sport.

[0490] "Movement" refers to an object changing its position or posture.

[0491] "Technical data" means numerical or measured data relating to the actions performed by athletes or workers.

[0492] A "sensor" is a device that detects changes in the surrounding environment or objects.

[0493] A "terminal" is a device for collecting and processing data, including smart devices and IoT devices.

[0494] A "server" is a computing system that stores, processes, and serves data.

[0495] A "database" is a system for managing a structured collection of data.

[0496] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to analyze data and make predictions.

[0497] "Evaluation" is the process of determining the characteristics and capabilities of players or workers based on collected data.

[0498] "Instructional methods" refers to the suggestion of appropriate behaviors or training programs for specific goals or tasks.

[0499] "User" refers to an individual or organization that uses the system.

[0500] "Facial expressions" are part of a human interface that express emotions through the movement of facial muscles.

[0501] "Audio" means sound waves, including speech and ambient sounds.

[0502] "Biometric data" refers to various physiological information collected from the human body.

[0503] An "emotion engine" is a system for recognizing and analyzing a user's emotional state.

[0504] "Motion data" includes data relating to the movement of an object, such as position, velocity, and acceleration.

[0505] "Work procedure" means detailed steps or methods for efficiently performing a particular task.

[0506] "Relaxation" refers to activities or methods that relieve physical or mental tension.

[0507] This invention provides a system that starts with a terminal equipped with multiple sensors that collects player movement and technical data in real time. The terminal uses IoT devices such as smart clothing and smart gloves. These devices collect movement and technical data in real time and temporarily store it in memory.

[0508] The collected data is then sent via a communication protocol (e.g., HTTP or HTTPS) to a server, which stores the data in a database and is powered by a generative AI model using TensorFlow.

[0509] The generative AI model takes data from the database and analyzes movement patterns and skill levels. Specifically, it uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. The results are used to generate appropriate coaching methods.

[0510] Furthermore, an emotion engine is used to analyze the user's facial expressions, voice, and biometric data to recognize their emotional state. The emotion engine uses technologies such as EmotionAI. For example, it analyzes facial expressions from camera footage and determines the user's stress level from the tone of voice.

[0511] Based on the evaluation and emotion recognition results, the server generates optimal instruction methods and work procedures, including suggestions for relaxation exercises and breaks as needed. The generated instruction methods are sent to the user's device via a communication protocol. Notifications can be sent via a smartphone application or a dedicated device.

[0512] As a concrete example, consider a scenario in which a factory worker provides motion and emotional data. As the worker wears smart gloves and performs work, their motion data is collected in real time. Their facial expressions and tone of voice while working are also collected and analyzed by an emotion engine. This data is sent to a server, where a generative AI model evaluates work efficiency and generates instructional methods. If the worker is feeling stressed, the server also suggests relaxation exercises. These instructional methods are then notified to the worker's smartphone.

[0513] An example prompt is:

[0514] "sensor_data = {'temperature': 25.5, 'humidity': 60, 'acceleration': [0.2, 0.3, 0.4]}

[0515] emotion_data = {'emotion': 'stressed', 'confidence': 0.85}

[0516] prediction = analyze_data(sensor_data)

[0517] instructions = generate_instructions(prediction, emotion_data)

[0518] notify_user(instructions)

[0519] The above system makes it possible to propose optimal coaching methods and work procedures that take into account the movements and emotional state of athletes and workers.

[0520] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0521] Step 1:

[0522] The device collects the movement and technical data of athletes and workers, as well as biometric data, in real time. Specifically, smart clothing, smart gloves, or cameras are used to collect motion data (e.g., acceleration, posture data) and biometric data (e.g., heart rate, facial expression data). This data is temporarily stored in the device's memory.

[0523] Input: Real-time data from smart clothing and smart gloves

[0524] Output: Temporary storage of collected motion data and biometric data

[0525] Step 2:

[0526] The device sends the collected data to a server via an internet connection, where it is converted into an appropriate format (e.g., JSON or CSV) and securely transmitted using a communication protocol (e.g., HTTP or HTTPS).

[0527] Input: Collected data (e.g., acceleration data, facial expression data)

[0528] Output: Acknowledgement of completion of transmission to the server

[0529] Step 3:

[0530] The server stores the received data in a database, which manages the data in a structured format for efficient access and analysis.

[0531] Input: Transmitted data (e.g., motion data in JSON format, biometric data)

[0532] Output: Data stored in the database

[0533] Step 4:

[0534] The server retrieves data for each player or worker from the database and performs real-time analysis using a generative AI model. Machine learning algorithms (e.g., random forests, neural networks) are used to evaluate the characteristics and capabilities of each player or worker, specifically detecting movement patterns, skill levels, and imbalanced movements.

[0535] Input: Motion and biometric data retrieved from the database

[0536] Output: Analysis results (e.g., evaluation of movement patterns, determination of skill level)

[0537] Step 5:

[0538] The server uses an emotion engine to analyze the user's facial expressions, voice, and biometric data to recognize their emotional state. For example, it uses EmotionAI technology to assess whether the user is feeling stressed based on facial expression data.

[0539] Input: facial expression data and biometric data collected in real time

[0540] Output: Perceived emotional state (e.g., stressed, relaxed)

[0541] Step 6:

[0542] The server generates optimal teaching methods and work procedures based on the evaluation and emotion recognition results. The generated teaching methods may include specific training methods or relaxation exercises to reduce stress.

[0543] Input: Analysis results and emotion recognition results

[0544] Output: Generated instructional instructions or work instructions

[0545] Step 7:

[0546] The server generates training methods and work procedures and notifies the user's device. Notifications are sent via smartphone applications or dedicated devices. HTTP, WebSocket, and other communication protocols are used.

[0547] Input: Generated instructional methods or work procedures

[0548] Output: Notification to user's device completed

[0549] Step 8:

[0550] The user receives a notification on the device and checks the instruction method or work procedure. The user then performs the training or work according to the suggested method.

[0551] Input: Instruction method or work procedure notified to the terminal

[0552] Output: Training and work procedures reviewed and implemented

[0553] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0554] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0555] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0556] [Second embodiment]

[0557] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0558] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0559] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0560] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0561] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0562] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0563] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0564] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0565] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0566] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0567] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0568] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0569] The present invention relates to a system that collects player movement and technical data in real time, and automatically analyzes the data using a generation AI to propose coaching methods. The following configurations and operations are included as embodiments of the invention.

[0570] System configuration

[0571] 1. Terminal (IOT device)

[0572] It includes multiple sensors that collect player movement and technical data in real time, such as smart shoes, smart clothing, and smart balls.

[0573] 2. Data transmission method

[0574] Data collected from the devices is sent to a server via the internet using communication protocols such as HTTP, HTTPS, and MQTT.

[0575] 3. Server

[0576] The received data is saved in the database.

[0577] Generative AI is used to analyze data and evaluate each player's characteristics and abilities.

[0578] Based on the evaluation results, a coaching method appropriate for each player is generated.

[0579] 4. Means of notification

[0580] The generated training method is sent to the user's device, where the user can receive the notification and check the specific training method and training plan.

[0581] Program processing overview

[0582] Data collection

[0583] The device (for example, smart shoes) collects foot movement and load in real time while the athlete is running. The sensors collect highly accurate data and temporarily store it in memory.

[0584] Data transmission

[0585] The device sends the collected data to a server via an internet connection, where it is converted into an appropriate format (e.g., JSON) and sent using a communication protocol (e.g., HTTP).

[0586] Data storage

[0587] The server receives the data sent from the devices and stores it in a database, which is organized by player and used for later analysis.

[0588] Data analysis

[0589] The server retrieves data for each athlete from the database and begins analysis using generative AI. For example, it uses smart shoe data to evaluate Athlete A's running form and analyzes the load distribution and movement patterns of the feet.

[0590] Teaching method generation

[0591] Based on the analysis results, the generative AI generates the optimal coaching method for each athlete. For example, if it is determined that Athlete A's running form is imbalanced, it will suggest one-legged squats to train specific muscles.

[0592] Result notification

[0593] The training method generated by the server is sent to the user's (coach or player's) device. The notification includes the data analysis results and specific training methods. The user receives the notification and can check and implement the training methods on their device.

[0594] Specific examples

[0595] Example 1: Improving your running form

[0596] 1. Data Collection

[0597] The smart shoes collect Athlete A's running data (foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[0598] 2. Data Transmission

[0599] The data collected by the device is converted into JSON format and sent to a server via the Internet.

[0600] 3. Data storage

[0601] The server stores the received data in a database.

[0602] 4. Data Analysis

[0603] The server analyzes the stored data using generated AI and discovers an imbalanced load distribution in Athlete A's running form.

[0604] 5. Generating Instructional Methods

[0605] Based on the generated AI, the server suggests specific muscle training exercises to Player A, including single-leg squats.

[0606] 6. Result notification

[0607] The server generates a training method and notifies the device of Player A. Player A checks the notification and starts the recommended training.

[0608] Example 2: Improving shooting technique

[0609] 1. Data Collection

[0610] The smart ball collects shot data (angle, power, distance) from Player B. The sensors also measure wrist movement and ball rotation.

[0611] 2. Data Transmission

[0612] The data collected by the terminal is converted into XML format and sent to the server via the HTTPS protocol.

[0613] 3. Data storage

[0614] The server stores the received data in a database.

[0615] 4. Data Analysis

[0616] The server analyzes the saved data using a generative AI and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[0617] 5. Generating Instructional Methods

[0618] Based on the generated AI, the server suggests exercises to Player B to improve wrist flexibility and repeated shooting practice.

[0619] 6. Result notification

[0620] The server generates a training method and notifies the device of Player B. Player B checks the notification and performs the recommended exercises and training.

[0621] The above is one embodiment of the present invention, which can provide high-quality individual instruction and significantly reduce the burden on instructors.

[0622] The processing flow will be explained below.

[0623] Step 1:

[0624] The terminal begins operation. Specifically, IoT devices such as smart shoes and smart clothing collect player movement and technical data in real time. For example, in the case of smart shoes, pressure sensors and acceleration sensors measure foot movement and load.

[0625] Step 2:

[0626] The device temporarily stores the collected data. For example, the collected data is stored in the memory inside the smart shoes. During this process, the raw data is converted into an appropriate format (for example, JSON or CSV).

[0627] Step 3:

[0628] The device sends data to the server via an internet connection, using communication protocols such as HTTP, HTTPS, and MQTT. The data is encrypted before transmission to ensure security.

[0629] Step 4:

[0630] The server receives the data sent from the device, which is usually temporarily stored in a buffer or queue.

[0631] Step 5:

[0632] The server stores the received data in a database. The database organizes data by player and stores it in an easy-to-search format. For example, related data can be linked using a player ID as a key.

[0633] Step 6:

[0634] The server retrieves data for each player from the database, and the data is cleaned and normalized as preprocessing for data analysis, such as removing outliers and filling in missing data.

[0635] Step 7:

[0636] The server analyzes the stored data using a generation AI. The generation AI uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. For example, it analyzes foot load distribution and movement patterns from running data.

[0637] Step 8:

[0638] The server uses generative AI to generate specific training methods for each player, for example, suggesting one-leg squat training for a player with uneven leg load distribution.

[0639] Step 9:

[0640] The server sends the generated teaching methods to the user's device using communication protocols such as HTTP or WebSocket. The notification includes analysis results and training suggestions.

[0641] Step 10:

[0642] The user (coach or player) receives a notification on their device and checks the analysis results and coaching methods. For example, a player checks the recommended training method and implements it as recommended.

[0643] Through these steps, the system of the present invention can provide optimal instruction tailored to the characteristics of each player, significantly reducing the burden on the instructor.

[0644] Example 1

[0645] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0646] With conventional coaching methods, it is difficult to accurately grasp the characteristics and abilities of each player, making it difficult to provide efficient training methods. Furthermore, because data is not collected and analyzed in real time, it is not possible to provide appropriate feedback quickly. This has resulted in the problem of it taking a long time for players to improve their technique and form.

[0647] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0648] In this invention, the server includes a terminal including a plurality of sensors that collect player movement and technique data in real time, means for transmitting the data collected from the terminal to the server, means for the server to store the received data in a database, means for the server to analyze the stored data using a generation AI and evaluate the characteristics and abilities of each player, means for the server to generate a coaching method suitable for each player based on the evaluation results using the generation AI, and means for notifying the user's terminal of the generated coaching method and the results of data analysis. This makes it possible to provide appropriate coaching methods based on the characteristics and abilities of each player in real time, enabling efficient training.

[0649] A "terminal" is a device containing multiple sensors that collects player movement and technical data in real time.

[0650] The "server" is a central processing unit that receives and stores data sent from the terminal, analyzes and evaluates it using generation AI, and generates teaching methods based on the results.

[0651] A "sensor" is a device that measures and collects data on the movements and techniques performed by athletes in real time.

[0652] "Database" means a data management system that stores received data in an organized manner and makes it available for later analysis and evaluation.

[0653] "Generative AI" is an artificial intelligence technology that analyzes collected data, evaluates the characteristics and abilities of each player, and generates optimal coaching methods.

[0654] "Data transmission means" refers to a means including communication protocols and techniques for transmitting data collected by a terminal to a server.

[0655] The "data storage means" is a means for storing data received by the server in a database.

[0656] The "data analysis method" is a method for analyzing data stored in a database using generative AI to evaluate the characteristics and abilities of each player.

[0657] The "training method generation means" is a means for generating a training method suitable for each player based on the evaluation results by the generation AI.

[0658] The "notification means" is a means for notifying the user's terminal of the generated teaching method and the results of the data analysis.

[0659] This invention is a system that collects player movement and technical data in real time, and automatically analyzes it using a generation AI to propose coaching methods. This system is composed of a terminal, a data transmission means, a server, a data storage means, a data analysis means, a coaching method generation means, and a notification means.

[0660] System configuration

[0661] 1. Terminal (IOT device)

[0662] The devices include multiple sensors that collect player movement and technical data in real time. Examples include smart shoes, smart clothing, and smart balls. These devices are equipped with acceleration sensors, pressure sensors, and other sensors to collect highly accurate data.

[0663] 2. Data transmission method

[0664] The data collected by the device is sent to a server via the internet using a communication protocol such as HTTP, HTTPS, or MQTT, and the data is converted into an appropriate format such as JSON.

[0665] 3. Server

[0666] The server receives the data sent from the devices and stores it in a database. It also uses a generation AI to analyze the received data and evaluate the characteristics and abilities of each player. The server has the function of generating individual coaching methods based on the results of the data analysis.

[0667] 4. Data storage method

[0668] The data received by the server is stored in a database, organized by player, and used for later analysis.

[0669] 5. Data Analysis Methods

[0670] The server retrieves the data of a specific player from the database and begins analysis using the generation AI, which analyzes the stored data and evaluates the player's characteristics such as running form, throwing motion, and shooting technique.

[0671] 6. Instruction method generation means

[0672] The server generates the optimal coaching method for each player based on the evaluation results obtained by the AI ​​generation. The generated coaching method is provided as a specific training menu or exercise.

[0673] 7. Means of notification

[0674] The server then sends the generated training method and data analysis results to the user's device. The notification contains detailed information about the analysis results and training method. The user can then receive the notification and implement the specific training plan.

[0675] Specific examples

[0676] Example 1: Improving your running form

[0677] 1. Data Collection

[0678] The smart shoes collect Athlete A's running data (foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[0679] 2. Data Transmission

[0680] The data collected by the device is converted into JSON format and sent to a server via the Internet.

[0681] 3. Data storage

[0682] The server stores the received data in a database.

[0683] 4. Data Analysis

[0684] The server analyzes the stored data using generated AI and discovers an imbalanced load distribution in Athlete A's running form.

[0685] 5. Generating Instructional Methods

[0686] Based on the generated AI, the server suggests specific muscle training exercises to Player A, including single-leg squats.

[0687] 6. Result notification

[0688] The server generates a training method and notifies the device of Player A. Player A checks the notification and starts the recommended training.

[0689] Example 2: Improving shooting technique

[0690] 1. Data Collection

[0691] The smart ball collects shot data (angle, power, distance) from Player B. The sensors also measure wrist movement and ball rotation.

[0692] 2. Data Transmission

[0693] The data collected by the terminal is converted into XML format and sent to the server via the HTTPS protocol.

[0694] 3. Data storage

[0695] The server stores the received data in a database.

[0696] 4. Data Analysis

[0697] The server analyzes the saved data using a generative AI and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[0698] 5. Generating Instructional Methods

[0699] Based on the generated AI, the server suggests exercises to Player B to improve wrist flexibility and repeated shooting practice.

[0700] 6. Result notification

[0701] The server generates a training method and notifies the device of Player B. Player B checks the notification and performs the recommended exercises and training.

[0702] Example of input prompt for generative AI model

[0703] "Please analyze Athlete A's running form and suggest an appropriate training method."

[0704] "What exercises can Player B do to improve his shooting technique?"

[0705] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0706] Step 1:

[0707] Data collection

[0708] The device collects the player's movements and technical data in real time. Specifically, the acceleration and pressure sensors in the smart shoes measure the player's stride length, speed, foot contact time, and pressure when stepping on the ball. The player's movements are input, and measurement data is generated as output. This data is temporarily stored in the device's memory.

[0709] Specific actions

[0710] When the athlete starts running, sensors in the smart shoes collect data and temporarily store it in the device's memory.

[0711] Step 2:

[0712] Data transmission

[0713] The data collected by the device is converted into JSON format and sent to a server via the Internet. The HTTP protocol is used for communication. The input is the measurement data stored in the device, and the output is the JSON data sent to the server.

[0714] Specific actions

[0715] The device's microcontroller converts the measurement data into JSON format, and the Wi-Fi module transmits this data to a server over the Internet.

[0716] Step 3:

[0717] Data storage

[0718] The server receives the data sent from the device and stores it in a database. The input is JSON data that arrives at the server, and the output is structured data stored in the database.

[0719] Specific actions

[0720] The server receives the HTTP request, parses the JSON data, and inserts it into a database, organized by player.

[0721] Step 4:

[0722] Data analysis

[0723] The server retrieves the data of a specific player from the database and begins analysis using the generative AI. The input is the measurement data stored in the database, and the output is an evaluation of the player's characteristics and abilities.

[0724] Specific actions

[0725] The server executes a scheduled job, querying the database for the latest data on the specified athlete, and inputs the acquired data into a generative AI model to analyze running form and evaluate foot load distribution.

[0726] Step 5:

[0727] Teaching method generation

[0728] The server generates the optimal coaching method for each player based on the evaluation results obtained by the generation AI. The input is the evaluation results from the generation AI, and the output is a specific coaching method and training menu.

[0729] Specific actions

[0730] A generative AI compiles the analysis results and generates training plans (e.g., single-leg squats) that address specific problems. These plans are formatted in text format.

[0731] Step 6:

[0732] Result notification

[0733] The server notifies the user's device of the generated teaching method and the results of the data analysis. The input is the generated teaching plan, and the output is a notification message displayed on the user's device.

[0734] Users receive notifications and receive specific training instructions.

[0735] Specific actions

[0736] The server generates a notification message and sends it to the user's device as a push notification, which the user can receive and view detailed instruction methods.

[0737] (Application example 1)

[0738] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0739] The problem that this invention aims to solve is to provide optimal training methods for individual athletes by collecting player movement and technical data in real time, and automatically analyzing and proposing coaching methods using generation AI based on that data. Also, the problem that this invention aims to solve is to improve operational efficiency and reduce maintenance costs by monitoring operational data of industrial automation equipment used in factories in real time, automatically detecting abnormalities and inefficient operations, and proposing optimal operation and maintenance methods.

[0740] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0741] In this invention, the server includes a terminal including multiple sensors that collect player movement and technical data in real time, a means for transmitting the data collected from the terminal to the server, a means for storing the received data in a database, a means for analyzing the stored data using a generation AI to evaluate the characteristics and abilities of each player, a means for the server to generate a coaching method suitable for each player based on the evaluation results using the generation AI, a means for notifying the user of the generated coaching method, a means for generating motion patterns for detecting abnormalities and optimizing the operation of industrial automation equipment based on the data analysis results by the generation AI, and a means for using the generated motion patterns to maintain or optimize the operation of the industrial automation equipment. This makes it possible to provide the optimal coaching method for each player, detect abnormalities in industrial automation equipment in factories, and propose optimal maintenance methods.

[0742] An "athlete" is an individual who participates in a sport or competition and trains its skills and movements.

[0743] "Motion and technical data" refers to numbers and information related to the operation and performance of athletes and industrial automation equipment.

[0744] "Real-time" refers to processing and data collection occurring at the exact moment an event occurs.

[0745] A "sensor" is a device that detects physical movements or changes in the environment and outputs them as electrical signals.

[0746] A "terminal" is a device that includes sensors and is a device that collects and transmits data.

[0747] A "server" is a computer system that stores and processes data over a network.

[0748] "Generative AI" is an artificial intelligence technology that analyzes collected data and automatically creates optimal teaching methods and movement patterns based on the results.

[0749] A "database" is a system for efficiently storing and managing structured data.

[0750] "User" refers to a coach, player, or factory manager who uses the system.

[0751] "Industrial automation equipment" refers to machinery and robots used to automate manufacturing processes.

[0752] "Maintenance" refers to inspection and repair activities performed to keep equipment or systems in working order.

[0753] "Operational optimization" refers to activities that optimize operational methods to maximize the performance of equipment and systems.

[0754] System Configuration

[0755] This invention is a system that collects player movement and technical data in real time, and automatically analyzes it using a generation AI to propose coaching methods. It also monitors the operation data of industrial automation equipment in real time, generates operation patterns for abnormalities and optimization, and supports maintenance and operational optimization.

[0756] Hardware

[0757] 1. Terminal (IOT device)

[0758] These devices are equipped with multiple sensors and collect player movement and technical data in real time. Examples include smart shoes, smart clothing, and smart balls.

[0759] In the case of industrial automation equipment, it is a sensor that detects the operation of robot arms, processing equipment, etc.

[0760] 2. Server

[0761] This is a computer system that stores and analyzes data. Collected data is stored, analyzed using AI, and results are generated and notified.

[0762] 3. User Device

[0763] A device such as a smartphone or head-mounted display (HMD) through which the user receives analysis results and instructional methods.

[0764] software

[0765] 1. Generative AI Models

[0766] It is an artificial intelligence that analyzes collected data and automatically generates optimal teaching methods and movement patterns based on the results.

[0767] 2. Data transmission method

[0768] This software allows the device to send collected data to a server via an internet connection, using communication protocols such as HTTP, HTTPS, and MQTT.

[0769] 3. Database

[0770] It is a system that runs on a server and stores and manages received data.

[0771] 4. Means of notification

[0772] This software notifies the user's device of the teaching methods and behavior patterns generated by the server. Examples include push notifications and email notifications.

[0773] Overview of program processing

[0774] The terminal uses sensors installed in the device to collect real-time movement and technical data from athletes and industrial automation equipment. For example, when collecting an athlete's running data using smart shoes, the sensors measure stride length, speed, foot contact time, etc. The collected data is then converted into JSON format and sent to a server via the HTTP protocol. Similarly, motion data from industrial automation equipment is collected by sensors and sent to a server.

[0775] The server stores the received data in a database and uses generative AI to analyze the data and evaluate the characteristics and capabilities of each athlete and piece of equipment. For example, if the generative AI detects an uneven load distribution in an athlete's running form, it will suggest one-legged squats to train specific muscles. Similarly, it analyzes the movement data of a robotic arm to detect abnormal or inefficient movements, identify the cause, and suggest appropriate adjustments or maintenance methods.

[0776] The generated training methods and operation patterns are sent from the server to the user's device, where the user receives the notification and confirms and carries out the specific training methods and maintenance methods via their smartphone or HMD.

[0777] Examples of specific examples and prompts

[0778] Example 1: Improving your running form

[0779] 1. Smart shoes collect Athlete A's running data (foot movement, load) in real time.

[0780] 2. The device converts the collected data into JSON format and sends it to a server via the Internet.

[0781] 3. The server stores the data, and the generative AI analyzes your running form and detects imbalanced load distribution.

[0782] 4. The generative AI suggests specific muscle training exercises, including single-leg squats, and notifies Athlete A's device.

[0783] Example 2: Optimizing the operation of industrial automation equipment

[0784] 1. Sensors collect real-time motion data (angle, force, speed) from the robot arm.

[0785] 2. The device converts the collected data into JSON format and sends it to a server via the Internet.

[0786] 3. The server stores the data, and the generating AI analyzes the operational data to detect abnormalities and operational patterns for optimization.

[0787] 4. The generative AI proposes optimal maintenance methods and operation patterns and notifies the administrator's device.

[0788] Prompt Sentence Examples

[0789] An example of a prompt sentence to input to the generative AI model is as follows:

[0790] Analyze the robot arm's motion data and check the following:

[0791] Ingres' deviation from the standard

[0792] Abnormal operating speed

[0793] Excessive use of force

[0794] If any of these abnormalities occur, please suggest the cause and appropriate maintenance methods.

[0795] By following the above procedure, it is possible to develop a specific application of the present invention to a factory robot.

[0796] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0797] Step 1:

[0798] The device uses multiple sensors to collect real-time data on player movements and techniques. Specifically, smart shoes measure stride length, speed, and foot contact time. For industrial automation equipment, it collects motion data such as the angle, force, and speed of a robotic arm. The input is physical data from the sensors, and the output is a digital representation of the data.

[0799] Step 2:

[0800] The terminal sends the collected data to a server via the Internet. At this time, the collected data is converted into JSON format and sent using a communication protocol (e.g., HTTP). The input is the digital data collected in the previous step, and the output is the data to be sent to the server.

[0801] Step 3:

[0802] The server stores the received data in a database. A database management system (DBMS) is used to protect the data from loss and store it in a structured format. The input is the data sent to the server and the output is a new record added to the database.

[0803] Step 4:

[0804] The server retrieves the stored data from the database and analyzes the data using a generative AI model. A specific example is analyzing running data to detect imbalanced load distribution in an athlete's running form. The input is the data retrieved from the database, and the output is the analysis result. An example of data processing is applying a machine learning algorithm to cluster the data.

[0805] Step 5:

[0806] The server generates optimal training methods and movement patterns for each athlete and equipment based on the analysis results of the generative AI model. For example, if a running form is imbalanced, it will suggest single-leg squats to train specific muscles. The input is the analysis results, and the output is the generated training methods and movement patterns. Here, the generative AI model operates based on prompt statements.

[0807] Step 6:

[0808] The server notifies the user's device of the generated teaching methods and behavior patterns. Possible notification methods include push notifications and email notifications. The input is the generated teaching methods and behavior patterns, and the output is a notification message sent to the user's device.

[0809] Step 7:

[0810] The user receives a notification and checks the instruction method or operation procedure via a smartphone or head-mounted display (HMD). The user follows the notification to perform the specific instruction method or maintenance procedure. The input is the notification message, and the output is the user's action.

[0811] Through the above steps, training methods for athletes and operational optimization of industrial automation equipment are realized.

[0812] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0813] The present invention combines a system that collects player movement and technical data in real time, automatically analyzes it using a generation AI, and proposes coaching methods, with an emotion engine that recognizes the user's emotions. The following configurations and operations are included as modes for carrying out the invention.

[0814] System configuration

[0815] 1. Terminal (IOT device)

[0816] It includes multiple sensors that collect player movement and technical data in real time, such as smart shoes, smart clothing, and smart balls.

[0817] 2. Data transmission method

[0818] Data collected from the devices is sent to a server via the internet using communication protocols such as HTTP, HTTPS, and MQTT.

[0819] 3. Server

[0820] The received data is saved in the database.

[0821] Generative AI is used to analyze data and evaluate each player's characteristics and abilities.

[0822] Based on the evaluation results, a coaching method appropriate for each player is generated.

[0823] 4. Emotion Engine

[0824] The emotion engine is a system for recognizing the emotions of users (players and coaches). The emotion engine recognizes emotions by analyzing facial expressions, tone of voice, or biometric data.

[0825] 5. Means of notification

[0826] The generated training method is sent to the user's device, where the user can receive the notification and check the specific training method and training plan.

[0827] 6. Adjustment means

[0828] Based on the user's emotional data, the server adjusts the content of the instruction method and the method of suggestions.

[0829] Program processing overview

[0830] Data collection

[0831] The device (for example, smart shoes) collects foot movement and load in real time while the athlete is exercising. The sensor collects highly accurate data and temporarily stores it in memory.

[0832] Data transmission

[0833] The device temporarily stores the collected data and transmits it to a server via an internet connection, where it is converted into an appropriate format (e.g., JSON or CSV) and transmitted using a communication protocol (e.g., HTTP).

[0834] Data storage

[0835] The server receives the data sent from the devices and stores it in a database, which is organized by player and used for later analysis.

[0836] Data analysis

[0837] The server retrieves data for each player from the database and begins analysis using the Generative AI. The Generative AI uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. For example, it analyzes foot load distribution and movement patterns from running data.

[0838] emotion recognition

[0839] The emotion engine collects the user's facial expression, voice, or biometric data in real time to recognize emotions. For example, it captures the user's facial expression with a camera and uses image analysis technology to determine whether they are smiling.

[0840] Teaching method generation

[0841] Based on the analysis results, the generative AI generates the optimal training method for each player. For example, it will suggest single-leg squat training for a player with an imbalanced leg load distribution. Furthermore, it will adjust the training plan based on feedback from the emotion engine. For example, if the user is feeling stressed, it will add relaxation exercises to relieve stress.

[0842] Result notification

[0843] The server generates training methods and sends them to the user's device. HTTP or WebSocket is used as the communication protocol. The notification includes the results of the data analysis and training suggestions.

[0844] User reception and execution

[0845] The user (coach or player) receives a notification on their device and checks the analysis results and coaching methods. For example, the player checks the recommended training method and implements it as recommended.

[0846] Specific examples

[0847] Example 1: Improving your running form

[0848] 1. Data Collection

[0849] The smart shoes collect Athlete A's running data (foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[0850] 2. Data Transmission

[0851] The data collected by the device is converted into JSON format and sent to a server via the Internet.

[0852] 3. Data storage

[0853] The server stores the received data in a database.

[0854] 4. Data Analysis

[0855] The server analyzes the stored data using generated AI and discovers an imbalanced load distribution in Athlete A's running form.

[0856] 5. Emotion recognition

[0857] The emotion engine collects facial expression data from Athlete A and recognizes his / her emotional state during exercise. For example, it determines that Athlete A looks tired.

[0858] 6. Generating Instructional Methods

[0859] Based on the generative AI, the server suggests specific muscle training exercises, including one-legged squats, to Player A. Additionally, it adds relaxation exercises based on feedback from the emotion engine.

[0860] 7. Result notification

[0861] The server generates a training method and notifies the device of Player A. Player A checks the notification and starts the recommended training.

[0862] Example 2: Improving shooting technique

[0863] 1. Data Collection

[0864] The smart ball collects shot data (angle, power, distance) from Player B. The sensors also measure wrist movement and ball rotation.

[0865] 2. Data Transmission

[0866] The data collected by the terminal is converted into XML format and sent to the server via the HTTPS protocol.

[0867] 3. Data storage

[0868] The server stores the received data in a database.

[0869] 4. Data Analysis

[0870] The server analyzes the saved data using a generative AI and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[0871] 5. Emotion recognition

[0872] The emotion engine analyzes Player B's tone of voice in real time to recognize his emotions, for example, determining whether he is relaxed or nervous.

[0873] 6. Generating Instructional Methods

[0874] Based on the generated AI, the server suggests wrist flexibility exercises and repeated shooting practice for Player B. Based on the emotional data, if Player B is nervous, it also adds relaxation techniques.

[0875] 7. Result notification

[0876] The server generates a training method and notifies the device of Player B. Player B checks the notification and performs wrist exercises and shooting practice.

[0877] The above is one embodiment of the present invention, which allows high-quality individual instruction to be provided, and also makes it possible to provide optimal instruction according to the emotional state of the player and coach.

[0878] The processing flow will be explained below.

[0879] Step 1:

[0880] The terminal begins operation. Specifically, IoT devices such as smart shoes and smart clothing collect player movement and technical data in real time. For example, in the case of smart shoes, pressure sensors and acceleration sensors measure foot movement and load.

[0881] Step 2:

[0882] The device temporarily stores the collected data. For example, the collected data is stored in the memory inside the smart shoes. During this process, the raw data is converted into an appropriate format (for example, JSON or CSV).

[0883] Step 3:

[0884] The device sends data to the server via an internet connection, using communication protocols such as HTTP, HTTPS, and MQTT. The data is encrypted before transmission to ensure security.

[0885] Step 4:

[0886] The server receives the data sent from the device, which is usually temporarily stored in a buffer or queue.

[0887] Step 5:

[0888] The server stores the received data in a database. The database organizes data by player and stores it in an easy-to-search format. For example, related data can be linked using a player ID as a key.

[0889] Step 6:

[0890] The server retrieves data for each player from the database, and the data is cleaned and normalized as preprocessing for data analysis, such as removing outliers and filling in missing data.

[0891] Step 7:

[0892] The server analyzes the stored data using a generation AI. The generation AI uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. For example, it analyzes foot load distribution and movement patterns from running data.

[0893] Step 8:

[0894] The emotion engine collects the user's facial expression, voice, or biometric data in real time to recognize emotions. For example, it captures the user's facial expression with a camera and uses image analysis technology to determine whether they are smiling.

[0895] Step 9:

[0896] The server receives data from the emotion engine and combines it with the analysis results of the generative AI to generate specific coaching methods for each player. For example, if a player has an imbalanced load distribution on their legs, it will suggest single-leg squat training, and if they are feeling stressed, it will add relaxation exercises.

[0897] Step 10:

[0898] The server then sends the generated training method to the user's device using a communication protocol such as HTTP or WebSocket. The notification includes the results of the data analysis and training suggestions.

[0899] Step 11:

[0900] The user (coach or player) receives a notification on their device and checks the analysis results and coaching methods. For example, a player checks the recommended training method and implements it as recommended.

[0901] Through these steps, the system of the present invention can provide optimal instruction tailored to the characteristics of each player, significantly reducing the burden on the coach. In addition, the introduction of an emotion engine enables detailed feedback tailored to the user's emotional state.

[0902] Example 2

[0903] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0904] In modern sports coaching, it is extremely important to collect real-time data on athletes' movements and techniques and provide appropriate instruction based on that data. However, currently, the entire process of data collection, analysis, and the creation of coaching methods requires a lot of manual work, making efficient training instruction difficult. Furthermore, the emotional state of athletes and coaches also has a significant impact on training effectiveness, but there are few systems that take this into account. The purpose of this project is to solve these issues.

[0905] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a terminal including multiple sensors that collect player movement and technique data in real time, means for transmitting the data collected from the terminal to the server via the Internet, means for storing the data received by the server in a database, means for analyzing the stored data by using a generation AI and evaluating the characteristics and abilities of each player, means for the server to generate a coaching method suitable for each player based on the evaluation results using the generation AI, means including an emotion engine that recognizes emotions by analyzing the user's facial expression, tone of voice, or biometric data, and means for adjusting the generated coaching method based on the recognized emotion data and notifying the user's terminal. This makes it possible to comprehensively improve player performance based on both scientific and emotional factors.

[0906] A "terminal" is a device containing multiple sensors that collects player movement and technical data in real time.

[0907] The "Internet" is a network infrastructure that allows information to be exchanged around the world.

[0908] A "server" is a computer system that receives, stores, and analyzes data sent from a terminal.

[0909] A "database" is a system for organizing and storing data received by a server.

[0910] "Generative AI" is an artificial intelligence system that uses machine learning algorithms to analyze data and evaluate each player's characteristics and abilities.

[0911] An "emotion engine" is a system that recognizes emotions by analyzing a user's facial expressions, tone of voice, or biometric data.

[0912] A "user terminal" is a device that receives and displays the generated teaching methods and analysis results.

[0913] "Instruction method" refers to the training plan and exercises that the generative AI will instruct each player on based on the analysis results.

[0914] This invention combines a system that collects player movement and technical data in real time, automatically analyzes it using a generation AI, and proposes coaching methods, with an emotion engine that recognizes the user's emotions. The system configuration and operation are as follows.

[0915] System configuration

[0916] 1. Terminal (IOT device)

[0917] Examples include smart shoes, smart clothing, smart balls, etc. These devices contain numerous sensors to collect player movement and technical data in real time.

[0918] 2. Data transmission method

[0919] The collected data is sent to a server via the internet using communication protocols such as HTTP, HTTPS, and MQTT.

[0920] 3. Server

[0921] The server stores the received data in a database, which can be, for example, MySQL or MongoDB.

[0922] The server analyzes the data using a generative AI, which uses machine learning algorithms (e.g., random forests and neural networks) to evaluate players' characteristics and abilities.

[0923] Based on the evaluation results, a coaching method appropriate for each player is generated.

[0924] 4. Emotion Engine

[0925] The emotion engine is a system that recognizes the emotions of users (players and coaches). For example, it uses a camera to capture facial expressions and uses image analysis technology to determine emotions. It also has the ability to analyze voice tone using audio analysis to recognize emotions.

[0926] 5. Means of notification

[0927] The generated teaching method is sent from the server to the user's device using HTTP or WebSocket as the communication protocol.

[0928] 6. Adjustment means

[0929] Based on the recognized emotion data, the server adjusts the content of the instruction method and the method of suggestions.

[0930] Specific examples

[0931] Example 1: Improving your running form

[0932] 1. Data Collection

[0933] The smart shoes collect Athlete A's running data (e.g., foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[0934] 2. Data Transmission

[0935] The collected data is converted into JSON format and sent to the server via the HTTP protocol.

[0936] 3. Data storage

[0937] The server stores the received data in a database.

[0938] 4. Data Analysis

[0939] The generative AI analyzes the saved data and discovers an imbalanced load distribution in Athlete A's running form.

[0940] 5. Emotion recognition

[0941] The emotion engine collects facial expression data of Athlete A and checks his emotional state during exercise. For example, it determines that Athlete A looks tired.

[0942] 6. Generating Instructional Methods

[0943] The generative AI suggests specific strength exercises, including single-leg squats, and also adds relaxation exercises based on feedback from the emotion engine.

[0944] 7. Result notification

[0945] A training method is generated and notified to the device of Player A. Player A checks the notification and starts the recommended training.

[0946] Example 2: Improving shooting technique

[0947] 1. Data Collection

[0948] The smart ball collects shot data (e.g., angle, power, and distance) from Player B. The sensors also measure wrist movement and ball rotation.

[0949] 2. Data Transmission

[0950] The collected data is converted into XML format and sent to the server via the HTTPS protocol.

[0951] 3. Data storage

[0952] The server stores the received data in a database.

[0953] 4. Data Analysis

[0954] The generative AI analyzes the saved data and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[0955] 5. Emotion recognition

[0956] The emotion engine analyzes Player B's tone of voice in real time to recognize his emotions, for example, determining whether he is relaxed or nervous.

[0957] 6. Generating Instructional Methods

[0958] The generative AI suggests wrist flexibility exercises and repeated shooting practice. Based on emotional data, if Player B is nervous, it will also add relaxation techniques.

[0959] 7. Result notification

[0960] A training method is generated and notified to the device of Player B. Player B checks the notification and performs wrist exercises and shooting practice.

[0961] Prompt Sentence Examples

[0962] Here is an example of a prompt to input to a generative AI model:

[0963] "Please suggest a training method to improve Athlete A's running form. Athlete A has an uneven load distribution on his feet. He also looks tired during exercise."

[0964] Using this prompt, the generative AI model can generate appropriate teaching methods and follow-up suggestions based on emotion.

[0965] As a result, the present invention provides a system for scientifically and comprehensively improving the performance of athletes.

[0966] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0967] Step 1:

[0968] Data collection

[0969] The devices (e.g., smart shoes, smart clothing, smart balls) collect data on players' movements and techniques in real time. Specifically, sensors collect data such as the player's stride length, speed, foot contact time, load, shot angle, power, and distance, and temporarily store this data in the device's memory.

[0970] Input: Player movements and technical data

[0971] Output: Temporarily saved data in the device memory

[0972] Example: When an athlete starts running, the sensors in the smart shoes are automatically activated and the collected data is written to memory.

[0973] Step 2:

[0974] Data transmission

[0975] The device converts the collected data into an appropriate format (e.g., JSON format) and sends it to a server via an internet connection using HTTP or HTTPS as the communication protocol. The data is sent in real time or at regular intervals.

[0976] Input: Temporarily saved data in the device memory

[0977] Output: Data sent to the server

[0978] Specific operation: The device sends the collected data in streaming format as a POST request to the specified server URL via Wi-Fi or mobile network.

[0979] Step 3:

[0980] Data storage

[0981] The server receives the data sent from the devices and stores it securely in a database, organizing it by player and indexing it for easy retrieval later.

[0982] Input: Data sent to the server

[0983] Output: Data stored in the database

[0984] What happens: A server endpoint receives the data and the program inserts it into a database, often MySQL or MongoDB.

[0985] Step 4:

[0986] Data analysis

[0987] The server retrieves data for each player from the database and analyzes it using a generative AI, which uses machine learning algorithms (e.g., random forests, neural networks) to evaluate the player's characteristics and abilities.

[0988] Input: Player data stored in the database

[0989] Output: Analysis results (player characteristics and ability evaluation)

[0990] Specific operation: The server periodically performs batch processing and streaming processing, inputting athlete data into the generative AI model for analysis. For example, it analyzes foot load distribution and movement patterns based on running data, and re-stores the results in the database.

[0991] Step 5:

[0992] emotion recognition

[0993] The emotion engine collects the user's facial expressions, tone of voice, biometric data, etc. in real time to recognize emotions. Specifically, it analyzes facial expression data captured by a camera and voice data to determine emotions.

[0994] Input: User facial expression data and voice data collected by camera and microphone

[0995] Output: Analysis results (user's emotional state)

[0996] Specific operation: Image data captured by the camera is input into a deep learning model to recognize the user's emotions. Voice data collected by the microphone is also recognized using voice analysis technology.

[0997] Step 6:

[0998] Teaching method generation

[0999] The server generates the optimal coaching method for each player based on the analysis results of the generative AI, and further adjusts the training plan based on feedback from the emotion engine.

[1000] Input: Analysis results and emotional state

[1001] Output: Optimized teaching methods and training plans

[1002] Specific movements: The generative AI combines running data and other exercise data with emotion recognition results to automatically generate training methods tailored to the athlete, such as one-legged squats and relaxation exercises.

[1003] Step 7:

[1004] Result notification

[1005] The server notifies the user's device of the generated teaching methods and training plans, using HTTP and WebSocket as communication protocols.

[1006] Input: Optimized teaching methods and training plans

[1007] Output: Instructions and training plans sent to the user's device

[1008] Specific operation: The server generates a notification message and sends an HTTP request to the IP address of the specified terminal. The user's terminal receives this notification and displays the content.

[1009] Step 8:

[1010] User reception and execution

[1011] The user receives a notification on their device, checks the analysis results and provides instructions, and then performs the training according to the instructions.

[1012] Input: Notification message from the server

[1013] Output: Training performed

[1014] Specific operation: After checking the notification on the device, the user performs actual training according to the displayed instruction method and training plan. The user's actions are again collected by the device's sensors and used in the next data collection phase.

[1015] (Application example 2)

[1016] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1017] While conventional sports coaching systems can collect and analyze athletes' movements and technical data in real time, they have difficulty providing coaching methods that take into account the emotional state of athletes and coaches. Furthermore, there is a lack of systems that collect movement data from factory workers to suggest efficient work procedures, or systems that recognize emotions and provide breaks and relaxation methods to reduce stress. This has made it difficult to provide optimal coaching to improve athletes' skills, increase worker efficiency, and reduce stress.

[1018] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1019] In this invention, the server includes a terminal including multiple sensors that collect player movement and technical data in real time, means for transmitting the data collected from the terminal to the server, means for storing the data received by the server in a database, an emotion engine that recognizes emotions by analyzing the user's facial expressions, voice, or biometric data, means for adjusting the content of the instruction method and the method of proposal based on the recognition results of the emotion engine, and means for notifying the user's terminal of the generated instruction method. This makes it possible to propose optimal instruction methods and work procedures that take into account the movements and emotional states of players and workers.

[1020] "Athlete" means an individual who performs an action or skill in a sport.

[1021] "Movement" refers to an object changing its position or posture.

[1022] "Technical data" means numerical or measured data relating to the actions performed by athletes or workers.

[1023] A "sensor" is a device that detects changes in the surrounding environment or objects.

[1024] A "terminal" is a device for collecting and processing data, including smart devices and IoT devices.

[1025] A "server" is a computing system that stores, processes, and serves data.

[1026] A "database" is a system for managing a structured collection of data.

[1027] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to analyze data and make predictions.

[1028] "Evaluation" is the process of determining the characteristics and capabilities of players or workers based on collected data.

[1029] "Instructional methods" refers to the suggestion of appropriate behaviors or training programs for specific goals or tasks.

[1030] "User" refers to an individual or organization that uses the system.

[1031] "Facial expressions" are part of a human interface that express emotions through the movement of facial muscles.

[1032] "Audio" means sound waves, including speech and ambient sounds.

[1033] "Biometric data" refers to various physiological information collected from the human body.

[1034] An "emotion engine" is a system for recognizing and analyzing a user's emotional state.

[1035] "Motion data" includes data relating to the movement of an object, such as position, velocity, and acceleration.

[1036] "Work procedure" means detailed steps or methods for efficiently performing a particular task.

[1037] "Relaxation" refers to activities or methods that relieve physical or mental tension.

[1038] This invention provides a system that starts with a terminal equipped with multiple sensors that collects player movement and technical data in real time. The terminal uses IoT devices such as smart clothing and smart gloves. These devices collect movement and technical data in real time and temporarily store it in memory.

[1039] The collected data is then sent via a communication protocol (e.g., HTTP or HTTPS) to a server, which stores the data in a database and is powered by a generative AI model using TensorFlow.

[1040] The generative AI model takes data from the database and analyzes movement patterns and skill levels. Specifically, it uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. The results are used to generate appropriate coaching methods.

[1041] Furthermore, an emotion engine is used to analyze the user's facial expressions, voice, and biometric data to recognize their emotional state. The emotion engine uses technologies such as EmotionAI. For example, it analyzes facial expressions from camera footage and determines the user's stress level from the tone of voice.

[1042] Based on the evaluation and emotion recognition results, the server generates optimal instruction methods and work procedures, including suggestions for relaxation exercises and breaks as needed. The generated instruction methods are sent to the user's device via a communication protocol. Notifications can be sent via a smartphone application or a dedicated device.

[1043] As a concrete example, consider a scenario in which a factory worker provides motion and emotional data. As the worker wears smart gloves and performs work, their motion data is collected in real time. Their facial expressions and tone of voice while working are also collected and analyzed by an emotion engine. This data is sent to a server, where a generative AI model evaluates work efficiency and generates instructional methods. If the worker is feeling stressed, the server also suggests relaxation exercises. These instructional methods are then notified to the worker's smartphone.

[1044] An example prompt is:

[1045] "sensor_data = {'temperature': 25.5, 'humidity': 60, 'acceleration': [0.2, 0.3, 0.4]}

[1046] emotion_data = {'emotion': 'stressed', 'confidence': 0.85}

[1047] prediction = analyze_data(sensor_data)

[1048] instructions = generate_instructions(prediction, emotion_data)

[1049] notify_user(instructions)

[1050] The above system makes it possible to propose optimal coaching methods and work procedures that take into account the movements and emotional state of athletes and workers.

[1051] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1052] Step 1:

[1053] The device collects the movement and technical data of athletes and workers, as well as biometric data, in real time. Specifically, smart clothing, smart gloves, or cameras are used to collect motion data (e.g., acceleration, posture data) and biometric data (e.g., heart rate, facial expression data). This data is temporarily stored in the device's memory.

[1054] Input: Real-time data from smart clothing and smart gloves

[1055] Output: Temporary storage of collected motion data and biometric data

[1056] Step 2:

[1057] The device sends the collected data to a server via an internet connection, where it is converted into an appropriate format (e.g., JSON or CSV) and securely transmitted using a communication protocol (e.g., HTTP or HTTPS).

[1058] Input: Collected data (e.g., acceleration data, facial expression data)

[1059] Output: Acknowledgement of completion of transmission to the server

[1060] Step 3:

[1061] The server stores the received data in a database, which manages the data in a structured format for efficient access and analysis.

[1062] Input: Transmitted data (e.g., motion data in JSON format, biometric data)

[1063] Output: Data stored in the database

[1064] Step 4:

[1065] The server retrieves data for each player or worker from the database and performs real-time analysis using a generative AI model. Machine learning algorithms (e.g., random forests, neural networks) are used to evaluate the characteristics and capabilities of each player or worker, specifically detecting movement patterns, skill levels, and imbalanced movements.

[1066] Input: Motion and biometric data retrieved from the database

[1067] Output: Analysis results (e.g., evaluation of movement patterns, determination of skill level)

[1068] Step 5:

[1069] The server uses an emotion engine to analyze the user's facial expressions, voice, and biometric data to recognize their emotional state. For example, it uses EmotionAI technology to assess whether the user is feeling stressed based on facial expression data.

[1070] Input: facial expression data and biometric data collected in real time

[1071] Output: Perceived emotional state (e.g., stressed, relaxed)

[1072] Step 6:

[1073] The server generates optimal teaching methods and work procedures based on the evaluation and emotion recognition results. The generated teaching methods may include specific training methods or relaxation exercises to reduce stress.

[1074] Input: Analysis results and emotion recognition results

[1075] Output: Generated instructional instructions or work instructions

[1076] Step 7:

[1077] The server generates training methods and work procedures and notifies the user's device. Notifications are sent via smartphone applications or dedicated devices. HTTP, WebSocket, and other communication protocols are used.

[1078] Input: Generated instructional methods or work procedures

[1079] Output: Notification to user's device completed

[1080] Step 8:

[1081] The user receives a notification on the device and checks the instruction method or work procedure. The user then performs the training or work according to the suggested method.

[1082] Input: Instruction method or work procedure notified to the terminal

[1083] Output: Training and work procedures reviewed and implemented

[1084] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1085] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1086] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1087] [Third embodiment]

[1088] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1089] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1090] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1091] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1092] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1093] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1094] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1095] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1096] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1097] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1098] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1099] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1100] The present invention relates to a system that collects player movement and technical data in real time, and automatically analyzes the data using a generation AI to propose coaching methods. The following configurations and operations are included as embodiments of the invention.

[1101] System configuration

[1102] 1. Terminal (IOT device)

[1103] It includes multiple sensors that collect player movement and technical data in real time, such as smart shoes, smart clothing, and smart balls.

[1104] 2. Data transmission method

[1105] Data collected from the devices is sent to a server via the internet using communication protocols such as HTTP, HTTPS, and MQTT.

[1106] 3. Server

[1107] The received data is saved in the database.

[1108] Generative AI is used to analyze data and evaluate each player's characteristics and abilities.

[1109] Based on the evaluation results, a coaching method appropriate for each player is generated.

[1110] 4. Means of notification

[1111] The generated training method is sent to the user's device, where the user can receive the notification and check the specific training method and training plan.

[1112] Program processing overview

[1113] Data collection

[1114] The device (for example, smart shoes) collects foot movement and load in real time while the athlete is running. The sensors collect highly accurate data and temporarily store it in memory.

[1115] Data transmission

[1116] The device sends the collected data to a server via an internet connection, where it is converted into an appropriate format (e.g., JSON) and sent using a communication protocol (e.g., HTTP).

[1117] Data storage

[1118] The server receives the data sent from the devices and stores it in a database, which is organized by player and used for later analysis.

[1119] Data analysis

[1120] The server retrieves data for each athlete from the database and begins analysis using generative AI. For example, it uses smart shoe data to evaluate Athlete A's running form and analyzes the load distribution and movement patterns of the feet.

[1121] Teaching method generation

[1122] Based on the analysis results, the generative AI generates the optimal coaching method for each athlete. For example, if it is determined that Athlete A's running form is imbalanced, it will suggest one-legged squats to train specific muscles.

[1123] Result notification

[1124] The training method generated by the server is sent to the user's (coach or player's) device. The notification includes the data analysis results and specific training methods. The user receives the notification and can check and implement the training methods on their device.

[1125] Specific examples

[1126] Example 1: Improving your running form

[1127] 1. Data Collection

[1128] The smart shoes collect Athlete A's running data (foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[1129] 2. Data Transmission

[1130] The data collected by the device is converted into JSON format and sent to a server via the Internet.

[1131] 3. Data storage

[1132] The server stores the received data in a database.

[1133] 4. Data Analysis

[1134] The server analyzes the stored data using generated AI and discovers an imbalanced load distribution in Athlete A's running form.

[1135] 5. Generating Instructional Methods

[1136] Based on the generated AI, the server suggests specific muscle training exercises to Player A, including single-leg squats.

[1137] 6. Result notification

[1138] The server generates a training method and notifies the device of Player A. Player A checks the notification and starts the recommended training.

[1139] Example 2: Improving shooting technique

[1140] 1. Data Collection

[1141] The smart ball collects shot data (angle, power, distance) from Player B. The sensors also measure wrist movement and ball rotation.

[1142] 2. Data Transmission

[1143] The data collected by the terminal is converted into XML format and sent to the server via the HTTPS protocol.

[1144] 3. Data storage

[1145] The server stores the received data in a database.

[1146] 4. Data Analysis

[1147] The server analyzes the saved data using a generative AI and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[1148] 5. Generating Instructional Methods

[1149] Based on the generated AI, the server suggests exercises to Player B to improve wrist flexibility and repeated shooting practice.

[1150] 6. Result notification

[1151] The server generates a training method and notifies the device of Player B. Player B checks the notification and performs the recommended exercises and training.

[1152] The above is one embodiment of the present invention, which can provide high-quality individual instruction and significantly reduce the burden on instructors.

[1153] The processing flow will be explained below.

[1154] Step 1:

[1155] The terminal begins operation. Specifically, IoT devices such as smart shoes and smart clothing collect player movement and technical data in real time. For example, in the case of smart shoes, pressure sensors and acceleration sensors measure foot movement and load.

[1156] Step 2:

[1157] The device temporarily stores the collected data. For example, the collected data is stored in the memory inside the smart shoes. During this process, the raw data is converted into an appropriate format (for example, JSON or CSV).

[1158] Step 3:

[1159] The device sends data to the server via an internet connection, using communication protocols such as HTTP, HTTPS, and MQTT. The data is encrypted before transmission to ensure security.

[1160] Step 4:

[1161] The server receives the data sent from the device, which is usually temporarily stored in a buffer or queue.

[1162] Step 5:

[1163] The server stores the received data in a database. The database organizes data by player and stores it in an easy-to-search format. For example, related data can be linked using a player ID as a key.

[1164] Step 6:

[1165] The server retrieves data for each player from the database, and the data is cleaned and normalized as preprocessing for data analysis, such as removing outliers and filling in missing data.

[1166] Step 7:

[1167] The server analyzes the stored data using a generation AI. The generation AI uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. For example, it analyzes foot load distribution and movement patterns from running data.

[1168] Step 8:

[1169] The server uses generative AI to generate specific training methods for each player, for example, suggesting one-leg squat training for a player with uneven leg load distribution.

[1170] Step 9:

[1171] The server sends the generated teaching methods to the user's device using communication protocols such as HTTP or WebSocket. The notification includes analysis results and training suggestions.

[1172] Step 10:

[1173] The user (coach or player) receives a notification on their device and checks the analysis results and coaching methods. For example, a player checks the recommended training method and implements it as recommended.

[1174] Through these steps, the system of the present invention can provide optimal instruction tailored to the characteristics of each player, significantly reducing the burden on the instructor.

[1175] Example 1

[1176] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1177] With conventional coaching methods, it is difficult to accurately grasp the characteristics and abilities of each player, making it difficult to provide efficient training methods. Furthermore, because data is not collected and analyzed in real time, it is not possible to provide appropriate feedback quickly. This has resulted in the problem of it taking a long time for players to improve their technique and form.

[1178] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1179] In this invention, the server includes a terminal including a plurality of sensors that collect player movement and technique data in real time, means for transmitting the data collected from the terminal to the server, means for the server to store the received data in a database, means for the server to analyze the stored data using a generation AI and evaluate the characteristics and abilities of each player, means for the server to generate a coaching method suitable for each player based on the evaluation results using the generation AI, and means for notifying the user's terminal of the generated coaching method and the results of data analysis. This makes it possible to provide appropriate coaching methods based on the characteristics and abilities of each player in real time, enabling efficient training.

[1180] A "terminal" is a device containing multiple sensors that collects player movement and technical data in real time.

[1181] The "server" is a central processing unit that receives and stores data sent from the terminal, analyzes and evaluates it using generation AI, and generates teaching methods based on the results.

[1182] A "sensor" is a device that measures and collects data on the movements and techniques performed by athletes in real time.

[1183] "Database" means a data management system that stores received data in an organized manner and makes it available for later analysis and evaluation.

[1184] "Generative AI" is an artificial intelligence technology that analyzes collected data, evaluates the characteristics and abilities of each player, and generates optimal coaching methods.

[1185] "Data transmission means" refers to a means including communication protocols and techniques for transmitting data collected by a terminal to a server.

[1186] The "data storage means" is a means for storing data received by the server in a database.

[1187] The "data analysis method" is a method for analyzing data stored in a database using generative AI to evaluate the characteristics and abilities of each player.

[1188] The "training method generation means" is a means for generating a training method suitable for each player based on the evaluation results by the generation AI.

[1189] The "notification means" is a means for notifying the user's terminal of the generated teaching method and the results of the data analysis.

[1190] This invention is a system that collects player movement and technical data in real time, and automatically analyzes it using a generation AI to propose coaching methods. This system is composed of a terminal, a data transmission means, a server, a data storage means, a data analysis means, a coaching method generation means, and a notification means.

[1191] System configuration

[1192] 1. Terminal (IOT device)

[1193] The devices include multiple sensors that collect player movement and technical data in real time. Examples include smart shoes, smart clothing, and smart balls. These devices are equipped with acceleration sensors, pressure sensors, and other sensors to collect highly accurate data.

[1194] 2. Data transmission method

[1195] The data collected by the device is sent to a server via the internet using a communication protocol such as HTTP, HTTPS, or MQTT, and the data is converted into an appropriate format such as JSON.

[1196] 3. Server

[1197] The server receives the data sent from the devices and stores it in a database. It also uses a generation AI to analyze the received data and evaluate the characteristics and abilities of each player. The server has the function of generating individual coaching methods based on the results of the data analysis.

[1198] 4. Data storage method

[1199] The data received by the server is stored in a database, organized by player, and used for later analysis.

[1200] 5. Data Analysis Methods

[1201] The server retrieves the data of a specific player from the database and begins analysis using the generation AI, which analyzes the stored data and evaluates the player's characteristics such as running form, throwing motion, and shooting technique.

[1202] 6. Instruction method generation means

[1203] The server generates the optimal coaching method for each player based on the evaluation results obtained by the AI ​​generation. The generated coaching method is provided as a specific training menu or exercise.

[1204] 7. Means of notification

[1205] The server then sends the generated training method and data analysis results to the user's device. The notification contains detailed information about the analysis results and training method. The user can then receive the notification and implement the specific training plan.

[1206] Specific examples

[1207] Example 1: Improving your running form

[1208] 1. Data Collection

[1209] The smart shoes collect Athlete A's running data (foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[1210] 2. Data Transmission

[1211] The data collected by the device is converted into JSON format and sent to a server via the Internet.

[1212] 3. Data storage

[1213] The server stores the received data in a database.

[1214] 4. Data Analysis

[1215] The server analyzes the stored data using generated AI and discovers an imbalanced load distribution in Athlete A's running form.

[1216] 5. Generating Instructional Methods

[1217] Based on the generated AI, the server suggests specific muscle training exercises to Player A, including single-leg squats.

[1218] 6. Result notification

[1219] The server generates a training method and notifies the device of Player A. Player A checks the notification and starts the recommended training.

[1220] Example 2: Improving shooting technique

[1221] 1. Data Collection

[1222] The smart ball collects shot data (angle, power, distance) from Player B. The sensors also measure wrist movement and ball rotation.

[1223] 2. Data Transmission

[1224] The data collected by the terminal is converted into XML format and sent to the server via the HTTPS protocol.

[1225] 3. Data storage

[1226] The server stores the received data in a database.

[1227] 4. Data Analysis

[1228] The server analyzes the saved data using a generative AI and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[1229] 5. Generating Instructional Methods

[1230] Based on the generated AI, the server suggests exercises to Player B to improve wrist flexibility and repeated shooting practice.

[1231] 6. Result notification

[1232] The server generates a training method and notifies the device of Player B. Player B checks the notification and performs the recommended exercises and training.

[1233] Example of input prompt for generative AI model

[1234] "Please analyze Athlete A's running form and suggest an appropriate training method."

[1235] "What exercises can Player B do to improve his shooting technique?"

[1236] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1237] Step 1:

[1238] Data collection

[1239] The device collects the player's movements and technical data in real time. Specifically, the acceleration and pressure sensors in the smart shoes measure the player's stride length, speed, foot contact time, and pressure when stepping on the ball. The player's movements are input, and measurement data is generated as output. This data is temporarily stored in the device's memory.

[1240] Specific actions

[1241] When the athlete starts running, sensors in the smart shoes collect data and temporarily store it in the device's memory.

[1242] Step 2:

[1243] Data transmission

[1244] The data collected by the device is converted into JSON format and sent to a server via the Internet. The HTTP protocol is used for communication. The input is the measurement data stored in the device, and the output is the JSON data sent to the server.

[1245] Specific actions

[1246] The device's microcontroller converts the measurement data into JSON format, and the Wi-Fi module transmits this data to a server over the Internet.

[1247] Step 3:

[1248] Data storage

[1249] The server receives the data sent from the device and stores it in a database. The input is JSON data that arrives at the server, and the output is structured data stored in the database.

[1250] Specific actions

[1251] The server receives the HTTP request, parses the JSON data, and inserts it into a database, organized by player.

[1252] Step 4:

[1253] Data analysis

[1254] The server retrieves the data of a specific player from the database and begins analysis using the generative AI. The input is the measurement data stored in the database, and the output is an evaluation of the player's characteristics and abilities.

[1255] Specific actions

[1256] The server executes a scheduled job, querying the database for the latest data on the specified athlete, and inputs the acquired data into a generative AI model to analyze running form and evaluate foot load distribution.

[1257] Step 5:

[1258] Teaching method generation

[1259] The server generates the optimal coaching method for each player based on the evaluation results obtained by the generation AI. The input is the evaluation results from the generation AI, and the output is a specific coaching method and training menu.

[1260] Specific actions

[1261] A generative AI compiles the analysis results and generates training plans (e.g., single-leg squats) that address specific problems. These plans are formatted in text format.

[1262] Step 6:

[1263] Result notification

[1264] The server notifies the user's device of the generated teaching method and the results of the data analysis. The input is the generated teaching plan, and the output is a notification message displayed on the user's device.

[1265] Users receive notifications and receive specific training instructions.

[1266] Specific actions

[1267] The server generates a notification message and sends it to the user's device as a push notification, which the user can receive and view detailed instruction methods.

[1268] (Application example 1)

[1269] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1270] The problem that this invention aims to solve is to provide optimal training methods for individual athletes by collecting player movement and technical data in real time, and automatically analyzing and proposing coaching methods using generation AI based on that data. Also, the problem that this invention aims to solve is to improve operational efficiency and reduce maintenance costs by monitoring operational data of industrial automation equipment used in factories in real time, automatically detecting abnormalities and inefficient operations, and proposing optimal operation and maintenance methods.

[1271] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1272] In this invention, the server includes a terminal including multiple sensors that collect player movement and technical data in real time, a means for transmitting the data collected from the terminal to the server, a means for storing the received data in a database, a means for analyzing the stored data using a generation AI to evaluate the characteristics and abilities of each player, a means for the server to generate a coaching method suitable for each player based on the evaluation results using the generation AI, a means for notifying the user of the generated coaching method, a means for generating motion patterns for detecting abnormalities and optimizing the operation of industrial automation equipment based on the data analysis results by the generation AI, and a means for using the generated motion patterns to maintain or optimize the operation of the industrial automation equipment. This makes it possible to provide the optimal coaching method for each player, detect abnormalities in industrial automation equipment in factories, and propose optimal maintenance methods.

[1273] An "athlete" is an individual who participates in a sport or competition and trains its skills and movements.

[1274] "Motion and technical data" refers to numbers and information related to the operation and performance of athletes and industrial automation equipment.

[1275] "Real-time" refers to processing and data collection occurring at the exact moment an event occurs.

[1276] A "sensor" is a device that detects physical movements or changes in the environment and outputs them as electrical signals.

[1277] A "terminal" is a device that includes sensors and is a device that collects and transmits data.

[1278] A "server" is a computer system that stores and processes data over a network.

[1279] "Generative AI" is an artificial intelligence technology that analyzes collected data and automatically creates optimal teaching methods and movement patterns based on the results.

[1280] A "database" is a system for efficiently storing and managing structured data.

[1281] "User" refers to a coach, player, or factory manager who uses the system.

[1282] "Industrial automation equipment" refers to machinery and robots used to automate manufacturing processes.

[1283] "Maintenance" refers to inspection and repair activities performed to keep equipment or systems in working order.

[1284] "Operational optimization" refers to activities that optimize operational methods to maximize the performance of equipment and systems.

[1285] System Configuration

[1286] This invention is a system that collects player movement and technical data in real time, and automatically analyzes it using a generation AI to propose coaching methods. It also monitors the operation data of industrial automation equipment in real time, generates operation patterns for abnormalities and optimization, and supports maintenance and operational optimization.

[1287] Hardware

[1288] 1. Terminal (IOT device)

[1289] These devices are equipped with multiple sensors and collect player movement and technical data in real time. Examples include smart shoes, smart clothing, and smart balls.

[1290] In the case of industrial automation equipment, it is a sensor that detects the operation of robot arms, processing equipment, etc.

[1291] 2. Server

[1292] This is a computer system that stores and analyzes data. Collected data is stored, analyzed using AI, and results are generated and notified.

[1293] 3. User Device

[1294] A device such as a smartphone or head-mounted display (HMD) through which the user receives analysis results and instructional methods.

[1295] software

[1296] 1. Generative AI Models

[1297] It is an artificial intelligence that analyzes collected data and automatically generates optimal teaching methods and movement patterns based on the results.

[1298] 2. Data transmission method

[1299] This software allows the device to send collected data to a server via an internet connection, using communication protocols such as HTTP, HTTPS, and MQTT.

[1300] 3. Database

[1301] It is a system that runs on a server and stores and manages received data.

[1302] 4. Means of notification

[1303] This software notifies the user's device of the teaching methods and behavior patterns generated by the server. Examples include push notifications and email notifications.

[1304] Overview of program processing

[1305] The terminal uses sensors installed in the device to collect real-time movement and technical data from athletes and industrial automation equipment. For example, when collecting an athlete's running data using smart shoes, the sensors measure stride length, speed, foot contact time, etc. The collected data is then converted into JSON format and sent to a server via the HTTP protocol. Similarly, motion data from industrial automation equipment is collected by sensors and sent to a server.

[1306] The server stores the received data in a database and uses generative AI to analyze the data and evaluate the characteristics and capabilities of each athlete and piece of equipment. For example, if the generative AI detects an uneven load distribution in an athlete's running form, it will suggest one-legged squats to train specific muscles. Similarly, it analyzes the movement data of a robotic arm to detect abnormal or inefficient movements, identify the cause, and suggest appropriate adjustments or maintenance methods.

[1307] The generated training methods and operation patterns are sent from the server to the user's device, where the user receives the notification and confirms and carries out the specific training methods and maintenance methods via their smartphone or HMD.

[1308] Examples of specific examples and prompts

[1309] Example 1: Improving your running form

[1310] 1. Smart shoes collect Athlete A's running data (foot movement, load) in real time.

[1311] 2. The device converts the collected data into JSON format and sends it to a server via the Internet.

[1312] 3. The server stores the data, and the generative AI analyzes your running form and detects imbalanced load distribution.

[1313] 4. The generative AI suggests specific muscle training exercises, including single-leg squats, and notifies Athlete A's device.

[1314] Example 2: Optimizing the operation of industrial automation equipment

[1315] 1. Sensors collect real-time motion data (angle, force, speed) from the robot arm.

[1316] 2. The device converts the collected data into JSON format and sends it to a server via the Internet.

[1317] 3. The server stores the data, and the generating AI analyzes the operational data to detect abnormalities and operational patterns for optimization.

[1318] 4. The generative AI proposes optimal maintenance methods and operation patterns and notifies the administrator's device.

[1319] Prompt Sentence Examples

[1320] An example of a prompt sentence to input to the generative AI model is as follows:

[1321] Analyze the robot arm's motion data and check the following:

[1322] Ingres' deviation from the standard

[1323] Abnormal operating speed

[1324] Excessive use of force

[1325] If any of these abnormalities occur, please suggest the cause and appropriate maintenance methods.

[1326] By following the above procedure, it is possible to develop a specific application of the present invention to a factory robot.

[1327] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1328] Step 1:

[1329] The device uses multiple sensors to collect real-time data on player movements and techniques. Specifically, smart shoes measure stride length, speed, and foot contact time. For industrial automation equipment, it collects motion data such as the angle, force, and speed of a robotic arm. The input is physical data from the sensors, and the output is a digital representation of the data.

[1330] Step 2:

[1331] The terminal sends the collected data to a server via the Internet. At this time, the collected data is converted into JSON format and sent using a communication protocol (e.g., HTTP). The input is the digital data collected in the previous step, and the output is the data to be sent to the server.

[1332] Step 3:

[1333] The server stores the received data in a database. A database management system (DBMS) is used to protect the data from loss and store it in a structured format. The input is the data sent to the server and the output is a new record added to the database.

[1334] Step 4:

[1335] The server retrieves the stored data from the database and analyzes the data using a generative AI model. A specific example is analyzing running data to detect imbalanced load distribution in an athlete's running form. The input is the data retrieved from the database, and the output is the analysis result. An example of data processing is applying a machine learning algorithm to cluster the data.

[1336] Step 5:

[1337] The server generates optimal training methods and movement patterns for each athlete and equipment based on the analysis results of the generative AI model. For example, if a running form is imbalanced, it will suggest single-leg squats to train specific muscles. The input is the analysis results, and the output is the generated training methods and movement patterns. Here, the generative AI model operates based on prompt statements.

[1338] Step 6:

[1339] The server notifies the user's device of the generated teaching methods and behavior patterns. Possible notification methods include push notifications and email notifications. The input is the generated teaching methods and behavior patterns, and the output is a notification message sent to the user's device.

[1340] Step 7:

[1341] The user receives a notification and checks the instruction method or operation procedure via a smartphone or head-mounted display (HMD). The user follows the notification to perform the specific instruction method or maintenance procedure. The input is the notification message, and the output is the user's action.

[1342] Through the above steps, training methods for athletes and operational optimization of industrial automation equipment are realized.

[1343] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1344] The present invention combines a system that collects player movement and technical data in real time, automatically analyzes it using a generation AI, and proposes coaching methods, with an emotion engine that recognizes the user's emotions. The following configurations and operations are included as modes for carrying out the invention.

[1345] System configuration

[1346] 1. Terminal (IOT device)

[1347] It includes multiple sensors that collect player movement and technical data in real time, such as smart shoes, smart clothing, and smart balls.

[1348] 2. Data transmission method

[1349] Data collected from the devices is sent to a server via the internet using communication protocols such as HTTP, HTTPS, and MQTT.

[1350] 3. Server

[1351] The received data is saved in the database.

[1352] Generative AI is used to analyze data and evaluate each player's characteristics and abilities.

[1353] Based on the evaluation results, a coaching method appropriate for each player is generated.

[1354] 4. Emotion Engine

[1355] The emotion engine is a system for recognizing the emotions of users (players and coaches). The emotion engine recognizes emotions by analyzing facial expressions, tone of voice, or biometric data.

[1356] 5. Means of notification

[1357] The generated training method is sent to the user's device, where the user can receive the notification and check the specific training method and training plan.

[1358] 6. Adjustment means

[1359] Based on the user's emotional data, the server adjusts the content of the instruction method and the method of suggestions.

[1360] Program processing overview

[1361] Data collection

[1362] The device (for example, smart shoes) collects foot movement and load in real time while the athlete is exercising. The sensor collects highly accurate data and temporarily stores it in memory.

[1363] Data transmission

[1364] The device temporarily stores the collected data and transmits it to a server via an internet connection, where it is converted into an appropriate format (e.g., JSON or CSV) and transmitted using a communication protocol (e.g., HTTP).

[1365] Data storage

[1366] The server receives the data sent from the devices and stores it in a database, which is organized by player and used for later analysis.

[1367] Data analysis

[1368] The server retrieves data for each player from the database and begins analysis using the Generative AI. The Generative AI uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. For example, it analyzes foot load distribution and movement patterns from running data.

[1369] emotion recognition

[1370] The emotion engine collects the user's facial expression, voice, or biometric data in real time to recognize emotions. For example, it captures the user's facial expression with a camera and uses image analysis technology to determine whether they are smiling.

[1371] Teaching method generation

[1372] Based on the analysis results, the generative AI generates the optimal training method for each player. For example, it will suggest single-leg squat training for a player with an imbalanced leg load distribution. Furthermore, it will adjust the training plan based on feedback from the emotion engine. For example, if the user is feeling stressed, it will add relaxation exercises to relieve stress.

[1373] Result notification

[1374] The server generates training methods and sends them to the user's device. HTTP or WebSocket is used as the communication protocol. The notification includes the results of the data analysis and training suggestions.

[1375] User reception and execution

[1376] The user (coach or player) receives a notification on their device and checks the analysis results and coaching methods. For example, the player checks the recommended training method and implements it as recommended.

[1377] Specific examples

[1378] Example 1: Improving your running form

[1379] 1. Data Collection

[1380] The smart shoes collect Athlete A's running data (foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[1381] 2. Data Transmission

[1382] The data collected by the device is converted into JSON format and sent to a server via the Internet.

[1383] 3. Data storage

[1384] The server stores the received data in a database.

[1385] 4. Data Analysis

[1386] The server analyzes the stored data using generated AI and discovers an imbalanced load distribution in Athlete A's running form.

[1387] 5. Emotion recognition

[1388] The emotion engine collects facial expression data from Athlete A and recognizes his / her emotional state during exercise. For example, it determines that Athlete A looks tired.

[1389] 6. Generating Instructional Methods

[1390] Based on the generative AI, the server suggests specific muscle training exercises, including one-legged squats, to Player A. Additionally, it adds relaxation exercises based on feedback from the emotion engine.

[1391] 7. Result notification

[1392] The server generates a training method and notifies the device of Player A. Player A checks the notification and starts the recommended training.

[1393] Example 2: Improving shooting technique

[1394] 1. Data Collection

[1395] The smart ball collects shot data (angle, power, distance) from Player B. The sensors also measure wrist movement and ball rotation.

[1396] 2. Data Transmission

[1397] The data collected by the terminal is converted into XML format and sent to the server via the HTTPS protocol.

[1398] 3. Data storage

[1399] The server stores the received data in a database.

[1400] 4. Data Analysis

[1401] The server analyzes the saved data using a generative AI and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[1402] 5. Emotion recognition

[1403] The emotion engine analyzes Player B's tone of voice in real time to recognize his emotions, for example, determining whether he is relaxed or nervous.

[1404] 6. Generating Instructional Methods

[1405] Based on the generated AI, the server suggests wrist flexibility exercises and repeated shooting practice for Player B. Based on the emotional data, if Player B is nervous, it also adds relaxation techniques.

[1406] 7. Result notification

[1407] The server generates a training method and notifies the device of Player B. Player B checks the notification and performs wrist exercises and shooting practice.

[1408] The above is one embodiment of the present invention, which allows high-quality individual instruction to be provided, and also makes it possible to provide optimal instruction according to the emotional state of the player and coach.

[1409] The processing flow will be explained below.

[1410] Step 1:

[1411] The terminal begins operation. Specifically, IoT devices such as smart shoes and smart clothing collect player movement and technical data in real time. For example, in the case of smart shoes, pressure sensors and acceleration sensors measure foot movement and load.

[1412] Step 2:

[1413] The device temporarily stores the collected data. For example, the collected data is stored in the memory inside the smart shoes. During this process, the raw data is converted into an appropriate format (for example, JSON or CSV).

[1414] Step 3:

[1415] The device sends data to the server via an internet connection, using communication protocols such as HTTP, HTTPS, and MQTT. The data is encrypted before transmission to ensure security.

[1416] Step 4:

[1417] The server receives the data sent from the device, which is usually temporarily stored in a buffer or queue.

[1418] Step 5:

[1419] The server stores the received data in a database. The database organizes data by player and stores it in an easy-to-search format. For example, related data can be linked using a player ID as a key.

[1420] Step 6:

[1421] The server retrieves data for each player from the database, and the data is cleaned and normalized as preprocessing for data analysis, such as removing outliers and filling in missing data.

[1422] Step 7:

[1423] The server analyzes the stored data using a generation AI. The generation AI uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. For example, it analyzes foot load distribution and movement patterns from running data.

[1424] Step 8:

[1425] The emotion engine collects the user's facial expression, voice, or biometric data in real time to recognize emotions. For example, it captures the user's facial expression with a camera and uses image analysis technology to determine whether they are smiling.

[1426] Step 9:

[1427] The server receives data from the emotion engine and combines it with the analysis results of the generative AI to generate specific coaching methods for each player. For example, if a player has an imbalanced load distribution on their legs, it will suggest single-leg squat training, and if they are feeling stressed, it will add relaxation exercises.

[1428] Step 10:

[1429] The server then sends the generated training method to the user's device using a communication protocol such as HTTP or WebSocket. The notification includes the results of the data analysis and training suggestions.

[1430] Step 11:

[1431] The user (coach or player) receives a notification on their device and checks the analysis results and coaching methods. For example, a player checks the recommended training method and implements it as recommended.

[1432] Through these steps, the system of the present invention can provide optimal instruction tailored to the characteristics of each player, significantly reducing the burden on the coach. In addition, the introduction of an emotion engine enables detailed feedback tailored to the user's emotional state.

[1433] Example 2

[1434] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1435] In modern sports coaching, it is extremely important to collect real-time data on athletes' movements and techniques and provide appropriate instruction based on that data. However, currently, the entire process of data collection, analysis, and the creation of coaching methods requires a lot of manual work, making efficient training instruction difficult. Furthermore, the emotional state of athletes and coaches also has a significant impact on training effectiveness, but there are few systems that take this into account. The purpose of this project is to solve these issues.

[1436] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a terminal including multiple sensors that collect player movement and technique data in real time, means for transmitting the data collected from the terminal to the server via the Internet, means for storing the data received by the server in a database, means for analyzing the stored data by using a generation AI and evaluating the characteristics and abilities of each player, means for the server to generate a coaching method suitable for each player based on the evaluation results using the generation AI, means including an emotion engine that recognizes emotions by analyzing the user's facial expression, tone of voice, or biometric data, and means for adjusting the generated coaching method based on the recognized emotion data and notifying the user's terminal. This makes it possible to comprehensively improve player performance based on both scientific and emotional factors.

[1437] A "terminal" is a device containing multiple sensors that collects player movement and technical data in real time.

[1438] The "Internet" is a network infrastructure that allows information to be exchanged around the world.

[1439] A "server" is a computer system that receives, stores, and analyzes data sent from a terminal.

[1440] A "database" is a system for organizing and storing data received by a server.

[1441] "Generative AI" is an artificial intelligence system that uses machine learning algorithms to analyze data and evaluate each player's characteristics and abilities.

[1442] An "emotion engine" is a system that recognizes emotions by analyzing a user's facial expressions, tone of voice, or biometric data.

[1443] A "user terminal" is a device that receives and displays the generated teaching methods and analysis results.

[1444] "Instruction method" refers to the training plan and exercises that the generative AI will instruct each player on based on the analysis results.

[1445] This invention combines a system that collects player movement and technical data in real time, automatically analyzes it using a generation AI, and proposes coaching methods, with an emotion engine that recognizes the user's emotions. The system configuration and operation are as follows.

[1446] System configuration

[1447] 1. Terminal (IOT device)

[1448] Examples include smart shoes, smart clothing, smart balls, etc. These devices contain numerous sensors to collect player movement and technical data in real time.

[1449] 2. Data transmission method

[1450] The collected data is sent to a server via the internet using communication protocols such as HTTP, HTTPS, and MQTT.

[1451] 3. Server

[1452] The server stores the received data in a database, which can be, for example, MySQL or MongoDB.

[1453] The server analyzes the data using a generative AI, which uses machine learning algorithms (e.g., random forests and neural networks) to evaluate players' characteristics and abilities.

[1454] Based on the evaluation results, a coaching method appropriate for each player is generated.

[1455] 4. Emotion Engine

[1456] The emotion engine is a system that recognizes the emotions of users (players and coaches). For example, it uses a camera to capture facial expressions and uses image analysis technology to determine emotions. It also has the ability to analyze voice tone using audio analysis to recognize emotions.

[1457] 5. Means of notification

[1458] The generated teaching method is sent from the server to the user's device using HTTP or WebSocket as the communication protocol.

[1459] 6. Adjustment means

[1460] Based on the recognized emotion data, the server adjusts the content of the instruction method and the method of suggestions.

[1461] Specific examples

[1462] Example 1: Improving your running form

[1463] 1. Data Collection

[1464] The smart shoes collect Athlete A's running data (e.g., foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[1465] 2. Data Transmission

[1466] The collected data is converted into JSON format and sent to the server via the HTTP protocol.

[1467] 3. Data storage

[1468] The server stores the received data in a database.

[1469] 4. Data Analysis

[1470] The generative AI analyzes the saved data and discovers an imbalanced load distribution in Athlete A's running form.

[1471] 5. Emotion recognition

[1472] The emotion engine collects facial expression data of Athlete A and checks his emotional state during exercise. For example, it determines that Athlete A looks tired.

[1473] 6. Generating Instructional Methods

[1474] The generative AI suggests specific strength exercises, including single-leg squats, and also adds relaxation exercises based on feedback from the emotion engine.

[1475] 7. Result notification

[1476] A training method is generated and notified to the device of Player A. Player A checks the notification and starts the recommended training.

[1477] Example 2: Improving shooting technique

[1478] 1. Data Collection

[1479] The smart ball collects shot data (e.g., angle, power, and distance) from Player B. The sensors also measure wrist movement and ball rotation.

[1480] 2. Data Transmission

[1481] The collected data is converted into XML format and sent to the server via the HTTPS protocol.

[1482] 3. Data storage

[1483] The server stores the received data in a database.

[1484] 4. Data Analysis

[1485] The generative AI analyzes the saved data and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[1486] 5. Emotion recognition

[1487] The emotion engine analyzes Player B's tone of voice in real time to recognize his emotions, for example, determining whether he is relaxed or nervous.

[1488] 6. Generating Instructional Methods

[1489] The generative AI suggests wrist flexibility exercises and repeated shooting practice. Based on emotional data, if Player B is nervous, it will also add relaxation techniques.

[1490] 7. Result notification

[1491] A training method is generated and notified to the device of Player B. Player B checks the notification and performs wrist exercises and shooting practice.

[1492] Prompt Sentence Examples

[1493] Here is an example of a prompt to input to a generative AI model:

[1494] "Please suggest a training method to improve Athlete A's running form. Athlete A has an uneven load distribution on his feet. He also looks tired during exercise."

[1495] Using this prompt, the generative AI model can generate appropriate teaching methods and follow-up suggestions based on emotion.

[1496] As a result, the present invention provides a system for scientifically and comprehensively improving the performance of athletes.

[1497] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1498] Step 1:

[1499] Data collection

[1500] The devices (e.g., smart shoes, smart clothing, smart balls) collect data on players' movements and techniques in real time. Specifically, sensors collect data such as the player's stride length, speed, foot contact time, load, shot angle, power, and distance, and temporarily store this data in the device's memory.

[1501] Input: Player movements and technical data

[1502] Output: Temporarily saved data in the device memory

[1503] Example: When an athlete starts running, the sensors in the smart shoes are automatically activated and the collected data is written to memory.

[1504] Step 2:

[1505] Data transmission

[1506] The device converts the collected data into an appropriate format (e.g., JSON format) and sends it to a server via an internet connection using HTTP or HTTPS as the communication protocol. The data is sent in real time or at regular intervals.

[1507] Input: Temporarily saved data in the device memory

[1508] Output: Data sent to the server

[1509] Specific operation: The device sends the collected data in streaming format as a POST request to the specified server URL via Wi-Fi or mobile network.

[1510] Step 3:

[1511] Data storage

[1512] The server receives the data sent from the devices and stores it securely in a database, organizing it by player and indexing it for easy retrieval later.

[1513] Input: Data sent to the server

[1514] Output: Data stored in the database

[1515] What happens: A server endpoint receives the data and the program inserts it into a database, often MySQL or MongoDB.

[1516] Step 4:

[1517] Data analysis

[1518] The server retrieves data for each player from the database and analyzes it using a generative AI, which uses machine learning algorithms (e.g., random forests, neural networks) to evaluate the player's characteristics and abilities.

[1519] Input: Player data stored in the database

[1520] Output: Analysis results (player characteristics and ability evaluation)

[1521] Specific operation: The server periodically performs batch processing and streaming processing, inputting athlete data into the generative AI model for analysis. For example, it analyzes foot load distribution and movement patterns based on running data, and re-stores the results in the database.

[1522] Step 5:

[1523] emotion recognition

[1524] The emotion engine collects the user's facial expressions, tone of voice, biometric data, etc. in real time to recognize emotions. Specifically, it analyzes facial expression data captured by a camera and voice data to determine emotions.

[1525] Input: User facial expression data and voice data collected by camera and microphone

[1526] Output: Analysis results (user's emotional state)

[1527] Specific operation: Image data captured by the camera is input into a deep learning model to recognize the user's emotions. Voice data collected by the microphone is also recognized using voice analysis technology.

[1528] Step 6:

[1529] Teaching method generation

[1530] The server generates the optimal coaching method for each player based on the analysis results of the generative AI, and further adjusts the training plan based on feedback from the emotion engine.

[1531] Input: Analysis results and emotional state

[1532] Output: Optimized teaching methods and training plans

[1533] Specific movements: The generative AI combines running data and other exercise data with emotion recognition results to automatically generate training methods tailored to the athlete, such as one-legged squats and relaxation exercises.

[1534] Step 7:

[1535] Result notification

[1536] The server notifies the user's device of the generated teaching methods and training plans, using HTTP and WebSocket as communication protocols.

[1537] Input: Optimized teaching methods and training plans

[1538] Output: Instructions and training plans sent to the user's device

[1539] Specific operation: The server generates a notification message and sends an HTTP request to the IP address of the specified terminal. The user's terminal receives this notification and displays the content.

[1540] Step 8:

[1541] User reception and execution

[1542] The user receives a notification on their device, checks the analysis results and provides instructions, and then performs the training according to the instructions.

[1543] Input: Notification message from the server

[1544] Output: Training performed

[1545] Specific operation: After checking the notification on the device, the user performs actual training according to the displayed instruction method and training plan. The user's actions are again collected by the device's sensors and used in the next data collection phase.

[1546] (Application example 2)

[1547] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1548] While conventional sports coaching systems can collect and analyze athletes' movements and technical data in real time, they have difficulty providing coaching methods that take into account the emotional state of athletes and coaches. Furthermore, there is a lack of systems that collect movement data from factory workers to suggest efficient work procedures, or systems that recognize emotions and provide breaks and relaxation methods to reduce stress. This has made it difficult to provide optimal coaching to improve athletes' skills, increase worker efficiency, and reduce stress.

[1549] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1550] In this invention, the server includes a terminal including multiple sensors that collect player movement and technical data in real time, means for transmitting the data collected from the terminal to the server, means for storing the data received by the server in a database, an emotion engine that recognizes emotions by analyzing the user's facial expressions, voice, or biometric data, means for adjusting the content of the instruction method and the method of proposal based on the recognition results of the emotion engine, and means for notifying the user's terminal of the generated instruction method. This makes it possible to propose optimal instruction methods and work procedures that take into account the movements and emotional states of players and workers.

[1551] "Athlete" means an individual who performs an action or skill in a sport.

[1552] "Movement" refers to an object changing its position or posture.

[1553] "Technical data" means numerical or measured data relating to the actions performed by athletes or workers.

[1554] A "sensor" is a device that detects changes in the surrounding environment or objects.

[1555] A "terminal" is a device for collecting and processing data, including smart devices and IoT devices.

[1556] A "server" is a computing system that stores, processes, and serves data.

[1557] A "database" is a system for managing a structured collection of data.

[1558] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to analyze data and make predictions.

[1559] "Evaluation" is the process of determining the characteristics and capabilities of players or workers based on collected data.

[1560] "Instructional methods" refers to the suggestion of appropriate behaviors or training programs for specific goals or tasks.

[1561] "User" refers to an individual or organization that uses the system.

[1562] "Facial expressions" are part of a human interface that express emotions through the movement of facial muscles.

[1563] "Audio" means sound waves, including speech and ambient sounds.

[1564] "Biometric data" refers to various physiological information collected from the human body.

[1565] An "emotion engine" is a system for recognizing and analyzing a user's emotional state.

[1566] "Motion data" includes data relating to the movement of an object, such as position, velocity, and acceleration.

[1567] "Work procedure" means detailed steps or methods for efficiently performing a particular task.

[1568] "Relaxation" refers to activities or methods that relieve physical or mental tension.

[1569] This invention provides a system that starts with a terminal equipped with multiple sensors that collects player movement and technical data in real time. The terminal uses IoT devices such as smart clothing and smart gloves. These devices collect movement and technical data in real time and temporarily store it in memory.

[1570] The collected data is then sent via a communication protocol (e.g., HTTP or HTTPS) to a server, which stores the data in a database and is powered by a generative AI model using TensorFlow.

[1571] The generative AI model takes data from the database and analyzes movement patterns and skill levels. Specifically, it uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. The results are used to generate appropriate coaching methods.

[1572] Furthermore, an emotion engine is used to analyze the user's facial expressions, voice, and biometric data to recognize their emotional state. The emotion engine uses technologies such as EmotionAI. For example, it analyzes facial expressions from camera footage and determines the user's stress level from the tone of voice.

[1573] Based on the evaluation and emotion recognition results, the server generates optimal instruction methods and work procedures, including suggestions for relaxation exercises and breaks as needed. The generated instruction methods are sent to the user's device via a communication protocol. Notifications can be sent via a smartphone application or a dedicated device.

[1574] As a concrete example, consider a scenario in which a factory worker provides motion and emotional data. As the worker wears smart gloves and performs work, their motion data is collected in real time. Their facial expressions and tone of voice while working are also collected and analyzed by an emotion engine. This data is sent to a server, where a generative AI model evaluates work efficiency and generates instructional methods. If the worker is feeling stressed, the server also suggests relaxation exercises. These instructional methods are then notified to the worker's smartphone.

[1575] An example prompt is:

[1576] "sensor_data = {'temperature': 25.5, 'humidity': 60, 'acceleration': [0.2, 0.3, 0.4]}

[1577] emotion_data = {'emotion': 'stressed', 'confidence': 0.85}

[1578] prediction = analyze_data(sensor_data)

[1579] instructions = generate_instructions(prediction, emotion_data)

[1580] notify_user(instructions)

[1581] The above system makes it possible to propose optimal coaching methods and work procedures that take into account the movements and emotional state of athletes and workers.

[1582] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1583] Step 1:

[1584] The device collects the movement and technical data of athletes and workers, as well as biometric data, in real time. Specifically, smart clothing, smart gloves, or cameras are used to collect motion data (e.g., acceleration, posture data) and biometric data (e.g., heart rate, facial expression data). This data is temporarily stored in the device's memory.

[1585] Input: Real-time data from smart clothing and smart gloves

[1586] Output: Temporary storage of collected motion data and biometric data

[1587] Step 2:

[1588] The device sends the collected data to a server via an internet connection, where it is converted into an appropriate format (e.g., JSON or CSV) and securely transmitted using a communication protocol (e.g., HTTP or HTTPS).

[1589] Input: Collected data (e.g., acceleration data, facial expression data)

[1590] Output: Acknowledgement of completion of transmission to the server

[1591] Step 3:

[1592] The server stores the received data in a database, which manages the data in a structured format for efficient access and analysis.

[1593] Input: Transmitted data (e.g., motion data in JSON format, biometric data)

[1594] Output: Data stored in the database

[1595] Step 4:

[1596] The server retrieves data for each player or worker from the database and performs real-time analysis using a generative AI model. Machine learning algorithms (e.g., random forests, neural networks) are used to evaluate the characteristics and capabilities of each player or worker, specifically detecting movement patterns, skill levels, and imbalanced movements.

[1597] Input: Motion and biometric data retrieved from the database

[1598] Output: Analysis results (e.g., evaluation of movement patterns, determination of skill level)

[1599] Step 5:

[1600] The server uses an emotion engine to analyze the user's facial expressions, voice, and biometric data to recognize their emotional state. For example, it uses EmotionAI technology to assess whether the user is feeling stressed based on facial expression data.

[1601] Input: facial expression data and biometric data collected in real time

[1602] Output: Perceived emotional state (e.g., stressed, relaxed)

[1603] Step 6:

[1604] The server generates optimal teaching methods and work procedures based on the evaluation and emotion recognition results. The generated teaching methods may include specific training methods or relaxation exercises to reduce stress.

[1605] Input: Analysis results and emotion recognition results

[1606] Output: Generated instructional instructions or work instructions

[1607] Step 7:

[1608] The server generates training methods and work procedures and notifies the user's device. Notifications are sent via smartphone applications or dedicated devices. HTTP, WebSocket, and other communication protocols are used.

[1609] Input: Generated instructional methods or work procedures

[1610] Output: Notification to user's device completed

[1611] Step 8:

[1612] The user receives a notification on the device and checks the instruction method or work procedure. The user then performs the training or work according to the suggested method.

[1613] Input: Instruction method or work procedure notified to the terminal

[1614] Output: Training and work procedures reviewed and implemented

[1615] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1616] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1617] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1618] [Fourth embodiment]

[1619] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1620] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1621] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1622] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1623] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1624] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1625] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1626] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1627] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1628] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1629] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1630] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1631] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1632] The present invention relates to a system that collects player movement and technical data in real time, and automatically analyzes the data using a generation AI to propose coaching methods. The following configurations and operations are included as embodiments of the invention.

[1633] System configuration

[1634] 1. Terminal (IOT device)

[1635] It includes multiple sensors that collect player movement and technical data in real time, such as smart shoes, smart clothing, and smart balls.

[1636] 2. Data transmission method

[1637] Data collected from the devices is sent to a server via the internet using communication protocols such as HTTP, HTTPS, and MQTT.

[1638] 3. Server

[1639] The received data is saved in the database.

[1640] Generative AI is used to analyze data and evaluate each player's characteristics and abilities.

[1641] Based on the evaluation results, a coaching method appropriate for each player is generated.

[1642] 4. Means of notification

[1643] The generated training method is sent to the user's device, where the user can receive the notification and check the specific training method and training plan.

[1644] Program processing overview

[1645] Data collection

[1646] The device (for example, smart shoes) collects foot movement and load in real time while the athlete is running. The sensors collect highly accurate data and temporarily store it in memory.

[1647] Data transmission

[1648] The device sends the collected data to a server via an internet connection, where it is converted into an appropriate format (e.g., JSON) and sent using a communication protocol (e.g., HTTP).

[1649] Data storage

[1650] The server receives the data sent from the devices and stores it in a database, which is organized by player and used for later analysis.

[1651] Data analysis

[1652] The server retrieves data for each athlete from the database and begins analysis using generative AI. For example, it uses smart shoe data to evaluate Athlete A's running form and analyzes the load distribution and movement patterns of the feet.

[1653] Teaching method generation

[1654] Based on the analysis results, the generative AI generates the optimal coaching method for each athlete. For example, if it is determined that Athlete A's running form is imbalanced, it will suggest one-legged squats to train specific muscles.

[1655] Result notification

[1656] The training method generated by the server is sent to the user's (coach or player's) device. The notification includes the data analysis results and specific training methods. The user receives the notification and can check and implement the training methods on their device.

[1657] Specific examples

[1658] Example 1: Improving your running form

[1659] 1. Data Collection

[1660] The smart shoes collect Athlete A's running data (foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[1661] 2. Data Transmission

[1662] The data collected by the device is converted into JSON format and sent to a server via the Internet.

[1663] 3. Data storage

[1664] The server stores the received data in a database.

[1665] 4. Data Analysis

[1666] The server analyzes the stored data using generated AI and discovers an imbalanced load distribution in Athlete A's running form.

[1667] 5. Generating Instructional Methods

[1668] Based on the generated AI, the server suggests specific muscle training exercises to Player A, including single-leg squats.

[1669] 6. Result notification

[1670] The server generates a training method and notifies the device of Player A. Player A checks the notification and starts the recommended training.

[1671] Example 2: Improving shooting technique

[1672] 1. Data Collection

[1673] The smart ball collects shot data (angle, power, distance) from Player B. The sensors also measure wrist movement and ball rotation.

[1674] 2. Data Transmission

[1675] The data collected by the terminal is converted into XML format and sent to the server via the HTTPS protocol.

[1676] 3. Data storage

[1677] The server stores the received data in a database.

[1678] 4. Data Analysis

[1679] The server analyzes the saved data using a generative AI and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[1680] 5. Generating Instructional Methods

[1681] Based on the generated AI, the server suggests exercises to Player B to improve wrist flexibility and repeated shooting practice.

[1682] 6. Result notification

[1683] The server generates a training method and notifies the device of Player B. Player B checks the notification and performs the recommended exercises and training.

[1684] The above is one embodiment of the present invention, which can provide high-quality individual instruction and significantly reduce the burden on instructors.

[1685] The processing flow will be explained below.

[1686] Step 1:

[1687] The terminal begins operation. Specifically, IoT devices such as smart shoes and smart clothing collect player movement and technical data in real time. For example, in the case of smart shoes, pressure sensors and acceleration sensors measure foot movement and load.

[1688] Step 2:

[1689] The device temporarily stores the collected data. For example, the collected data is stored in the memory inside the smart shoes. During this process, the raw data is converted into an appropriate format (for example, JSON or CSV).

[1690] Step 3:

[1691] The device sends data to the server via an internet connection, using communication protocols such as HTTP, HTTPS, and MQTT. The data is encrypted before transmission to ensure security.

[1692] Step 4:

[1693] The server receives the data sent from the device, which is usually temporarily stored in a buffer or queue.

[1694] Step 5:

[1695] The server stores the received data in a database. The database organizes data by player and stores it in an easy-to-search format. For example, related data can be linked using a player ID as a key.

[1696] Step 6:

[1697] The server retrieves data for each player from the database, and the data is cleaned and normalized as preprocessing for data analysis, such as removing outliers and filling in missing data.

[1698] Step 7:

[1699] The server analyzes the stored data using a generation AI. The generation AI uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. For example, it analyzes foot load distribution and movement patterns from running data.

[1700] Step 8:

[1701] The server uses generative AI to generate specific training methods for each player, for example, suggesting one-leg squat training for a player with uneven leg load distribution.

[1702] Step 9:

[1703] The server sends the generated teaching methods to the user's device using communication protocols such as HTTP or WebSocket. The notification includes analysis results and training suggestions.

[1704] Step 10:

[1705] The user (coach or player) receives a notification on their device and checks the analysis results and coaching methods. For example, a player checks the recommended training method and implements it as recommended.

[1706] Through these steps, the system of the present invention can provide optimal instruction tailored to the characteristics of each player, significantly reducing the burden on the instructor.

[1707] Example 1

[1708] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1709] With conventional coaching methods, it is difficult to accurately grasp the characteristics and abilities of each player, making it difficult to provide efficient training methods. Furthermore, because data is not collected and analyzed in real time, it is not possible to provide appropriate feedback quickly. This has resulted in the problem of it taking a long time for players to improve their technique and form.

[1710] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1711] In this invention, the server includes a terminal including a plurality of sensors that collect player movement and technique data in real time, means for transmitting the data collected from the terminal to the server, means for the server to store the received data in a database, means for the server to analyze the stored data using a generation AI and evaluate the characteristics and abilities of each player, means for the server to generate a coaching method suitable for each player based on the evaluation results using the generation AI, and means for notifying the user's terminal of the generated coaching method and the results of data analysis. This makes it possible to provide appropriate coaching methods based on the characteristics and abilities of each player in real time, enabling efficient training.

[1712] A "terminal" is a device containing multiple sensors that collects player movement and technical data in real time.

[1713] The "server" is a central processing unit that receives and stores data sent from the terminal, analyzes and evaluates it using generation AI, and generates teaching methods based on the results.

[1714] A "sensor" is a device that measures and collects data on the movements and techniques performed by athletes in real time.

[1715] "Database" means a data management system that stores received data in an organized manner and makes it available for later analysis and evaluation.

[1716] "Generative AI" is an artificial intelligence technology that analyzes collected data, evaluates the characteristics and abilities of each player, and generates optimal coaching methods.

[1717] "Data transmission means" refers to a means including communication protocols and techniques for transmitting data collected by a terminal to a server.

[1718] The "data storage means" is a means for storing data received by the server in a database.

[1719] The "data analysis method" is a method for analyzing data stored in a database using generative AI to evaluate the characteristics and abilities of each player.

[1720] The "training method generation means" is a means for generating a training method suitable for each player based on the evaluation results by the generation AI.

[1721] The "notification means" is a means for notifying the user's terminal of the generated teaching method and the results of the data analysis.

[1722] This invention is a system that collects player movement and technical data in real time, and automatically analyzes it using a generation AI to propose coaching methods. This system is composed of a terminal, a data transmission means, a server, a data storage means, a data analysis means, a coaching method generation means, and a notification means.

[1723] System configuration

[1724] 1. Terminal (IOT device)

[1725] The devices include multiple sensors that collect player movement and technical data in real time. Examples include smart shoes, smart clothing, and smart balls. These devices are equipped with acceleration sensors, pressure sensors, and other sensors to collect highly accurate data.

[1726] 2. Data transmission method

[1727] The data collected by the device is sent to a server via the internet using a communication protocol such as HTTP, HTTPS, or MQTT, and the data is converted into an appropriate format such as JSON.

[1728] 3. Server

[1729] The server receives the data sent from the devices and stores it in a database. It also uses a generation AI to analyze the received data and evaluate the characteristics and abilities of each player. The server has the function of generating individual coaching methods based on the results of the data analysis.

[1730] 4. Data storage method

[1731] The data received by the server is stored in a database, organized by player, and used for later analysis.

[1732] 5. Data Analysis Methods

[1733] The server retrieves the data of a specific player from the database and begins analysis using the generation AI, which analyzes the stored data and evaluates the player's characteristics such as running form, throwing motion, and shooting technique.

[1734] 6. Instruction method generation means

[1735] The server generates the optimal coaching method for each player based on the evaluation results obtained by the AI ​​generation. The generated coaching method is provided as a specific training menu or exercise.

[1736] 7. Means of notification

[1737] The server then sends the generated training method and data analysis results to the user's device. The notification contains detailed information about the analysis results and training method. The user can then receive the notification and implement the specific training plan.

[1738] Specific examples

[1739] Example 1: Improving your running form

[1740] 1. Data Collection

[1741] The smart shoes collect Athlete A's running data (foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[1742] 2. Data Transmission

[1743] The data collected by the device is converted into JSON format and sent to a server via the Internet.

[1744] 3. Data storage

[1745] The server stores the received data in a database.

[1746] 4. Data Analysis

[1747] The server analyzes the stored data using generated AI and discovers an imbalanced load distribution in Athlete A's running form.

[1748] 5. Generating Instructional Methods

[1749] Based on the generated AI, the server suggests specific muscle training exercises to Player A, including single-leg squats.

[1750] 6. Result notification

[1751] The server generates a training method and notifies the device of Player A. Player A checks the notification and starts the recommended training.

[1752] Example 2: Improving shooting technique

[1753] 1. Data Collection

[1754] The smart ball collects shot data (angle, power, distance) from Player B. The sensors also measure wrist movement and ball rotation.

[1755] 2. Data Transmission

[1756] The data collected by the terminal is converted into XML format and sent to the server via the HTTPS protocol.

[1757] 3. Data storage

[1758] The server stores the received data in a database.

[1759] 4. Data Analysis

[1760] The server analyzes the saved data using a generative AI and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[1761] 5. Generating Instructional Methods

[1762] Based on the generated AI, the server suggests exercises to Player B to improve wrist flexibility and repeated shooting practice.

[1763] 6. Result notification

[1764] The server generates a training method and notifies the device of Player B. Player B checks the notification and performs the recommended exercises and training.

[1765] Example of input prompt for generative AI model

[1766] "Please analyze Athlete A's running form and suggest an appropriate training method."

[1767] "What exercises can Player B do to improve his shooting technique?"

[1768] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1769] Step 1:

[1770] Data collection

[1771] The device collects the player's movements and technical data in real time. Specifically, the acceleration and pressure sensors in the smart shoes measure the player's stride length, speed, foot contact time, and pressure when stepping on the ball. The player's movements are input, and measurement data is generated as output. This data is temporarily stored in the device's memory.

[1772] Specific actions

[1773] When the athlete starts running, sensors in the smart shoes collect data and temporarily store it in the device's memory.

[1774] Step 2:

[1775] Data transmission

[1776] The data collected by the device is converted into JSON format and sent to a server via the Internet. The HTTP protocol is used for communication. The input is the measurement data stored in the device, and the output is the JSON data sent to the server.

[1777] Specific actions

[1778] The device's microcontroller converts the measurement data into JSON format, and the Wi-Fi module transmits this data to a server over the Internet.

[1779] Step 3:

[1780] Data storage

[1781] The server receives the data sent from the device and stores it in a database. The input is JSON data that arrives at the server, and the output is structured data stored in the database.

[1782] Specific actions

[1783] The server receives the HTTP request, parses the JSON data, and inserts it into a database, organized by player.

[1784] Step 4:

[1785] Data analysis

[1786] The server retrieves the data of a specific player from the database and begins analysis using the generative AI. The input is the measurement data stored in the database, and the output is an evaluation of the player's characteristics and abilities.

[1787] Specific actions

[1788] The server executes a scheduled job, querying the database for the latest data on the specified athlete, and inputs the acquired data into a generative AI model to analyze running form and evaluate foot load distribution.

[1789] Step 5:

[1790] Teaching method generation

[1791] The server generates the optimal coaching method for each player based on the evaluation results obtained by the generation AI. The input is the evaluation results from the generation AI, and the output is a specific coaching method and training menu.

[1792] Specific actions

[1793] A generative AI compiles the analysis results and generates training plans (e.g., single-leg squats) that address specific problems. These plans are formatted in text format.

[1794] Step 6:

[1795] Result notification

[1796] The server notifies the user's device of the generated teaching method and the results of the data analysis. The input is the generated teaching plan, and the output is a notification message displayed on the user's device.

[1797] Users receive notifications and receive specific training instructions.

[1798] Specific actions

[1799] The server generates a notification message and sends it to the user's device as a push notification, which the user can receive and view detailed instruction methods.

[1800] (Application example 1)

[1801] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1802] The problem that this invention aims to solve is to provide optimal training methods for individual athletes by collecting player movement and technical data in real time, and automatically analyzing and proposing coaching methods using generation AI based on that data. Also, the problem that this invention aims to solve is to improve operational efficiency and reduce maintenance costs by monitoring operational data of industrial automation equipment used in factories in real time, automatically detecting abnormalities and inefficient operations, and proposing optimal operation and maintenance methods.

[1803] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1804] In this invention, the server includes a terminal including multiple sensors that collect player movement and technical data in real time, a means for transmitting the data collected from the terminal to the server, a means for storing the received data in a database, a means for analyzing the stored data using a generation AI to evaluate the characteristics and abilities of each player, a means for the server to generate a coaching method suitable for each player based on the evaluation results using the generation AI, a means for notifying the user of the generated coaching method, a means for generating motion patterns for detecting abnormalities and optimizing the operation of industrial automation equipment based on the data analysis results by the generation AI, and a means for using the generated motion patterns to maintain or optimize the operation of the industrial automation equipment. This makes it possible to provide the optimal coaching method for each player, detect abnormalities in industrial automation equipment in factories, and propose optimal maintenance methods.

[1805] An "athlete" is an individual who participates in a sport or competition and trains its skills and movements.

[1806] "Motion and technical data" refers to numbers and information related to the operation and performance of athletes and industrial automation equipment.

[1807] "Real-time" refers to processing and data collection occurring at the exact moment an event occurs.

[1808] A "sensor" is a device that detects physical movements or changes in the environment and outputs them as electrical signals.

[1809] A "terminal" is a device that includes sensors and is a device that collects and transmits data.

[1810] A "server" is a computer system that stores and processes data over a network.

[1811] "Generative AI" is an artificial intelligence technology that analyzes collected data and automatically creates optimal teaching methods and movement patterns based on the results.

[1812] A "database" is a system for efficiently storing and managing structured data.

[1813] "User" refers to a coach, player, or factory manager who uses the system.

[1814] "Industrial automation equipment" refers to machinery and robots used to automate manufacturing processes.

[1815] "Maintenance" refers to inspection and repair activities performed to keep equipment or systems in working order.

[1816] "Operational optimization" refers to activities that optimize operational methods to maximize the performance of equipment and systems.

[1817] System Configuration

[1818] This invention is a system that collects player movement and technical data in real time, and automatically analyzes it using a generation AI to propose coaching methods. It also monitors the operation data of industrial automation equipment in real time, generates operation patterns for abnormalities and optimization, and supports maintenance and operational optimization.

[1819] Hardware

[1820] 1. Terminal (IOT device)

[1821] These devices are equipped with multiple sensors and collect player movement and technical data in real time. Examples include smart shoes, smart clothing, and smart balls.

[1822] In the case of industrial automation equipment, it is a sensor that detects the operation of robot arms, processing equipment, etc.

[1823] 2. Server

[1824] This is a computer system that stores and analyzes data. Collected data is stored, analyzed using AI, and results are generated and notified.

[1825] 3. User Device

[1826] A device such as a smartphone or head-mounted display (HMD) through which the user receives analysis results and instructional methods.

[1827] software

[1828] 1. Generative AI Models

[1829] It is an artificial intelligence that analyzes collected data and automatically generates optimal teaching methods and movement patterns based on the results.

[1830] 2. Data transmission method

[1831] This software allows the device to send collected data to a server via an internet connection, using communication protocols such as HTTP, HTTPS, and MQTT.

[1832] 3. Database

[1833] It is a system that runs on a server and stores and manages received data.

[1834] 4. Means of notification

[1835] This software notifies the user's device of the teaching methods and behavior patterns generated by the server. Examples include push notifications and email notifications.

[1836] Overview of program processing

[1837] The terminal uses sensors installed in the device to collect real-time movement and technical data from athletes and industrial automation equipment. For example, when collecting an athlete's running data using smart shoes, the sensors measure stride length, speed, foot contact time, etc. The collected data is then converted into JSON format and sent to a server via the HTTP protocol. Similarly, motion data from industrial automation equipment is collected by sensors and sent to a server.

[1838] The server stores the received data in a database and uses generative AI to analyze the data and evaluate the characteristics and capabilities of each athlete and piece of equipment. For example, if the generative AI detects an uneven load distribution in an athlete's running form, it will suggest one-legged squats to train specific muscles. Similarly, it analyzes the movement data of a robotic arm to detect abnormal or inefficient movements, identify the cause, and suggest appropriate adjustments or maintenance methods.

[1839] The generated training methods and operation patterns are sent from the server to the user's device, where the user receives the notification and confirms and carries out the specific training methods and maintenance methods via their smartphone or HMD.

[1840] Examples of specific examples and prompts

[1841] Example 1: Improving your running form

[1842] 1. Smart shoes collect Athlete A's running data (foot movement, load) in real time.

[1843] 2. The device converts the collected data into JSON format and sends it to a server via the Internet.

[1844] 3. The server stores the data, and the generative AI analyzes your running form and detects imbalanced load distribution.

[1845] 4. The generative AI suggests specific muscle training exercises, including single-leg squats, and notifies Athlete A's device.

[1846] Example 2: Optimizing the operation of industrial automation equipment

[1847] 1. Sensors collect real-time motion data (angle, force, speed) from the robot arm.

[1848] 2. The device converts the collected data into JSON format and sends it to a server via the Internet.

[1849] 3. The server stores the data, and the generating AI analyzes the operational data to detect abnormalities and operational patterns for optimization.

[1850] 4. The generative AI proposes optimal maintenance methods and operation patterns and notifies the administrator's device.

[1851] Prompt Sentence Examples

[1852] An example of a prompt sentence to input to the generative AI model is as follows:

[1853] Analyze the robot arm's motion data and check the following:

[1854] Ingres' deviation from the standard

[1855] Abnormal operating speed

[1856] Excessive use of force

[1857] If any of these abnormalities occur, please suggest the cause and appropriate maintenance methods.

[1858] By following the above procedure, it is possible to develop a specific application of the present invention to a factory robot.

[1859] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1860] Step 1:

[1861] The device uses multiple sensors to collect real-time data on player movements and techniques. Specifically, smart shoes measure stride length, speed, and foot contact time. For industrial automation equipment, it collects motion data such as the angle, force, and speed of a robotic arm. The input is physical data from the sensors, and the output is a digital representation of the data.

[1862] Step 2:

[1863] The terminal sends the collected data to a server via the Internet. At this time, the collected data is converted into JSON format and sent using a communication protocol (e.g., HTTP). The input is the digital data collected in the previous step, and the output is the data to be sent to the server.

[1864] Step 3:

[1865] The server stores the received data in a database. A database management system (DBMS) is used to protect the data from loss and store it in a structured format. The input is the data sent to the server and the output is a new record added to the database.

[1866] Step 4:

[1867] The server retrieves the stored data from the database and analyzes the data using a generative AI model. A specific example is analyzing running data to detect imbalanced load distribution in an athlete's running form. The input is the data retrieved from the database, and the output is the analysis result. An example of data processing is applying a machine learning algorithm to cluster the data.

[1868] Step 5:

[1869] The server generates optimal training methods and movement patterns for each athlete and equipment based on the analysis results of the generative AI model. For example, if a running form is imbalanced, it will suggest single-leg squats to train specific muscles. The input is the analysis results, and the output is the generated training methods and movement patterns. Here, the generative AI model operates based on prompt statements.

[1870] Step 6:

[1871] The server notifies the user's device of the generated teaching methods and behavior patterns. Possible notification methods include push notifications and email notifications. The input is the generated teaching methods and behavior patterns, and the output is a notification message sent to the user's device.

[1872] Step 7:

[1873] The user receives a notification and checks the instruction method or operation procedure via a smartphone or head-mounted display (HMD). The user follows the notification to perform the specific instruction method or maintenance procedure. The input is the notification message, and the output is the user's action.

[1874] Through the above steps, training methods for athletes and operational optimization of industrial automation equipment are realized.

[1875] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1876] The present invention combines a system that collects player movement and technical data in real time, automatically analyzes it using a generation AI, and proposes coaching methods, with an emotion engine that recognizes the user's emotions. The following configurations and operations are included as modes for carrying out the invention.

[1877] System configuration

[1878] 1. Terminal (IOT device)

[1879] It includes multiple sensors that collect player movement and technical data in real time, such as smart shoes, smart clothing, and smart balls.

[1880] 2. Data transmission method

[1881] Data collected from the devices is sent to a server via the internet using communication protocols such as HTTP, HTTPS, and MQTT.

[1882] 3. Server

[1883] The received data is saved in the database.

[1884] Generative AI is used to analyze data and evaluate each player's characteristics and abilities.

[1885] Based on the evaluation results, a coaching method appropriate for each player is generated.

[1886] 4. Emotion Engine

[1887] The emotion engine is a system for recognizing the emotions of users (players and coaches). The emotion engine recognizes emotions by analyzing facial expressions, tone of voice, or biometric data.

[1888] 5. Means of notification

[1889] The generated training method is sent to the user's device, where the user can receive the notification and check the specific training method and training plan.

[1890] 6. Adjustment means

[1891] Based on the user's emotional data, the server adjusts the content of the instruction method and the method of suggestions.

[1892] Program processing overview

[1893] Data collection

[1894] The device (for example, smart shoes) collects foot movement and load in real time while the athlete is exercising. The sensor collects highly accurate data and temporarily stores it in memory.

[1895] Data transmission

[1896] The device temporarily stores the collected data and transmits it to a server via an internet connection, where it is converted into an appropriate format (e.g., JSON or CSV) and transmitted using a communication protocol (e.g., HTTP).

[1897] Data storage

[1898] The server receives the data sent from the devices and stores it in a database, which is organized by player and used for later analysis.

[1899] Data analysis

[1900] The server retrieves data for each player from the database and begins analysis using the Generative AI. The Generative AI uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. For example, it analyzes foot load distribution and movement patterns from running data.

[1901] emotion recognition

[1902] The emotion engine collects the user's facial expression, voice, or biometric data in real time to recognize emotions. For example, it captures the user's facial expression with a camera and uses image analysis technology to determine whether they are smiling.

[1903] Teaching method generation

[1904] Based on the analysis results, the generative AI generates the optimal training method for each player. For example, it will suggest single-leg squat training for a player with an imbalanced leg load distribution. Furthermore, it will adjust the training plan based on feedback from the emotion engine. For example, if the user is feeling stressed, it will add relaxation exercises to relieve stress.

[1905] Result notification

[1906] The server generates training methods and sends them to the user's device. HTTP or WebSocket is used as the communication protocol. The notification includes the results of the data analysis and training suggestions.

[1907] User reception and execution

[1908] The user (coach or player) receives a notification on their device and checks the analysis results and coaching methods. For example, the player checks the recommended training method and implements it as recommended.

[1909] Specific examples

[1910] Example 1: Improving your running form

[1911] 1. Data Collection

[1912] The smart shoes collect Athlete A's running data (foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[1913] 2. Data Transmission

[1914] The data collected by the device is converted into JSON format and sent to a server via the Internet.

[1915] 3. Data storage

[1916] The server stores the received data in a database.

[1917] 4. Data Analysis

[1918] The server analyzes the stored data using generated AI and discovers an imbalanced load distribution in Athlete A's running form.

[1919] 5. Emotion recognition

[1920] The emotion engine collects facial expression data from Athlete A and recognizes his / her emotional state during exercise. For example, it determines that Athlete A looks tired.

[1921] 6. Generating Instructional Methods

[1922] Based on the generative AI, the server suggests specific muscle training exercises, including one-legged squats, to Player A. Additionally, it adds relaxation exercises based on feedback from the emotion engine.

[1923] 7. Result notification

[1924] The server generates a training method and notifies the device of Player A. Player A checks the notification and starts the recommended training.

[1925] Example 2: Improving shooting technique

[1926] 1. Data Collection

[1927] The smart ball collects shot data (angle, power, distance) from Player B. The sensors also measure wrist movement and ball rotation.

[1928] 2. Data Transmission

[1929] The data collected by the terminal is converted into XML format and sent to the server via the HTTPS protocol.

[1930] 3. Data storage

[1931] The server stores the received data in a database.

[1932] 4. Data Analysis

[1933] The server analyzes the saved data using a generative AI and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[1934] 5. Emotion recognition

[1935] The emotion engine analyzes Player B's tone of voice in real time to recognize his emotions, for example, determining whether he is relaxed or nervous.

[1936] 6. Generating Instructional Methods

[1937] Based on the generated AI, the server suggests wrist flexibility exercises and repeated shooting practice for Player B. Based on the emotional data, if Player B is nervous, it also adds relaxation techniques.

[1938] 7. Result notification

[1939] The server generates a training method and notifies the device of Player B. Player B checks the notification and performs wrist exercises and shooting practice.

[1940] The above is one embodiment of the present invention, which allows high-quality individual instruction to be provided, and also makes it possible to provide optimal instruction according to the emotional state of the player and coach.

[1941] The processing flow will be explained below.

[1942] Step 1:

[1943] The terminal begins operation. Specifically, IoT devices such as smart shoes and smart clothing collect player movement and technical data in real time. For example, in the case of smart shoes, pressure sensors and acceleration sensors measure foot movement and load.

[1944] Step 2:

[1945] The device temporarily stores the collected data. For example, the collected data is stored in the memory inside the smart shoes. During this process, the raw data is converted into an appropriate format (for example, JSON or CSV).

[1946] Step 3:

[1947] The device sends data to the server via an internet connection, using communication protocols such as HTTP, HTTPS, and MQTT. The data is encrypted before transmission to ensure security.

[1948] Step 4:

[1949] The server receives the data sent from the device, which is usually temporarily stored in a buffer or queue.

[1950] Step 5:

[1951] The server stores the received data in a database. The database organizes data by player and stores it in an easy-to-search format. For example, related data can be linked using a player ID as a key.

[1952] Step 6:

[1953] The server retrieves data for each player from the database, and the data is cleaned and normalized as preprocessing for data analysis, such as removing outliers and filling in missing data.

[1954] Step 7:

[1955] The server analyzes the stored data using a generation AI. The generation AI uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. For example, it analyzes foot load distribution and movement patterns from running data.

[1956] Step 8:

[1957] The emotion engine collects the user's facial expression, voice, or biometric data in real time to recognize emotions. For example, it captures the user's facial expression with a camera and uses image analysis technology to determine whether they are smiling.

[1958] Step 9:

[1959] The server receives data from the emotion engine and combines it with the analysis results of the generative AI to generate specific coaching methods for each player. For example, if a player has an imbalanced load distribution on their legs, it will suggest single-leg squat training, and if they are feeling stressed, it will add relaxation exercises.

[1960] Step 10:

[1961] The server then sends the generated training method to the user's device using a communication protocol such as HTTP or WebSocket. The notification includes the results of the data analysis and training suggestions.

[1962] Step 11:

[1963] The user (coach or player) receives a notification on their device and checks the analysis results and coaching methods. For example, a player checks the recommended training method and implements it as recommended.

[1964] Through these steps, the system of the present invention can provide optimal instruction tailored to the characteristics of each player, significantly reducing the burden on the coach. In addition, the introduction of an emotion engine enables detailed feedback tailored to the user's emotional state.

[1965] Example 2

[1966] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1967] In modern sports coaching, it is extremely important to collect real-time data on athletes' movements and techniques and provide appropriate instruction based on that data. However, currently, the entire process of data collection, analysis, and the creation of coaching methods requires a lot of manual work, making efficient training instruction difficult. Furthermore, the emotional state of athletes and coaches also has a significant impact on training effectiveness, but there are few systems that take this into account. The purpose of this project is to solve these issues.

[1968] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a terminal including multiple sensors that collect player movement and technique data in real time, means for transmitting the data collected from the terminal to the server via the Internet, means for storing the data received by the server in a database, means for analyzing the stored data by using a generation AI and evaluating the characteristics and abilities of each player, means for the server to generate a coaching method suitable for each player based on the evaluation results using the generation AI, means including an emotion engine that recognizes emotions by analyzing the user's facial expression, tone of voice, or biometric data, and means for adjusting the generated coaching method based on the recognized emotion data and notifying the user's terminal. This makes it possible to comprehensively improve player performance based on both scientific and emotional factors.

[1969] A "terminal" is a device containing multiple sensors that collects player movement and technical data in real time.

[1970] The "Internet" is a network infrastructure that allows information to be exchanged around the world.

[1971] A "server" is a computer system that receives, stores, and analyzes data sent from a terminal.

[1972] A "database" is a system for organizing and storing data received by a server.

[1973] "Generative AI" is an artificial intelligence system that uses machine learning algorithms to analyze data and evaluate each player's characteristics and abilities.

[1974] An "emotion engine" is a system that recognizes emotions by analyzing a user's facial expressions, tone of voice, or biometric data.

[1975] A "user terminal" is a device that receives and displays the generated teaching methods and analysis results.

[1976] "Instruction method" refers to the training plan and exercises that the generative AI will instruct each player on based on the analysis results.

[1977] This invention combines a system that collects player movement and technical data in real time, automatically analyzes it using a generation AI, and proposes coaching methods, with an emotion engine that recognizes the user's emotions. The system configuration and operation are as follows.

[1978] System configuration

[1979] 1. Terminal (IOT device)

[1980] Examples include smart shoes, smart clothing, smart balls, etc. These devices contain numerous sensors to collect player movement and technical data in real time.

[1981] 2. Data transmission method

[1982] The collected data is sent to a server via the internet using communication protocols such as HTTP, HTTPS, and MQTT.

[1983] 3. Server

[1984] The server stores the received data in a database, which can be, for example, MySQL or MongoDB.

[1985] The server analyzes the data using a generative AI, which uses machine learning algorithms (e.g., random forests and neural networks) to evaluate players' characteristics and abilities.

[1986] Based on the evaluation results, a coaching method appropriate for each player is generated.

[1987] 4. Emotion Engine

[1988] The emotion engine is a system that recognizes the emotions of users (players and coaches). For example, it uses a camera to capture facial expressions and uses image analysis technology to determine emotions. It also has the ability to analyze voice tone using audio analysis to recognize emotions.

[1989] 5. Means of notification

[1990] The generated teaching method is sent from the server to the user's device using HTTP or WebSocket as the communication protocol.

[1991] 6. Adjustment means

[1992] Based on the recognized emotion data, the server adjusts the content of the instruction method and the method of suggestions.

[1993] Specific examples

[1994] Example 1: Improving your running form

[1995] 1. Data Collection

[1996] The smart shoes collect Athlete A's running data (e.g., foot movement, load) in real time. The sensors measure stride length, speed, foot contact time, etc.

[1997] 2. Data Transmission

[1998] The collected data is converted into JSON format and sent to the server via the HTTP protocol.

[1999] 3. Data storage

[2000] The server stores the received data in a database.

[2001] 4. Data Analysis

[2002] The generative AI analyzes the saved data and discovers an imbalanced load distribution in Athlete A's running form.

[2003] 5. Emotion recognition

[2004] The emotion engine collects facial expression data of Athlete A and checks his emotional state during exercise. For example, it determines that Athlete A looks tired.

[2005] 6. Generating Instructional Methods

[2006] The generative AI suggests specific strength exercises, including single-leg squats, and also adds relaxation exercises based on feedback from the emotion engine.

[2007] 7. Result notification

[2008] A training method is generated and notified to the device of Player A. Player A checks the notification and starts the recommended training.

[2009] Example 2: Improving shooting technique

[2010] 1. Data Collection

[2011] The smart ball collects shot data (e.g., angle, power, and distance) from Player B. The sensors also measure wrist movement and ball rotation.

[2012] 2. Data Transmission

[2013] The collected data is converted into XML format and sent to the server via the HTTPS protocol.

[2014] 3. Data storage

[2015] The server stores the received data in a database.

[2016] 4. Data Analysis

[2017] The generative AI analyzes the saved data and discovers that there is a problem with the balance of angle and force in Player B's shooting motion.

[2018] 5. Emotion recognition

[2019] The emotion engine analyzes Player B's tone of voice in real time to recognize his emotions, for example, determining whether he is relaxed or nervous.

[2020] 6. Generating Instructional Methods

[2021] The generative AI suggests wrist flexibility exercises and repeated shooting practice. Based on emotional data, if Player B is nervous, it will also add relaxation techniques.

[2022] 7. Result notification

[2023] A training method is generated and notified to the device of Player B. Player B checks the notification and performs wrist exercises and shooting practice.

[2024] Prompt Sentence Examples

[2025] Here is an example of a prompt to input to a generative AI model:

[2026] "Please suggest a training method to improve Athlete A's running form. Athlete A has an uneven load distribution on his feet. He also looks tired during exercise."

[2027] Using this prompt, the generative AI model can generate appropriate teaching methods and follow-up suggestions based on emotion.

[2028] As a result, the present invention provides a system for scientifically and comprehensively improving the performance of athletes.

[2029] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2030] Step 1:

[2031] Data collection

[2032] The devices (e.g., smart shoes, smart clothing, smart balls) collect data on players' movements and techniques in real time. Specifically, sensors collect data such as the player's stride length, speed, foot contact time, load, shot angle, power, and distance, and temporarily store this data in the device's memory.

[2033] Input: Player movements and technical data

[2034] Output: Temporarily saved data in the device memory

[2035] Example: When an athlete starts running, the sensors in the smart shoes are automatically activated and the collected data is written to memory.

[2036] Step 2:

[2037] Data transmission

[2038] The device converts the collected data into an appropriate format (e.g., JSON format) and sends it to a server via an internet connection using HTTP or HTTPS as the communication protocol. The data is sent in real time or at regular intervals.

[2039] Input: Temporarily saved data in the device memory

[2040] Output: Data sent to the server

[2041] Specific operation: The device sends the collected data in streaming format as a POST request to the specified server URL via Wi-Fi or mobile network.

[2042] Step 3:

[2043] Data storage

[2044] The server receives the data sent from the devices and stores it securely in a database, organizing it by player and indexing it for easy retrieval later.

[2045] Input: Data sent to the server

[2046] Output: Data stored in the database

[2047] What happens: A server endpoint receives the data and the program inserts it into a database, often MySQL or MongoDB.

[2048] Step 4:

[2049] Data analysis

[2050] The server retrieves data for each player from the database and analyzes it using a generative AI, which uses machine learning algorithms (e.g., random forests, neural networks) to evaluate the player's characteristics and abilities.

[2051] Input: Player data stored in the database

[2052] Output: Analysis results (player characteristics and ability evaluation)

[2053] Specific operation: The server periodically performs batch processing and streaming processing, inputting athlete data into the generative AI model for analysis. For example, it analyzes foot load distribution and movement patterns based on running data, and re-stores the results in the database.

[2054] Step 5:

[2055] emotion recognition

[2056] The emotion engine collects the user's facial expressions, tone of voice, biometric data, etc. in real time to recognize emotions. Specifically, it analyzes facial expression data captured by a camera and voice data to determine emotions.

[2057] Input: User facial expression data and voice data collected by camera and microphone

[2058] Output: Analysis results (user's emotional state)

[2059] Specific operation: Image data captured by the camera is input into a deep learning model to recognize the user's emotions. Voice data collected by the microphone is also recognized using voice analysis technology.

[2060] Step 6:

[2061] Teaching method generation

[2062] The server generates the optimal coaching method for each player based on the analysis results of the generative AI, and further adjusts the training plan based on feedback from the emotion engine.

[2063] Input: Analysis results and emotional state

[2064] Output: Optimized teaching methods and training plans

[2065] Specific movements: The generative AI combines running data and other exercise data with emotion recognition results to automatically generate training methods tailored to the athlete, such as one-legged squats and relaxation exercises.

[2066] Step 7:

[2067] Result notification

[2068] The server notifies the user's device of the generated teaching methods and training plans, using HTTP and WebSocket as communication protocols.

[2069] Input: Optimized teaching methods and training plans

[2070] Output: Instructions and training plans sent to the user's device

[2071] Specific operation: The server generates a notification message and sends an HTTP request to the IP address of the specified terminal. The user's terminal receives this notification and displays the content.

[2072] Step 8:

[2073] User reception and execution

[2074] The user receives a notification on their device, checks the analysis results and provides instructions, and then performs the training according to the instructions.

[2075] Input: Notification message from the server

[2076] Output: Training performed

[2077] Specific operation: After checking the notification on the device, the user performs actual training according to the displayed instruction method and training plan. The user's actions are again collected by the device's sensors and used in the next data collection phase.

[2078] (Application example 2)

[2079] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2080] While conventional sports coaching systems can collect and analyze athletes' movements and technical data in real time, they have difficulty providing coaching methods that take into account the emotional state of athletes and coaches. Furthermore, there is a lack of systems that collect movement data from factory workers to suggest efficient work procedures, or systems that recognize emotions and provide breaks and relaxation methods to reduce stress. This has made it difficult to provide optimal coaching to improve athletes' skills, increase worker efficiency, and reduce stress.

[2081] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2082] In this invention, the server includes a terminal including multiple sensors that collect player movement and technical data in real time, means for transmitting the data collected from the terminal to the server, means for storing the data received by the server in a database, an emotion engine that recognizes emotions by analyzing the user's facial expressions, voice, or biometric data, means for adjusting the content of the instruction method and the method of proposal based on the recognition results of the emotion engine, and means for notifying the user's terminal of the generated instruction method. This makes it possible to propose optimal instruction methods and work procedures that take into account the movements and emotional states of players and workers.

[2083] "Athlete" means an individual who performs an action or skill in a sport.

[2084] "Movement" refers to an object changing its position or posture.

[2085] "Technical data" means numerical or measured data relating to the actions performed by athletes or workers.

[2086] A "sensor" is a device that detects changes in the surrounding environment or objects.

[2087] A "terminal" is a device for collecting and processing data, including smart devices and IoT devices.

[2088] A "server" is a computing system that stores, processes, and serves data.

[2089] A "database" is a system for managing a structured collection of data.

[2090] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to analyze data and make predictions.

[2091] "Evaluation" is the process of determining the characteristics and capabilities of players or workers based on collected data.

[2092] "Instructional methods" refers to the suggestion of appropriate behaviors or training programs for specific goals or tasks.

[2093] "User" refers to an individual or organization that uses the system.

[2094] "Facial expressions" are part of a human interface that express emotions through the movement of facial muscles.

[2095] "Audio" means sound waves, including speech and ambient sounds.

[2096] "Biometric data" refers to various physiological information collected from the human body.

[2097] An "emotion engine" is a system for recognizing and analyzing a user's emotional state.

[2098] "Motion data" includes data relating to the movement of an object, such as position, velocity, and acceleration.

[2099] "Work procedure" means detailed steps or methods for efficiently performing a particular task.

[2100] "Relaxation" refers to activities or methods that relieve physical or mental tension.

[2101] This invention provides a system that starts with a terminal equipped with multiple sensors that collects player movement and technical data in real time. The terminal uses IoT devices such as smart clothing and smart gloves. These devices collect movement and technical data in real time and temporarily store it in memory.

[2102] The collected data is then sent via a communication protocol (e.g., HTTP or HTTPS) to a server, which stores the data in a database and is powered by a generative AI model using TensorFlow.

[2103] The generative AI model takes data from the database and analyzes movement patterns and skill levels. Specifically, it uses machine learning algorithms (e.g., random forests and neural networks) to evaluate each player's characteristics and abilities. The results are used to generate appropriate coaching methods.

[2104] Furthermore, an emotion engine is used to analyze the user's facial expressions, voice, and biometric data to recognize their emotional state. The emotion engine uses technologies such as EmotionAI. For example, it analyzes facial expressions from camera footage and determines the user's stress level from the tone of voice.

[2105] Based on the evaluation and emotion recognition results, the server generates optimal instruction methods and work procedures, including suggestions for relaxation exercises and breaks as needed. The generated instruction methods are sent to the user's device via a communication protocol. Notifications can be sent via a smartphone application or a dedicated device.

[2106] As a concrete example, consider a scenario in which a factory worker provides motion and emotional data. As the worker wears smart gloves and performs work, their motion data is collected in real time. Their facial expressions and tone of voice while working are also collected and analyzed by an emotion engine. This data is sent to a server, where a generative AI model evaluates work efficiency and generates instructional methods. If the worker is feeling stressed, the server also suggests relaxation exercises. These instructional methods are then notified to the worker's smartphone.

[2107] An example prompt is:

[2108] "sensor_data = {'temperature': 25.5, 'humidity': 60, 'acceleration': [0.2, 0.3, 0.4]}

[2109] emotion_data = {'emotion': 'stressed', 'confidence': 0.85}

[2110] prediction = analyze_data(sensor_data)

[2111] instructions = generate_instructions(prediction, emotion_data)

[2112] notify_user(instructions)

[2113] The above system makes it possible to propose optimal coaching methods and work procedures that take into account the movements and emotional state of athletes and workers.

[2114] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2115] Step 1:

[2116] The device collects the movement and technical data of athletes and workers, as well as biometric data, in real time. Specifically, smart clothing, smart gloves, or cameras are used to collect motion data (e.g., acceleration, posture data) and biometric data (e.g., heart rate, facial expression data). This data is temporarily stored in the device's memory.

[2117] Input: Real-time data from smart clothing and smart gloves

[2118] Output: Temporary storage of collected motion data and biometric data

[2119] Step 2:

[2120] The device sends the collected data to a server via an internet connection, where it is converted into an appropriate format (e.g., JSON or CSV) and securely transmitted using a communication protocol (e.g., HTTP or HTTPS).

[2121] Input: Collected data (e.g., acceleration data, facial expression data)

[2122] Output: Acknowledgement of completion of transmission to the server

[2123] Step 3:

[2124] The server stores the received data in a database, which manages the data in a structured format for efficient access and analysis.

[2125] Input: Transmitted data (e.g., motion data in JSON format, biometric data)

[2126] Output: Data stored in the database

[2127] Step 4:

[2128] The server retrieves data for each player or worker from the database and performs real-time analysis using a generative AI model. Machine learning algorithms (e.g., random forests, neural networks) are used to evaluate the characteristics and capabilities of each player or worker, specifically detecting movement patterns, skill levels, and imbalanced movements.

[2129] Input: Motion and biometric data retrieved from the database

[2130] Output: Analysis results (e.g., evaluation of movement patterns, determination of skill level)

[2131] Step 5:

[2132] The server uses an emotion engine to analyze the user's facial expressions, voice, and biometric data to recognize their emotional state. For example, it uses EmotionAI technology to assess whether the user is feeling stressed based on facial expression data.

[2133] Input: facial expression data and biometric data collected in real time

[2134] Output: Perceived emotional state (e.g., stressed, relaxed)

[2135] Step 6:

[2136] The server generates optimal teaching methods and work procedures based on the evaluation and emotion recognition results. The generated teaching methods may include specific training methods or relaxation exercises to reduce stress.

[2137] Input: Analysis results and emotion recognition results

[2138] Output: Generated instructional instructions or work instructions

[2139] Step 7:

[2140] The server generates training methods and work procedures and notifies the user's device. Notifications are sent via smartphone applications or dedicated devices. HTTP, WebSocket, and other communication protocols are used.

[2141] Input: Generated instructional methods or work procedures

[2142] Output: Notification to user's device completed

[2143] Step 8:

[2144] The user receives a notification on the device and checks the instruction method or work procedure. The user then performs the training or work according to the suggested method.

[2145] Input: Instruction method or work procedure notified to the terminal

[2146] Output: Training and work procedures reviewed and implemented

[2147] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2148] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2149] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2150] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2151] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2152] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2153] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2154] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2155] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2156] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2157] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be imple...

Claims

1. A device containing multiple sensors that collects player movement and technical data in real time, means for transmitting the data collected from the terminal to a server; means for storing the data received by the server in a database; A means for analyzing the data stored by the server using a generating AI and evaluating the characteristics and abilities of each player; A means for the server to generate a coaching method suitable for each player based on the evaluation results using a generation AI; means for notifying a user terminal of the generated teaching method; A system including:

2. 10. The system of claim 1, further comprising means for generating exercises and training plans to train specific muscles to improve the athlete's form.

3. 2. The system according to claim 1, further comprising means for measuring a player's shooting technique and throwing motion in detail and generating a coaching method for improving the technique based on the data.

Images