system

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting sensor information of a player from an IOT device; means for transmitting the collected sensor information to a server; means for storing the transmitted sensor information in the server; means for automatically analyzing the stored sensor information using a generation AI; means for generating an instruction method for the player based on a result of the analyzing; and means for allowing the player to perform training based on 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 educational settings and sports clubs, particularly in club activities where teachers with no athletic experience are burdened with coaching, is a serious problem. Using traditional methods, it is difficult to provide high-quality instruction to all athletes, resulting in players struggling to improve their skills. To solve this problem, a method is needed that allows even inexperienced coaches to efficiently and effectively provide instruction tailored to the individual characteristics of each athlete. [Means for solving the problem]

[0005] This invention solves this problem by collecting sensor data from athletes using IoT devices and sending it to a server for storage. The stored sensor data is then automatically analyzed using AI, and a coaching method for each athlete is generated based on the analysis results. The generated coaching method is then sent back to the device and displayed to the user. This allows even inexperienced coaches to provide specific coaching tailored to the athlete's characteristics. Furthermore, new data obtained from repeated training sessions can be analyzed to continuously optimize coaching methods. This includes sensor data on athletes' movements, techniques, loads, positions, and speeds, and there is a means to analyze this data to provide training menus, action plans, and advice for skill improvement.

[0006] An "IoT device" is a physical device that is connected to the internet and is used to collect and transmit data.

[0007] "Sensor Data" refers to physical, environmental, or behavioral information collected by IoT devices.

[0008] A "terminal" is an electronic device that receives data from an IOT device and transmits or displays it to a server.

[0009] A "server" is a computer system for receiving, storing, and processing large amounts of data.

[0010] A "database" is a collection of data that is systematically stored and managed.

[0011] "Generative AI" is an artificial intelligence system that analyzes collected data and generates instructional methods and other meaningful information.

[0012] "Coaching methods" are specific plans that include training menus and advice for improving skills based on the player's characteristics and abilities.

[0013] "Training" refers to the exercise and practice activities that athletes undertake to improve their skills and physical abilities.

[0014] "User" refers to a coach who uses this system to provide instruction to a player, or the player himself. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

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

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention is a system that uses IoT devices and generative AI to analyze sensor data from athletes and provide individually optimized coaching methods. The program processing of this system is explained in detail below.

[0037] Data Collection Phase

[0038] The terminal collects real-time sensor data from players' IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.), which records detailed information about players' movements, techniques, loads, positions, speeds, etc.

[0039] Example: The device collects the number of basketball shots, distance, and angle from the smart ball's sensor.

[0040] Data transmission phase

[0041] The device sends the collected sensor data to a server, where it is collected at regular intervals.

[0042] Example: The device sends running data measured by the smart shoes to the server every minute.

[0043] Data reception and storage phase

[0044] The server receives the sensor data sent from the devices and stores it in a database, where each player's data is stored in chronological order for later analysis.

[0045] Example: The server's API receives running data from a smartphone and stores it in a NoSQL database.

[0046] Data analysis phase

[0047] The server then passes the stored sensor data to the AI ​​generator, which then uses machine learning algorithms to analyze the data in detail and evaluate the player's technique and performance.

[0048] Example: The server analyzes running data to identify areas for improvement in a player's pace and form.

[0049] Teaching method generation phase

[0050] The server generates the optimal coaching method for each player based on the AI-generated evaluation results, including specific training menus and advice for improving skills.

[0051] Example: The server uses running data to suggest stretching methods and interval training to improve the angle of the athlete's knees.

[0052] Results feedback phase

[0053] The server sends the generated instruction method to the terminal, which receives it and displays it to the user. The user (instructor or player) then uses this information to provide training and technical instruction.

[0054] Example: The device displays a notification to the athlete via a smartphone app, saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees."

[0055] Training implementation and feedback loop phase

[0056] The user (athlete) will then train based on the proposed training method. Sensor data will be collected during the training and used for further analysis.

[0057] Example: Athletes train and the data collected during training is sent back to the server to help improve the accuracy of evaluation results and coaching methods.

[0058] This system will solve the problem of a shortage of instructors in educational settings and sports clubs, and will effectively support athletes in improving their performance.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The terminal collects real-time sensor data from players' IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.), which measure information such as players' movements, techniques, load, position, and speed.

[0062] Example: The device collects the number of steps, acceleration, and ground contact time from smart shoes.

[0063] Step 2:

[0064] The device sends the collected sensor data to a server using a secure communication protocol at regular intervals.

[0065] Example: The device sends running data measured by the smart shoes to a server every minute via Wi-Fi.

[0066] Step 3:

[0067] The server receives sensor data sent from the device via API, and the received data is immediately stored in a database.

[0068] Example: The server's API stores the running data received from the device in an analysis database in real time.

[0069] Step 4:

[0070] The server then passes the sensor data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to analyze the data and generate evaluation results for the player's movements and techniques.

[0071] Example: The server passes running data to an AI module to identify areas for improvement in the athlete's pace and form.

[0072] Step 5:

[0073] Based on the evaluation results, the server generates a coaching method optimized for each player, including specific training menus and advice for improving their skills.

[0074] Example: The server uses running data to generate stretching techniques to improve knee angle and interval training menus three times a week.

[0075] Step 6:

[0076] The server sends the generated training method to the terminal, which then displays the received training method to the user. The user (instructor or player) uses this information to train.

[0077] Example: The device displays a notification to the user through a smartphone app saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees."

[0078] Step 7:

[0079] The user (athlete) conducts training based on the proposed coaching method. Sensor data is continuously collected during and after the training and sent back to the server for use in new evaluation results and to improve the accuracy of the coaching method.

[0080] Example: A player performs training, and new data collected during that training is sent back to the server for analysis and use in the next training session.

[0081] Example 1

[0082] 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."

[0083] In traditional sports coaching, providing optimal training methods for individual athletes requires the resources of specialized instructors. However, due to factors such as a lack of instructors and limited coaching time, it is difficult to provide sufficient instruction to all athletes. It is also difficult to efficiently collect and analyze athletes' performance data in detail, making it difficult to provide optimal instruction to each individual athlete. Given this background, there is a demand for a system that uses IoT devices and generative AI to analyze athletes' sensor data and provide individually optimized coaching methods.

[0084] 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.

[0085] In this invention, the server includes means for collecting sensor data of athletes from IOT devices, means for transmitting the collected sensor data to the server at regular intervals, means for the server to store the transmitted sensor data in a database, means for analyzing the stored sensor data using a machine learning algorithm, means for generating an individual coaching method for the athletes based on the analysis results, means for transmitting the generated coaching method from the server to a terminal, means for the athletes to train based on the coaching method displayed on the terminal, and means for re-collecting sensor data during training and using it for analysis. This makes it possible to provide an effective and individually optimized coaching method for each athlete.

[0086] An "IoT device" is a device that is connected to the Internet and can use various sensors to detect and measure the condition of the environment and objects, and collect data.

[0087] "Sensor data" refers to various types of information collected through IoT devices, specifically data on players' movements, techniques, load, position, speed, etc.

[0088] A "terminal" is a computing device that connects to other devices or systems, sends and receives data, and performs processing, and specifically includes smartphones and tablets.

[0089] A "server" is a dedicated computer system that responds to requests from other devices or systems on a network and stores and processes data.

[0090] A "database" refers to a collection of structured information that can efficiently store large amounts of data and enable manipulation and search, and includes NoSQL databases and relational databases.

[0091] A "machine learning algorithm" is a computer programming technique that learns patterns from data and makes predictions, classifications, and analyses, including generative AI models.

[0092] "Coaching methods" refer to specific training menus, advice for improving techniques, and concrete action plans provided to improve players' performance.

[0093] "Analysis results" refers to information generated as a result of data processing using machine learning algorithms, and includes evaluations of players' skills and performance, as well as areas for improvement.

[0094] This invention is a system that utilizes IoT devices and generative AI to analyze sensor data of athletes and provide individually optimized coaching methods. Specific embodiments for implementing the invention are described below.

[0095] Hardware and software used

[0096] Terminal: IoT device (e.g. smart shoes, smart wear, smart ball, etc.)

[0097] Server: Database server (e.g. NoSQL database, MongoDB)

[0098] Generative AI models: machine learning algorithms (e.g., TensorFlow, scikit-learn)

[0099] Network communication: Bluetooth, Wi-Fi, HTTP API

[0100] Data collection

[0101] The terminal uses IoT devices to collect sensor data from players. For example, smart shoes collect running data (position, speed, foot angle, etc.) The terminal communicates with the smart ball's sensor using Bluetooth to collect data such as the number of shots, distance, and angle.

[0102] Data transmission

[0103] The device sends the collected sensor data to the server at regular intervals (e.g., every minute). The data is sent using an HTTP POST request to the server's API endpoint. For example, the device sends the collected running data to the server every minute.

[0104] Data reception and storage

[0105] The server receives sensor data sent from the device and stores it in a database. The database uses a NoSQL database (e.g., MongoDB) and stores the data in chronological order. For example, the server's API receives running data sent from a smartphone and stores it in a NoSQL database.

[0106] Data analysis

[0107] The server analyzes the stored sensor data using machine learning algorithms. Generative AI models are used to evaluate the player's technique and performance. For example, the server uses Python machine learning libraries (e.g., TensorFlow and scikit-learn) to analyze running data and identify areas for improvement in the player's pace and form.

[0108] Instruction method generation

[0109] The server generates personalized coaching methods for each athlete based on the analysis results. These include specific training menus, advice for improving technique, and action plans. For example, the server uses a generative AI model to generate suggestions for stretching and interval training to improve a player's knee angle based on running data.

[0110] Results feedback

[0111] The server sends the generated training method to the device, and the device notifies the user. The user (instructor or player) performs training or technical instruction based on the notification content. As a specific example, the server sends the training method to the device using an HTTP POST request, and the device displays on the smartphone app, "Perform interval training three times a week and try stretching methods to improve knee angle."

[0112] Training implementation and feedback loop

[0113] The user (athlete) performs training based on the proposed coaching method. Sensor data during training is collected again and analyzed again to improve the accuracy of the coaching method. As a specific example, the athlete performs training, and new data collected by the smart shoes during training is sent again via the device to the server, which then analyzes it again.

[0114] Prompt Sentence Examples

[0115] "The running data collected by the smart shoes should be analyzed in real time, and an algorithm should be generated to suggest the optimal training method for each individual athlete based on their pace and form. Specifically, this should include suggestions for stretching methods and interval training to improve the athlete's knee angle."

[0116] This system can solve the problem of a shortage of instructors in educational settings and sports clubs, and effectively support athletes in improving their performance.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1: Data collection

[0119] The terminal uses IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.) to collect sensor data of players in real time, including their movements, technique, load, position, speed, etc.

[0120] Input: Sensor data from IOT devices

[0121] Data processing: Real-time data collection and format conversion

[0122] Output: Formatted sensor data

[0123] Specific operation: The device communicates with the smart ball's sensors using Bluetooth and Wi-Fi to collect information such as the number of shots, distance, and angle.

[0124] Step 2: Send data

[0125] The device sends the collected sensor data to the server at regular intervals, typically every one or five minutes.

[0126] Input: Collected sensor data

[0127] Data processing: Packetizing data and network protocol processing

[0128] Output: Data packet sent to the server

[0129] Specific operation: The device sends the collected running data every minute by sending an HTTP POST request to the server's API endpoint.

[0130] Step 3: Data reception and storage

[0131] The server receives the sensor data sent from the devices and stores it in a database, where each player's data is stored in chronological order for later analysis.

[0132] Input: Data packets sent from the device

[0133] Data processing: Data analysis, format conversion, and storage in a database

[0134] Output: Stored time series data

[0135] Specific operation: The server's API receives running data sent from the smartphone and stores it in a NoSQL database (e.g., MongoDB).

[0136] Step 4: Data analysis

[0137] The server analyzes the stored sensor data using machine learning algorithms, and uses generative AI models to evaluate players' skills and performance.

[0138] Input: Stored time series data

[0139] Data Computing: Data analysis and performance evaluation using machine learning algorithms

[0140] Output: Player performance evaluation results

[0141] What it does: The server uses Python machine learning libraries (e.g., TensorFlow and scikit-learn) to analyze running data and identify areas for improvement in the athlete's pace and form.

[0142] Step 5: Instructional method generation

[0143] Based on the analysis results, the server generates the optimal coaching method for each player, including specific training menus and advice for improving their skills.

[0144] Input: Player performance evaluation results

[0145] Data calculation: generating instruction methods and creating training menus

[0146] Output: Individually optimized teaching methods

[0147] How it works: The server uses a generative AI model to suggest stretching techniques and interval training to improve the athlete's knee angle based on running data.

[0148] Step 6: Feedback

[0149] The server sends the generated instruction method to the terminal, which then notifies the user. The user (instructor or player) then performs training and technical instruction based on this notification.

[0150] Input: Individually optimized teaching methods

[0151] Data processing: Packetizing feedback data and generating notifications

[0152] Output: Instructional method notified to the user

[0153] Specific operation: The server sends the training method to the device using an HTTP POST request, and the device uses its notification function to display a notification on the smartphone app saying, "Perform interval training three times a week and try stretching methods to improve knee angle by 10 degrees."

[0154] Step 7: Training and feedback loop

[0155] The user (athlete) will then train based on the proposed coaching method. Sensor data during training will be collected and analyzed again to improve the accuracy of the coaching method.

[0156] Input: Newly collected sensor data

[0157] Data processing: Real-time data collection, transmission, storage, and analysis, repeated

[0158] Output: Improved teaching methods

[0159] Specific operation: The athlete performs training, and new data collected during that time is sent to the server via the device again, and the server then analyzes it again.

[0160] As described above, this system can provide individually optimized teaching methods through each processing step.

[0161] (Application example 1)

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

[0163] Conventional factory robot operation management and maintenance is based on specific patterns, which makes it inefficient and difficult to take preventative measures against failures.In addition, there is no system in place to provide specific instructions or maintenance plans aimed at improving operation efficiency and reducing the risk of failure, making it difficult to prevent problems before they occur.

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

[0165] In this invention, the server includes means for collecting machine sensor data from an IOT device, means for transmitting the collected sensor data to a central processing unit, means for storing the transmitted sensor data in the central processing unit, means for automatically analyzing the stored sensor data using a generation AI, means for generating operation instructions and maintenance methods for each machine based on the analysis results, means for transmitting the generated operation instructions and maintenance methods to a terminal, and means for controlling the machine based on the operation instructions and maintenance methods displayed on the terminal. This makes it possible to optimize the operating efficiency of the machine and preventatively reduce the risk of breakdown.

[0166] "IOT devices" are various sensors and devices connected to the Internet that collect and transmit data in real time.

[0167] "Machine" is a general term for automated equipment and devices used to perform specific tasks in a factory.

[0168] "Sensor data" is data collected by IoT devices that indicates the state of an object or environment.

[0169] A "central processing unit" is a server or computer system for receiving, storing, and analyzing collected sensor data.

[0170] "Generative AI" is artificial intelligence that uses machine learning algorithms to automatically analyze sensor data and generate optimal operating instructions and maintenance methods.

[0171] "Operational instructions" are specific instructions proposed by the generative AI based on the results of analyzing sensor data to improve the operating efficiency of the machine.

[0172] A "maintenance method" is a specific maintenance procedure for maintaining the safety and performance of a machine, proposed by the generative AI based on the results of analyzing sensor data.

[0173] "Terminal" refers to a device for displaying generated operating instructions and maintenance methods, and includes control systems and display devices.

[0174] This invention is a system that combines IoT devices, central processing units, generative AI models, and terminals to optimize the operating efficiency of machines in a factory.

[0175] First, various IoT devices are attached to each machine, such as motion sensors, pressure sensors, distance sensors, etc. These IoT devices collect data on the machine's operating status, pressure, position, speed, etc. in real time. The collected sensor data is sent to a central processing unit at regular intervals.

[0176] The central processing unit receives the collected sensor data and stores it in a database. The database used is a NoSQL database with the ability to store data in chronological order. This database stores daily operating data and maintenance information for each machine, which is used for later analysis.

[0177] Next, the central processing unit passes the stored sensor data to the generation AI, which begins analysis. The generation AI uses machine learning algorithms to perform detailed analysis of the collected data. Specifically, the analysis is aimed at improving operational efficiency and reducing the risk of breakdowns. For example, it can identify abnormal operation patterns based on past data, enabling predictive maintenance. It can also generate operational instructions to improve operational efficiency.

[0178] Based on the analysis results, the AI ​​generates optimal operating instructions and maintenance methods for each machine. This includes specific instructions to improve operating efficiency and inspection procedures to prevent breakdowns. This information is sent from the central processing unit to the terminal.

[0179] The terminal displays the received operation instructions and maintenance methods on a display, providing real-time information to robot operators and maintenance personnel using the control system and display device.

[0180] As a specific example, if the pressure sensor data is judged to be excessive, the generation AI will generate an operation instruction such as, "The machine's current gripping pressure is excessive. By reducing the pressure by 20%, it will be possible to hold the object stably while reducing energy consumption." Also, if abnormal movement is detected from the motion sensor data, the AI ​​will provide a maintenance method such as, "The operating angle of the robot's arm is outside the normal range, so we recommend regular maintenance and part replacement."

[0181] Additionally, examples of prompts for generative AI models include:

[0182] "Please provide guidance on how to improve operational efficiency and reduce the risk of breakdowns based on the robot's motion sensor data and pressure sensor data."

[0183] This allows the operating efficiency of machines in the factory to be continuously improved, and also makes it possible to take preventive measures against breakdowns.

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

[0185] Step 1:

[0186] Sensor data is collected from IOT devices. The server acquires data in real time from motion sensors, pressure sensors, and distance sensors attached to the machine. The input is data from each sensor, and the output is a set of sensor data. Specifically, data such as the machine's operating status, pressure, position, and speed are collected.

[0187] Step 2:

[0188] The collected sensor data is sent to a central processing unit. The server sends the collected sensor data to a database at regular intervals. The input is the collected sensor data, and the output is the data stored in the database. Specifically, the sensor data is formatted in JSON format and sent to a NoSQL database.

[0189] Step 3:

[0190] The transmitted sensor data is stored in the central processing unit. The server stores the received sensor data in a database in chronological order. The input is the transmitted sensor data, and the output is the data stored in the database. Specifically, a new entry is added to the database and saved together with the previous data.

[0191] Step 4:

[0192] The stored sensor data is passed to the generation AI to begin analysis. The server retrieves the sensor data stored in the database and sends it to the generation AI to request analysis. The input is the sensor data read from the database, and the output is the analysis results by the generation AI. Specifically, it uses a REST API to communicate with the generation AI and send data.

[0193] Step 5:

[0194] Generative AI analyzes sensor data to evaluate operational efficiency and risk of failure. It uses machine learning algorithms to analyze the data and identify abnormal patterns and optimization points. The input is the transmitted sensor data, and the output is the analysis results. Specifically, generative AI compares data with past data and detects outliers.

[0195] Step 6:

[0196] Based on the analysis results of the generation AI, the server generates operating instructions and maintenance methods for each machine. Based on the analysis results of the generation AI, the server creates optimal operating instructions and maintenance methods. The input is the analysis results of the generation AI, and the output is specific operating instructions and maintenance methods. Specifically, clear instructions such as "reduce pressure by 20%" and "adjust the operating angle of the arm" are generated.

[0197] Step 7:

[0198] The generated operation instructions and maintenance methods are sent to the terminal. The server sends the generated instruction contents to the terminal and displays them. The input is the generated operation instructions and maintenance methods, and the output is the information displayed on the terminal. Specifically, each instruction content is formatted in text format and sent to the terminal.

[0199] Step 8:

[0200] Machine control is based on the operating instructions and maintenance methods displayed on the terminal. The user checks the instructions displayed on the terminal and operates or maintains the machine based on them. The input is the operating instructions and maintenance methods displayed on the terminal, and the output is the results of the user's operation of the machine. Specifically, the user performs operations such as adjusting pressure and replacing parts.

[0201] This enables the system to continuously improve the operating efficiency of machines in the factory and proactively manage the risk of breakdowns.

[0202] 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.

[0203] This invention is a system that combines IoT devices, generative AI, and an emotion engine to analyze sensor data and emotion data of players and provide individually optimized coaching methods. The program processing of this system is explained in detail below.

[0204] Data Collection Phase

[0205] The terminal collects sensor data of players in real time from IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.). This data records players' movements, techniques, loads, positions, speeds, etc. in detail. The terminal also uses an emotion engine to collect users' emotional data (e.g., joy, anger, sadness, stress, etc.) in real time.

[0206] Example: The device collects the number of basketball shots, their distance, and angle from the smart ball's sensors, while the emotion engine collects emotional data from the user's facial expressions and voice.

[0207] Data transmission phase

[0208] The device sends the collected sensor data and emotion data to a server at regular intervals, where it is aggregated.

[0209] Example: The device transmits running data and emotional data measured by the smart shoes to a server every minute via Wi-Fi.

[0210] Data reception and storage phase

[0211] The server receives sensor data and emotion data sent from the device via API, and the received data is immediately stored in a database.

[0212] Example: The server's API stores running data and emotional data received from the device in a database for analysis in real time.

[0213] Data analysis phase

[0214] The server then passes the sensor data and emotion data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to perform a detailed analysis of the data and generate evaluations of the player's technique, performance, and emotions.

[0215] Example: The server passes running data and emotional data to an AI module to identify areas for improvement in the athlete's pace, form, and motivation.

[0216] Teaching method generation phase

[0217] The server generates the optimal coaching method for each player based on the evaluation results generated by the AI. The coaching method includes specific training menus and advice for improving skills, as well as coaching that takes into account the user's motivation based on their emotional state.

[0218] Example: The server uses running data to generate stretching methods to improve knee angle and interval training menus three times a week, and adds advice such as "listen to music to increase motivation" based on data from the emotion engine.

[0219] Results feedback phase

[0220] The server sends the generated coaching method and advice based on emotions to the device, which receives it and displays it to the user. The user (coach or player) uses this information to train.

[0221] Example: Through a smartphone app, the device displays a message to the user saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees," along with a notification saying, "We recommend listening to your favorite music to motivate you."

[0222] Training implementation and feedback loop phase

[0223] The user (athlete) then performs training according to the proposed coaching methods and emotional advice. Sensor data and emotional data are continuously collected during and after training and sent back to the server for use in developing new evaluation results and improving the accuracy of coaching methods.

[0224] Example: A player performs training, and new sensor data and emotional data collected during that training are sent back to the server for analysis and use in the next training session.

[0225] This system will solve the problem of a shortage of instructors in educational settings and sports clubs, and will effectively support athletes in improving their performance and managing their motivation.

[0226] The processing flow will be explained below.

[0227] Step 1:

[0228] The terminal collects sensor data of players in real time from IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.). The IoT devices measure information such as players' movements, techniques, load, position, and speed. The terminal also uses an emotion engine to collect user emotional data (e.g., joy, anger, sadness, stress, etc.).

[0229] Example: The device collects data from smart shoes about the number of steps, acceleration, and ground contact time while running, and also obtains the user's current emotional state from their facial expressions and voice.

[0230] Step 2:

[0231] The device sends the collected sensor data and emotion data to the server at regular intervals (e.g., every minute).

[0232] Example: The device transmits running data measured by the smart shoes and the user's emotional data acquired by the emotion engine to a server via Wi-Fi.

[0233] Step 3:

[0234] The server receives sensor data and emotion data sent from the device via API and stores the received data in a database in real time.

[0235] Example: The server's API receives running and emotion data and immediately stores it in a database for analysis.

[0236] Step 4:

[0237] The server then passes the sensor data and emotion data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to analyze the data in detail and generate an evaluation of the player's technique and performance, while also evaluating the user's emotional state.

[0238] Example: The server passes running data and emotional data to an AI module to identify areas for improvement in the athlete's pace and form, as well as emotional fluctuations.

[0239] Step 5:

[0240] Based on the evaluation results generated by the AI, the server generates the optimal coaching method for each player, which includes specific training menus and advice for improving skills, as well as coaching that takes into account the user's motivation based on their emotional state.

[0241] Example: The server generates stretching methods to improve knee angle and interval training menus three times a week from running data, and adds advice such as "listen to music to increase motivation" based on the user's emotional state.

[0242] Step 6:

[0243] The server sends the generated coaching method and advice based on emotions to the device, which receives it and displays it to the user. The user (coach or player) uses this information to train.

[0244] Example: Through a smartphone app, the device displays a message to the user saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees," and a notification saying, "We recommend listening to your favorite music to motivate you."

[0245] Step 7:

[0246] The user (athlete) then performs training according to the proposed coaching methods and emotional advice. Sensor data and emotional data are continuously collected during and after training and sent back to the server for use in developing new evaluation results and improving the accuracy of coaching methods.

[0247] Example: A player performs training, and new sensor data and emotional data collected during that training are sent back to the server for analysis and use in the next training session.

[0248] Example 2

[0249] 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."

[0250] Conventional training systems have struggled to provide individually optimized coaching methods for improving athletes' performance and managing their motivation. Furthermore, they have not implemented coaching methods that take athletes' emotional states into account, and uniform coaching has resulted in insufficient improvement in athletes' motivation and performance. Furthermore, there is a lack of a process for reanalyzing post-training data, making it difficult to improve the accuracy of coaching methods. To solve these issues, a system is needed that can integrate and analyze athletes' sensor data and emotional data, and provide individually optimized coaching methods and advice based on their emotions.

[0251] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0252] In this invention, the server includes means for collecting sensor data of players from IoT devices, means for transmitting the sensor data collected by the terminal and the user's emotional data to the server, means for receiving the sensor data and emotional data transmitted by the server via an API and storing them in a database, means for automatically analyzing the stored sensor data and emotional data using a generation AI, means for generating individual coaching methods and emotional advice for the player based on the analysis results, means for transmitting the generated coaching methods and advice to the terminal, and means for the player to train based on the coaching methods and advice displayed on the terminal. This makes it possible to integrate and analyze the sensor data and emotional data of the player and provide individually optimized coaching methods and emotional advice.

[0253] An "IoT device" is a physical device that connects to the Internet and has the ability to collect and transmit data.

[0254] "Sensor data" refers to data obtained from IoT devices regarding players' movements, techniques, load, position, speed, etc.

[0255] "Emotion data" is data that indicates an emotional state such as joy, anger, sadness, or stress, obtained by analyzing the user's facial expressions and voice.

[0256] "Generative AI" is an artificial intelligence that uses machine learning algorithms to automatically analyze collected data and generate evaluation results of players' skills, performance, and emotions.

[0257] The "evaluation results" are information about the player's technique, performance status, and emotional state obtained by the generating AI analyzing sensor data and emotional data.

[0258] "Coaching methods" are training menus for individual players, advice for improving skills, and emotionally-based coaching content for increasing motivation, all generated based on the analysis results.

[0259] A "terminal" is a computing device for collecting and transmitting data from an IOT device to a server, and displaying the instructional methods received from the server to a user.

[0260] The "server" is a computing system that receives and stores data sent from the terminal, analyzes it using a generative AI, generates teaching methods, and sends them to the terminal.

[0261] The "database" is an information management system installed in the server for storing received sensor data and emotion data.

[0262] This invention is a system that combines IoT devices, generative AI, and an emotion engine to analyze sensor data and emotion data of athletes and provide individually optimized coaching methods. Hereinafter, specific embodiments for implementing this system will be described.

[0263] Use of IOT devices

[0264] The device collects sensor data from players using IoT devices such as smart shoes, smart clothing, and smart balls, allowing for detailed recording of players' movements, techniques, load, position, speed, etc. The device also incorporates an emotion engine that analyzes the user's facial expressions and voice in real time to collect emotional data.

[0265] As a specific example, the device collects the number of basketball shots, their distance, and angle from the smart ball's sensors, and also collects emotional data (e.g., joy, anger, sadness, stress, etc.) from the user's facial expressions and voice using an emotion engine.

[0266] Sending and Receiving Data

[0267] The device sends the collected sensor data and emotion data to a server via Wi-Fi or mobile data communication. This data is sent at regular intervals (for example, every minute) and received via the server's API. The received data is stored in a database in real time.

[0268] For example, the device transmits running data and emotional data measured by the smart shoes every minute to a server via Wi-Fi. The server's API stores the running data and emotional data received from the device in a database for analysis in real time.

[0269] Analyzing the data

[0270] The server then passes the sensor data and emotion data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to perform a detailed analysis of the data and generate evaluations of the player's technique, performance, and emotions.

[0271] As a concrete example, the server passes running data and emotional data to a generative AI module to identify areas for improvement in the athlete's pace, form, and motivation.

[0272] Teaching method generation

[0273] Based on the evaluation results generated by the AI, the server generates optimal coaching methods for each player, including specific training menus and advice for improving skills, as well as guidance to increase motivation based on the user's emotional state.

[0274] As a specific example, the server uses running data to generate stretching techniques to improve knee angle and a three-times-a-week interval training menu, and adds advice such as "listen to music to increase motivation" based on data from the emotion engine.

[0275] Feedback of results

[0276] The server sends the generated advice based on the coaching method and emotions to the terminal. The terminal receives it and displays it to the user. The user (coach or player) uses it as a reference for training.

[0277] For example, the device will display a message to the user through a smartphone app saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees," along with a notification saying, "We recommend listening to your favorite music to motivate you."

[0278] Training implementation and feedback loop

[0279] The user (athlete) then performs training according to the proposed coaching methods and emotion-based advice. New sensor data and emotion data are continuously collected during and after training, and are sent back to the server to be used to refine the new evaluation results and coaching methods.

[0280] As a concrete example, a player performs training, and new sensor data and emotional data collected during that training are sent back to the server, where they are used for the next analysis and for generating coaching methods.

[0281] This system can solve the problem of a shortage of instructors in educational settings and sports clubs, and effectively support athletes in improving their performance and managing their motivation.

[0282] Example prompts to input to the generative AI model

[0283] "Analyze this athlete's running and emotional data and generate advice to improve their technique and coaching methods to increase their motivation."

[0284] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0285] Step 1:

[0286] Input: Sensor data from IOT devices and emotion data from built-in cameras and microphones

[0287] Processing: The terminal communicates with IoT devices (smart shoes, smart wear, smart balls, etc.) to collect sensor data, and at the same time collects emotion data using the built-in camera and microphone. For example, distance and speed information is obtained from smart shoes, and the user's facial expressions are captured with the camera and analyzed by the emotion engine.

[0288] Output: Sensor data and emotion data

[0289] Step 2:

[0290] Input: Sensor data and emotion data

[0291] Processing: The device sends the collected sensor data and emotion data to the server via Wi-Fi or mobile communication. Every minute, the data is sent to the server's API endpoint via an HTTP POST request. For example, running data and emotion data are sent in JSON format.

[0292] Output: Sensor data and emotion data sent to the server

[0293] Step 3:

[0294] Input: Sensor data and emotion data sent to the server

[0295] Processing: The server receives the sensor data and emotion data via the API. The API parses the HTTP request and generates a query to store it in the database. For example, it sends an insert query to the database to store the sensor data in the "sensor table" and the emotion data in the "emotion table."

[0296] Output: Sensor data and emotion data stored in a database

[0297] Step 4:

[0298] Input: Sensor data and emotion data stored in a database

[0299] Processing: The server passes the stored data to the generative AI model, which then uses machine learning algorithms to evaluate the athlete's technical performance and emotions, such as running pace, form, and the user's motivation.

[0300] Output: Technical, performance and emotional evaluation results

[0301] Step 5:

[0302] Input: Evaluation result

[0303] Processing: The server generates personalized coaching methods and emotional advice for each player based on the evaluation results. Using specific algorithms, it generates training menus, advice for improving technique, and motivational guidance. For example, it generates stretching methods to improve knee angle and a menu of interval training sessions three times a week, and adds advice such as "listen to your favorite music" based on data from the emotion engine.

[0304] Output: Generated teaching methods and emotion-based advice

[0305] Step 6:

[0306] Input: Generated teaching methods and emotion-based advice

[0307] Processing: The server sends the generated training method and advice to the device. It sends data to the device via an HTTP POST request. For example, it sends data containing training menus and motivational advice in JSON format.

[0308] Output: Instructions and advice sent to the device

[0309] Step 7:

[0310] Input: Instructions and advice sent to the device

[0311] Processing: The device displays the received training methods and advice to the user. The smartphone app displays a notification to inform the user of specific training content and motivational advice. For example, a notification may be displayed saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees."

[0312] Output: Instructions and advice displayed to the user

[0313] Step 8:

[0314] Input: Instructions and advice displayed to the user

[0315] Processing: The user performs training according to the suggested instructional methods and emotion-based advice. For example, the user performs the suggested stretching methods and training menu.

[0316] Output: New sensor and emotion data during and after training

[0317] Step 9:

[0318] Input: New sensor and emotion data during and after training

[0319] Processing: The device again collects new sensor data and emotion data during and after training and sends them to the server. For example, it collects new running data and emotion data and sends them to the server via Wi-Fi.

[0320] Output: New sensor and emotion data sent to the server.

[0321] This creates a feedback loop that continually improves players' performance and motivates them.

[0322] (Application example 2)

[0323] 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."

[0324] Conventional driving assistance systems and training assistance systems simply collect and analyze driving and training data and provide the results, without adequately considering the user's emotional state or motivation. Therefore, there is a growing need for a system that can appropriately evaluate a user's emotions and stress state and provide optimal advice based on that evaluation. The present invention aims to solve this problem by providing a system that provides individually optimized driving assistance and training assistance.

[0325] 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.

[0326] In this invention, the server includes means for collecting sensor data and emotional data of the player from the IoT device, means for transmitting the collected sensor data and emotional data to the server, means for storing the transmitted sensor data and emotional data in the server, means for automatically analyzing the stored sensor data and emotional data using a generation AI, means for generating a coaching method and emotion-based motivational advice for the player based on the analysis results of the generation AI, means for transmitting the generated coaching method and emotion-based motivational advice to a terminal, and means for the player to train based on the coaching method and emotion-based motivational advice displayed on the terminal. This enables individually optimized driving assistance and training assistance that takes into account the user's emotional state.

[0327] An "IoT device" is a physical device that can connect to the internet and collect and exchange data.

[0328] "Sensor data" refers to information on various physical quantities such as movement, position, temperature, and pressure obtained from IoT devices.

[0329] "Emotion data" is information about the user's emotional state, such as joy, anger, sadness, or stress, obtained by face recognition or voice recognition.

[0330] "Generative AI" is an artificial intelligence technology that automatically generates new information and results based on input data.

[0331] "Instruction methods" are advice and suggestions for optimal exercise and training for users, generated based on the analysis results of the generative AI.

[0332] "Motivation advice" is advice and suggestions based on emotional data to maintain and improve a user's motivation.

[0333] A "server" is a computer system for collecting, storing, analyzing, and transmitting data over a network.

[0334] "Terminal" means a device that a user directly operates and uses to display and receive information, including smartphones and tablets.

[0335] "Analysis results" are the output information generated by analyzing sensor data and emotional data using the generation AI.

[0336] "Workout" means any physical or technical exercise or practice performed by a user.

[0337] This invention is a system that combines IoT devices, generative AI, and an emotion engine to analyze sensor data and emotion data of athletes and drivers, and provide optimized coaching methods and motivational advice. An embodiment of this system is described in detail below.

[0338] First, we will describe the system's hardware configuration. The system uses IoT devices (e.g., driver seat sensors, in-car cameras, smart clothing, smart shoes, etc.) to collect data on athletes and drivers. These devices collect sensor data such as movement, position, speed, facial expressions, and voice, as well as emotional data.

[0339] Next, we will explain the device. The device takes the form of a smartphone or tablet and provides an interface with the user. The device sends the collected data to the server and displays the instruction methods and advice from the server to the user. The device also connects to the server via Wi-Fi or mobile data communication.

[0340] The server is the central processing unit of this system and is responsible for the following processes: First, it receives sensor data and emotion data sent from the device via an API and stores it in a database in real time. Next, it passes the stored data to the generative AI, which then automatically begins analyzing it. The generative AI analyzes the data using machine learning algorithms and generates evaluation results regarding the user's behavioral patterns and emotional state. Well-known generative AI models such as GPT-3 and BERT are used for this.

[0341] Based on the analysis results, the server generates optimal instruction methods and emotionally-based motivational advice for the user. This process includes, for example, specific action plans and training menus for safe driving, as well as advice for improving skills. Based on the emotional data, the server also generates suggestions for music and break timing to maintain and improve motivation.

[0342] The generated instruction methods and motivation advice are sent back to the device and notified to the user. The user uses this information to drive or train. Furthermore, new sensor data and emotional data collected during and after the training are sent back to the server and used to improve the accuracy of the next instruction methods and advice.

[0343] As a concrete example, the following prompt sentences could be input to a generative AI model:

[0344] Analyze driving and emotional data to generate advice for safe and comfortable driving.

[0345] Operation data: {Operation data: . . .}

[0346] Emotion data: {Emotion data: . . .}

[0347] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0348] Step 1:

[0349] Data Collection Phase

[0350] The terminal collects driving and emotion data in real time from IoT devices such as driver seat sensors, in-car cameras, and smart clothing. Specifically, the driver seat sensors collect pressure data, the in-car cameras collect facial expression data through facial recognition, and the microphone collects voice data. The terminal integrates this data and temporarily stores it as an initial data set.

[0351] Input: Data obtained from driver seat sensors, in-car cameras, microphones, etc.

[0352] Output: Temporarily saved initial dataset

[0353] Step 2:

[0354] Data transmission phase

[0355] The device sends the collected sensor data and emotion data to the server at regular intervals (e.g., every minute) using Wi-Fi or mobile data. The device confirms that the data was sent properly and displays a success message to the user.

[0356] Input: Temporarily saved initial dataset

[0357] Output: Data sent to the server, and a notification message to the user

[0358] Step 3:

[0359] Data reception and storage phase

[0360] The server receives sensor data and emotion data sent from the device via API. The received data is stored in a database in real time. The server confirms that the data has been stored and records it in a log.

[0361] Input: Data sent from the terminal

[0362] Output: Data stored in the database, and log entries

[0363] Step 4:

[0364] Data analysis phase

[0365] The server passes the sensor data and emotion data stored in the database to the generative AI, which then automatically begins analysis. Using a generative AI model (such as GPT-3 or BERT), the server evaluates driving behavior and emotional state and generates analysis results based on that.

[0366] For example, the following prompts could be input to the generator:

[0367] Analyze driving and emotional data to generate advice for safe and comfortable driving.

[0368] Operation data: {Operation data: . . .}

[0369] Emotion data: {Emotion data: . . .}

[0370] Input: Sensor data and emotion data stored in a database

[0371] Output: Analysis results generated by generative AI

[0372] Step 5:

[0373] Teaching method generation phase

[0374] Based on the analysis results provided by the AI, the server generates optimal instruction methods and motivational advice for the user, such as suggestions for adjusting speed and timing breaks for safe driving, and music recommendations for stress reduction.

[0375] Input: Analysis results generated by generative AI

[0376] Output: Optimal teaching methods and motivation advice for users

[0377] Step 6:

[0378] Results feedback phase

[0379] The server sends the generated teaching method and motivation advice to the terminal, which receives it, displays it to the user as a notification, and also provides feedback to the server that the user has confirmed the notification.

[0380] Input: Server-generated instructional and motivational advice

[0381] Output: Notifications displayed to the user and feedback to the server

[0382] Step 7:

[0383] Training implementation and feedback loop phase

[0384] The user drives or trains based on the instruction methods and motivation advice displayed on the device. New sensor data and emotional data are collected during and after the training and sent to the server via the device. This allows the system to improve the accuracy of the next training methods and motivation advice.

[0385] Input: User driving data and emotion data

[0386] Output: Data used to generate new teaching methods and motivational advice

[0387] 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.

[0388] 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.

[0389] 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.

[0390] [Second embodiment]

[0391] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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."

[0403] This invention is a system that uses IoT devices and generative AI to analyze sensor data from athletes and provide individually optimized coaching methods. The program processing of this system is explained in detail below.

[0404] Data Collection Phase

[0405] The terminal collects real-time sensor data from players' IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.), which records detailed information about players' movements, techniques, loads, positions, speeds, etc.

[0406] Example: The device collects the number of basketball shots, distance, and angle from the smart ball's sensor.

[0407] Data transmission phase

[0408] The device sends the collected sensor data to a server, where it is collected at regular intervals.

[0409] Example: The device sends running data measured by the smart shoes to the server every minute.

[0410] Data reception and storage phase

[0411] The server receives the sensor data sent from the devices and stores it in a database, where each player's data is stored in chronological order for later analysis.

[0412] Example: The server's API receives running data from a smartphone and stores it in a NoSQL database.

[0413] Data analysis phase

[0414] The server then passes the stored sensor data to the AI ​​generator, which then uses machine learning algorithms to analyze the data in detail and evaluate the player's technique and performance.

[0415] Example: The server analyzes running data to identify areas for improvement in a player's pace and form.

[0416] Teaching method generation phase

[0417] The server generates the optimal coaching method for each player based on the AI-generated evaluation results, including specific training menus and advice for improving skills.

[0418] Example: The server uses running data to suggest stretching methods and interval training to improve the angle of the athlete's knees.

[0419] Results feedback phase

[0420] The server sends the generated instruction method to the terminal, which receives it and displays it to the user. The user (instructor or player) then uses this information to provide training and technical instruction.

[0421] Example: The device displays a notification to the athlete via a smartphone app, saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees."

[0422] Training implementation and feedback loop phase

[0423] The user (athlete) will then train based on the proposed training method. Sensor data will be collected during the training and used for further analysis.

[0424] Example: Athletes train and the data collected during training is sent back to the server to help improve the accuracy of evaluation results and coaching methods.

[0425] This system will solve the problem of a shortage of instructors in educational settings and sports clubs, and will effectively support athletes in improving their performance.

[0426] The processing flow will be explained below.

[0427] Step 1:

[0428] The terminal collects real-time sensor data from players' IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.), which measure information such as players' movements, techniques, load, position, and speed.

[0429] Example: The device collects the number of steps, acceleration, and ground contact time from smart shoes.

[0430] Step 2:

[0431] The device sends the collected sensor data to a server using a secure communication protocol at regular intervals.

[0432] Example: The device sends running data measured by the smart shoes to a server every minute via Wi-Fi.

[0433] Step 3:

[0434] The server receives sensor data sent from the device via API, and the received data is immediately stored in a database.

[0435] Example: The server's API stores the running data received from the device in an analysis database in real time.

[0436] Step 4:

[0437] The server then passes the sensor data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to analyze the data and generate evaluation results for the player's movements and techniques.

[0438] Example: The server passes running data to an AI module to identify areas for improvement in the athlete's pace and form.

[0439] Step 5:

[0440] Based on the evaluation results, the server generates a coaching method optimized for each player, including specific training menus and advice for improving their skills.

[0441] Example: The server uses running data to generate stretching techniques to improve knee angle and interval training menus three times a week.

[0442] Step 6:

[0443] The server sends the generated training method to the terminal, which then displays the received training method to the user. The user (instructor or player) uses this information to train.

[0444] Example: The device displays a notification to the user through a smartphone app saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees."

[0445] Step 7:

[0446] The user (athlete) conducts training based on the proposed coaching method. Sensor data is continuously collected during and after the training and sent back to the server for use in new evaluation results and to improve the accuracy of the coaching method.

[0447] Example: A player performs training, and new data collected during that training is sent back to the server for analysis and use in the next training session.

[0448] Example 1

[0449] 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."

[0450] In traditional sports coaching, providing optimal training methods for individual athletes requires the resources of specialized instructors. However, due to factors such as a lack of instructors and limited coaching time, it is difficult to provide sufficient instruction to all athletes. It is also difficult to efficiently collect and analyze athletes' performance data in detail, making it difficult to provide optimal instruction to each individual athlete. Given this background, there is a demand for a system that uses IoT devices and generative AI to analyze athletes' sensor data and provide individually optimized coaching methods.

[0451] 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.

[0452] In this invention, the server includes means for collecting sensor data of athletes from IOT devices, means for transmitting the collected sensor data to the server at regular intervals, means for the server to store the transmitted sensor data in a database, means for analyzing the stored sensor data using a machine learning algorithm, means for generating an individual coaching method for the athletes based on the analysis results, means for transmitting the generated coaching method from the server to a terminal, means for the athletes to train based on the coaching method displayed on the terminal, and means for re-collecting sensor data during training and using it for analysis. This makes it possible to provide an effective and individually optimized coaching method for each athlete.

[0453] An "IoT device" is a device that is connected to the Internet and can use various sensors to detect and measure the condition of the environment and objects, and collect data.

[0454] "Sensor data" refers to various types of information collected through IoT devices, specifically data on players' movements, techniques, load, position, speed, etc.

[0455] A "terminal" is a computing device that connects to other devices or systems, sends and receives data, and performs processing, and specifically includes smartphones and tablets.

[0456] A "server" is a dedicated computer system that responds to requests from other devices or systems on a network and stores and processes data.

[0457] A "database" refers to a collection of structured information that can efficiently store large amounts of data and enable manipulation and search, and includes NoSQL databases and relational databases.

[0458] A "machine learning algorithm" is a computer programming technique that learns patterns from data and makes predictions, classifications, and analyses, including generative AI models.

[0459] "Coaching methods" refer to specific training menus, advice for improving techniques, and concrete action plans provided to improve players' performance.

[0460] "Analysis results" refers to information generated as a result of data processing using machine learning algorithms, and includes evaluations of players' skills and performance, as well as areas for improvement.

[0461] This invention is a system that utilizes IoT devices and generative AI to analyze sensor data of athletes and provide individually optimized coaching methods. Specific embodiments for implementing the invention are described below.

[0462] Hardware and software used

[0463] Terminal: IoT device (e.g. smart shoes, smart wear, smart ball, etc.)

[0464] Server: Database server (e.g. NoSQL database, MongoDB)

[0465] Generative AI models: machine learning algorithms (e.g., TensorFlow, scikit-learn)

[0466] Network communication: Bluetooth, Wi-Fi, HTTP API

[0467] Data collection

[0468] The terminal uses IoT devices to collect sensor data from players. For example, smart shoes collect running data (position, speed, foot angle, etc.) The terminal communicates with the smart ball's sensor using Bluetooth to collect data such as the number of shots, distance, and angle.

[0469] Data transmission

[0470] The device sends the collected sensor data to the server at regular intervals (e.g., every minute). The data is sent using an HTTP POST request to the server's API endpoint. For example, the device sends the collected running data to the server every minute.

[0471] Data reception and storage

[0472] The server receives sensor data sent from the device and stores it in a database. The database uses a NoSQL database (e.g., MongoDB) and stores the data in chronological order. For example, the server's API receives running data sent from a smartphone and stores it in a NoSQL database.

[0473] Data analysis

[0474] The server analyzes the stored sensor data using machine learning algorithms. Generative AI models are used to evaluate the player's technique and performance. For example, the server uses Python machine learning libraries (e.g., TensorFlow and scikit-learn) to analyze running data and identify areas for improvement in the player's pace and form.

[0475] Instruction method generation

[0476] The server generates personalized coaching methods for each athlete based on the analysis results. These include specific training menus, advice for improving technique, and action plans. For example, the server uses a generative AI model to generate suggestions for stretching and interval training to improve a player's knee angle based on running data.

[0477] Results feedback

[0478] The server sends the generated training method to the device, and the device notifies the user. The user (instructor or player) performs training or technical instruction based on the notification content. As a specific example, the server sends the training method to the device using an HTTP POST request, and the device displays on the smartphone app, "Perform interval training three times a week and try stretching methods to improve knee angle."

[0479] Training implementation and feedback loop

[0480] The user (athlete) performs training based on the proposed coaching method. Sensor data during training is collected again and analyzed again to improve the accuracy of the coaching method. As a specific example, the athlete performs training, and new data collected by the smart shoes during training is sent again via the device to the server, which then analyzes it again.

[0481] Prompt Sentence Examples

[0482] "The running data collected by the smart shoes should be analyzed in real time, and an algorithm should be generated to suggest the optimal training method for each individual athlete based on their pace and form. Specifically, this should include suggestions for stretching methods and interval training to improve the athlete's knee angle."

[0483] This system can solve the problem of a shortage of instructors in educational settings and sports clubs, and effectively support athletes in improving their performance.

[0484] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0485] Step 1: Data collection

[0486] The terminal uses IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.) to collect sensor data of players in real time, including their movements, technique, load, position, speed, etc.

[0487] Input: Sensor data from IOT devices

[0488] Data processing: Real-time data collection and format conversion

[0489] Output: Formatted sensor data

[0490] Specific operation: The device communicates with the smart ball's sensors using Bluetooth and Wi-Fi to collect information such as the number of shots, distance, and angle.

[0491] Step 2: Send data

[0492] The device sends the collected sensor data to the server at regular intervals, typically every one or five minutes.

[0493] Input: Collected sensor data

[0494] Data processing: Packetizing data and network protocol processing

[0495] Output: Data packet sent to the server

[0496] Specific operation: The device sends the collected running data every minute by sending an HTTP POST request to the server's API endpoint.

[0497] Step 3: Data reception and storage

[0498] The server receives the sensor data sent from the devices and stores it in a database, where each player's data is stored in chronological order for later analysis.

[0499] Input: Data packets sent from the device

[0500] Data processing: Data analysis, format conversion, and storage in a database

[0501] Output: Stored time series data

[0502] Specific operation: The server's API receives running data sent from the smartphone and stores it in a NoSQL database (e.g., MongoDB).

[0503] Step 4: Data analysis

[0504] The server analyzes the stored sensor data using machine learning algorithms, and uses generative AI models to evaluate players' skills and performance.

[0505] Input: Stored time series data

[0506] Data Computing: Data analysis and performance evaluation using machine learning algorithms

[0507] Output: Player performance evaluation results

[0508] What it does: The server uses Python machine learning libraries (e.g., TensorFlow and scikit-learn) to analyze running data and identify areas for improvement in the athlete's pace and form.

[0509] Step 5: Instructional method generation

[0510] Based on the analysis results, the server generates the optimal coaching method for each player, including specific training menus and advice for improving their skills.

[0511] Input: Player performance evaluation results

[0512] Data calculation: generating instruction methods and creating training menus

[0513] Output: Individually optimized teaching methods

[0514] How it works: The server uses a generative AI model to suggest stretching techniques and interval training to improve the athlete's knee angle based on running data.

[0515] Step 6: Feedback

[0516] The server sends the generated instruction method to the terminal, which then notifies the user. The user (instructor or player) then performs training and technical instruction based on this notification.

[0517] Input: Individually optimized teaching methods

[0518] Data processing: Packetizing feedback data and generating notifications

[0519] Output: Instructional method notified to the user

[0520] Specific operation: The server sends the training method to the device using an HTTP POST request, and the device uses its notification function to display a notification on the smartphone app saying, "Perform interval training three times a week and try stretching methods to improve knee angle by 10 degrees."

[0521] Step 7: Training and feedback loop

[0522] The user (athlete) will then train based on the proposed coaching method. Sensor data during training will be collected and analyzed again to improve the accuracy of the coaching method.

[0523] Input: Newly collected sensor data

[0524] Data processing: Real-time data collection, transmission, storage, and analysis, repeated

[0525] Output: Improved teaching methods

[0526] Specific operation: The athlete performs training, and new data collected during that time is sent to the server via the device again, and the server then analyzes it again.

[0527] As described above, this system can provide individually optimized teaching methods through each processing step.

[0528] (Application example 1)

[0529] 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."

[0530] Conventional factory robot operation management and maintenance is based on specific patterns, which makes it inefficient and difficult to take preventative measures against failures.In addition, there is no system in place to provide specific instructions or maintenance plans aimed at improving operation efficiency and reducing the risk of failure, making it difficult to prevent problems before they occur.

[0531] 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.

[0532] In this invention, the server includes means for collecting machine sensor data from an IOT device, means for transmitting the collected sensor data to a central processing unit, means for storing the transmitted sensor data in the central processing unit, means for automatically analyzing the stored sensor data using a generation AI, means for generating operation instructions and maintenance methods for each machine based on the analysis results, means for transmitting the generated operation instructions and maintenance methods to a terminal, and means for controlling the machine based on the operation instructions and maintenance methods displayed on the terminal. This makes it possible to optimize the operating efficiency of the machine and preventatively reduce the risk of breakdown.

[0533] "IOT devices" are various sensors and devices connected to the Internet that collect and transmit data in real time.

[0534] "Machine" is a general term for automated equipment and devices used to perform specific tasks in a factory.

[0535] "Sensor data" is data collected by IoT devices that indicates the state of an object or environment.

[0536] A "central processing unit" is a server or computer system for receiving, storing, and analyzing collected sensor data.

[0537] "Generative AI" is artificial intelligence that uses machine learning algorithms to automatically analyze sensor data and generate optimal operating instructions and maintenance methods.

[0538] "Operational instructions" are specific instructions proposed by the generative AI based on the results of analyzing sensor data to improve the operating efficiency of the machine.

[0539] A "maintenance method" is a specific maintenance procedure for maintaining the safety and performance of a machine, proposed by the generative AI based on the results of analyzing sensor data.

[0540] "Terminal" refers to a device for displaying generated operating instructions and maintenance methods, and includes control systems and display devices.

[0541] This invention is a system that combines IoT devices, central processing units, generative AI models, and terminals to optimize the operating efficiency of machines in a factory.

[0542] First, various IoT devices are attached to each machine, such as motion sensors, pressure sensors, distance sensors, etc. These IoT devices collect data on the machine's operating status, pressure, position, speed, etc. in real time. The collected sensor data is sent to a central processing unit at regular intervals.

[0543] The central processing unit receives the collected sensor data and stores it in a database. The database used is a NoSQL database with the ability to store data in chronological order. This database stores daily operating data and maintenance information for each machine, which is used for later analysis.

[0544] Next, the central processing unit passes the stored sensor data to the generation AI, which begins analysis. The generation AI uses machine learning algorithms to perform detailed analysis of the collected data. Specifically, the analysis is aimed at improving operational efficiency and reducing the risk of breakdowns. For example, it can identify abnormal operation patterns based on past data, enabling predictive maintenance. It can also generate operational instructions to improve operational efficiency.

[0545] Based on the analysis results, the AI ​​generates optimal operating instructions and maintenance methods for each machine. This includes specific instructions to improve operating efficiency and inspection procedures to prevent breakdowns. This information is sent from the central processing unit to the terminal.

[0546] The terminal displays the received operation instructions and maintenance methods on a display, providing real-time information to robot operators and maintenance personnel using the control system and display device.

[0547] As a specific example, if the pressure sensor data is judged to be excessive, the generation AI will generate an operation instruction such as, "The machine's current gripping pressure is excessive. By reducing the pressure by 20%, it will be possible to hold the object stably while reducing energy consumption." Also, if abnormal movement is detected from the motion sensor data, the AI ​​will provide a maintenance method such as, "The operating angle of the robot's arm is outside the normal range, so we recommend regular maintenance and part replacement."

[0548] Additionally, examples of prompts for generative AI models include:

[0549] "Please provide guidance on how to improve operational efficiency and reduce the risk of breakdowns based on the robot's motion sensor data and pressure sensor data."

[0550] This allows the operating efficiency of machines in the factory to be continuously improved, and also makes it possible to take preventive measures against breakdowns.

[0551] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0552] Step 1:

[0553] Sensor data is collected from IOT devices. The server acquires data in real time from motion sensors, pressure sensors, and distance sensors attached to the machine. The input is data from each sensor, and the output is a set of sensor data. Specifically, data such as the machine's operating status, pressure, position, and speed are collected.

[0554] Step 2:

[0555] The collected sensor data is sent to a central processing unit. The server sends the collected sensor data to a database at regular intervals. The input is the collected sensor data, and the output is the data stored in the database. Specifically, the sensor data is formatted in JSON format and sent to a NoSQL database.

[0556] Step 3:

[0557] The transmitted sensor data is stored in the central processing unit. The server stores the received sensor data in a database in chronological order. The input is the transmitted sensor data, and the output is the data stored in the database. Specifically, a new entry is added to the database and saved together with the previous data.

[0558] Step 4:

[0559] The stored sensor data is passed to the generation AI to begin analysis. The server retrieves the sensor data stored in the database and sends it to the generation AI to request analysis. The input is the sensor data read from the database, and the output is the analysis results by the generation AI. Specifically, it uses a REST API to communicate with the generation AI and send data.

[0560] Step 5:

[0561] Generative AI analyzes sensor data to evaluate operational efficiency and risk of failure. It uses machine learning algorithms to analyze the data and identify abnormal patterns and optimization points. The input is the transmitted sensor data, and the output is the analysis results. Specifically, generative AI compares data with past data and detects outliers.

[0562] Step 6:

[0563] Based on the analysis results of the generation AI, the server generates operating instructions and maintenance methods for each machine. Based on the analysis results of the generation AI, the server creates optimal operating instructions and maintenance methods. The input is the analysis results of the generation AI, and the output is specific operating instructions and maintenance methods. Specifically, clear instructions such as "reduce pressure by 20%" and "adjust the operating angle of the arm" are generated.

[0564] Step 7:

[0565] The generated operation instructions and maintenance methods are sent to the terminal. The server sends the generated instruction contents to the terminal and displays them. The input is the generated operation instructions and maintenance methods, and the output is the information displayed on the terminal. Specifically, each instruction content is formatted in text format and sent to the terminal.

[0566] Step 8:

[0567] Machine control is based on the operating instructions and maintenance methods displayed on the terminal. The user checks the instructions displayed on the terminal and operates or maintains the machine based on them. The input is the operating instructions and maintenance methods displayed on the terminal, and the output is the results of the user's operation of the machine. Specifically, the user performs operations such as adjusting pressure and replacing parts.

[0568] This enables the system to continuously improve the operating efficiency of machines in the factory and proactively manage the risk of breakdowns.

[0569] 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.

[0570] This invention is a system that combines IoT devices, generative AI, and an emotion engine to analyze sensor data and emotion data of players and provide individually optimized coaching methods. The program processing of this system is explained in detail below.

[0571] Data Collection Phase

[0572] The terminal collects sensor data of players in real time from IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.). This data records players' movements, techniques, loads, positions, speeds, etc. in detail. The terminal also uses an emotion engine to collect users' emotional data (e.g., joy, anger, sadness, stress, etc.) in real time.

[0573] Example: The device collects the number of basketball shots, their distance, and angle from the smart ball's sensors, while the emotion engine collects emotional data from the user's facial expressions and voice.

[0574] Data transmission phase

[0575] The device sends the collected sensor data and emotion data to a server at regular intervals, where it is aggregated.

[0576] Example: The device transmits running data and emotional data measured by the smart shoes to a server every minute via Wi-Fi.

[0577] Data reception and storage phase

[0578] The server receives sensor data and emotion data sent from the device via API, and the received data is immediately stored in a database.

[0579] Example: The server's API stores running data and emotional data received from the device in a database for analysis in real time.

[0580] Data analysis phase

[0581] The server then passes the sensor data and emotion data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to perform a detailed analysis of the data and generate evaluations of the player's technique, performance, and emotions.

[0582] Example: The server passes running data and emotional data to an AI module to identify areas for improvement in the athlete's pace, form, and motivation.

[0583] Teaching method generation phase

[0584] The server generates the optimal coaching method for each player based on the evaluation results generated by the AI. The coaching method includes specific training menus and advice for improving skills, as well as coaching that takes into account the user's motivation based on their emotional state.

[0585] Example: The server uses running data to generate stretching methods to improve knee angle and interval training menus three times a week, and adds advice such as "listen to music to increase motivation" based on data from the emotion engine.

[0586] Results feedback phase

[0587] The server sends the generated coaching method and advice based on emotions to the device, which receives it and displays it to the user. The user (coach or player) uses this information to train.

[0588] Example: Through a smartphone app, the device displays a message to the user saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees," along with a notification saying, "We recommend listening to your favorite music to motivate you."

[0589] Training implementation and feedback loop phase

[0590] The user (athlete) then performs training according to the proposed coaching methods and emotional advice. Sensor data and emotional data are continuously collected during and after training and sent back to the server for use in developing new evaluation results and improving the accuracy of coaching methods.

[0591] Example: A player performs training, and new sensor data and emotional data collected during that training are sent back to the server for analysis and use in the next training session.

[0592] This system will solve the problem of a shortage of instructors in educational settings and sports clubs, and will effectively support athletes in improving their performance and managing their motivation.

[0593] The processing flow will be explained below.

[0594] Step 1:

[0595] The terminal collects sensor data of players in real time from IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.). The IoT devices measure information such as players' movements, techniques, load, position, and speed. The terminal also uses an emotion engine to collect user emotional data (e.g., joy, anger, sadness, stress, etc.).

[0596] Example: The device collects data from smart shoes about the number of steps, acceleration, and ground contact time while running, and also obtains the user's current emotional state from their facial expressions and voice.

[0597] Step 2:

[0598] The device sends the collected sensor data and emotion data to the server at regular intervals (e.g., every minute).

[0599] Example: The device transmits running data measured by the smart shoes and the user's emotional data acquired by the emotion engine to a server via Wi-Fi.

[0600] Step 3:

[0601] The server receives sensor data and emotion data sent from the device via API and stores the received data in a database in real time.

[0602] Example: The server's API receives running and emotion data and immediately stores it in a database for analysis.

[0603] Step 4:

[0604] The server then passes the sensor data and emotion data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to analyze the data in detail and generate an evaluation of the player's technique and performance, while also evaluating the user's emotional state.

[0605] Example: The server passes running data and emotional data to an AI module to identify areas for improvement in the athlete's pace and form, as well as emotional fluctuations.

[0606] Step 5:

[0607] Based on the evaluation results generated by the AI, the server generates the optimal coaching method for each player, which includes specific training menus and advice for improving skills, as well as coaching that takes into account the user's motivation based on their emotional state.

[0608] Example: The server generates stretching methods to improve knee angle and interval training menus three times a week from running data, and adds advice such as "listen to music to increase motivation" based on the user's emotional state.

[0609] Step 6:

[0610] The server sends the generated coaching method and advice based on emotions to the device, which receives it and displays it to the user. The user (coach or player) uses this information to train.

[0611] Example: Through a smartphone app, the device displays a message to the user saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees," and a notification saying, "We recommend listening to your favorite music to motivate you."

[0612] Step 7:

[0613] The user (athlete) then performs training according to the proposed coaching methods and emotional advice. Sensor data and emotional data are continuously collected during and after training and sent back to the server for use in developing new evaluation results and improving the accuracy of coaching methods.

[0614] Example: A player performs training, and new sensor data and emotional data collected during that training are sent back to the server for analysis and use in the next training session.

[0615] Example 2

[0616] 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."

[0617] Conventional training systems have struggled to provide individually optimized coaching methods for improving athletes' performance and managing their motivation. Furthermore, they have not implemented coaching methods that take athletes' emotional states into account, and uniform coaching has resulted in insufficient improvement in athletes' motivation and performance. Furthermore, there is a lack of a process for reanalyzing post-training data, making it difficult to improve the accuracy of coaching methods. To solve these issues, a system is needed that can integrate and analyze athletes' sensor data and emotional data, and provide individually optimized coaching methods and advice based on their emotions.

[0618] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0619] In this invention, the server includes means for collecting sensor data of players from IoT devices, means for transmitting the sensor data collected by the terminal and the user's emotional data to the server, means for receiving the sensor data and emotional data transmitted by the server via an API and storing them in a database, means for automatically analyzing the stored sensor data and emotional data using a generation AI, means for generating individual coaching methods and emotional advice for the player based on the analysis results, means for transmitting the generated coaching methods and advice to the terminal, and means for the player to train based on the coaching methods and advice displayed on the terminal. This makes it possible to integrate and analyze the sensor data and emotional data of the player and provide individually optimized coaching methods and emotional advice.

[0620] An "IoT device" is a physical device that connects to the Internet and has the ability to collect and transmit data.

[0621] "Sensor data" refers to data obtained from IoT devices regarding players' movements, techniques, load, position, speed, etc.

[0622] "Emotion data" is data that indicates an emotional state such as joy, anger, sadness, or stress, obtained by analyzing the user's facial expressions and voice.

[0623] "Generative AI" is an artificial intelligence that uses machine learning algorithms to automatically analyze collected data and generate evaluation results of players' skills, performance, and emotions.

[0624] The "evaluation results" are information about the player's technique, performance status, and emotional state obtained by the generating AI analyzing sensor data and emotional data.

[0625] "Coaching methods" are training menus for individual players, advice for improving skills, and emotionally-based coaching content for increasing motivation, all generated based on the analysis results.

[0626] A "terminal" is a computing device for collecting and transmitting data from an IOT device to a server, and displaying the instructional methods received from the server to a user.

[0627] The "server" is a computing system that receives and stores data sent from the terminal, analyzes it using a generative AI, generates teaching methods, and sends them to the terminal.

[0628] The "database" is an information management system installed in the server for storing received sensor data and emotion data.

[0629] This invention is a system that combines IoT devices, generative AI, and an emotion engine to analyze sensor data and emotion data of athletes and provide individually optimized coaching methods. Hereinafter, specific embodiments for implementing this system will be described.

[0630] Use of IOT devices

[0631] The device collects sensor data from players using IoT devices such as smart shoes, smart clothing, and smart balls, allowing for detailed recording of players' movements, techniques, load, position, speed, etc. The device also incorporates an emotion engine that analyzes the user's facial expressions and voice in real time to collect emotional data.

[0632] As a specific example, the device collects the number of basketball shots, their distance, and angle from the smart ball's sensors, and also collects emotional data (e.g., joy, anger, sadness, stress, etc.) from the user's facial expressions and voice using an emotion engine.

[0633] Sending and Receiving Data

[0634] The device sends the collected sensor data and emotion data to a server via Wi-Fi or mobile data communication. This data is sent at regular intervals (for example, every minute) and received via the server's API. The received data is stored in a database in real time.

[0635] For example, the device transmits running data and emotional data measured by the smart shoes every minute to a server via Wi-Fi. The server's API stores the running data and emotional data received from the device in a database for analysis in real time.

[0636] Analyzing the data

[0637] The server then passes the sensor data and emotion data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to perform a detailed analysis of the data and generate evaluations of the player's technique, performance, and emotions.

[0638] As a concrete example, the server passes running data and emotional data to a generative AI module to identify areas for improvement in the athlete's pace, form, and motivation.

[0639] Teaching method generation

[0640] Based on the evaluation results generated by the AI, the server generates optimal coaching methods for each player, including specific training menus and advice for improving skills, as well as guidance to increase motivation based on the user's emotional state.

[0641] As a specific example, the server uses running data to generate stretching techniques to improve knee angle and a three-times-a-week interval training menu, and adds advice such as "listen to music to increase motivation" based on data from the emotion engine.

[0642] Feedback of results

[0643] The server sends the generated advice based on the coaching method and emotions to the terminal. The terminal receives it and displays it to the user. The user (coach or player) uses it as a reference for training.

[0644] For example, the device will display a message to the user through a smartphone app saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees," along with a notification saying, "We recommend listening to your favorite music to motivate you."

[0645] Training implementation and feedback loop

[0646] The user (athlete) then performs training according to the proposed coaching methods and emotion-based advice. New sensor data and emotion data are continuously collected during and after training, and are sent back to the server to be used to refine the new evaluation results and coaching methods.

[0647] As a concrete example, a player performs training, and new sensor data and emotional data collected during that training are sent back to the server, where they are used for the next analysis and for generating coaching methods.

[0648] This system can solve the problem of a shortage of instructors in educational settings and sports clubs, and effectively support athletes in improving their performance and managing their motivation.

[0649] Example prompts to input to the generative AI model

[0650] "Analyze this athlete's running and emotional data and generate advice to improve their technique and coaching methods to increase their motivation."

[0651] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0652] Step 1:

[0653] Input: Sensor data from IOT devices and emotion data from built-in cameras and microphones

[0654] Processing: The terminal communicates with IoT devices (smart shoes, smart wear, smart balls, etc.) to collect sensor data, and at the same time collects emotion data using the built-in camera and microphone. For example, distance and speed information is obtained from smart shoes, and the user's facial expressions are captured with the camera and analyzed by the emotion engine.

[0655] Output: Sensor data and emotion data

[0656] Step 2:

[0657] Input: Sensor data and emotion data

[0658] Processing: The device sends the collected sensor data and emotion data to the server via Wi-Fi or mobile communication. Every minute, the data is sent to the server's API endpoint via an HTTP POST request. For example, running data and emotion data are sent in JSON format.

[0659] Output: Sensor data and emotion data sent to the server

[0660] Step 3:

[0661] Input: Sensor data and emotion data sent to the server

[0662] Processing: The server receives the sensor data and emotion data via the API. The API parses the HTTP request and generates a query to store it in the database. For example, it sends an insert query to the database to store the sensor data in the "sensor table" and the emotion data in the "emotion table."

[0663] Output: Sensor data and emotion data stored in a database

[0664] Step 4:

[0665] Input: Sensor data and emotion data stored in a database

[0666] Processing: The server passes the stored data to the generative AI model, which then uses machine learning algorithms to evaluate the athlete's technical performance and emotions, such as running pace, form, and the user's motivation.

[0667] Output: Technical, performance and emotional evaluation results

[0668] Step 5:

[0669] Input: Evaluation result

[0670] Processing: The server generates personalized coaching methods and emotional advice for each player based on the evaluation results. Using specific algorithms, it generates training menus, advice for improving technique, and motivational guidance. For example, it generates stretching methods to improve knee angle and a menu of interval training sessions three times a week, and adds advice such as "listen to your favorite music" based on data from the emotion engine.

[0671] Output: Generated teaching methods and emotion-based advice

[0672] Step 6:

[0673] Input: Generated teaching methods and emotion-based advice

[0674] Processing: The server sends the generated training method and advice to the device. It sends data to the device via an HTTP POST request. For example, it sends data containing training menus and motivational advice in JSON format.

[0675] Output: Instructions and advice sent to the device

[0676] Step 7:

[0677] Input: Instructions and advice sent to the device

[0678] Processing: The device displays the received training methods and advice to the user. The smartphone app displays a notification to inform the user of specific training content and motivational advice. For example, a notification may be displayed saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees."

[0679] Output: Instructions and advice displayed to the user

[0680] Step 8:

[0681] Input: Instructions and advice displayed to the user

[0682] Processing: The user performs training according to the suggested instructional methods and emotion-based advice. For example, the user performs the suggested stretching methods and training menu.

[0683] Output: New sensor and emotion data during and after training

[0684] Step 9:

[0685] Input: New sensor and emotion data during and after training

[0686] Processing: The device again collects new sensor data and emotion data during and after training and sends them to the server. For example, it collects new running data and emotion data and sends them to the server via Wi-Fi.

[0687] Output: New sensor and emotion data sent to the server.

[0688] This creates a feedback loop that continually improves players' performance and motivates them.

[0689] (Application example 2)

[0690] 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."

[0691] Conventional driving assistance systems and training assistance systems simply collect and analyze driving and training data and provide the results, without adequately considering the user's emotional state or motivation. Therefore, there is a growing need for a system that can appropriately evaluate a user's emotions and stress state and provide optimal advice based on that evaluation. The present invention aims to solve this problem by providing a system that provides individually optimized driving assistance and training assistance.

[0692] 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.

[0693] In this invention, the server includes means for collecting sensor data and emotional data of the player from the IoT device, means for transmitting the collected sensor data and emotional data to the server, means for storing the transmitted sensor data and emotional data in the server, means for automatically analyzing the stored sensor data and emotional data using a generation AI, means for generating a coaching method and emotion-based motivational advice for the player based on the analysis results of the generation AI, means for transmitting the generated coaching method and emotion-based motivational advice to a terminal, and means for the player to train based on the coaching method and emotion-based motivational advice displayed on the terminal. This enables individually optimized driving assistance and training assistance that takes into account the user's emotional state.

[0694] An "IoT device" is a physical device that can connect to the internet and collect and exchange data.

[0695] "Sensor data" refers to information on various physical quantities such as movement, position, temperature, and pressure obtained from IoT devices.

[0696] "Emotion data" is information about the user's emotional state, such as joy, anger, sadness, or stress, obtained by face recognition or voice recognition.

[0697] "Generative AI" is an artificial intelligence technology that automatically generates new information and results based on input data.

[0698] "Instruction methods" are advice and suggestions for optimal exercise and training for users, generated based on the analysis results of the generative AI.

[0699] "Motivation advice" is advice and suggestions based on emotional data to maintain and improve a user's motivation.

[0700] A "server" is a computer system for collecting, storing, analyzing, and transmitting data over a network.

[0701] "Terminal" means a device that a user directly operates and uses to display and receive information, including smartphones and tablets.

[0702] "Analysis results" are the output information generated by analyzing sensor data and emotional data using the generation AI.

[0703] "Workout" means any physical or technical exercise or practice performed by a user.

[0704] This invention is a system that combines IoT devices, generative AI, and an emotion engine to analyze sensor data and emotion data of athletes and drivers, and provide optimized coaching methods and motivational advice. An embodiment of this system is described in detail below.

[0705] First, we will describe the system's hardware configuration. The system uses IoT devices (e.g., driver seat sensors, in-car cameras, smart clothing, smart shoes, etc.) to collect data on athletes and drivers. These devices collect sensor data such as movement, position, speed, facial expressions, and voice, as well as emotional data.

[0706] Next, we will explain the device. The device takes the form of a smartphone or tablet and provides an interface with the user. The device sends the collected data to the server and displays the instruction methods and advice from the server to the user. The device also connects to the server via Wi-Fi or mobile data communication.

[0707] The server is the central processing unit of this system and is responsible for the following processes: First, it receives sensor data and emotion data sent from the device via an API and stores it in a database in real time. Next, it passes the stored data to the generative AI, which then automatically begins analyzing it. The generative AI analyzes the data using machine learning algorithms and generates evaluation results regarding the user's behavioral patterns and emotional state. Well-known generative AI models such as GPT-3 and BERT are used for this.

[0708] Based on the analysis results, the server generates optimal instruction methods and emotionally-based motivational advice for the user. This process includes, for example, specific action plans and training menus for safe driving, as well as advice for improving skills. Based on the emotional data, the server also generates suggestions for music and break timing to maintain and improve motivation.

[0709] The generated instruction methods and motivation advice are sent back to the device and notified to the user. The user uses this information to drive or train. Furthermore, new sensor data and emotional data collected during and after the training are sent back to the server and used to improve the accuracy of the next instruction methods and advice.

[0710] As a concrete example, the following prompt sentences could be input to a generative AI model:

[0711] Analyze driving and emotional data to generate advice for safe and comfortable driving.

[0712] Operation data: {Operation data: . . .}

[0713] Emotion data: {Emotion data: . . .}

[0714] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0715] Step 1:

[0716] Data Collection Phase

[0717] The terminal collects driving and emotion data in real time from IoT devices such as driver seat sensors, in-car cameras, and smart clothing. Specifically, the driver seat sensors collect pressure data, the in-car cameras collect facial expression data through facial recognition, and the microphone collects voice data. The terminal integrates this data and temporarily stores it as an initial data set.

[0718] Input: Data obtained from driver seat sensors, in-car cameras, microphones, etc.

[0719] Output: Temporarily saved initial dataset

[0720] Step 2:

[0721] Data transmission phase

[0722] The device sends the collected sensor data and emotion data to the server at regular intervals (e.g., every minute) using Wi-Fi or mobile data. The device confirms that the data was sent properly and displays a success message to the user.

[0723] Input: Temporarily saved initial dataset

[0724] Output: Data sent to the server, and a notification message to the user

[0725] Step 3:

[0726] Data reception and storage phase

[0727] The server receives sensor data and emotion data sent from the device via API. The received data is stored in a database in real time. The server confirms that the data has been stored and records it in a log.

[0728] Input: Data sent from the terminal

[0729] Output: Data stored in the database, and log entries

[0730] Step 4:

[0731] Data analysis phase

[0732] The server passes the sensor data and emotion data stored in the database to the generative AI, which then automatically begins analysis. Using a generative AI model (such as GPT-3 or BERT), the server evaluates driving behavior and emotional state and generates analysis results based on that.

[0733] For example, the following prompts could be input to the generator:

[0734] Analyze driving and emotional data to generate advice for safe and comfortable driving.

[0735] Operation data: {Operation data: . . .}

[0736] Emotion data: {Emotion data: . . .}

[0737] Input: Sensor data and emotion data stored in a database

[0738] Output: Analysis results generated by generative AI

[0739] Step 5:

[0740] Teaching method generation phase

[0741] Based on the analysis results provided by the AI, the server generates optimal instruction methods and motivational advice for the user, such as suggestions for adjusting speed and timing breaks for safe driving, and music recommendations for stress reduction.

[0742] Input: Analysis results generated by generative AI

[0743] Output: Optimal teaching methods and motivation advice for users

[0744] Step 6:

[0745] Results feedback phase

[0746] The server sends the generated teaching method and motivation advice to the terminal, which receives it, displays it to the user as a notification, and also provides feedback to the server that the user has confirmed the notification.

[0747] Input: Server-generated instructional and motivational advice

[0748] Output: Notifications displayed to the user and feedback to the server

[0749] Step 7:

[0750] Training implementation and feedback loop phase

[0751] The user drives or trains based on the instruction methods and motivation advice displayed on the device. New sensor data and emotional data are collected during and after the training and sent to the server via the device. This allows the system to improve the accuracy of the next training methods and motivation advice.

[0752] Input: User driving data and emotion data

[0753] Output: Data used to generate new teaching methods and motivational advice

[0754] 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.

[0755] 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.

[0756] 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.

[0757] [Third embodiment]

[0758] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0759] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0760] 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).

[0761] 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.

[0762] 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.

[0763] 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).

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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."

[0770] This invention is a system that uses IoT devices and generative AI to analyze sensor data from athletes and provide individually optimized coaching methods. The program processing of this system is explained in detail below.

[0771] Data Collection Phase

[0772] The terminal collects real-time sensor data from players' IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.), which records detailed information about players' movements, techniques, loads, positions, speeds, etc.

[0773] Example: The device collects the number of basketball shots, distance, and angle from the smart ball's sensor.

[0774] Data transmission phase

[0775] The device sends the collected sensor data to a server, where it is collected at regular intervals.

[0776] Example: The device sends running data measured by the smart shoes to the server every minute.

[0777] Data reception and storage phase

[0778] The server receives the sensor data sent from the devices and stores it in a database, where each player's data is stored in chronological order for later analysis.

[0779] Example: The server's API receives running data from a smartphone and stores it in a NoSQL database.

[0780] Data analysis phase

[0781] The server then passes the stored sensor data to the AI ​​generator, which then uses machine learning algorithms to analyze the data in detail and evaluate the player's technique and performance.

[0782] Example: The server analyzes running data to identify areas for improvement in a player's pace and form.

[0783] Teaching method generation phase

[0784] The server generates the optimal coaching method for each player based on the AI-generated evaluation results, including specific training menus and advice for improving skills.

[0785] Example: The server uses running data to suggest stretching methods and interval training to improve the angle of the athlete's knees.

[0786] Results feedback phase

[0787] The server sends the generated instruction method to the terminal, which receives it and displays it to the user. The user (instructor or player) then uses this information to provide training and technical instruction.

[0788] Example: The device displays a notification to the athlete via a smartphone app, saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees."

[0789] Training implementation and feedback loop phase

[0790] The user (athlete) will then train based on the proposed training method. Sensor data will be collected during the training and used for further analysis.

[0791] Example: Athletes train and the data collected during training is sent back to the server to help improve the accuracy of evaluation results and coaching methods.

[0792] This system will solve the problem of a shortage of instructors in educational settings and sports clubs, and will effectively support athletes in improving their performance.

[0793] The processing flow will be explained below.

[0794] Step 1:

[0795] The terminal collects real-time sensor data from players' IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.), which measure information such as players' movements, techniques, load, position, and speed.

[0796] Example: The device collects the number of steps, acceleration, and ground contact time from smart shoes.

[0797] Step 2:

[0798] The device sends the collected sensor data to a server using a secure communication protocol at regular intervals.

[0799] Example: The device sends running data measured by the smart shoes to a server every minute via Wi-Fi.

[0800] Step 3:

[0801] The server receives sensor data sent from the device via API, and the received data is immediately stored in a database.

[0802] Example: The server's API stores the running data received from the device in an analysis database in real time.

[0803] Step 4:

[0804] The server then passes the sensor data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to analyze the data and generate evaluation results for the player's movements and techniques.

[0805] Example: The server passes running data to an AI module to identify areas for improvement in the athlete's pace and form.

[0806] Step 5:

[0807] Based on the evaluation results, the server generates a coaching method optimized for each player, including specific training menus and advice for improving their skills.

[0808] Example: The server uses running data to generate stretching techniques to improve knee angle and interval training menus three times a week.

[0809] Step 6:

[0810] The server sends the generated training method to the terminal, which then displays the received training method to the user. The user (instructor or player) uses this information to train.

[0811] Example: The device displays a notification to the user through a smartphone app saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees."

[0812] Step 7:

[0813] The user (athlete) conducts training based on the proposed coaching method. Sensor data is continuously collected during and after the training and sent back to the server for use in new evaluation results and to improve the accuracy of the coaching method.

[0814] Example: A player performs training, and new data collected during that training is sent back to the server for analysis and use in the next training session.

[0815] Example 1

[0816] 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."

[0817] In traditional sports coaching, providing optimal training methods for individual athletes requires the resources of specialized instructors. However, due to factors such as a lack of instructors and limited coaching time, it is difficult to provide sufficient instruction to all athletes. It is also difficult to efficiently collect and analyze athletes' performance data in detail, making it difficult to provide optimal instruction to each individual athlete. Given this background, there is a demand for a system that uses IoT devices and generative AI to analyze athletes' sensor data and provide individually optimized coaching methods.

[0818] 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.

[0819] In this invention, the server includes means for collecting sensor data of athletes from IOT devices, means for transmitting the collected sensor data to the server at regular intervals, means for the server to store the transmitted sensor data in a database, means for analyzing the stored sensor data using a machine learning algorithm, means for generating an individual coaching method for the athletes based on the analysis results, means for transmitting the generated coaching method from the server to a terminal, means for the athletes to train based on the coaching method displayed on the terminal, and means for re-collecting sensor data during training and using it for analysis. This makes it possible to provide an effective and individually optimized coaching method for each athlete.

[0820] An "IoT device" is a device that is connected to the Internet and can use various sensors to detect and measure the condition of the environment and objects, and collect data.

[0821] "Sensor data" refers to various types of information collected through IoT devices, specifically data on players' movements, techniques, load, position, speed, etc.

[0822] A "terminal" is a computing device that connects to other devices or systems, sends and receives data, and performs processing, and specifically includes smartphones and tablets.

[0823] A "server" is a dedicated computer system that responds to requests from other devices or systems on a network and stores and processes data.

[0824] A "database" refers to a collection of structured information that can efficiently store large amounts of data and enable manipulation and search, and includes NoSQL databases and relational databases.

[0825] A "machine learning algorithm" is a computer programming technique that learns patterns from data and makes predictions, classifications, and analyses, including generative AI models.

[0826] "Coaching methods" refer to specific training menus, advice for improving techniques, and concrete action plans provided to improve players' performance.

[0827] "Analysis results" refers to information generated as a result of data processing using machine learning algorithms, and includes evaluations of players' skills and performance, as well as areas for improvement.

[0828] This invention is a system that utilizes IoT devices and generative AI to analyze sensor data of athletes and provide individually optimized coaching methods. Specific embodiments for implementing the invention are described below.

[0829] Hardware and software used

[0830] Terminal: IoT device (e.g. smart shoes, smart wear, smart ball, etc.)

[0831] Server: Database server (e.g. NoSQL database, MongoDB)

[0832] Generative AI models: machine learning algorithms (e.g., TensorFlow, scikit-learn)

[0833] Network communication: Bluetooth, Wi-Fi, HTTP API

[0834] Data collection

[0835] The terminal uses IoT devices to collect sensor data from players. For example, smart shoes collect running data (position, speed, foot angle, etc.) The terminal communicates with the smart ball's sensor using Bluetooth to collect data such as the number of shots, distance, and angle.

[0836] Data transmission

[0837] The device sends the collected sensor data to the server at regular intervals (e.g., every minute). The data is sent using an HTTP POST request to the server's API endpoint. For example, the device sends the collected running data to the server every minute.

[0838] Data reception and storage

[0839] The server receives sensor data sent from the device and stores it in a database. The database uses a NoSQL database (e.g., MongoDB) and stores the data in chronological order. For example, the server's API receives running data sent from a smartphone and stores it in a NoSQL database.

[0840] Data analysis

[0841] The server analyzes the stored sensor data using machine learning algorithms. Generative AI models are used to evaluate the player's technique and performance. For example, the server uses Python machine learning libraries (e.g., TensorFlow and scikit-learn) to analyze running data and identify areas for improvement in the player's pace and form.

[0842] Instruction method generation

[0843] The server generates personalized coaching methods for each athlete based on the analysis results. These include specific training menus, advice for improving technique, and action plans. For example, the server uses a generative AI model to generate suggestions for stretching and interval training to improve a player's knee angle based on running data.

[0844] Results feedback

[0845] The server sends the generated training method to the device, and the device notifies the user. The user (instructor or player) performs training or technical instruction based on the notification content. As a specific example, the server sends the training method to the device using an HTTP POST request, and the device displays on the smartphone app, "Perform interval training three times a week and try stretching methods to improve knee angle."

[0846] Training implementation and feedback loop

[0847] The user (athlete) performs training based on the proposed coaching method. Sensor data during training is collected again and analyzed again to improve the accuracy of the coaching method. As a specific example, the athlete performs training, and new data collected by the smart shoes during training is sent again via the device to the server, which then analyzes it again.

[0848] Prompt Sentence Examples

[0849] "The running data collected by the smart shoes should be analyzed in real time, and an algorithm should be generated to suggest the optimal training method for each individual athlete based on their pace and form. Specifically, this should include suggestions for stretching methods and interval training to improve the athlete's knee angle."

[0850] This system can solve the problem of a shortage of instructors in educational settings and sports clubs, and effectively support athletes in improving their performance.

[0851] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0852] Step 1: Data collection

[0853] The terminal uses IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.) to collect sensor data of players in real time, including their movements, technique, load, position, speed, etc.

[0854] Input: Sensor data from IOT devices

[0855] Data processing: Real-time data collection and format conversion

[0856] Output: Formatted sensor data

[0857] Specific operation: The device communicates with the smart ball's sensors using Bluetooth and Wi-Fi to collect information such as the number of shots, distance, and angle.

[0858] Step 2: Send data

[0859] The device sends the collected sensor data to the server at regular intervals, typically every one or five minutes.

[0860] Input: Collected sensor data

[0861] Data processing: Packetizing data and network protocol processing

[0862] Output: Data packet sent to the server

[0863] Specific operation: The device sends the collected running data every minute by sending an HTTP POST request to the server's API endpoint.

[0864] Step 3: Data reception and storage

[0865] The server receives the sensor data sent from the devices and stores it in a database, where each player's data is stored in chronological order for later analysis.

[0866] Input: Data packets sent from the device

[0867] Data processing: Data analysis, format conversion, and storage in a database

[0868] Output: Stored time series data

[0869] Specific operation: The server's API receives running data sent from the smartphone and stores it in a NoSQL database (e.g., MongoDB).

[0870] Step 4: Data analysis

[0871] The server analyzes the stored sensor data using machine learning algorithms, and uses generative AI models to evaluate players' skills and performance.

[0872] Input: Stored time series data

[0873] Data Computing: Data analysis and performance evaluation using machine learning algorithms

[0874] Output: Player performance evaluation results

[0875] What it does: The server uses Python machine learning libraries (e.g., TensorFlow and scikit-learn) to analyze running data and identify areas for improvement in the athlete's pace and form.

[0876] Step 5: Instructional method generation

[0877] Based on the analysis results, the server generates the optimal coaching method for each player, including specific training menus and advice for improving their skills.

[0878] Input: Player performance evaluation results

[0879] Data calculation: generating instruction methods and creating training menus

[0880] Output: Individually optimized teaching methods

[0881] How it works: The server uses a generative AI model to suggest stretching techniques and interval training to improve the athlete's knee angle based on running data.

[0882] Step 6: Feedback

[0883] The server sends the generated instruction method to the terminal, which then notifies the user. The user (instructor or player) then performs training and technical instruction based on this notification.

[0884] Input: Individually optimized teaching methods

[0885] Data processing: Packetizing feedback data and generating notifications

[0886] Output: Instructional method notified to the user

[0887] Specific operation: The server sends the training method to the device using an HTTP POST request, and the device uses its notification function to display a notification on the smartphone app saying, "Perform interval training three times a week and try stretching methods to improve knee angle by 10 degrees."

[0888] Step 7: Training and feedback loop

[0889] The user (athlete) will then train based on the proposed coaching method. Sensor data during training will be collected and analyzed again to improve the accuracy of the coaching method.

[0890] Input: Newly collected sensor data

[0891] Data processing: Real-time data collection, transmission, storage, and analysis, repeated

[0892] Output: Improved teaching methods

[0893] Specific operation: The athlete performs training, and new data collected during that time is sent to the server via the device again, and the server then analyzes it again.

[0894] As described above, this system can provide individually optimized teaching methods through each processing step.

[0895] (Application example 1)

[0896] 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."

[0897] Conventional factory robot operation management and maintenance is based on specific patterns, which makes it inefficient and difficult to take preventative measures against failures.In addition, there is no system in place to provide specific instructions or maintenance plans aimed at improving operation efficiency and reducing the risk of failure, making it difficult to prevent problems before they occur.

[0898] 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.

[0899] In this invention, the server includes means for collecting machine sensor data from an IOT device, means for transmitting the collected sensor data to a central processing unit, means for storing the transmitted sensor data in the central processing unit, means for automatically analyzing the stored sensor data using a generation AI, means for generating operation instructions and maintenance methods for each machine based on the analysis results, means for transmitting the generated operation instructions and maintenance methods to a terminal, and means for controlling the machine based on the operation instructions and maintenance methods displayed on the terminal. This makes it possible to optimize the operating efficiency of the machine and preventatively reduce the risk of breakdown.

[0900] "IOT devices" are various sensors and devices connected to the Internet that collect and transmit data in real time.

[0901] "Machine" is a general term for automated equipment and devices used to perform specific tasks in a factory.

[0902] "Sensor data" is data collected by IoT devices that indicates the state of an object or environment.

[0903] A "central processing unit" is a server or computer system for receiving, storing, and analyzing collected sensor data.

[0904] "Generative AI" is artificial intelligence that uses machine learning algorithms to automatically analyze sensor data and generate optimal operating instructions and maintenance methods.

[0905] "Operational instructions" are specific instructions proposed by the generative AI based on the results of analyzing sensor data to improve the operating efficiency of the machine.

[0906] A "maintenance method" is a specific maintenance procedure for maintaining the safety and performance of a machine, proposed by the generative AI based on the results of analyzing sensor data.

[0907] "Terminal" refers to a device for displaying generated operating instructions and maintenance methods, and includes control systems and display devices.

[0908] This invention is a system that combines IoT devices, central processing units, generative AI models, and terminals to optimize the operating efficiency of machines in a factory.

[0909] First, various IoT devices are attached to each machine, such as motion sensors, pressure sensors, distance sensors, etc. These IoT devices collect data on the machine's operating status, pressure, position, speed, etc. in real time. The collected sensor data is sent to a central processing unit at regular intervals.

[0910] The central processing unit receives the collected sensor data and stores it in a database. The database used is a NoSQL database with the ability to store data in chronological order. This database stores daily operating data and maintenance information for each machine, which is used for later analysis.

[0911] Next, the central processing unit passes the stored sensor data to the generation AI, which begins analysis. The generation AI uses machine learning algorithms to perform detailed analysis of the collected data. Specifically, the analysis is aimed at improving operational efficiency and reducing the risk of breakdowns. For example, it can identify abnormal operation patterns based on past data, enabling predictive maintenance. It can also generate operational instructions to improve operational efficiency.

[0912] Based on the analysis results, the AI ​​generates optimal operating instructions and maintenance methods for each machine. This includes specific instructions to improve operating efficiency and inspection procedures to prevent breakdowns. This information is sent from the central processing unit to the terminal.

[0913] The terminal displays the received operation instructions and maintenance methods on a display, providing real-time information to robot operators and maintenance personnel using the control system and display device.

[0914] As a specific example, if the pressure sensor data is judged to be excessive, the generation AI will generate an operation instruction such as, "The machine's current gripping pressure is excessive. By reducing the pressure by 20%, it will be possible to hold the object stably while reducing energy consumption." Also, if abnormal movement is detected from the motion sensor data, the AI ​​will provide a maintenance method such as, "The operating angle of the robot's arm is outside the normal range, so we recommend regular maintenance and part replacement."

[0915] Additionally, examples of prompts for generative AI models include:

[0916] "Please provide guidance on how to improve operational efficiency and reduce the risk of breakdowns based on the robot's motion sensor data and pressure sensor data."

[0917] This allows the operating efficiency of machines in the factory to be continuously improved, and also makes it possible to take preventive measures against breakdowns.

[0918] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0919] Step 1:

[0920] Sensor data is collected from IOT devices. The server acquires data in real time from motion sensors, pressure sensors, and distance sensors attached to the machine. The input is data from each sensor, and the output is a set of sensor data. Specifically, data such as the machine's operating status, pressure, position, and speed are collected.

[0921] Step 2:

[0922] The collected sensor data is sent to a central processing unit. The server sends the collected sensor data to a database at regular intervals. The input is the collected sensor data, and the output is the data stored in the database. Specifically, the sensor data is formatted in JSON format and sent to a NoSQL database.

[0923] Step 3:

[0924] The transmitted sensor data is stored in the central processing unit. The server stores the received sensor data in a database in chronological order. The input is the transmitted sensor data, and the output is the data stored in the database. Specifically, a new entry is added to the database and saved together with the previous data.

[0925] Step 4:

[0926] The stored sensor data is passed to the generation AI to begin analysis. The server retrieves the sensor data stored in the database and sends it to the generation AI to request analysis. The input is the sensor data read from the database, and the output is the analysis results by the generation AI. Specifically, it uses a REST API to communicate with the generation AI and send data.

[0927] Step 5:

[0928] Generative AI analyzes sensor data to evaluate operational efficiency and risk of failure. It uses machine learning algorithms to analyze the data and identify abnormal patterns and optimization points. The input is the transmitted sensor data, and the output is the analysis results. Specifically, generative AI compares data with past data and detects outliers.

[0929] Step 6:

[0930] Based on the analysis results of the generation AI, the server generates operating instructions and maintenance methods for each machine. Based on the analysis results of the generation AI, the server creates optimal operating instructions and maintenance methods. The input is the analysis results of the generation AI, and the output is specific operating instructions and maintenance methods. Specifically, clear instructions such as "reduce pressure by 20%" and "adjust the operating angle of the arm" are generated.

[0931] Step 7:

[0932] The generated operation instructions and maintenance methods are sent to the terminal. The server sends the generated instruction contents to the terminal and displays them. The input is the generated operation instructions and maintenance methods, and the output is the information displayed on the terminal. Specifically, each instruction content is formatted in text format and sent to the terminal.

[0933] Step 8:

[0934] Machine control is based on the operating instructions and maintenance methods displayed on the terminal. The user checks the instructions displayed on the terminal and operates or maintains the machine based on them. The input is the operating instructions and maintenance methods displayed on the terminal, and the output is the results of the user's operation of the machine. Specifically, the user performs operations such as adjusting pressure and replacing parts.

[0935] This enables the system to continuously improve the operating efficiency of machines in the factory and proactively manage the risk of breakdowns.

[0936] 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.

[0937] This invention is a system that combines IoT devices, generative AI, and an emotion engine to analyze sensor data and emotion data of players and provide individually optimized coaching methods. The program processing of this system is explained in detail below.

[0938] Data Collection Phase

[0939] The terminal collects sensor data of players in real time from IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.). This data records players' movements, techniques, loads, positions, speeds, etc. in detail. The terminal also uses an emotion engine to collect users' emotional data (e.g., joy, anger, sadness, stress, etc.) in real time.

[0940] Example: The device collects the number of basketball shots, their distance, and angle from the smart ball's sensors, while the emotion engine collects emotional data from the user's facial expressions and voice.

[0941] Data transmission phase

[0942] The device sends the collected sensor data and emotion data to a server at regular intervals, where it is aggregated.

[0943] Example: The device transmits running data and emotional data measured by the smart shoes to a server every minute via Wi-Fi.

[0944] Data reception and storage phase

[0945] The server receives sensor data and emotion data sent from the device via API, and the received data is immediately stored in a database.

[0946] Example: The server's API stores running data and emotional data received from the device in a database for analysis in real time.

[0947] Data analysis phase

[0948] The server then passes the sensor data and emotion data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to perform a detailed analysis of the data and generate evaluations of the player's technique, performance, and emotions.

[0949] Example: The server passes running data and emotional data to an AI module to identify areas for improvement in the athlete's pace, form, and motivation.

[0950] Teaching method generation phase

[0951] The server generates the optimal coaching method for each player based on the evaluation results generated by the AI. The coaching method includes specific training menus and advice for improving skills, as well as coaching that takes into account the user's motivation based on their emotional state.

[0952] Example: The server uses running data to generate stretching methods to improve knee angle and interval training menus three times a week, and adds advice such as "listen to music to increase motivation" based on data from the emotion engine.

[0953] Results feedback phase

[0954] The server sends the generated coaching method and advice based on emotions to the device, which receives it and displays it to the user. The user (coach or player) uses this information to train.

[0955] Example: Through a smartphone app, the device displays a message to the user saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees," along with a notification saying, "We recommend listening to your favorite music to motivate you."

[0956] Training implementation and feedback loop phase

[0957] The user (athlete) then performs training according to the proposed coaching methods and emotional advice. Sensor data and emotional data are continuously collected during and after training and sent back to the server for use in developing new evaluation results and improving the accuracy of coaching methods.

[0958] Example: A player performs training, and new sensor data and emotional data collected during that training are sent back to the server for analysis and use in the next training session.

[0959] This system will solve the problem of a shortage of instructors in educational settings and sports clubs, and will effectively support athletes in improving their performance and managing their motivation.

[0960] The processing flow will be explained below.

[0961] Step 1:

[0962] The terminal collects sensor data of players in real time from IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.). The IoT devices measure information such as players' movements, techniques, load, position, and speed. The terminal also uses an emotion engine to collect user emotional data (e.g., joy, anger, sadness, stress, etc.).

[0963] Example: The device collects data from smart shoes about the number of steps, acceleration, and ground contact time while running, and also obtains the user's current emotional state from their facial expressions and voice.

[0964] Step 2:

[0965] The device sends the collected sensor data and emotion data to the server at regular intervals (e.g., every minute).

[0966] Example: The device transmits running data measured by the smart shoes and the user's emotional data acquired by the emotion engine to a server via Wi-Fi.

[0967] Step 3:

[0968] The server receives sensor data and emotion data sent from the device via API and stores the received data in a database in real time.

[0969] Example: The server's API receives running and emotion data and immediately stores it in a database for analysis.

[0970] Step 4:

[0971] The server then passes the sensor data and emotion data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to analyze the data in detail and generate an evaluation of the player's technique and performance, while also evaluating the user's emotional state.

[0972] Example: The server passes running data and emotional data to an AI module to identify areas for improvement in the athlete's pace and form, as well as emotional fluctuations.

[0973] Step 5:

[0974] Based on the evaluation results generated by the AI, the server generates the optimal coaching method for each player, which includes specific training menus and advice for improving skills, as well as coaching that takes into account the user's motivation based on their emotional state.

[0975] Example: The server generates stretching methods to improve knee angle and interval training menus three times a week from running data, and adds advice such as "listen to music to increase motivation" based on the user's emotional state.

[0976] Step 6:

[0977] The server sends the generated coaching method and advice based on emotions to the device, which receives it and displays it to the user. The user (coach or player) uses this information to train.

[0978] Example: Through a smartphone app, the device displays a message to the user saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees," and a notification saying, "We recommend listening to your favorite music to motivate you."

[0979] Step 7:

[0980] The user (athlete) then performs training according to the proposed coaching methods and emotional advice. Sensor data and emotional data are continuously collected during and after training and sent back to the server for use in developing new evaluation results and improving the accuracy of coaching methods.

[0981] Example: A player performs training, and new sensor data and emotional data collected during that training are sent back to the server for analysis and use in the next training session.

[0982] Example 2

[0983] 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."

[0984] Conventional training systems have struggled to provide individually optimized coaching methods for improving athletes' performance and managing their motivation. Furthermore, they have not implemented coaching methods that take athletes' emotional states into account, and uniform coaching has resulted in insufficient improvement in athletes' motivation and performance. Furthermore, there is a lack of a process for reanalyzing post-training data, making it difficult to improve the accuracy of coaching methods. To solve these issues, a system is needed that can integrate and analyze athletes' sensor data and emotional data, and provide individually optimized coaching methods and advice based on their emotions.

[0985] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0986] In this invention, the server includes means for collecting sensor data of players from IoT devices, means for transmitting the sensor data collected by the terminal and the user's emotional data to the server, means for receiving the sensor data and emotional data transmitted by the server via an API and storing them in a database, means for automatically analyzing the stored sensor data and emotional data using a generation AI, means for generating individual coaching methods and emotional advice for the player based on the analysis results, means for transmitting the generated coaching methods and advice to the terminal, and means for the player to train based on the coaching methods and advice displayed on the terminal. This makes it possible to integrate and analyze the sensor data and emotional data of the player and provide individually optimized coaching methods and emotional advice.

[0987] An "IoT device" is a physical device that connects to the Internet and has the ability to collect and transmit data.

[0988] "Sensor data" refers to data obtained from IoT devices regarding players' movements, techniques, load, position, speed, etc.

[0989] "Emotion data" is data that indicates an emotional state such as joy, anger, sadness, or stress, obtained by analyzing the user's facial expressions and voice.

[0990] "Generative AI" is an artificial intelligence that uses machine learning algorithms to automatically analyze collected data and generate evaluation results of players' skills, performance, and emotions.

[0991] The "evaluation results" are information about the player's technique, performance status, and emotional state obtained by the generating AI analyzing sensor data and emotional data.

[0992] "Coaching methods" are training menus for individual players, advice for improving skills, and emotionally-based coaching content for increasing motivation, all generated based on the analysis results.

[0993] A "terminal" is a computing device for collecting and transmitting data from an IOT device to a server, and displaying the instructional methods received from the server to a user.

[0994] The "server" is a computing system that receives and stores data sent from the terminal, analyzes it using a generative AI, generates teaching methods, and sends them to the terminal.

[0995] The "database" is an information management system installed in the server for storing received sensor data and emotion data.

[0996] This invention is a system that combines IoT devices, generative AI, and an emotion engine to analyze sensor data and emotion data of athletes and provide individually optimized coaching methods. Hereinafter, specific embodiments for implementing this system will be described.

[0997] Use of IOT devices

[0998] The device collects sensor data from players using IoT devices such as smart shoes, smart clothing, and smart balls, allowing for detailed recording of players' movements, techniques, load, position, speed, etc. The device also incorporates an emotion engine that analyzes the user's facial expressions and voice in real time to collect emotional data.

[0999] As a specific example, the device collects the number of basketball shots, their distance, and angle from the smart ball's sensors, and also collects emotional data (e.g., joy, anger, sadness, stress, etc.) from the user's facial expressions and voice using an emotion engine.

[1000] Sending and Receiving Data

[1001] The device sends the collected sensor data and emotion data to a server via Wi-Fi or mobile data communication. This data is sent at regular intervals (for example, every minute) and received via the server's API. The received data is stored in a database in real time.

[1002] For example, the device transmits running data and emotional data measured by the smart shoes every minute to a server via Wi-Fi. The server's API stores the running data and emotional data received from the device in a database for analysis in real time.

[1003] Analyzing the data

[1004] The server then passes the sensor data and emotion data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to perform a detailed analysis of the data and generate evaluations of the player's technique, performance, and emotions.

[1005] As a concrete example, the server passes running data and emotional data to a generative AI module to identify areas for improvement in the athlete's pace, form, and motivation.

[1006] Teaching method generation

[1007] Based on the evaluation results generated by the AI, the server generates optimal coaching methods for each player, including specific training menus and advice for improving skills, as well as guidance to increase motivation based on the user's emotional state.

[1008] As a specific example, the server uses running data to generate stretching techniques to improve knee angle and a three-times-a-week interval training menu, and adds advice such as "listen to music to increase motivation" based on data from the emotion engine.

[1009] Feedback of results

[1010] The server sends the generated advice based on the coaching method and emotions to the terminal. The terminal receives it and displays it to the user. The user (coach or player) uses it as a reference for training.

[1011] For example, the device will display a message to the user through a smartphone app saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees," along with a notification saying, "We recommend listening to your favorite music to motivate you."

[1012] Training implementation and feedback loop

[1013] The user (athlete) then performs training according to the proposed coaching methods and emotion-based advice. New sensor data and emotion data are continuously collected during and after training, and are sent back to the server to be used to refine the new evaluation results and coaching methods.

[1014] As a concrete example, a player performs training, and new sensor data and emotional data collected during that training are sent back to the server, where they are used for the next analysis and for generating coaching methods.

[1015] This system can solve the problem of a shortage of instructors in educational settings and sports clubs, and effectively support athletes in improving their performance and managing their motivation.

[1016] Example prompts to input to the generative AI model

[1017] "Analyze this athlete's running and emotional data and generate advice to improve their technique and coaching methods to increase their motivation."

[1018] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1019] Step 1:

[1020] Input: Sensor data from IOT devices and emotion data from built-in cameras and microphones

[1021] Processing: The terminal communicates with IoT devices (smart shoes, smart wear, smart balls, etc.) to collect sensor data, and at the same time collects emotion data using the built-in camera and microphone. For example, distance and speed information is obtained from smart shoes, and the user's facial expressions are captured with the camera and analyzed by the emotion engine.

[1022] Output: Sensor data and emotion data

[1023] Step 2:

[1024] Input: Sensor data and emotion data

[1025] Processing: The device sends the collected sensor data and emotion data to the server via Wi-Fi or mobile communication. Every minute, the data is sent to the server's API endpoint via an HTTP POST request. For example, running data and emotion data are sent in JSON format.

[1026] Output: Sensor data and emotion data sent to the server

[1027] Step 3:

[1028] Input: Sensor data and emotion data sent to the server

[1029] Processing: The server receives the sensor data and emotion data via the API. The API parses the HTTP request and generates a query to store it in the database. For example, it sends an insert query to the database to store the sensor data in the "sensor table" and the emotion data in the "emotion table."

[1030] Output: Sensor data and emotion data stored in a database

[1031] Step 4:

[1032] Input: Sensor data and emotion data stored in a database

[1033] Processing: The server passes the stored data to the generative AI model, which then uses machine learning algorithms to evaluate the athlete's technical performance and emotions, such as running pace, form, and the user's motivation.

[1034] Output: Technical, performance and emotional evaluation results

[1035] Step 5:

[1036] Input: Evaluation result

[1037] Processing: The server generates personalized coaching methods and emotional advice for each player based on the evaluation results. Using specific algorithms, it generates training menus, advice for improving technique, and motivational guidance. For example, it generates stretching methods to improve knee angle and a menu of interval training sessions three times a week, and adds advice such as "listen to your favorite music" based on data from the emotion engine.

[1038] Output: Generated teaching methods and emotion-based advice

[1039] Step 6:

[1040] Input: Generated teaching methods and emotion-based advice

[1041] Processing: The server sends the generated training method and advice to the device. It sends data to the device via an HTTP POST request. For example, it sends data containing training menus and motivational advice in JSON format.

[1042] Output: Instructions and advice sent to the device

[1043] Step 7:

[1044] Input: Instructions and advice sent to the device

[1045] Processing: The device displays the received training methods and advice to the user. The smartphone app displays a notification to inform the user of specific training content and motivational advice. For example, a notification may be displayed saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees."

[1046] Output: Instructions and advice displayed to the user

[1047] Step 8:

[1048] Input: Instructions and advice displayed to the user

[1049] Processing: The user performs training according to the suggested instructional methods and emotion-based advice. For example, the user performs the suggested stretching methods and training menu.

[1050] Output: New sensor and emotion data during and after training

[1051] Step 9:

[1052] Input: New sensor and emotion data during and after training

[1053] Processing: The device again collects new sensor data and emotion data during and after training and sends them to the server. For example, it collects new running data and emotion data and sends them to the server via Wi-Fi.

[1054] Output: New sensor and emotion data sent to the server.

[1055] This creates a feedback loop that continually improves players' performance and motivates them.

[1056] (Application example 2)

[1057] 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."

[1058] Conventional driving assistance systems and training assistance systems simply collect and analyze driving and training data and provide the results, without adequately considering the user's emotional state or motivation. Therefore, there is a growing need for a system that can appropriately evaluate a user's emotions and stress state and provide optimal advice based on that evaluation. The present invention aims to solve this problem by providing a system that provides individually optimized driving assistance and training assistance.

[1059] 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.

[1060] In this invention, the server includes means for collecting sensor data and emotional data of the player from the IoT device, means for transmitting the collected sensor data and emotional data to the server, means for storing the transmitted sensor data and emotional data in the server, means for automatically analyzing the stored sensor data and emotional data using a generation AI, means for generating a coaching method and emotion-based motivational advice for the player based on the analysis results of the generation AI, means for transmitting the generated coaching method and emotion-based motivational advice to a terminal, and means for the player to train based on the coaching method and emotion-based motivational advice displayed on the terminal. This enables individually optimized driving assistance and training assistance that takes into account the user's emotional state.

[1061] An "IoT device" is a physical device that can connect to the internet and collect and exchange data.

[1062] "Sensor data" refers to information on various physical quantities such as movement, position, temperature, and pressure obtained from IoT devices.

[1063] "Emotion data" is information about the user's emotional state, such as joy, anger, sadness, or stress, obtained by face recognition or voice recognition.

[1064] "Generative AI" is an artificial intelligence technology that automatically generates new information and results based on input data.

[1065] "Instruction methods" are advice and suggestions for optimal exercise and training for users, generated based on the analysis results of the generative AI.

[1066] "Motivation advice" is advice and suggestions based on emotional data to maintain and improve a user's motivation.

[1067] A "server" is a computer system for collecting, storing, analyzing, and transmitting data over a network.

[1068] "Terminal" means a device that a user directly operates and uses to display and receive information, including smartphones and tablets.

[1069] "Analysis results" are the output information generated by analyzing sensor data and emotional data using the generation AI.

[1070] "Workout" means any physical or technical exercise or practice performed by a user.

[1071] This invention is a system that combines IoT devices, generative AI, and an emotion engine to analyze sensor data and emotion data of athletes and drivers, and provide optimized coaching methods and motivational advice. An embodiment of this system is described in detail below.

[1072] First, we will describe the system's hardware configuration. The system uses IoT devices (e.g., driver seat sensors, in-car cameras, smart clothing, smart shoes, etc.) to collect data on athletes and drivers. These devices collect sensor data such as movement, position, speed, facial expressions, and voice, as well as emotional data.

[1073] Next, we will explain the device. The device takes the form of a smartphone or tablet and provides an interface with the user. The device sends the collected data to the server and displays the instruction methods and advice from the server to the user. The device also connects to the server via Wi-Fi or mobile data communication.

[1074] The server is the central processing unit of this system and is responsible for the following processes: First, it receives sensor data and emotion data sent from the device via an API and stores it in a database in real time. Next, it passes the stored data to the generative AI, which then automatically begins analyzing it. The generative AI analyzes the data using machine learning algorithms and generates evaluation results regarding the user's behavioral patterns and emotional state. Well-known generative AI models such as GPT-3 and BERT are used for this.

[1075] Based on the analysis results, the server generates optimal instruction methods and emotionally-based motivational advice for the user. This process includes, for example, specific action plans and training menus for safe driving, as well as advice for improving skills. Based on the emotional data, the server also generates suggestions for music and break timing to maintain and improve motivation.

[1076] The generated instruction methods and motivation advice are sent back to the device and notified to the user. The user uses this information to drive or train. Furthermore, new sensor data and emotional data collected during and after the training are sent back to the server and used to improve the accuracy of the next instruction methods and advice.

[1077] As a concrete example, the following prompt sentences could be input to a generative AI model:

[1078] Analyze driving and emotional data to generate advice for safe and comfortable driving.

[1079] Operation data: {Operation data: . . .}

[1080] Emotion data: {Emotion data: . . .}

[1081] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1082] Step 1:

[1083] Data Collection Phase

[1084] The terminal collects driving and emotion data in real time from IoT devices such as driver seat sensors, in-car cameras, and smart clothing. Specifically, the driver seat sensors collect pressure data, the in-car cameras collect facial expression data through facial recognition, and the microphone collects voice data. The terminal integrates this data and temporarily stores it as an initial data set.

[1085] Input: Data obtained from driver seat sensors, in-car cameras, microphones, etc.

[1086] Output: Temporarily saved initial dataset

[1087] Step 2:

[1088] Data transmission phase

[1089] The device sends the collected sensor data and emotion data to the server at regular intervals (e.g., every minute) using Wi-Fi or mobile data. The device confirms that the data was sent properly and displays a success message to the user.

[1090] Input: Temporarily saved initial dataset

[1091] Output: Data sent to the server, and a notification message to the user

[1092] Step 3:

[1093] Data reception and storage phase

[1094] The server receives sensor data and emotion data sent from the device via API. The received data is stored in a database in real time. The server confirms that the data has been stored and records it in a log.

[1095] Input: Data sent from the terminal

[1096] Output: Data stored in the database, and log entries

[1097] Step 4:

[1098] Data analysis phase

[1099] The server passes the sensor data and emotion data stored in the database to the generative AI, which then automatically begins analysis. Using a generative AI model (such as GPT-3 or BERT), the server evaluates driving behavior and emotional state and generates analysis results based on that.

[1100] For example, the following prompts could be input to the generator:

[1101] Analyze driving and emotional data to generate advice for safe and comfortable driving.

[1102] Operation data: {Operation data: . . .}

[1103] Emotion data: {Emotion data: . . .}

[1104] Input: Sensor data and emotion data stored in a database

[1105] Output: Analysis results generated by generative AI

[1106] Step 5:

[1107] Teaching method generation phase

[1108] Based on the analysis results provided by the AI, the server generates optimal instruction methods and motivational advice for the user, such as suggestions for adjusting speed and timing breaks for safe driving, and music recommendations for stress reduction.

[1109] Input: Analysis results generated by generative AI

[1110] Output: Optimal teaching methods and motivation advice for users

[1111] Step 6:

[1112] Results feedback phase

[1113] The server sends the generated teaching method and motivation advice to the terminal, which receives it, displays it to the user as a notification, and also provides feedback to the server that the user has confirmed the notification.

[1114] Input: Server-generated instructional and motivational advice

[1115] Output: Notifications displayed to the user and feedback to the server

[1116] Step 7:

[1117] Training implementation and feedback loop phase

[1118] The user drives or trains based on the instruction methods and motivation advice displayed on the device. New sensor data and emotional data are collected during and after the training and sent to the server via the device. This allows the system to improve the accuracy of the next training methods and motivation advice.

[1119] Input: User driving data and emotion data

[1120] Output: Data used to generate new teaching methods and motivational advice

[1121] 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.

[1122] 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.

[1123] 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.

[1124] [Fourth embodiment]

[1125] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1126] 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.

[1127] 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).

[1128] 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.

[1129] 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.

[1130] 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).

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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.

[1136] 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.

[1137] 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."

[1138] This invention is a system that uses IoT devices and generative AI to analyze sensor data from athletes and provide individually optimized coaching methods. The program processing of this system is explained in detail below.

[1139] Data Collection Phase

[1140] The terminal collects real-time sensor data from players' IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.), which records detailed information about players' movements, techniques, loads, positions, speeds, etc.

[1141] Example: The device collects the number of basketball shots, distance, and angle from the smart ball's sensor.

[1142] Data transmission phase

[1143] The device sends the collected sensor data to a server, where it is collected at regular intervals.

[1144] Example: The device sends running data measured by the smart shoes to the server every minute.

[1145] Data reception and storage phase

[1146] The server receives the sensor data sent from the devices and stores it in a database, where each player's data is stored in chronological order for later analysis.

[1147] Example: The server's API receives running data from a smartphone and stores it in a NoSQL database.

[1148] Data analysis phase

[1149] The server then passes the stored sensor data to the AI ​​generator, which then uses machine learning algorithms to analyze the data in detail and evaluate the player's technique and performance.

[1150] Example: The server analyzes running data to identify areas for improvement in a player's pace and form.

[1151] Teaching method generation phase

[1152] The server generates the optimal coaching method for each player based on the AI-generated evaluation results, including specific training menus and advice for improving skills.

[1153] Example: The server uses running data to suggest stretching methods and interval training to improve the angle of the athlete's knees.

[1154] Results feedback phase

[1155] The server sends the generated instruction method to the terminal, which receives it and displays it to the user. The user (instructor or player) then uses this information to provide training and technical instruction.

[1156] Example: The device displays a notification to the athlete via a smartphone app, saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees."

[1157] Training implementation and feedback loop phase

[1158] The user (athlete) will then train based on the proposed training method. Sensor data will be collected during the training and used for further analysis.

[1159] Example: Athletes train and the data collected during training is sent back to the server to help improve the accuracy of evaluation results and coaching methods.

[1160] This system will solve the problem of a shortage of instructors in educational settings and sports clubs, and will effectively support athletes in improving their performance.

[1161] The processing flow will be explained below.

[1162] Step 1:

[1163] The terminal collects real-time sensor data from players' IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.), which measure information such as players' movements, techniques, load, position, and speed.

[1164] Example: The device collects the number of steps, acceleration, and ground contact time from smart shoes.

[1165] Step 2:

[1166] The device sends the collected sensor data to a server using a secure communication protocol at regular intervals.

[1167] Example: The device sends running data measured by the smart shoes to a server every minute via Wi-Fi.

[1168] Step 3:

[1169] The server receives sensor data sent from the device via API, and the received data is immediately stored in a database.

[1170] Example: The server's API stores the running data received from the device in an analysis database in real time.

[1171] Step 4:

[1172] The server then passes the sensor data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to analyze the data and generate evaluation results for the player's movements and techniques.

[1173] Example: The server passes running data to an AI module to identify areas for improvement in the athlete's pace and form.

[1174] Step 5:

[1175] Based on the evaluation results, the server generates a coaching method optimized for each player, including specific training menus and advice for improving their skills.

[1176] Example: The server uses running data to generate stretching techniques to improve knee angle and interval training menus three times a week.

[1177] Step 6:

[1178] The server sends the generated training method to the terminal, which then displays the received training method to the user. The user (instructor or player) uses this information to train.

[1179] Example: The device displays a notification to the user through a smartphone app saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees."

[1180] Step 7:

[1181] The user (athlete) conducts training based on the proposed coaching method. Sensor data is continuously collected during and after the training and sent back to the server for use in new evaluation results and to improve the accuracy of the coaching method.

[1182] Example: A player performs training, and new data collected during that training is sent back to the server for analysis and use in the next training session.

[1183] Example 1

[1184] 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."

[1185] In traditional sports coaching, providing optimal training methods for individual athletes requires the resources of specialized instructors. However, due to factors such as a lack of instructors and limited coaching time, it is difficult to provide sufficient instruction to all athletes. It is also difficult to efficiently collect and analyze athletes' performance data in detail, making it difficult to provide optimal instruction to each individual athlete. Given this background, there is a demand for a system that uses IoT devices and generative AI to analyze athletes' sensor data and provide individually optimized coaching methods.

[1186] 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.

[1187] In this invention, the server includes means for collecting sensor data of athletes from IOT devices, means for transmitting the collected sensor data to the server at regular intervals, means for the server to store the transmitted sensor data in a database, means for analyzing the stored sensor data using a machine learning algorithm, means for generating an individual coaching method for the athletes based on the analysis results, means for transmitting the generated coaching method from the server to a terminal, means for the athletes to train based on the coaching method displayed on the terminal, and means for re-collecting sensor data during training and using it for analysis. This makes it possible to provide an effective and individually optimized coaching method for each athlete.

[1188] An "IoT device" is a device that is connected to the Internet and can use various sensors to detect and measure the condition of the environment and objects, and collect data.

[1189] "Sensor data" refers to various types of information collected through IoT devices, specifically data on players' movements, techniques, load, position, speed, etc.

[1190] A "terminal" is a computing device that connects to other devices or systems, sends and receives data, and performs processing, and specifically includes smartphones and tablets.

[1191] A "server" is a dedicated computer system that responds to requests from other devices or systems on a network and stores and processes data.

[1192] A "database" refers to a collection of structured information that can efficiently store large amounts of data and enable manipulation and search, and includes NoSQL databases and relational databases.

[1193] A "machine learning algorithm" is a computer programming technique that learns patterns from data and makes predictions, classifications, and analyses, including generative AI models.

[1194] "Coaching methods" refer to specific training menus, advice for improving techniques, and concrete action plans provided to improve players' performance.

[1195] "Analysis results" refers to information generated as a result of data processing using machine learning algorithms, and includes evaluations of players' skills and performance, as well as areas for improvement.

[1196] This invention is a system that utilizes IoT devices and generative AI to analyze sensor data of athletes and provide individually optimized coaching methods. Specific embodiments for implementing the invention are described below.

[1197] Hardware and software used

[1198] Terminal: IoT device (e.g. smart shoes, smart wear, smart ball, etc.)

[1199] Server: Database server (e.g. NoSQL database, MongoDB)

[1200] Generative AI models: machine learning algorithms (e.g., TensorFlow, scikit-learn)

[1201] Network communication: Bluetooth, Wi-Fi, HTTP API

[1202] Data collection

[1203] The terminal uses IoT devices to collect sensor data from players. For example, smart shoes collect running data (position, speed, foot angle, etc.) The terminal communicates with the smart ball's sensor using Bluetooth to collect data such as the number of shots, distance, and angle.

[1204] Data transmission

[1205] The device sends the collected sensor data to the server at regular intervals (e.g., every minute). The data is sent using an HTTP POST request to the server's API endpoint. For example, the device sends the collected running data to the server every minute.

[1206] Data reception and storage

[1207] The server receives sensor data sent from the device and stores it in a database. The database uses a NoSQL database (e.g., MongoDB) and stores the data in chronological order. For example, the server's API receives running data sent from a smartphone and stores it in a NoSQL database.

[1208] Data analysis

[1209] The server analyzes the stored sensor data using machine learning algorithms. Generative AI models are used to evaluate the player's technique and performance. For example, the server uses Python machine learning libraries (e.g., TensorFlow and scikit-learn) to analyze running data and identify areas for improvement in the player's pace and form.

[1210] Instruction method generation

[1211] The server generates personalized coaching methods for each athlete based on the analysis results. These include specific training menus, advice for improving technique, and action plans. For example, the server uses a generative AI model to generate suggestions for stretching and interval training to improve a player's knee angle based on running data.

[1212] Results feedback

[1213] The server sends the generated training method to the device, and the device notifies the user. The user (instructor or player) performs training or technical instruction based on the notification content. As a specific example, the server sends the training method to the device using an HTTP POST request, and the device displays on the smartphone app, "Perform interval training three times a week and try stretching methods to improve knee angle."

[1214] Training implementation and feedback loop

[1215] The user (athlete) performs training based on the proposed coaching method. Sensor data during training is collected again and analyzed again to improve the accuracy of the coaching method. As a specific example, the athlete performs training, and new data collected by the smart shoes during training is sent again via the device to the server, which then analyzes it again.

[1216] Prompt Sentence Examples

[1217] "The running data collected by the smart shoes should be analyzed in real time, and an algorithm should be generated to suggest the optimal training method for each individual athlete based on their pace and form. Specifically, this should include suggestions for stretching methods and interval training to improve the athlete's knee angle."

[1218] This system can solve the problem of a shortage of instructors in educational settings and sports clubs, and effectively support athletes in improving their performance.

[1219] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1220] Step 1: Data collection

[1221] The terminal uses IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.) to collect sensor data of players in real time, including their movements, technique, load, position, speed, etc.

[1222] Input: Sensor data from IOT devices

[1223] Data processing: Real-time data collection and format conversion

[1224] Output: Formatted sensor data

[1225] Specific operation: The device communicates with the smart ball's sensors using Bluetooth and Wi-Fi to collect information such as the number of shots, distance, and angle.

[1226] Step 2: Send data

[1227] The device sends the collected sensor data to the server at regular intervals, typically every one or five minutes.

[1228] Input: Collected sensor data

[1229] Data processing: Packetizing data and network protocol processing

[1230] Output: Data packet sent to the server

[1231] Specific operation: The device sends the collected running data every minute by sending an HTTP POST request to the server's API endpoint.

[1232] Step 3: Data reception and storage

[1233] The server receives the sensor data sent from the devices and stores it in a database, where each player's data is stored in chronological order for later analysis.

[1234] Input: Data packets sent from the device

[1235] Data processing: Data analysis, format conversion, and storage in a database

[1236] Output: Stored time series data

[1237] Specific operation: The server's API receives running data sent from the smartphone and stores it in a NoSQL database (e.g., MongoDB).

[1238] Step 4: Data analysis

[1239] The server analyzes the stored sensor data using machine learning algorithms, and uses generative AI models to evaluate players' skills and performance.

[1240] Input: Stored time series data

[1241] Data Computing: Data analysis and performance evaluation using machine learning algorithms

[1242] Output: Player performance evaluation results

[1243] What it does: The server uses Python machine learning libraries (e.g., TensorFlow and scikit-learn) to analyze running data and identify areas for improvement in the athlete's pace and form.

[1244] Step 5: Instructional method generation

[1245] Based on the analysis results, the server generates the optimal coaching method for each player, including specific training menus and advice for improving their skills.

[1246] Input: Player performance evaluation results

[1247] Data calculation: generating instruction methods and creating training menus

[1248] Output: Individually optimized teaching methods

[1249] How it works: The server uses a generative AI model to suggest stretching techniques and interval training to improve the athlete's knee angle based on running data.

[1250] Step 6: Feedback

[1251] The server sends the generated instruction method to the terminal, which then notifies the user. The user (instructor or player) then performs training and technical instruction based on this notification.

[1252] Input: Individually optimized teaching methods

[1253] Data processing: Packetizing feedback data and generating notifications

[1254] Output: Instructional method notified to the user

[1255] Specific operation: The server sends the training method to the device using an HTTP POST request, and the device uses its notification function to display a notification on the smartphone app saying, "Perform interval training three times a week and try stretching methods to improve knee angle by 10 degrees."

[1256] Step 7: Training and feedback loop

[1257] The user (athlete) will then train based on the proposed coaching method. Sensor data during training will be collected and analyzed again to improve the accuracy of the coaching method.

[1258] Input: Newly collected sensor data

[1259] Data processing: Real-time data collection, transmission, storage, and analysis, repeated

[1260] Output: Improved teaching methods

[1261] Specific operation: The athlete performs training, and new data collected during that time is sent to the server via the device again, and the server then analyzes it again.

[1262] As described above, this system can provide individually optimized teaching methods through each processing step.

[1263] (Application example 1)

[1264] 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."

[1265] Conventional factory robot operation management and maintenance is based on specific patterns, which makes it inefficient and difficult to take preventative measures against failures.In addition, there is no system in place to provide specific instructions or maintenance plans aimed at improving operation efficiency and reducing the risk of failure, making it difficult to prevent problems before they occur.

[1266] 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.

[1267] In this invention, the server includes means for collecting machine sensor data from an IOT device, means for transmitting the collected sensor data to a central processing unit, means for storing the transmitted sensor data in the central processing unit, means for automatically analyzing the stored sensor data using a generation AI, means for generating operation instructions and maintenance methods for each machine based on the analysis results, means for transmitting the generated operation instructions and maintenance methods to a terminal, and means for controlling the machine based on the operation instructions and maintenance methods displayed on the terminal. This makes it possible to optimize the operating efficiency of the machine and preventatively reduce the risk of breakdown.

[1268] "IOT devices" are various sensors and devices connected to the Internet that collect and transmit data in real time.

[1269] "Machine" is a general term for automated equipment and devices used to perform specific tasks in a factory.

[1270] "Sensor data" is data collected by IoT devices that indicates the state of an object or environment.

[1271] A "central processing unit" is a server or computer system for receiving, storing, and analyzing collected sensor data.

[1272] "Generative AI" is artificial intelligence that uses machine learning algorithms to automatically analyze sensor data and generate optimal operating instructions and maintenance methods.

[1273] "Operational instructions" are specific instructions proposed by the generative AI based on the results of analyzing sensor data to improve the operating efficiency of the machine.

[1274] A "maintenance method" is a specific maintenance procedure for maintaining the safety and performance of a machine, proposed by the generative AI based on the results of analyzing sensor data.

[1275] "Terminal" refers to a device for displaying generated operating instructions and maintenance methods, and includes control systems and display devices.

[1276] This invention is a system that combines IoT devices, central processing units, generative AI models, and terminals to optimize the operating efficiency of machines in a factory.

[1277] First, various IoT devices are attached to each machine, such as motion sensors, pressure sensors, distance sensors, etc. These IoT devices collect data on the machine's operating status, pressure, position, speed, etc. in real time. The collected sensor data is sent to a central processing unit at regular intervals.

[1278] The central processing unit receives the collected sensor data and stores it in a database. The database used is a NoSQL database with the ability to store data in chronological order. This database stores daily operating data and maintenance information for each machine, which is used for later analysis.

[1279] Next, the central processing unit passes the stored sensor data to the generation AI, which begins analysis. The generation AI uses machine learning algorithms to perform detailed analysis of the collected data. Specifically, the analysis is aimed at improving operational efficiency and reducing the risk of breakdowns. For example, it can identify abnormal operation patterns based on past data, enabling predictive maintenance. It can also generate operational instructions to improve operational efficiency.

[1280] Based on the analysis results, the AI ​​generates optimal operating instructions and maintenance methods for each machine. This includes specific instructions to improve operating efficiency and inspection procedures to prevent breakdowns. This information is sent from the central processing unit to the terminal.

[1281] The terminal displays the received operation instructions and maintenance methods on a display, providing real-time information to robot operators and maintenance personnel using the control system and display device.

[1282] As a specific example, if the pressure sensor data is judged to be excessive, the generation AI will generate an operation instruction such as, "The machine's current gripping pressure is excessive. By reducing the pressure by 20%, it will be possible to hold the object stably while reducing energy consumption." Also, if abnormal movement is detected from the motion sensor data, the AI ​​will provide a maintenance method such as, "The operating angle of the robot's arm is outside the normal range, so we recommend regular maintenance and part replacement."

[1283] Additionally, examples of prompts for generative AI models include:

[1284] "Please provide guidance on how to improve operational efficiency and reduce the risk of breakdowns based on the robot's motion sensor data and pressure sensor data."

[1285] This allows the operating efficiency of machines in the factory to be continuously improved, and also makes it possible to take preventive measures against breakdowns.

[1286] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1287] Step 1:

[1288] Sensor data is collected from IOT devices. The server acquires data in real time from motion sensors, pressure sensors, and distance sensors attached to the machine. The input is data from each sensor, and the output is a set of sensor data. Specifically, data such as the machine's operating status, pressure, position, and speed are collected.

[1289] Step 2:

[1290] The collected sensor data is sent to a central processing unit. The server sends the collected sensor data to a database at regular intervals. The input is the collected sensor data, and the output is the data stored in the database. Specifically, the sensor data is formatted in JSON format and sent to a NoSQL database.

[1291] Step 3:

[1292] The transmitted sensor data is stored in the central processing unit. The server stores the received sensor data in a database in chronological order. The input is the transmitted sensor data, and the output is the data stored in the database. Specifically, a new entry is added to the database and saved together with the previous data.

[1293] Step 4:

[1294] The stored sensor data is passed to the generation AI to begin analysis. The server retrieves the sensor data stored in the database and sends it to the generation AI to request analysis. The input is the sensor data read from the database, and the output is the analysis results by the generation AI. Specifically, it uses a REST API to communicate with the generation AI and send data.

[1295] Step 5:

[1296] Generative AI analyzes sensor data to evaluate operational efficiency and risk of failure. It uses machine learning algorithms to analyze the data and identify abnormal patterns and optimization points. The input is the transmitted sensor data, and the output is the analysis results. Specifically, generative AI compares data with past data and detects outliers.

[1297] Step 6:

[1298] Based on the analysis results of the generation AI, the server generates operating instructions and maintenance methods for each machine. Based on the analysis results of the generation AI, the server creates optimal operating instructions and maintenance methods. The input is the analysis results of the generation AI, and the output is specific operating instructions and maintenance methods. Specifically, clear instructions such as "reduce pressure by 20%" and "adjust the operating angle of the arm" are generated.

[1299] Step 7:

[1300] The generated operation instructions and maintenance methods are sent to the terminal. The server sends the generated instruction contents to the terminal and displays them. The input is the generated operation instructions and maintenance methods, and the output is the information displayed on the terminal. Specifically, each instruction content is formatted in text format and sent to the terminal.

[1301] Step 8:

[1302] Machine control is based on the operating instructions and maintenance methods displayed on the terminal. The user checks the instructions displayed on the terminal and operates or maintains the machine based on them. The input is the operating instructions and maintenance methods displayed on the terminal, and the output is the results of the user's operation of the machine. Specifically, the user performs operations such as adjusting pressure and replacing parts.

[1303] This enables the system to continuously improve the operating efficiency of machines in the factory and proactively manage the risk of breakdowns.

[1304] 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.

[1305] This invention is a system that combines IoT devices, generative AI, and an emotion engine to analyze sensor data and emotion data of players and provide individually optimized coaching methods. The program processing of this system is explained in detail below.

[1306] Data Collection Phase

[1307] The terminal collects sensor data of players in real time from IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.). This data records players' movements, techniques, loads, positions, speeds, etc. in detail. The terminal also uses an emotion engine to collect users' emotional data (e.g., joy, anger, sadness, stress, etc.) in real time.

[1308] Example: The device collects the number of basketball shots, their distance, and angle from the smart ball's sensors, while the emotion engine collects emotional data from the user's facial expressions and voice.

[1309] Data transmission phase

[1310] The device sends the collected sensor data and emotion data to a server at regular intervals, where it is aggregated.

[1311] Example: The device transmits running data and emotional data measured by the smart shoes to a server every minute via Wi-Fi.

[1312] Data reception and storage phase

[1313] The server receives sensor data and emotion data sent from the device via API, and the received data is immediately stored in a database.

[1314] Example: The server's API stores running data and emotional data received from the device in a database for analysis in real time.

[1315] Data analysis phase

[1316] The server then passes the sensor data and emotion data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to perform a detailed analysis of the data and generate evaluations of the player's technique, performance, and emotions.

[1317] Example: The server passes running data and emotional data to an AI module to identify areas for improvement in the athlete's pace, form, and motivation.

[1318] Teaching method generation phase

[1319] The server generates the optimal coaching method for each player based on the evaluation results generated by the AI. The coaching method includes specific training menus and advice for improving skills, as well as coaching that takes into account the user's motivation based on their emotional state.

[1320] Example: The server uses running data to generate stretching methods to improve knee angle and interval training menus three times a week, and adds advice such as "listen to music to increase motivation" based on data from the emotion engine.

[1321] Results feedback phase

[1322] The server sends the generated coaching method and advice based on emotions to the device, which receives it and displays it to the user. The user (coach or player) uses this information to train.

[1323] Example: Through a smartphone app, the device displays a message to the user saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees," along with a notification saying, "We recommend listening to your favorite music to motivate you."

[1324] Training implementation and feedback loop phase

[1325] The user (athlete) then performs training according to the proposed coaching methods and emotional advice. Sensor data and emotional data are continuously collected during and after training and sent back to the server for use in developing new evaluation results and improving the accuracy of coaching methods.

[1326] Example: A player performs training, and new sensor data and emotional data collected during that training are sent back to the server for analysis and use in the next training session.

[1327] This system will solve the problem of a shortage of instructors in educational settings and sports clubs, and will effectively support athletes in improving their performance and managing their motivation.

[1328] The processing flow will be explained below.

[1329] Step 1:

[1330] The terminal collects sensor data of players in real time from IoT devices (e.g., smart shoes, smart clothing, smart balls, etc.). The IoT devices measure information such as players' movements, techniques, load, position, and speed. The terminal also uses an emotion engine to collect user emotional data (e.g., joy, anger, sadness, stress, etc.).

[1331] Example: The device collects data from smart shoes about the number of steps, acceleration, and ground contact time while running, and also obtains the user's current emotional state from their facial expressions and voice.

[1332] Step 2:

[1333] The device sends the collected sensor data and emotion data to the server at regular intervals (e.g., every minute).

[1334] Example: The device transmits running data measured by the smart shoes and the user's emotional data acquired by the emotion engine to a server via Wi-Fi.

[1335] Step 3:

[1336] The server receives sensor data and emotion data sent from the device via API and stores the received data in a database in real time.

[1337] Example: The server's API receives running and emotion data and immediately stores it in a database for analysis.

[1338] Step 4:

[1339] The server then passes the sensor data and emotion data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to analyze the data in detail and generate an evaluation of the player's technique and performance, while also evaluating the user's emotional state.

[1340] Example: The server passes running data and emotional data to an AI module to identify areas for improvement in the athlete's pace and form, as well as emotional fluctuations.

[1341] Step 5:

[1342] Based on the evaluation results generated by the AI, the server generates the optimal coaching method for each player, which includes specific training menus and advice for improving skills, as well as coaching that takes into account the user's motivation based on their emotional state.

[1343] Example: The server generates stretching methods to improve knee angle and interval training menus three times a week from running data, and adds advice such as "listen to music to increase motivation" based on the user's emotional state.

[1344] Step 6:

[1345] The server sends the generated coaching method and advice based on emotions to the device, which receives it and displays it to the user. The user (coach or player) uses this information to train.

[1346] Example: Through a smartphone app, the device displays a message to the user saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees," and a notification saying, "We recommend listening to your favorite music to motivate you."

[1347] Step 7:

[1348] The user (athlete) then performs training according to the proposed coaching methods and emotional advice. Sensor data and emotional data are continuously collected during and after training and sent back to the server for use in developing new evaluation results and improving the accuracy of coaching methods.

[1349] Example: A player performs training, and new sensor data and emotional data collected during that training are sent back to the server for analysis and use in the next training session.

[1350] Example 2

[1351] 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."

[1352] Conventional training systems have struggled to provide individually optimized coaching methods for improving athletes' performance and managing their motivation. Furthermore, they have not implemented coaching methods that take athletes' emotional states into account, and uniform coaching has resulted in insufficient improvement in athletes' motivation and performance. Furthermore, there is a lack of a process for reanalyzing post-training data, making it difficult to improve the accuracy of coaching methods. To solve these issues, a system is needed that can integrate and analyze athletes' sensor data and emotional data, and provide individually optimized coaching methods and advice based on their emotions.

[1353] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1354] In this invention, the server includes means for collecting sensor data of players from IoT devices, means for transmitting the sensor data collected by the terminal and the user's emotional data to the server, means for receiving the sensor data and emotional data transmitted by the server via an API and storing them in a database, means for automatically analyzing the stored sensor data and emotional data using a generation AI, means for generating individual coaching methods and emotional advice for the player based on the analysis results, means for transmitting the generated coaching methods and advice to the terminal, and means for the player to train based on the coaching methods and advice displayed on the terminal. This makes it possible to integrate and analyze the sensor data and emotional data of the player and provide individually optimized coaching methods and emotional advice.

[1355] An "IoT device" is a physical device that connects to the Internet and has the ability to collect and transmit data.

[1356] "Sensor data" refers to data obtained from IoT devices regarding players' movements, techniques, load, position, speed, etc.

[1357] "Emotion data" is data that indicates an emotional state such as joy, anger, sadness, or stress, obtained by analyzing the user's facial expressions and voice.

[1358] "Generative AI" is an artificial intelligence that uses machine learning algorithms to automatically analyze collected data and generate evaluation results of players' skills, performance, and emotions.

[1359] The "evaluation results" are information about the player's technique, performance status, and emotional state obtained by the generating AI analyzing sensor data and emotional data.

[1360] "Coaching methods" are training menus for individual players, advice for improving skills, and emotionally-based coaching content for increasing motivation, all generated based on the analysis results.

[1361] A "terminal" is a computing device for collecting and transmitting data from an IOT device to a server, and displaying the instructional methods received from the server to a user.

[1362] The "server" is a computing system that receives and stores data sent from the terminal, analyzes it using a generative AI, generates teaching methods, and sends them to the terminal.

[1363] The "database" is an information management system installed in the server for storing received sensor data and emotion data.

[1364] This invention is a system that combines IoT devices, generative AI, and an emotion engine to analyze sensor data and emotion data of athletes and provide individually optimized coaching methods. Hereinafter, specific embodiments for implementing this system will be described.

[1365] Use of IOT devices

[1366] The device collects sensor data from players using IoT devices such as smart shoes, smart clothing, and smart balls, allowing for detailed recording of players' movements, techniques, load, position, speed, etc. The device also incorporates an emotion engine that analyzes the user's facial expressions and voice in real time to collect emotional data.

[1367] As a specific example, the device collects the number of basketball shots, their distance, and angle from the smart ball's sensors, and also collects emotional data (e.g., joy, anger, sadness, stress, etc.) from the user's facial expressions and voice using an emotion engine.

[1368] Sending and Receiving Data

[1369] The device sends the collected sensor data and emotion data to a server via Wi-Fi or mobile data communication. This data is sent at regular intervals (for example, every minute) and received via the server's API. The received data is stored in a database in real time.

[1370] For example, the device transmits running data and emotional data measured by the smart shoes every minute to a server via Wi-Fi. The server's API stores the running data and emotional data received from the device in a database for analysis in real time.

[1371] Analyzing the data

[1372] The server then passes the sensor data and emotion data stored in the database to the AI ​​generator, which then automatically begins analyzing it. The AI ​​generator then uses machine learning algorithms to perform a detailed analysis of the data and generate evaluations of the player's technique, performance, and emotions.

[1373] As a concrete example, the server passes running data and emotional data to a generative AI module to identify areas for improvement in the athlete's pace, form, and motivation.

[1374] Teaching method generation

[1375] Based on the evaluation results generated by the AI, the server generates optimal coaching methods for each player, including specific training menus and advice for improving skills, as well as guidance to increase motivation based on the user's emotional state.

[1376] As a specific example, the server uses running data to generate stretching techniques to improve knee angle and a three-times-a-week interval training menu, and adds advice such as "listen to music to increase motivation" based on data from the emotion engine.

[1377] Feedback of results

[1378] The server sends the generated advice based on the coaching method and emotions to the terminal. The terminal receives it and displays it to the user. The user (coach or player) uses it as a reference for training.

[1379] For example, the device will display a message to the user through a smartphone app saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees," along with a notification saying, "We recommend listening to your favorite music to motivate you."

[1380] Training implementation and feedback loop

[1381] The user (athlete) then performs training according to the proposed coaching methods and emotion-based advice. New sensor data and emotion data are continuously collected during and after training, and are sent back to the server to be used to refine the new evaluation results and coaching methods.

[1382] As a concrete example, a player performs training, and new sensor data and emotional data collected during that training are sent back to the server, where they are used for the next analysis and for generating coaching methods.

[1383] This system can solve the problem of a shortage of instructors in educational settings and sports clubs, and effectively support athletes in improving their performance and managing their motivation.

[1384] Example prompts to input to the generative AI model

[1385] "Analyze this athlete's running and emotional data and generate advice to improve their technique and coaching methods to increase their motivation."

[1386] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1387] Step 1:

[1388] Input: Sensor data from IOT devices and emotion data from built-in cameras and microphones

[1389] Processing: The terminal communicates with IoT devices (smart shoes, smart wear, smart balls, etc.) to collect sensor data, and at the same time collects emotion data using the built-in camera and microphone. For example, distance and speed information is obtained from smart shoes, and the user's facial expressions are captured with the camera and analyzed by the emotion engine.

[1390] Output: Sensor data and emotion data

[1391] Step 2:

[1392] Input: Sensor data and emotion data

[1393] Processing: The device sends the collected sensor data and emotion data to the server via Wi-Fi or mobile communication. Every minute, the data is sent to the server's API endpoint via an HTTP POST request. For example, running data and emotion data are sent in JSON format.

[1394] Output: Sensor data and emotion data sent to the server

[1395] Step 3:

[1396] Input: Sensor data and emotion data sent to the server

[1397] Processing: The server receives the sensor data and emotion data via the API. The API parses the HTTP request and generates a query to store it in the database. For example, it sends an insert query to the database to store the sensor data in the "sensor table" and the emotion data in the "emotion table."

[1398] Output: Sensor data and emotion data stored in a database

[1399] Step 4:

[1400] Input: Sensor data and emotion data stored in a database

[1401] Processing: The server passes the stored data to the generative AI model, which then uses machine learning algorithms to evaluate the athlete's technical performance and emotions, such as running pace, form, and the user's motivation.

[1402] Output: Technical, performance and emotional evaluation results

[1403] Step 5:

[1404] Input: Evaluation result

[1405] Processing: The server generates personalized coaching methods and emotional advice for each player based on the evaluation results. Using specific algorithms, it generates training menus, advice for improving technique, and motivational guidance. For example, it generates stretching methods to improve knee angle and a menu of interval training sessions three times a week, and adds advice such as "listen to your favorite music" based on data from the emotion engine.

[1406] Output: Generated teaching methods and emotion-based advice

[1407] Step 6:

[1408] Input: Generated teaching methods and emotion-based advice

[1409] Processing: The server sends the generated training method and advice to the device. It sends data to the device via an HTTP POST request. For example, it sends data containing training menus and motivational advice in JSON format.

[1410] Output: Instructions and advice sent to the device

[1411] Step 7:

[1412] Input: Instructions and advice sent to the device

[1413] Processing: The device displays the received training methods and advice to the user. The smartphone app displays a notification to inform the user of specific training content and motivational advice. For example, a notification may be displayed saying, "Perform interval training three times a week and try stretching techniques to improve knee angle by 10 degrees."

[1414] Output: Instructions and advice displayed to the user

[1415] Step 8:

[1416] Input: Instructions and advice displayed to the user

[1417] Processing: The user performs training according to the suggested instructional methods and emotion-based advice. For example, the user performs the suggested stretching methods and training menu.

[1418] Output: New sensor and emotion data during and after training

[1419] Step 9:

[1420] Input: New sensor and emotion data during and after training

[1421] Processing: The device again collects new sensor data and emotion data during and after training and sends them to the server. For example, it collects new running data and emotion data and sends them to the server via Wi-Fi.

[1422] Output: New sensor and emotion data sent to the server.

[1423] This creates a feedback loop that continually improves players' performance and motivates them.

[1424] (Application example 2)

[1425] 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."

[1426] Conventional driving assistance systems and training assistance systems simply collect and analyze driving and training data and provide the results, without adequately considering the user's emotional state or motivation. Therefore, there is a growing need for a system that can appropriately evaluate a user's emotions and stress state and provide optimal advice based on that evaluation. The present invention aims to solve this problem by providing a system that provides individually optimized driving assistance and training assistance.

[1427] 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.

[1428] In this invention, the server includes means for collecting sensor data and emotional data of the player from the IoT device, means for transmitting the collected sensor data and emotional data to the server, means for storing the transmitted sensor data and emotional data in the server, means for automatically analyzing the stored sensor data and emotional data using a generation AI, means for generating a coaching method and emotion-based motivational advice for the player based on the analysis results of the generation AI, means for transmitting the generated coaching method and emotion-based motivational advice to a terminal, and means for the player to train based on the coaching method and emotion-based motivational advice displayed on the terminal. This enables individually optimized driving assistance and training assistance that takes into account the user's emotional state.

[1429] An "IoT device" is a physical device that can connect to the internet and collect and exchange data.

[1430] "Sensor data" refers to information on various physical quantities such as movement, position, temperature, and pressure obtained from IoT devices.

[1431] "Emotion data" is information about the user's emotional state, such as joy, anger, sadness, or stress, obtained by face recognition or voice recognition.

[1432] "Generative AI" is an artificial intelligence technology that automatically generates new information and results based on input data.

[1433] "Instruction methods" are advice and suggestions for optimal exercise and training for users, generated based on the analysis results of the generative AI.

[1434] "Motivation advice" is advice and suggestions based on emotional data to maintain and improve a user's motivation.

[1435] A "server" is a computer system for collecting, storing, analyzing, and transmitting data over a network.

[1436] "Terminal" means a device that a user directly operates and uses to display and receive information, including smartphones and tablets.

[1437] "Analysis results" are the output information generated by analyzing sensor data and emotional data using the generation AI.

[1438] "Workout" means any physical or technical exercise or practice performed by a user.

[1439] This invention is a system that combines IoT devices, generative AI, and an emotion engine to analyze sensor data and emotion data of athletes and drivers, and provide optimized coaching methods and motivational advice. An embodiment of this system is described in detail below.

[1440] First, we will describe the system's hardware configuration. The system uses IoT devices (e.g., driver seat sensors, in-car cameras, smart clothing, smart shoes, etc.) to collect data on athletes and drivers. These devices collect sensor data such as movement, position, speed, facial expressions, and voice, as well as emotional data.

[1441] Next, we will explain the device. The device takes the form of a smartphone or tablet and provides an interface with the user. The device sends the collected data to the server and displays the instruction methods and advice from the server to the user. The device also connects to the server via Wi-Fi or mobile data communication.

[1442] The server is the central processing unit of this system and is responsible for the following processes: First, it receives sensor data and emotion data sent from the device via an API and stores it in a database in real time. Next, it passes the stored data to the generative AI, which then automatically begins analyzing it. The generative AI analyzes the data using machine learning algorithms and generates evaluation results regarding the user's behavioral patterns and emotional state. Well-known generative AI models such as GPT-3 and BERT are used for this.

[1443] Based on the analysis results, the server generates optimal instruction methods and emotionally-based motivational advice for the user. This process includes, for example, specific action plans and training menus for safe driving, as well as advice for improving skills. Based on the emotional data, the server also generates suggestions for music and break timing to maintain and improve motivation.

[1444] The generated instruction methods and motivation advice are sent back to the device and notified to the user. The user uses this information to drive or train. Furthermore, new sensor data and emotional data collected during and after the training are sent back to the server and used to improve the accuracy of the next instruction methods and advice.

[1445] As a concrete example, the following prompt sentences could be input to a generative AI model:

[1446] Analyze driving and emotional data to generate advice for safe and comfortable driving.

[1447] Operation data: {Operation data: . . .}

[1448] Emotion data: {Emotion data: . . .}

[1449] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1450] Step 1:

[1451] Data Collection Phase

[1452] The terminal collects driving and emotion data in real time from IoT devices such as driver seat sensors, in-car cameras, and smart clothing. Specifically, the driver seat sensors collect pressure data, the in-car cameras collect facial expression data through facial recognition, and the microphone collects voice data. The terminal integrates this data and temporarily stores it as an initial data set.

[1453] Input: Data obtained from driver seat sensors, in-car cameras, microphones, etc.

[1454] Output: Temporarily saved initial dataset

[1455] Step 2:

[1456] Data transmission phase

[1457] The device sends the collected sensor data and emotion data to the server at regular intervals (e.g., every minute) using Wi-Fi or mobile data. The device confirms that the data was sent properly and displays a success message to the user.

[1458] Input: Temporarily saved initial dataset

[1459] Output: Data sent to the server, and a notification message to the user

[1460] Step 3:

[1461] Data reception and storage phase

[1462] The server receives sensor data and emotion data sent from the device via API. The received data is stored in a database in real time. The server confirms that the data has been stored and records it in a log.

[1463] Input: Data sent from the terminal

[1464] Output: Data stored in the database, and log entries

[1465] Step 4:

[1466] Data analysis phase

[1467] The server passes the sensor data and emotion data stored in the database to the generative AI, which then automatically begins analysis. Using a generative AI model (such as GPT-3 or BERT), the server evaluates driving behavior and emotional state and generates analysis results based on that.

[1468] For example, the following prompts could be input to the generator:

[1469] Analyze driving and emotional data to generate advice for safe and comfortable driving.

[1470] Operation data: {Operation data: . . .}

[1471] Emotion data: {Emotion data: . . .}

[1472] Input: Sensor data and emotion data stored in a database

[1473] Output: Analysis results generated by generative AI

[1474] Step 5:

[1475] Teaching method generation phase

[1476] Based on the analysis results provided by the AI, the server generates optimal instruction methods and motivational advice for the user, such as suggestions for adjusting speed and timing breaks for safe driving, and music recommendations for stress reduction.

[1477] Input: Analysis results generated by generative AI

[1478] Output: Optimal teaching methods and motivation advice for users

[1479] Step 6:

[1480] Results feedback phase

[1481] The server sends the generated teaching method and motivation advice to the terminal, which receives it, displays it to the user as a notification, and also provides feedback to the server that the user has confirmed the notification.

[1482] Input: Server-generated instructional and motivational advice

[1483] Output: Notifications displayed to the user and feedback to the server

[1484] Step 7:

[1485] Training implementation and feedback loop phase

[1486] The user drives or trains based on the instruction methods and motivation advice displayed on the device. New sensor data and emotional data are collected during and after the training and sent to the server via the device. This allows the system to improve the accuracy of the next training methods and motivation advice.

[1487] Input: User driving data and emotion data

[1488] Output: Data used to generate new teaching methods and motivational advice

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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.

[1493] FIG. 9 illustrates 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 behaviors 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.

[1494] 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.

[1495] 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).

[1496] 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.

[1497] 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."

[1498] 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.

[1499] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1500] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1501] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1502] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1503] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1504] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1505] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1506] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1507] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1508] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1509] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1510] The following is further disclosed regarding the above embodiment.

[1511] (Claim 1)

[1512] A means of collecting athlete sensor data from IOT devices;

[1513] means for transmitting the collected sensor data to a server;

[1514] means for storing the transmitted sensor data in a server;

[1515] A means of automatically analyzing stored sensor data using generative AI;

[1516] A means for generating a coaching method for each player based on the analysis results;

[1517] means for transmitting the generated teaching method to a terminal;

[1518] A means for players to carry out training based on the instruction methods displayed on the device;

[1519] A system including:

[1520] (Claim 2)

[1521] A means to evaluate the characteristics of each player from their sensor data and reflect this in coaching methods,

[1522] A method to analyze the data obtained by retraining and improve the accuracy of the teaching method.

[1523] 10. The system of claim 1, comprising:

[1524] (Claim 3)

[1525] Sensor data is collected on the player's movements, technique, load, position, speed, etc.

[1526] A means of analyzing that data using generative AI; and

[1527] Based on the analysis results, we provide training menus, concrete action plans, and advice for technical improvement.

[1528] 10. The system of claim 1, comprising:

[1529] "Example 1"

[1530] (Claim 1)

[1531] A means of collecting athlete sensor data from IOT devices;

[1532] a means for transmitting the collected sensor data to a server at regular intervals;

[1533] a means for the server to store the transmitted sensor data in a database;

[1534] means for analyzing the stored sensor data using machine learning algorithms;

[1535] A means for generating a coaching method for each player based on the analysis results;

[1536] means for transmitting the generated teaching method from the server to the terminal;

[1537] A means for players to carry out training based on the instruction methods displayed on the device;

[1538] A means to re-collect the sensor data during training and use it for analysis;

[1539] A system including:

[1540] (Claim 2)

[1541] A means to evaluate the characteristics of each player from their sensor data and reflect this in coaching methods,

[1542] A method to analyze the data obtained by retraining and improve the accuracy of the teaching method.

[1543] a means for providing feedback of training results to the user;

[1544] 10. The system of claim 1, comprising:

[1545] (Claim 3)

[1546] Sensor data is collected on the player's movements, technique, load, position, speed, etc.

[1547] means for analyzing the data using machine learning algorithms; and

[1548] Based on the analysis results, we provide training menus, concrete action plans, and advice for technical improvement.

[1549] 10. The system of claim 1, comprising:

[1550] "Application Example 1"

[1551] (Claim 1)

[1552] A means of collecting machine sensor data from IOT devices;

[1553] means for transmitting collected sensor data to a central processing unit;

[1554] means for storing the transmitted sensor data in a central processing unit;

[1555] A means of automatically analyzing stored sensor data using generative AI;

[1556] A means for generating operation instructions and maintenance methods for individual machines based on the analysis results;

[1557] means for transmitting the generated operation instructions and maintenance methods to the terminal;

[1558] A means for controlling the machine based on the operation instructions and maintenance methods displayed on the terminal;

[1559] A system including:

[1560] (Claim 2)

[1561] A method for evaluating the characteristics of each machine from its sensor data and reflecting this in operational instructions and maintenance methods.

[1562] A means for analyzing data obtained by performing the operation again and improving the accuracy of operation instructions and maintenance methods;

[1563] 10. The system of claim 1, comprising:

[1564] (Claim 3)

[1565] Sensor data such as machine operation, pressure, position, and speed are collected,

[1566] A means of analyzing that data using generative AI; and

[1567] A means for providing instructions for improving operational efficiency and specific maintenance plans based on the analysis results;

[1568] 10. The system of claim 1, comprising:

[1569] "Example 2: Combining Emotion Engines"

[1570] (Claim 1)

[1571] A means of collecting athlete sensor data from IOT devices;

[1572] means for transmitting the sensor data and user emotion data collected by the terminal to a server;

[1573] A means for receiving the sensor data and emotion data transmitted by the server via an API and storing them in a database;

[1574] A means for automatically analyzing the stored sensor data and emotion data using generative AI;

[1575] A means for generating a coaching method and emotion-based advice for an individual player based on the analysis results;

[1576] means for transmitting the generated teaching method and advice to the terminal;

[1577] A means for players to carry out training based on the instruction methods and advice displayed on the terminal;

[1578] A system including:

[1579] (Claim 2)

[1580] A means for evaluating the characteristics and emotional state of each player from their sensor data and emotional data, and reflecting this in coaching methods;

[1581] A method to analyze the data obtained by retraining and improve the accuracy of the teaching method.

[1582] 10. The system of claim 1, comprising:

[1583] (Claim 3)

[1584] Sensor data is collected, including data on the player's movements, technique, load, position, speed, and emotional data.

[1585] a means for analyzing the data and the sentiment data using generative AI;

[1586] A means for providing training menus, specific action plans, advice for improving skills, and emotional motivational guidance based on the analysis results;

[1587] 10. The system of claim 1, comprising:

[1588] "Application example 2 when combining emotion engines"

[1589] (Claim 1)

[1590] A means for collecting sensor data and emotional data of players from IOT devices;

[1591] means for transmitting the collected sensor data and emotion data to a server;

[1592] means for storing the transmitted sensor data and emotion data in a server;

[1593] A means for automatically analyzing the stored sensor data and emotion data using generative AI;

[1594] A means for generating coaching methods and emotion-based motivation advice for individual players based on the analysis results of the generation AI;

[1595] means for transmitting the generated teaching method and emotion-based motivation advice to the terminal;

[1596] a means for the athlete to carry out training based on the coaching method and emotion-based motivation advice displayed on the device;

[1597] A system including:

[1598] (Claim 2)

[1599] A means for evaluating the characteristics and emotional state of each player from the sensor data and emotional data of each player, and reflecting this in coaching methods and motivation advice based on emotions;

[1600] A means for analyzing data obtained by retraining and improving the accuracy of instructional methods and emotion-based motivation advice;

[1601] 10. The system of claim 1, comprising:

[1602] (Claim 3)

[1603] Sensor data and emotional data such as player movement, technique, load, position, speed, facial expression, and voice are collected,

[1604] A means of analyzing that data using generative AI; and

[1605] A means for providing training menus, specific action plans, advice for improving skills, and emotion-based motivation advice based on the analysis results;

[1606] 10. The system of claim 1, comprising: [Explanation of symbols]

[1607] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting athlete sensor data from IOT devices; means for transmitting the collected sensor data to a server; means for storing the transmitted sensor data in a server; A means of automatically analyzing stored sensor data using generative AI; A means for generating a coaching method for each player based on the analysis results; means for transmitting the generated teaching method to a terminal; A means for players to carry out training based on the instruction methods displayed on the device; A system including:

2. A means to evaluate the characteristics of each player from their sensor data and reflect this in coaching methods, A method to analyze the data obtained by retraining and improve the accuracy of the teaching method. The system of claim 1 , comprising:

3. Sensor data is collected on the player's movements, technique, load, position, speed, etc. A means of analyzing that data using generative AI; and Based on the analysis results, we provide training menus, concrete action plans, and advice for technical improvement. The system of claim 1 , comprising:

Images