System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting performance data of an athlete; means for performing a biomechanical analysis to identify abnormal movements and loads; means for suggesting a personalized training program based on the analysis; and means for providing real-time advice and care to the athlete.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] In competitive sports, improving athlete performance and preventing injuries are extremely important, but sophisticated data analysis and training guidance are essential, which requires a lot of resources and time. Traditional methods make it difficult to do this efficiently, making it difficult to find optimal training and injury prevention strategies. There is a need for a solution to this problem and to achieve more effective training and injury prevention. [Means for solving the problem]

[0005] The present invention provides a system that uses AI to collect athlete performance data and perform biomechanical analysis to identify abnormal movements and loads. Specifically, the system includes a means for analyzing performance data acquired by a collection means and proposing a training program tailored to individual characteristics. The system also includes a means for providing advice and care in real time, thereby improving athlete performance and reducing injury risk. Furthermore, the system includes a means for assessing fatigue levels and predicting injury risk, as well as a means for preprocessing, cleaning, and normalizing collected data, enabling more accurate analysis and training suggestions.

[0006] An "athlete" is an individual who participates in competitive sports with the goal of achieving high performance.

[0007] "Performance data" is a collection of measurements related to an athlete's movement or physical function, such as heart rate, acceleration, or electromyogram.

[0008] "Collection means" is a general term for devices and sensors used to obtain performance data from athletes.

[0009] "Biomechanics analysis" is a method of analyzing the movements and mechanical characteristics of the human body to detect abnormalities in movements and loads.

[0010] "Abnormal movement" refers to any movement that deviates from normal movement patterns and may lead to injury or reduced performance.

[0011] "Load" is a general term for the physical, psychological, or physiological stress placed on an athlete.

[0012] "Analytics tools" are software and algorithms used to process collected performance data and derive meaningful information.

[0013] A "training program" is a plan of exercise or physical activity that an athlete undertakes with the goal of improving their performance.

[0014] The "suggestion means" is a system or method for presenting optimal training content based on the analysis results.

[0015] "Advice" refers to instructions or recommendations given to athletes to improve performance or prevent injury.

[0016] "Care" is a general term for health management aimed at helping athletes recover from fatigue and prevent injuries.

[0017] "Fatigue state" refers to the athlete's level of physical or mental fatigue.

[0018] "Injury risk" refers to the possibility that an athlete will be injured.

[0019] "Preprocessing" is a process for preparing collected data in a form suitable for analysis.

[0020] "Cleaning" is a process for removing noise and outliers from collected data to improve data quality.

[0021] "Normalization" is the process of converting data to a unified scale to make it comparable. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries. This system collects and analyzes performance data, proposes optimal training programs for athletes, and provides advice and care in real time.

[0044] The system consists of the following main components:

[0045] 1. Data Collection Methods

[0046] Sensors or smartwatches worn by athletes collect biometric data such as heart rate, acceleration, and electromyogram in real time. The devices receive this data and send it to a server.

[0047] 2. Data analysis methods

[0048] The server preprocesses the received biometric data, removing noise and normalizing it. It then performs biomechanics analysis to detect abnormalities in movement and load. It also simultaneously evaluates fatigue levels and predicts injury risk.

[0049] 3. Training program proposal methods

[0050] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics. The program includes details such as exercise content, intensity, number of repetitions, and rest periods. The terminal displays the generated program to the athlete.

[0051] 4. Real-time advice and care delivery tools

[0052] During training, the device continuously collects and transmits real-time data to the server, which analyzes it and generates immediate feedback as needed. If signs of fatigue or abnormal movements are detected, the device will notify the athlete and advise them to rest or modify their movements.

[0053] Specific flow and examples of program processing

[0054] To concretely explain how this system works, let's describe the program's processing in natural language:

[0055] 1. Data collection

[0056] The device collects heart rate and electromyogram data from the athlete in real time. For example, if the athlete's heart rate spikes during training, the device sends that data to a server.

[0057] 2. Data Preprocessing and Analysis

[0058] The server cleans the collected data, removes noise, and normalizes it to make it easier to analyze.

[0059] The server then performs an analysis and, if it determines that, for example, the athlete's heart rate fluctuations are abnormal, it records the abnormality.

[0060] 3. Training program proposals

[0061] Based on the results of the biomechanics analysis, the server generates a training program optimized for the athlete's characteristics, providing detailed guidelines such as specific exercises to strengthen muscles, as well as the number of repetitions and intensity of those exercises.

[0062] The terminal displays the generated training program to the athlete, and the user confirms the training plan for the day.

[0063] 4. Real-time advice and care

[0064] During training, the device continuously collects and transmits real-time data to a server that analyzes the data and, if it detects signs of fatigue, for example, sends instructions to the athlete to rest.

[0065] If the movement is determined to be abnormal, the server will provide advice to the athlete in real time via the device, such as "Pay attention to the position of your toes to correct your running form."

[0066] In this way, this system will improve athletes' performance and prevent injuries by consistently collecting and analyzing data, creating training programs, and providing real-time feedback.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] The device collects biometric data such as heart rate, acceleration, and electromyogram in real time from sensors worn by athletes, and the collected data is temporarily stored on the device.

[0070] Step 2:

[0071] The device transmits the collected biometric data to the server. This communication occurs periodically to ensure that real-time data is transmitted to the server.

[0072] Step 3:

[0073] The server receives the data sent from the terminal. The received data is first cleaned. Cleaning is a process in which noise and outliers are removed and missing data is filled in.

[0074] Step 4:

[0075] The server normalizes the cleaned data. Normalization refers to converting data from different scales into a unified scale to make it easier to analyze.

[0076] Step 5:

[0077] The server uses the normalized data for biomechanical analysis, including machine learning algorithms, to identify abnormal movements and loads.

[0078] Step 6:

[0079] The server uses data analysis to assess an athlete's fatigue state and predict injury risk, integrating past and current data to make a comprehensive judgment.

[0080] Step 7:

[0081] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics, including exercise content, intensity, number of repetitions, and rest periods.

[0082] Step 8:

[0083] The server transmits the generated training program to the terminal, which receives it and displays it to the user.

[0084] Step 9:

[0085] The user checks the training program presented and makes a training plan for the day. The terminal records the user's operations and transmits the necessary data to the server.

[0086] Step 10:

[0087] During training, the device continuously collects biometric data in real time and transmits it to a server, which then analyzes the data to detect fatigue and abnormalities in real time.

[0088] Step 11:

[0089] The server generates real-time advice and care based on the analysis results and notifies the device. For example, if fatigue is detected, it will instruct the user to rest, and if abnormal behavior is detected, it will send advice for correction.

[0090] Step 12:

[0091] The terminal displays real-time advice and care notifications from the server to the user, who then checks these notifications and acts according to the instructions.

[0092] In this way, the system efficiently collects and analyzes athletes' performance data, creates optimal training programs, and provides advice and care in real time, thereby improving athletes' performance and preventing injuries.

[0093] Example 1

[0094] 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."

[0095] Conventional training systems for athletes have struggled to comprehensively and centrally manage the collection and analysis of real-time biometric data, as well as the proposal of training programs based on the analysis results. It has been particularly difficult to provide fast and accurate advice in situations where real-time feedback during training or immediate action is required to prevent injury. Furthermore, insufficient pre-processing, such as data noise removal and normalization, can reduce the accuracy of the analysis, potentially resulting in a decline in the quality of the training program.

[0096] 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.

[0097] In this invention, the server includes means for collecting athlete performance data, means for transmitting the data to the server, means for preprocessing, cleaning, and normalizing the collected data, means for performing biomechanics analysis to identify abnormal movements and loads, means for generating an individual training program based on the analysis results, means for displaying the generated training program on a terminal, means for providing advice and care to the athlete in real time, and means for collecting data in real time during training and transmitting it to the server. This enables a system that can perform all processes from collection to analysis, generation of a training program, and provision of real-time feedback.

[0098] "Athlete" refers to a person who participates in competitive activities in sports or athletic competitions.

[0099] "Performance data" refers to biometric information that indicates an athlete's physical ability, physical condition, exercise status, etc. Specifically, it includes data such as heart rate, acceleration, and electromyogram.

[0100] "Data Collection Instruments" refers to devices or equipment used to obtain real-time performance data from athletes, including, for example, sensors and smartwatches.

[0101] "Server" refers to a data processing device accessible via the Internet or a local network that analyzes data and generates training programs.

[0102] "Preprocessing" refers to the process carried out before data analysis, such as removing noise and normalizing the data. This process improves the quality of the data and increases the accuracy of the analysis.

[0103] "Cleaning" refers to the process of removing unnecessary noise and outliers from acquired performance data.

[0104] "Normalization" is a process of constraining data variation within a certain range, and is performed to ensure consistency between different data sets.

[0105] "Biomechanics analysis" refers to a data-based method of analyzing an athlete's physical movements and stress conditions. This analysis can detect abnormalities in movement and excessive stress.

[0106] A "training program" is a plan that specifically outlines the exercises and training that an athlete should perform, including the content, intensity, number of repetitions, and rest times.

[0107] "Real-time advice and care delivery tools" refer to tools that provide immediate feedback and instruction based on data collected during training.

[0108] "Terminal" refers to a device that an athlete can operate and view displayed information, including, specifically, a smartphone or tablet.

[0109] "Analysis results" refers to the evaluation and diagnostic results of data obtained through preprocessing and biomechanics analysis.

[0110] "Abnormal movements or loads" refers to conditions that exceed normal movement patterns or physical load ranges, and indicates movements or excessive loads that may have adverse effects on the body.

[0111] MODE FOR CARRYING OUT THE INVENTION

[0112] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries. This system collects and analyzes performance data to propose optimal training programs for athletes and provides advice and care in real time. Specific embodiments of this system are described below.

[0113] The system consists of the following main components:

[0114] 1. Data Collection Methods

[0115] Sensors, smartwatches, and other devices collect biometric data, such as heart rate, acceleration, and electromyograms, in real time. Users wear these devices. The device receives this data and transmits it to a server. For example, if a user's heart rate spikes while running, the device sends that data to the server.

[0116] 2. Data Preprocessing and Analysis

[0117] The server first cleans the biometric data received from the device to remove noise. Then, it normalizes the data to make it easier to analyze. The server then uses the normalized data to perform biomechanics analysis and detect abnormalities in movement and load. For example, if a sudden change in heart rate is detected, the server records the abnormality and considers countermeasures.

[0118] 3. Training program proposals

[0119] The server generates a training program optimized for the athlete's characteristics based on the analysis results. The program includes details such as exercise content, intensity, number of repetitions, and rest time. For example, if it is determined that muscle strengthening is necessary, detailed guidelines such as "3 sets of 12 squats, with a load of 50% of body weight, with 90 seconds of rest between sets" will be generated. The device displays the generated training program to the user.

[0120] 4. Real-time advice and care delivery tools

[0121] During training, the device continuously transmits collected real-time data to the server, which immediately analyzes it and generates immediate feedback as needed. For example, if signs of fatigue are detected, the device will instruct the user to rest. If abnormal movements are detected, specific advice such as "Pay attention to the position of your toes to correct your running form" will be provided.

[0122] Specific examples

[0123] For example, to generate an optimal training program for Athlete A to improve muscle strength and prevent injury based on their heart rate, EMG data, and training history from the past week, the prompt would be:

[0124] Based on Athlete A's heart rate, EMG data, and training history from the past week, please generate an optimal training program for improving muscle strength and preventing injury. Please recommend specific exercises, number of repetitions, intensity, and rest periods.

[0125] An example of the output produced is:

[0126] Strength Training Program:

[0127] Exercise: Squats

[0128] Reps: 3 sets x 12 reps

[0129] Intensity: 50% of body weight

[0130] Rest Time: 90 seconds rest between sets

[0131] Additional tips: Focus on form, foot position and knee movement. After this exercise, do some gentle stretching to loosen up your muscles.

[0132] In this way, this system starts with collecting data from the device worn by the user, then analyzes the data on the server, creates training programs, and provides real-time feedback, all in an integrated manner, effectively supporting athletes in improving their performance and preventing injuries.

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] Step 1: Collect data

[0135] How it works: The user wears a smartwatch and sensors, which collect biometric data such as heart rate, acceleration, and electromyogram in real time. The smartwatch measures heart rate every 10 seconds and sends the data to the device.

[0136] Input: Biometric data from smartwatches and sensors.

[0137] Output: Real-time biometric data sent to the device.

[0138] Step 2: Sending data

[0139] Specific operation: The device sends the collected biometric data to the server at any time. The data is securely transmitted via the Internet.

[0140] Input: Biometric data collected on the device.

[0141] Output: Biometric data sent to the server.

[0142] Step 3: Preprocessing the data

[0143] Specific operation: The server first cleans the received biometric data, removes noise if it is present, and corrects outliers. Then, it normalizes the data and converts it into a unified format.

[0144] Input: Biometric data sent to the server.

[0145] Output: Cleaned and normalized biometric data.

[0146] Step 4: Analyze the data

[0147] Specific actions: The server performs biomechanical analysis based on the normalized data. This determines whether the athlete's movements and loads are appropriate. If abnormal movements or excessive loads are detected, they are recorded and countermeasures are considered.

[0148] Input: Cleaned and normalized biometric data.

[0149] Output: Biomechanical analysis results, assessment of abnormalities and loads.

[0150] Step 5: Generate a training program

[0151] Specific actions: Based on the analysis results, the server generates a training program that is optimal for the athlete's characteristics. The program includes details such as exercise content, intensity, number of repetitions, and rest time. For example, it creates guidelines such as "3 sets of 12 squats, with a load of 50% of body weight, and 90 seconds of rest between sets."

[0152] Input: Biomechanical analysis results.

[0153] Output: Training program details.

[0154] Step 6: View your training program

[0155] Specific operation: The device displays the generated training program to the athlete, who can then check the training plan for the day through the device.

[0156] Input: Training program details.

[0157] Output: The training program displayed on the terminal.

[0158] Step 7: Collect real-time data

[0159] Specific operation: During training, the device continues to collect biometric data in real time and transmits it to the server.

[0160] Input: Real-time biometric data during training.

[0161] Output: Real-time biometric data sent to the server.

[0162] Step 8: Real-time feedback

[0163] Specific operation: The server immediately analyzes the data received in real time and generates immediate feedback as needed. If signs of fatigue or abnormal movements are detected, the server notifies the athlete via the device with appropriate instructions. For example, it gives advice such as "You are showing signs of fatigue. Please take a break" or "Pay attention to the position of your toes to correct your running form."

[0164] Input: Biometric data received in real time.

[0165] Output: Real-time feedback displayed on the device.

[0166] These steps enable the system to consistently collect and analyze data, generate training programs, and provide real-time feedback, thereby effectively supporting athletes in improving their performance and preventing injuries.

[0167] (Application example 1)

[0168] 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."

[0169] Conventional industrial equipment does not adequately collect and analyze operational data, making it difficult to detect signs of abnormal operation early. As a result, abnormalities are often not noticed until a failure occurs, leading to sudden machine shutdowns and production delays. Furthermore, even when an abnormality is detected, there is a lack of means to provide immediate, appropriate feedback, making it difficult to operate industrial equipment efficiently. A new system is needed to solve these issues, improve operational performance, and prevent failures.

[0170] 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.

[0171] In this invention, the server includes means for collecting operational data of industrial equipment, means for performing machine operation analysis and identifying abnormal operations and loads, means for proposing individual operation schedules based on the analysis results, means for providing advice and correction instructions to the industrial equipment in real time, means for evaluating the fatigue state and predicting the risk of failure, and means for preprocessing, cleaning, and normalizing the collected data, thereby improving the operational performance of the industrial equipment, reducing the risk of failure, and enabling stable operation.

[0172] "Industrial equipment" is a general term for machines and devices used in factories and manufacturing facilities to automate, streamline, or support the production process.

[0173] "Operational data" refers to information relating to the movement of a device, including measurements such as position, speed, temperature, and vibration.

[0174] "Machine operation analysis" is a technology that analyzes the operating status of equipment based on collected operation data and distinguishes between normal and abnormal operation.

[0175] "Abnormal operation" refers to the occurrence of behavior that is different from normal in the operation of equipment, which may cause a malfunction if it continues.

[0176] "Load" refers to external factors such as force, pressure, and temperature that are applied to equipment when it is operating, and if this load becomes excessive it can have a negative effect on the equipment.

[0177] An "operation schedule" is a timetable for systematically managing the operation and running of equipment, and lists optimal operating times and maintenance timings.

[0178] "Advice" means appropriate instructions or suggestions regarding the operation of equipment, intended to facilitate adjustments to operation or maintenance.

[0179] "Correction instructions" refer to instructions on specific operating methods or changes to be made to deal with abnormal equipment operation or load.

[0180] "Fatigue" refers to a state in which equipment parts or systems begin to deteriorate due to prolonged or excessive use.

[0181] "Failure risk" is the probability of a failure occurring that can be predicted from the operation and condition of equipment, and by predicting this, it is possible to take measures in advance.

[0182] "Data preprocessing" refers to the process of preparing collected raw data in a form that is easier to analyze, and includes processes such as removing noise and normalizing the data.

[0183] "Cleaning" is the process of removing unnecessary information and errors from collected data.

[0184] "Normalization" is a process of standardizing data values ​​to a certain scale, and is performed to improve the accuracy of analysis.

[0185] This invention relates to an AI system aimed at improving the operational performance and preventing breakdowns of industrial equipment. This system collects and analyzes operational data, proposes optimal operation schedules for industrial equipment, and provides advice and correction instructions in real time. The system consists of the following main components:

[0186] Data collection methods

[0187] Sensors attached to industrial equipment collect operational data such as position, speed, temperature, and vibration in real time, and the collected data is sent to a server via the terminal.

[0188] Data Analysis Methods

[0189] The server preprocesses the collected operational data, removing noise and normalizing the data, and performs machine operation analysis to detect abnormalities in operation and load. It also evaluates fatigue status and predicts failure risk.

[0190] Operation schedule suggestion means

[0191] Based on the analysis results, the server generates an optimal operation schedule tailored to the characteristics of the industrial equipment. The schedule includes details such as operating hours, load balancing, and maintenance periods. The terminal displays the generated schedule to the industrial equipment operator.

[0192] Real-time advice and corrective action methods

[0193] During operation, the terminal continuously transmits real-time collected data to the server, which analyzes the data and generates immediate feedback as needed. If abnormal behavior or excessive load is detected, the terminal will notify the operator with appropriate corrective instructions.

[0194] System Operation

[0195] 1. Data collection: Sensors attached to industrial equipment continuously collect operational data in real time, such as position, speed, temperature, and vibration. For example, if a robot arm experiences a sudden rise in temperature while in operation, the data is sent to a server via the terminal.

[0196] 2. Data preprocessing and analysis: The server cleans the collected data and removes noise. It also normalizes the data to make it easier to analyze. Next, the server analyzes the machine's operation to detect abnormal behavior or excessive loads. For example, if analysis of vibration data reveals that a particular part is wearing out, the server records that information.

[0197] 3. Proposing an operation schedule: Based on the analysis results, the server generates an optimal operation schedule tailored to the characteristics of the industrial equipment. As a specific example, it proposes a short-term maintenance schedule taking into account parts that are deteriorating. The terminal displays the generated schedule to the operator, who then confirms the plan.

[0198] 4. Real-time advice and correction instructions: If an abnormality is detected during operation, the server immediately analyzes it and generates appropriate correction instructions. For example, specific advice such as "Please reduce the operating speed" or "A specific part needs to be replaced" is provided in real time via the terminal.

[0199] Hardware and software used

[0200] To implement the present invention, the following hardware and software are used:

[0201] Hardware: Industrial equipment, accelerometers, temperature sensors, vibration sensors.

[0202] Software: Python, TensorFlow, SQL Server, GUI development frameworks (such as Tkinter).

[0203] Examples and prompts

[0204] Specific examples

[0205] 1. Example 1: If the motor temperature suddenly rises while an industrial robot is operating, the system will issue a warning saying "Motor temperature is too high. Please reduce speed."

[0206] 2. Example 2: If abnormal vibration is detected, notify the user that "Abnormal vibration has been detected. Please change the operation route."

[0207] Prompt statement

[0208] Example prompts to enter into the Data Analysis module:

[0209] Check for motor temperature spikes and display warnings if necessary. Use temperature data from the past 24 hours.

[0210] Example prompts for the optimization algorithm:

[0211] "Optimize the operating schedule of industrial equipment and distribute the load to specific time periods. Consider detailed load data and operating history."

[0212] As described above, this system performs all processes from data collection and analysis to generating operation schedules and providing real-time feedback, thereby improving the operational performance of industrial equipment and preventing breakdowns.

[0213] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0214] Step 1:

[0215] Sensors collect operational data

[0216] Sensors attached to industrial equipment collect operational data such as position, speed, temperature, and vibration in real time. This data is sent to a server via a terminal. The input data is the measurement value from the sensor, and the output is the raw data sent to the server. For example, the temperature and vibration data of a robot arm in operation is constantly recorded and transferred to the terminal.

[0217] Step 2:

[0218] Data Preprocessing

[0219] The server cleans the received motion data, removes noise, and normalizes it to make it easier to analyze. The input data is raw data sent from the sensors, and the output is cleaned and normalized data. Specific operations include missing value imputation, outlier removal, and range scaling.

[0220] Step 3:

[0221] Data analysis

[0222] The server uses the preprocessed data to analyze machine operation to identify abnormal behavior and loads. A generative AI model is used for the analysis to detect anomalies and evaluate failure risks. The input data is preprocessed data, and the output is the analysis results, including abnormal behavior detection results and risk assessment data. Specifically, the AI ​​model analyzes sensor data to detect abnormal temperature increases and excessive vibrations.

[0223] Step 4:

[0224] Generate an operation schedule

[0225] Based on the analysis results, the server generates an optimal operation schedule tailored to the characteristics of the industrial equipment. The input data are the analysis results, and the output is a recommended operation schedule. In terms of specific operations, the system generates plans for maintenance periods and load balancing based on the analysis results and presents them to the operator.

[0226] Step 5:

[0227] Viewing Schedules

[0228] The terminal displays the generated operation schedule to the industrial equipment operator. The input data is the operation schedule sent from the server, and the output is data in a display format that can be checked by the operator. In concrete terms, the operation schedule is displayed on the terminal display, and the operator checks it.

[0229] Step 6:

[0230] Real-time data monitoring and feedback

[0231] During operation, the terminal continuously collects and transmits real-time operational data to the server. The server analyzes this data and generates immediate feedback as needed. The input data is real-time operational data, and the output is feedback such as advice and correction instructions. Specifically, if abnormal movement or excessive load is detected, instructions such as "Please reduce speed" are displayed in real time on the operator's terminal.

[0232] 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.

[0233] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries, and also provides a system that combines an emotion engine that recognizes athletes' emotions. This system collects and analyzes performance and emotion data, proposes optimal training programs for athletes, and provides advice and care in real time, thereby achieving overall performance improvement and injury prevention for athletes.

[0234] The system consists of the following main components:

[0235] 1. Data Collection Methods

[0236] The sensors and smartwatches worn by athletes collect biometric data such as heart rate, acceleration, and electromyograms, as well as emotional data from the athletes' facial expressions and voice. The devices receive this data and send it to a server.

[0237] 2. Emotion recognition means

[0238] The server uses the collected facial and voice data to analyze the athlete's emotional state using an emotion engine, which identifies emotions such as joy, sadness, anger, and stress.

[0239] 3. Data Analysis Methods

[0240] The server preprocesses the received biometric and emotional data, cleansing and normalizing them, and then performs biomechanics analysis to comprehensively evaluate abnormalities in movement and load, as well as emotional states.

[0241] 4. Training program proposal methods

[0242] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics and emotional state. The program includes details such as exercise content, intensity, number of repetitions, and rest periods. The terminal displays the generated program to the athlete.

[0243] 5. Real-time advice and care delivery methods

[0244] During training, the device continuously collects and transmits real-time biometric and emotional data to the server, which analyzes it and generates immediate feedback as needed. If signs of fatigue, abnormal movements, or emotional stress are detected, the device will notify the athlete and advise them to rest or modify their movements.

[0245] Specific flow and examples of program processing

[0246] To concretely explain how this system works, let's describe the program's processing in natural language:

[0247] 1. Data collection

[0248] The device collects real-time data from athletes, including their heart rate, electromyogram, facial expression data from a facial recognition sensor, and audio data from a voice recognition microphone. For example, if an athlete does not smile during training, their facial expression and audio data will also be collected.

[0249] 2. Data Preprocessing and Emotion Recognition

[0250] The server cleans the collected data, removes noise, and normalizes it to make it easier to analyze.

[0251] The emotion engine identifies the athlete's emotions from facial and voice data. For example, if a high level of stress or fatigue is detected, the emotion data is recorded.

[0252] 3. Data analysis and evaluation

[0253] The server uses normalized biometric and emotional data for biomechanical analysis, using machine learning algorithms to identify abnormalities in movement and stress.

[0254] The server uses data analysis to comprehensively assess an athlete's fatigue and emotional state, adjusting the intensity of specific training sessions if, for example, emotional stress is high.

[0255] 4. Training program proposals

[0256] Based on the analysis results, the server generates a training program that is optimal for the athlete's characteristics and emotional state. For example, it adds relaxation exercises when stress levels are high, and suggests high-intensity training when joy levels are high.

[0257] 5. Real-time advice and care

[0258] During training, the device continuously collects biometric and emotional data in real time and transmits it to a server, which then analyzes the data to detect fatigue, abnormalities in movement, and emotional changes in real time.

[0259] Based on the analysis results, real-time advice and care is provided. For example, if emotional stress is detected, it will suggest ways to relax, and if abnormal movements are detected, it will advise on the correct way to move.

[0260] In this way, by combining this system with an emotion engine, it is possible to comprehensively evaluate an athlete's physical and emotional state, suggest more accurate training programs, and provide real-time advice, thereby improving athlete performance and preventing injuries.

[0261] The processing flow will be explained below.

[0262] Step 1:

[0263] The device collects biometric data such as heart rate, acceleration, and electromyogram in real time from sensors worn by athletes. It also collects facial expression and voice data from facial recognition sensors and a voice recognition microphone for emotion recognition. This collected data is temporarily stored on the device.

[0264] Step 2:

[0265] The device transmits all collected biometric and emotional data to a server periodically, delivering the data in near real time.

[0266] Step 3:

[0267] The server receives the data sent from the device, which is first cleaned to remove noise and outliers and fill in missing data, improving the accuracy of the data.

[0268] Step 4:

[0269] The server normalizes the cleaned data. Normalization is the process of converting data from different scales into a unified scale to make it easier to analyze.

[0270] Step 5:

[0271] The server analyzes the normalized data with an emotion engine, which identifies the athlete's emotional state (e.g., joy, sadness, anger, stress, etc.) based on facial and voice data.

[0272] Step 6:

[0273] The server uses the emotion engine results and biological data for biomechanical analysis, which identifies abnormalities in the athlete's movements, loads, and fatigue.

[0274] Step 7:

[0275] Based on the analysis results, the server generates a training program optimized for the athlete's characteristics and emotional state. The program includes details such as exercise content, intensity, number of repetitions, and rest periods. For example, if an athlete is in a high stress state, relaxation exercises will be added.

[0276] Step 8:

[0277] The server transmits the generated training program to the terminal, which receives it and displays it to the user.

[0278] Step 9:

[0279] The user checks the training program presented and makes a training plan for the day. The terminal records the user's operations and transmits the necessary data to the server.

[0280] Step 10:

[0281] During training, the device continues to collect real-time biometric and emotional data and transmits it to the server, which is used to monitor the training progress in real time.

[0282] Step 11:

[0283] The server analyzes the data received in real time to detect the athlete's fatigue, abnormalities in their movements, and emotional changes. For example, if an athlete's heart rate spikes or stress is detected in their facial expressions, the server generates appropriate feedback.

[0284] Step 12:

[0285] The server generates real-time advice and care based on the analysis results and notifies the device. For example, it suggests resting if fatigue suddenly increases, instructs corrective actions if abnormal behavior is detected, and sends instructions for relaxation if emotional stress increases.

[0286] Step 13:

[0287] The device displays real-time advice and care notifications from the server to the user, who then checks these notifications and acts accordingly, for example, accepting suggestions for rest or modifying their behavior.

[0288] In this way, the system comprehensively analyzes biometric and emotional data and provides optimal training programs and real-time advice tailored to the athlete's condition, thereby improving their performance and preventing injuries.

[0289] Example 2

[0290] 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."

[0291] Conventional training systems for athletes focus on collecting and analyzing only biological data, and lack comprehensive evaluation and advice that takes into account the athlete's emotional state. This often leaves them inadequate for maximizing athletes' performance and preventing injuries. Real-time feedback and immediate care during training are also limited. To address this situation, a system is needed that can comprehensively analyze athletes' biological and emotional data and provide optimal training programs and real-time advice tailored to their individual characteristics.

[0292] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting the athlete's biological data and emotional data, means for cleaning and normalizing the collected data, means for identifying the athlete's emotions using an emotion engine, means for performing biomechanics analysis and identifying abnormalities in movement and load, means for generating a training program optimal for the athlete's characteristics and emotional state based on the analysis results, and means for providing advice and care to the athlete in real time. This makes it possible to comprehensively evaluate the athlete's physical and emotional state and propose more accurate training programs and provide real-time advice.

[0293] "Biometric data" refers to data that indicates the physiological state of the body, such as an athlete's heart rate, acceleration, and electromyogram.

[0294] "Emotional data" is data that indicates the emotional state of an athlete, obtained from facial expressions, voice, etc.

[0295] An "emotion engine" is software or algorithm that identifies an athlete's emotions from collected facial and voice data.

[0296] "Biomechanics analysis" is an analytical method that analyzes an athlete's movements and loads to identify abnormalities.

[0297] A "training program" is a program that includes the optimal exercise content, intensity, number of repetitions, rest time, etc., according to the athlete's characteristics and emotional state.

[0298] "Real-time advice" refers to instructions and advice provided to athletes instantly based on collected biometric and emotional data.

[0299] "Care" means the instruction and support to maintain and promote the athlete's physical and mental health.

[0300] "Cleaning" is the process of removing noise from collected data and preparing it in a form that can be analyzed.

[0301] "Normalization" is the process of converting data into a consistent format that makes it easier to analyze.

[0302] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries. Furthermore, this invention provides a system that combines an emotion engine that recognizes athletes' emotions to achieve comprehensive performance improvement and injury prevention for athletes.

[0303] The system consists of the following main components:

[0304] 1. Data Collection Methods

[0305] The device collects biometric data such as heart rate, acceleration, and electromyogram in real time from sensors or smartwatches worn by athletes. The device also collects facial expression and voice data using a camera and voice recognition microphone. For example, when an athlete is running, the device collects not only heart rate and electromyogram data, but also facial expressions while running and comments on training in real time.

[0306] 2. Emotion recognition means

[0307] The server inputs the collected facial and voice data into an emotion engine to identify the athlete's emotions. The emotion engine utilizes machine learning models to assess the athlete's emotional state in real time. For example, it can analyze whether the athlete is feeling stressed based on facial expressions and tone of voice.

[0308] 3. Data Analysis Methods

[0309] The server cleans the collected biometric and emotional data to remove noise. It then normalizes the data to make it easier to analyze. It then performs biomechanical analysis to identify abnormalities in movement and load. For example, it can detect an anomaly if an athlete takes a stride that differs from their normal walking style.

[0310] 4. Training program proposal methods

[0311] Based on the analysis results, the server generates a training program optimized for the athlete's characteristics and emotional state. This program includes details such as exercise content, intensity, number of repetitions, and rest periods. For example, if the athlete is feeling stressed, it will suggest relaxation exercises.

[0312] 5. Real-time advice and care delivery methods

[0313] During training, the device continuously collects and transmits real-time biometric and emotional data to the server, which analyzes it and generates immediate feedback as needed. For example, if your heart rate spikes, the device will prompt you to take a short break.

[0314] To use the system, the generative AI model might be fed prompts like the following example:

[0315] "Please explain how an AI system that analyzes athletes' performance and emotional data and proposes optimal training programs works from the perspectives of the server, device, and user."

[0316] This system will enable a comprehensive assessment of an athlete's physical and emotional state, providing more accurate training program suggestions and real-time advice.

[0317] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0318] Step 1:

[0319] Data collection

[0320] The device collects biometric data in real time from sensors or smartwatches worn by athletes. For example, it acquires heart rate (collected data) and electromyograms. The input data is the athlete's real-time heart rate and electromyogram, and the output is a stream of collected biometric data.

[0321] The device uses a camera and a voice recognition microphone to collect facial and voice data of the athlete. For example, it captures the athlete's smile and tone of voice (emotion data). The input data is real-time captured information from the camera and microphone, and the output is a stream of emotion data.

[0322] Step 2:

[0323] Data Preprocessing

[0324] The server receives the biometric data and emotion data sent from the terminal, and the input data is the collected biometric data and emotion data.

[0325] The server cleans (denoises) and normalizes the data to make it easier to analyze. For example, it removes outliers from heart rate data and aligns them along a time axis. The output is cleaned and normalized biometric and emotion data.

[0326] Step 3:

[0327] emotion recognition

[0328] The server inputs the cleaned and normalized emotion data into the emotion engine to identify emotions. The input data is the preprocessed facial expression data and speech data.

[0329] The server uses an emotion engine to analyze emotions such as stress, joy, anger, etc. For example, a smiling face can be recognized as joy, and a low voice as stress. The output is data indicating the emotional state.

[0330] Step 4:

[0331] Data analysis

[0332] The server performs biomechanics analysis using the biometric data and emotion data, and the input data is the preprocessed biometric data and emotion data.

[0333] The server uses machine learning algorithms to identify abnormalities in movement and load, for example, detecting unusual running form. The output is an analysis result that includes the abnormal movement and load.

[0334] Step 5:

[0335] Generate a training program

[0336] The server generates a training program that is optimal for the athlete's characteristics and emotional state based on the analysis results. The input data are the biological data, the emotional data, and the analysis results.

[0337] The server automatically generates a training program including exercise type, intensity, number of repetitions, and rest time. For example, it suggests relaxation exercises when stress is high, and high-intensity training when energy is high. The output is a customized training program.

[0338] Step 6:

[0339] Training Program Notification

[0340] The server sends the generated training program to the terminal, and the input data is the generated training program.

[0341] The device displays the information to the athlete and notifies them of the next action. For example, specific instructions such as "Next, stretch after 10 minutes of running" are displayed. The output is the notification to the athlete.

[0342] Step 7:

[0343] Real-time monitoring and feedback

[0344] The device continuously transmits the biological data and emotional data collected in real time during training to the server. The input data is the data collected in real time.

[0345] The server analyzes the data received in real time and generates immediate feedback if necessary. For example, if your heart rate spikes, it will generate a prompt to "take a short break." The output is real-time feedback.

[0346] The device provides real-time advice to the athlete based on feedback from the server. For example, if there is an abnormality in movement, specific advice such as "Check your right foot step" is displayed. The output is real-time advice to the athlete.

[0347] Through these steps, the system will be able to perform detailed analysis of athletes' biometric and emotional data, and provide training programs and real-time advice tailored to their individual characteristics.

[0348] (Application example 2)

[0349] 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."

[0350] Previous systems have focused on improving athletes' performance and managing their workload, but few systems have considered the influence of emotions. Furthermore, technology for managing passenger emotions and comfort levels in real time in autonomous vehicles is still immature, and a method to improve the overall passenger experience is needed. Therefore, a new system that utilizes emotion data is needed in the context of both athletes and autonomous vehicles.

[0351] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting athlete performance data, means for performing biomechanics analysis to identify abnormal movements and loads, means for proposing an individual training program based on the analysis results, means for providing advice and care to the athlete in real time, means for collecting passenger emotional data, means for analyzing the collected emotional data and evaluating comfort levels, means for automatically adjusting the in-vehicle environment based on the evaluation results, and means for suggesting entertainment and relaxation to passengers based on their emotional states. This makes it possible to optimize athlete performance while preventing injuries and managing loads, and enables real-time management of passenger emotions and comfort levels in autonomous vehicles.

[0352] "Means for collecting athlete performance data" refers to equipment that uses sensors or devices worn by athletes to obtain biometric data such as heart rate, electromyogram, and acceleration.

[0353] "Means for conducting biomechanical analysis and identifying abnormal movements and loads" refers to algorithms and programs that analyze collected biometric data and identify any abnormalities in an athlete's movements or loads.

[0354] The "means for proposing individual training programs based on the analysis results" is a system for generating training programs specifically for athletes based on the results of data analysis.

[0355] "Means for providing athletes with real-time advice and care" refers to applications that provide athletes with immediate feedback and care instructions based on data collected during training.

[0356] The "means for collecting passenger emotional data" is a device that uses a camera or microphone to capture passenger facial expressions and voices and collect emotional data based on them.

[0357] The "means for analyzing collected emotion data and evaluating the comfort level" is a system that analyzes the acquired emotion data and evaluates the comfort level of passengers using the analysis results.

[0358] The "means for automatically adjusting the in-car environment based on the evaluation results" is a device that automatically sets and changes the in-car environment, such as temperature, lighting, and music, based on the evaluation results of emotional data.

[0359] The "means for suggesting entertainment and relaxation methods to passengers based on their emotional state" is a system that presents entertainment content and relaxation methods appropriate for passengers based on the results of analyzing their emotions.

[0360] This invention relates to an AI system for improving athletic performance and injury prevention, and a passenger comfort management system for autonomous vehicles. The system includes the following main components and processes:

[0361] Data collection

[0362] The server uses sensors and devices to collect biometric data from athletes and emotional data from passengers. Specifically, it uses devices such as smartwatches worn by athletes, accelerometers, electromyogram sensors, cameras, and microphones to collect heart rate, electromyogram, acceleration, facial expression data, and voice data. To collect emotional data from passengers in the in-car environment, it uses cameras and microphones installed in the vehicle.

[0363] Data preprocessing and emotion recognition

[0364] The server cleans the collected data and removes noise. It uses Python and R libraries to normalize the data and make it easier to analyze. For emotion recognition, it uses emotion recognition models built with TensorFlow and Keras. For example, if a passenger is not smiling, their facial expression data is also collected and analyzed along with the voice data.

[0365] Data analysis and evaluation

[0366] The server performs biomechanics analysis using normalized biometric and emotional data. It uses machine learning algorithms, such as scikit-learn and TensorFlow, to identify abnormalities in movement and load. To assess passenger comfort, it generates a comfort score based on the emotional data.

[0367] Training program suggestions and automatic adjustment of the in-car environment

[0368] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics and emotional state. The program includes details such as exercise type, intensity, number of repetitions, and rest periods. Inside the autonomous vehicle, a control program is executed that automatically adjusts the in-car environment, including temperature, lighting, and music, based on the evaluation results of the emotional data.

[0369] Real-time advice and care

[0370] During training or while the vehicle is in operation, the device continuously collects real-time biometric and emotional data and transmits it to the server. The server analyzes this data and provides immediate feedback. For example, if fatigue or abnormal movements are detected, the device will instruct the athlete to rest or correct their movements. It will also suggest relaxation and entertainment options based on the passenger's emotional state.

[0371] Examples of specific examples and prompts

[0372] For example, when an athlete is training, the system can detect their fatigue level in real time using electromyograms and heart rate data and immediately instruct them to rest. Based on passenger emotional data, the in-car environment can be optimally adjusted to provide a comfortable travel experience.

[0373] Example prompts to input to a generative AI model:

[0374] 1. "Suggest a list of music to play when passengers are happy."

[0375] 2. "Decide on environmental settings for passengers experiencing stress and adjust temperature and lighting settings for accountability."

[0376] 3. "Analyze real-time sentiment data and show passengers the entertainment they want."

[0377] In this way, the system, combined with the emotion engine, can comprehensively assess the athlete's physical and emotional state, improving passenger comfort in autonomous vehicles.

[0378] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0379] Step 1:

[0380] The device collects biometric and emotional data from athletes or passengers. Specifically, it uses devices such as smartwatches worn by athletes, accelerometers, electromyogram sensors, cameras, and microphones to obtain heart rate, electromyogram, acceleration, facial expression data, and voice data in real time. The device then transmits this data to a server.

[0381] Step 2:

[0382] The server cleans the received data and removes noise. Specifically, it uses data preprocessing libraries in Python and R to impute missing values ​​and remove outliers from the collected biometric and emotional data. The input data includes biometric signals from biometric sensors and camera and microphone data, and the output data is clean data.

[0383] Step 3:

[0384] The server normalizes the cleaned data and prepares it for easier analysis. Specifically, it scales and standardizes the biometric and emotional data. Here, the input data is the cleaned biometric and emotional data, and the output data is the normalized data.

[0385] Step 4:

[0386] The server uses the normalized data to perform emotion recognition. Specifically, it inputs the data into an emotion recognition model built using TensorFlow and Keras to analyze the emotional state. The input data includes normalized facial expression data and voice data, and the output data is the emotional state (happiness, sadness, anger, stress, etc.).

[0387] Step 5:

[0388] The server performs biomechanics analysis using normalized biometric and emotional data. It uses machine learning algorithms to identify abnormalities in movement and stress. Specifically, it uses scikit-learn and TensorFlow to apply a motion analysis model to detect abnormal movements and overload. The input data is normalized biometric and emotional data, and the output data includes abnormal movements and stress.

[0389] Step 6:

[0390] The server generates a training program that matches the athlete's characteristics and emotional state based on the analysis results. Specifically, if overload or abnormal movement is detected, it provides a program that includes appropriate exercise content, intensity, number of repetitions, rest periods, etc. The input data are the biomechanics analysis results and emotion analysis results, and the output data includes a training program.

[0391] Step 7:

[0392] The server evaluates the passenger's comfort level based on emotional data in the autonomous vehicle and automatically adjusts the in-car environment. Specifically, if the emotional state indicates stress, it adjusts the temperature and lighting and plays relaxation music. The input data is the emotion analysis results, and the output data includes the in-car environment settings.

[0393] Step 8:

[0394] The terminal continuously transmits the data collected in real time to the server, which then provides immediate feedback. Specifically, it displays rest instructions and movement modification advice to athletes, and relaxation and entertainment suggestions to passengers. The input data is real-time biometric and emotional data, and the output data includes the content of the feedback.

[0395] This way, proper care and feedback can be provided to both the athlete and the passengers at each step.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] [Second embodiment]

[0400] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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).

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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."

[0412] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries. This system collects and analyzes performance data, proposes optimal training programs for athletes, and provides advice and care in real time.

[0413] The system consists of the following main components:

[0414] 1. Data Collection Methods

[0415] Sensors or smartwatches worn by athletes collect biometric data such as heart rate, acceleration, and electromyogram in real time. The devices receive this data and send it to a server.

[0416] 2. Data analysis methods

[0417] The server preprocesses the received biometric data, removing noise and normalizing it. It then performs biomechanics analysis to detect abnormalities in movement and load. It also simultaneously evaluates fatigue levels and predicts injury risk.

[0418] 3. Training program proposal methods

[0419] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics. The program includes details such as exercise content, intensity, number of repetitions, and rest periods. The terminal displays the generated program to the athlete.

[0420] 4. Real-time advice and care delivery tools

[0421] During training, the device continuously collects and transmits real-time data to the server, which analyzes it and generates immediate feedback as needed. If signs of fatigue or abnormal movements are detected, the device will notify the athlete and advise them to rest or modify their movements.

[0422] Specific flow and examples of program processing

[0423] To concretely explain how this system works, let's describe the program's processing in natural language:

[0424] 1. Data collection

[0425] The device collects heart rate and electromyogram data from the athlete in real time. For example, if the athlete's heart rate spikes during training, the device sends that data to a server.

[0426] 2. Data Preprocessing and Analysis

[0427] The server cleans the collected data, removes noise, and normalizes it to make it easier to analyze.

[0428] The server then performs an analysis and, if it determines that, for example, the athlete's heart rate fluctuations are abnormal, it records the abnormality.

[0429] 3. Training program proposals

[0430] Based on the results of the biomechanics analysis, the server generates a training program optimized for the athlete's characteristics, providing detailed guidelines such as specific exercises to strengthen muscles, as well as the number of repetitions and intensity of those exercises.

[0431] The terminal displays the generated training program to the athlete, and the user confirms the training plan for the day.

[0432] 4. Real-time advice and care

[0433] During training, the device continuously collects and transmits real-time data to a server that analyzes the data and, if it detects signs of fatigue, for example, sends instructions to the athlete to rest.

[0434] If the movement is determined to be abnormal, the server will provide advice to the athlete in real time via the device, such as "Pay attention to the position of your toes to correct your running form."

[0435] In this way, this system will improve athletes' performance and prevent injuries by consistently collecting and analyzing data, creating training programs, and providing real-time feedback.

[0436] The processing flow will be explained below.

[0437] Step 1:

[0438] The device collects biometric data such as heart rate, acceleration, and electromyogram in real time from sensors worn by athletes, and the collected data is temporarily stored on the device.

[0439] Step 2:

[0440] The device transmits the collected biometric data to the server. This communication occurs periodically to ensure that real-time data is transmitted to the server.

[0441] Step 3:

[0442] The server receives the data sent from the terminal. The received data is first cleaned. Cleaning is a process in which noise and outliers are removed and missing data is filled in.

[0443] Step 4:

[0444] The server normalizes the cleaned data. Normalization refers to converting data from different scales into a unified scale to make it easier to analyze.

[0445] Step 5:

[0446] The server uses the normalized data for biomechanical analysis, including machine learning algorithms, to identify abnormal movements and loads.

[0447] Step 6:

[0448] The server uses data analysis to assess an athlete's fatigue state and predict injury risk, integrating past and current data to make a comprehensive judgment.

[0449] Step 7:

[0450] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics, including exercise content, intensity, number of repetitions, and rest periods.

[0451] Step 8:

[0452] The server transmits the generated training program to the terminal, which receives it and displays it to the user.

[0453] Step 9:

[0454] The user checks the training program presented and makes a training plan for the day. The terminal records the user's operations and transmits the necessary data to the server.

[0455] Step 10:

[0456] During training, the device continuously collects biometric data in real time and transmits it to a server, which then analyzes the data to detect fatigue and abnormalities in real time.

[0457] Step 11:

[0458] The server generates real-time advice and care based on the analysis results and notifies the device. For example, if fatigue is detected, it will instruct the user to rest, and if abnormal behavior is detected, it will send advice for correction.

[0459] Step 12:

[0460] The terminal displays real-time advice and care notifications from the server to the user, who then checks these notifications and acts according to the instructions.

[0461] In this way, the system efficiently collects and analyzes athletes' performance data, creates optimal training programs, and provides advice and care in real time, thereby improving athletes' performance and preventing injuries.

[0462] Example 1

[0463] 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."

[0464] Conventional training systems for athletes have struggled to comprehensively and centrally manage the collection and analysis of real-time biometric data, as well as the proposal of training programs based on the analysis results. It has been particularly difficult to provide fast and accurate advice in situations where real-time feedback during training or immediate action is required to prevent injury. Furthermore, insufficient pre-processing, such as data noise removal and normalization, can reduce the accuracy of the analysis, potentially resulting in a decline in the quality of the training program.

[0465] 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.

[0466] In this invention, the server includes means for collecting athlete performance data, means for transmitting the data to the server, means for preprocessing, cleaning, and normalizing the collected data, means for performing biomechanics analysis to identify abnormal movements and loads, means for generating an individual training program based on the analysis results, means for displaying the generated training program on a terminal, means for providing advice and care to the athlete in real time, and means for collecting data in real time during training and transmitting it to the server. This enables a system that can perform all processes from collection to analysis, generation of a training program, and provision of real-time feedback.

[0467] "Athlete" refers to a person who participates in competitive activities in sports or athletic competitions.

[0468] "Performance data" refers to biometric information that indicates an athlete's physical ability, physical condition, exercise status, etc. Specifically, it includes data such as heart rate, acceleration, and electromyogram.

[0469] "Data Collection Instruments" refers to devices or equipment used to obtain real-time performance data from athletes, including, for example, sensors and smartwatches.

[0470] "Server" refers to a data processing device accessible via the Internet or a local network that analyzes data and generates training programs.

[0471] "Preprocessing" refers to the process carried out before data analysis, such as removing noise and normalizing the data. This process improves the quality of the data and increases the accuracy of the analysis.

[0472] "Cleaning" refers to the process of removing unnecessary noise and outliers from acquired performance data.

[0473] "Normalization" is a process of constraining data variation within a certain range, and is performed to ensure consistency between different data sets.

[0474] "Biomechanics analysis" refers to a data-based method of analyzing an athlete's physical movements and stress conditions. This analysis can detect abnormalities in movement and excessive stress.

[0475] A "training program" is a plan that specifically outlines the exercises and training that an athlete should perform, including the content, intensity, number of repetitions, and rest times.

[0476] "Real-time advice and care delivery tools" refer to tools that provide immediate feedback and instruction based on data collected during training.

[0477] "Terminal" refers to a device that an athlete can operate and view displayed information, including, specifically, a smartphone or tablet.

[0478] "Analysis results" refers to the evaluation and diagnostic results of data obtained through preprocessing and biomechanics analysis.

[0479] "Abnormal movements or loads" refers to conditions that exceed normal movement patterns or physical load ranges, and indicates movements or excessive loads that may have adverse effects on the body.

[0480] MODE FOR CARRYING OUT THE INVENTION

[0481] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries. This system collects and analyzes performance data to propose optimal training programs for athletes and provides advice and care in real time. Specific embodiments of this system are described below.

[0482] The system consists of the following main components:

[0483] 1. Data Collection Methods

[0484] Sensors, smartwatches, and other devices collect biometric data, such as heart rate, acceleration, and electromyograms, in real time. Users wear these devices. The device receives this data and transmits it to a server. For example, if a user's heart rate spikes while running, the device sends that data to the server.

[0485] 2. Data Preprocessing and Analysis

[0486] The server first cleans the biometric data received from the device to remove noise. Then, it normalizes the data to make it easier to analyze. The server then uses the normalized data to perform biomechanics analysis and detect abnormalities in movement and load. For example, if a sudden change in heart rate is detected, the server records the abnormality and considers countermeasures.

[0487] 3. Training program proposals

[0488] The server generates a training program optimized for the athlete's characteristics based on the analysis results. The program includes details such as exercise content, intensity, number of repetitions, and rest time. For example, if it is determined that muscle strengthening is necessary, detailed guidelines such as "3 sets of 12 squats, with a load of 50% of body weight, with 90 seconds of rest between sets" will be generated. The device displays the generated training program to the user.

[0489] 4. Real-time advice and care delivery tools

[0490] During training, the device continuously transmits collected real-time data to the server, which immediately analyzes it and generates immediate feedback as needed. For example, if signs of fatigue are detected, the device will instruct the user to rest. If abnormal movements are detected, specific advice such as "Pay attention to the position of your toes to correct your running form" will be provided.

[0491] Specific examples

[0492] For example, to generate an optimal training program for Athlete A to improve muscle strength and prevent injury based on their heart rate, EMG data, and training history from the past week, the prompt would be:

[0493] Based on Athlete A's heart rate, EMG data, and training history from the past week, please generate an optimal training program for improving muscle strength and preventing injury. Please recommend specific exercises, number of repetitions, intensity, and rest periods.

[0494] An example of the output produced is:

[0495] Strength Training Program:

[0496] Exercise: Squats

[0497] Reps: 3 sets x 12 reps

[0498] Intensity: 50% of body weight

[0499] Rest Time: 90 seconds rest between sets

[0500] Additional tips: Focus on form, foot position and knee movement. After this exercise, do some gentle stretching to loosen up your muscles.

[0501] In this way, this system starts with collecting data from the device worn by the user, then analyzes the data on the server, creates training programs, and provides real-time feedback, all in an integrated manner, effectively supporting athletes in improving their performance and preventing injuries.

[0502] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0503] Step 1: Collect data

[0504] How it works: The user wears a smartwatch and sensors, which collect biometric data such as heart rate, acceleration, and electromyogram in real time. The smartwatch measures heart rate every 10 seconds and sends the data to the device.

[0505] Input: Biometric data from smartwatches and sensors.

[0506] Output: Real-time biometric data sent to the device.

[0507] Step 2: Sending data

[0508] Specific operation: The device sends the collected biometric data to the server at any time. The data is securely transmitted via the Internet.

[0509] Input: Biometric data collected on the device.

[0510] Output: Biometric data sent to the server.

[0511] Step 3: Preprocessing the data

[0512] Specific operation: The server first cleans the received biometric data, removes noise if it is present, and corrects outliers. Then, it normalizes the data and converts it into a unified format.

[0513] Input: Biometric data sent to the server.

[0514] Output: Cleaned and normalized biometric data.

[0515] Step 4: Analyze the data

[0516] Specific actions: The server performs biomechanical analysis based on the normalized data. This determines whether the athlete's movements and loads are appropriate. If abnormal movements or excessive loads are detected, they are recorded and countermeasures are considered.

[0517] Input: Cleaned and normalized biometric data.

[0518] Output: Biomechanical analysis results, assessment of abnormalities and loads.

[0519] Step 5: Generate a training program

[0520] Specific actions: Based on the analysis results, the server generates a training program that is optimal for the athlete's characteristics. The program includes details such as exercise content, intensity, number of repetitions, and rest time. For example, it creates guidelines such as "3 sets of 12 squats, with a load of 50% of body weight, and 90 seconds of rest between sets."

[0521] Input: Biomechanical analysis results.

[0522] Output: Training program details.

[0523] Step 6: View your training program

[0524] Specific operation: The device displays the generated training program to the athlete, who can then check the training plan for the day through the device.

[0525] Input: Training program details.

[0526] Output: The training program displayed on the terminal.

[0527] Step 7: Collect real-time data

[0528] Specific operation: During training, the device continues to collect biometric data in real time and transmits it to the server.

[0529] Input: Real-time biometric data during training.

[0530] Output: Real-time biometric data sent to the server.

[0531] Step 8: Real-time feedback

[0532] Specific operation: The server immediately analyzes the data received in real time and generates immediate feedback as needed. If signs of fatigue or abnormal movements are detected, the server notifies the athlete via the device with appropriate instructions. For example, it gives advice such as "You are showing signs of fatigue. Please take a break" or "Pay attention to the position of your toes to correct your running form."

[0533] Input: Biometric data received in real time.

[0534] Output: Real-time feedback displayed on the device.

[0535] These steps enable the system to consistently collect and analyze data, generate training programs, and provide real-time feedback, thereby effectively supporting athletes in improving their performance and preventing injuries.

[0536] (Application example 1)

[0537] 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."

[0538] Conventional industrial equipment does not adequately collect and analyze operational data, making it difficult to detect signs of abnormal operation early. As a result, abnormalities are often not noticed until a failure occurs, leading to sudden machine shutdowns and production delays. Furthermore, even when an abnormality is detected, there is a lack of means to provide immediate, appropriate feedback, making it difficult to operate industrial equipment efficiently. A new system is needed to solve these issues, improve operational performance, and prevent failures.

[0539] 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.

[0540] In this invention, the server includes means for collecting operational data of industrial equipment, means for performing machine operation analysis and identifying abnormal operations and loads, means for proposing individual operation schedules based on the analysis results, means for providing advice and correction instructions to the industrial equipment in real time, means for evaluating the fatigue state and predicting the risk of failure, and means for preprocessing, cleaning, and normalizing the collected data, thereby improving the operational performance of the industrial equipment, reducing the risk of failure, and enabling stable operation.

[0541] "Industrial equipment" is a general term for machines and devices used in factories and manufacturing facilities to automate, streamline, or support the production process.

[0542] "Operational data" refers to information relating to the movement of a device, including measurements such as position, speed, temperature, and vibration.

[0543] "Machine operation analysis" is a technology that analyzes the operating status of equipment based on collected operation data and distinguishes between normal and abnormal operation.

[0544] "Abnormal operation" refers to the occurrence of behavior that is different from normal in the operation of equipment, which may cause a malfunction if it continues.

[0545] "Load" refers to external factors such as force, pressure, and temperature that are applied to equipment when it is operating, and if this load becomes excessive it can have a negative effect on the equipment.

[0546] An "operation schedule" is a timetable for systematically managing the operation and running of equipment, and lists optimal operating times and maintenance timings.

[0547] "Advice" means appropriate instructions or suggestions regarding the operation of equipment, intended to facilitate adjustments to operation or maintenance.

[0548] "Correction instructions" refer to instructions on specific operating methods or changes to be made to deal with abnormal equipment operation or load.

[0549] "Fatigue" refers to a state in which equipment parts or systems begin to deteriorate due to prolonged or excessive use.

[0550] "Failure risk" is the probability of a failure occurring that can be predicted from the operation and condition of equipment, and by predicting this, it is possible to take measures in advance.

[0551] "Data preprocessing" refers to the process of preparing collected raw data in a form that is easier to analyze, and includes processes such as removing noise and normalizing the data.

[0552] "Cleaning" is the process of removing unnecessary information and errors from collected data.

[0553] "Normalization" is a process of standardizing data values ​​to a certain scale, and is performed to improve the accuracy of analysis.

[0554] This invention relates to an AI system aimed at improving the operational performance and preventing breakdowns of industrial equipment. This system collects and analyzes operational data, proposes optimal operation schedules for industrial equipment, and provides advice and correction instructions in real time. The system consists of the following main components:

[0555] Data collection methods

[0556] Sensors attached to industrial equipment collect operational data such as position, speed, temperature, and vibration in real time, and the collected data is sent to a server via the terminal.

[0557] Data Analysis Methods

[0558] The server preprocesses the collected operational data, removing noise and normalizing the data, and performs machine operation analysis to detect abnormalities in operation and load. It also evaluates fatigue status and predicts failure risk.

[0559] Operation schedule suggestion means

[0560] Based on the analysis results, the server generates an optimal operation schedule tailored to the characteristics of the industrial equipment. The schedule includes details such as operating hours, load balancing, and maintenance periods. The terminal displays the generated schedule to the industrial equipment operator.

[0561] Real-time advice and corrective action methods

[0562] During operation, the terminal continuously transmits real-time collected data to the server, which analyzes the data and generates immediate feedback as needed. If abnormal behavior or excessive load is detected, the terminal will notify the operator with appropriate corrective instructions.

[0563] System Operation

[0564] 1. Data collection: Sensors attached to industrial equipment continuously collect operational data in real time, such as position, speed, temperature, and vibration. For example, if a robot arm experiences a sudden rise in temperature while in operation, the data is sent to a server via the terminal.

[0565] 2. Data preprocessing and analysis: The server cleans the collected data and removes noise. It also normalizes the data to make it easier to analyze. Next, the server analyzes the machine's operation to detect abnormal behavior or excessive loads. For example, if analysis of vibration data reveals that a particular part is wearing out, the server records that information.

[0566] 3. Proposing an operation schedule: Based on the analysis results, the server generates an optimal operation schedule tailored to the characteristics of the industrial equipment. As a specific example, it proposes a short-term maintenance schedule taking into account parts that are deteriorating. The terminal displays the generated schedule to the operator, who then confirms the plan.

[0567] 4. Real-time advice and correction instructions: If an abnormality is detected during operation, the server immediately analyzes it and generates appropriate correction instructions. For example, specific advice such as "Please reduce the operating speed" or "A specific part needs to be replaced" is provided in real time via the terminal.

[0568] Hardware and software used

[0569] To implement the present invention, the following hardware and software are used:

[0570] Hardware: Industrial equipment, accelerometers, temperature sensors, vibration sensors.

[0571] Software: Python, TensorFlow, SQL Server, GUI development frameworks (such as Tkinter).

[0572] Examples and prompts

[0573] Specific examples

[0574] 1. Example 1: If the motor temperature suddenly rises while an industrial robot is operating, the system will issue a warning saying "Motor temperature is too high. Please reduce speed."

[0575] 2. Example 2: If abnormal vibration is detected, notify the user that "Abnormal vibration has been detected. Please change the operation route."

[0576] Prompt statement

[0577] Example prompts to enter into the Data Analysis module:

[0578] Check for motor temperature spikes and display warnings if necessary. Use temperature data from the past 24 hours.

[0579] Example prompts for the optimization algorithm:

[0580] "Optimize the operating schedule of industrial equipment and distribute the load to specific time periods. Consider detailed load data and operating history."

[0581] As described above, this system performs all processes from data collection and analysis to generating operation schedules and providing real-time feedback, thereby improving the operational performance of industrial equipment and preventing breakdowns.

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

[0583] Step 1:

[0584] Sensors collect operational data

[0585] Sensors attached to industrial equipment collect operational data such as position, speed, temperature, and vibration in real time. This data is sent to a server via a terminal. The input data is the measurement value from the sensor, and the output is the raw data sent to the server. For example, the temperature and vibration data of a robot arm in operation is constantly recorded and transferred to the terminal.

[0586] Step 2:

[0587] Data Preprocessing

[0588] The server cleans the received motion data, removes noise, and normalizes it to make it easier to analyze. The input data is raw data sent from the sensors, and the output is cleaned and normalized data. Specific operations include missing value imputation, outlier removal, and range scaling.

[0589] Step 3:

[0590] Data analysis

[0591] The server uses the preprocessed data to analyze machine operation to identify abnormal behavior and loads. A generative AI model is used for the analysis to detect anomalies and evaluate failure risks. The input data is preprocessed data, and the output is the analysis results, including abnormal behavior detection results and risk assessment data. Specifically, the AI ​​model analyzes sensor data to detect abnormal temperature increases and excessive vibrations.

[0592] Step 4:

[0593] Generate an operation schedule

[0594] Based on the analysis results, the server generates an optimal operation schedule tailored to the characteristics of the industrial equipment. The input data are the analysis results, and the output is a recommended operation schedule. In terms of specific operations, the system generates plans for maintenance periods and load balancing based on the analysis results and presents them to the operator.

[0595] Step 5:

[0596] Viewing Schedules

[0597] The terminal displays the generated operation schedule to the industrial equipment operator. The input data is the operation schedule sent from the server, and the output is data in a display format that can be checked by the operator. In concrete terms, the operation schedule is displayed on the terminal display, and the operator checks it.

[0598] Step 6:

[0599] Real-time data monitoring and feedback

[0600] During operation, the terminal continuously collects and transmits real-time operational data to the server. The server analyzes this data and generates immediate feedback as needed. The input data is real-time operational data, and the output is feedback such as advice and correction instructions. Specifically, if abnormal movement or excessive load is detected, instructions such as "Please reduce speed" are displayed in real time on the operator's terminal.

[0601] 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.

[0602] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries, and also provides a system that combines an emotion engine that recognizes athletes' emotions. This system collects and analyzes performance and emotion data, proposes optimal training programs for athletes, and provides advice and care in real time, thereby achieving overall performance improvement and injury prevention for athletes.

[0603] The system consists of the following main components:

[0604] 1. Data Collection Methods

[0605] The sensors and smartwatches worn by athletes collect biometric data such as heart rate, acceleration, and electromyograms, as well as emotional data from the athletes' facial expressions and voice. The devices receive this data and send it to a server.

[0606] 2. Emotion recognition means

[0607] The server uses the collected facial and voice data to analyze the athlete's emotional state using an emotion engine, which identifies emotions such as joy, sadness, anger, and stress.

[0608] 3. Data Analysis Methods

[0609] The server preprocesses the received biometric and emotional data, cleansing and normalizing them, and then performs biomechanics analysis to comprehensively evaluate abnormalities in movement and load, as well as emotional states.

[0610] 4. Training program proposal methods

[0611] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics and emotional state. The program includes details such as exercise content, intensity, number of repetitions, and rest periods. The terminal displays the generated program to the athlete.

[0612] 5. Real-time advice and care delivery methods

[0613] During training, the device continuously collects and transmits real-time biometric and emotional data to the server, which analyzes it and generates immediate feedback as needed. If signs of fatigue, abnormal movements, or emotional stress are detected, the device will notify the athlete and advise them to rest or modify their movements.

[0614] Specific flow and examples of program processing

[0615] To concretely explain how this system works, let's describe the program's processing in natural language:

[0616] 1. Data collection

[0617] The device collects real-time data from athletes, including their heart rate, electromyogram, facial expression data from a facial recognition sensor, and audio data from a voice recognition microphone. For example, if an athlete does not smile during training, their facial expression and audio data will also be collected.

[0618] 2. Data Preprocessing and Emotion Recognition

[0619] The server cleans the collected data, removes noise, and normalizes it to make it easier to analyze.

[0620] The emotion engine identifies the athlete's emotions from facial and voice data. For example, if a high level of stress or fatigue is detected, the emotion data is recorded.

[0621] 3. Data analysis and evaluation

[0622] The server uses normalized biometric and emotional data for biomechanical analysis, using machine learning algorithms to identify abnormalities in movement and stress.

[0623] The server uses data analysis to comprehensively assess an athlete's fatigue and emotional state, adjusting the intensity of specific training sessions if, for example, emotional stress is high.

[0624] 4. Training program proposals

[0625] Based on the analysis results, the server generates a training program that is optimal for the athlete's characteristics and emotional state. For example, it adds relaxation exercises when stress levels are high, and suggests high-intensity training when joy levels are high.

[0626] 5. Real-time advice and care

[0627] During training, the device continuously collects biometric and emotional data in real time and transmits it to a server, which then analyzes the data to detect fatigue, abnormalities in movement, and emotional changes in real time.

[0628] Based on the analysis results, real-time advice and care is provided. For example, if emotional stress is detected, it will suggest ways to relax, and if abnormal movements are detected, it will advise on the correct way to move.

[0629] In this way, by combining this system with an emotion engine, it is possible to comprehensively evaluate an athlete's physical and emotional state, suggest more accurate training programs, and provide real-time advice, thereby improving athlete performance and preventing injuries.

[0630] The processing flow will be explained below.

[0631] Step 1:

[0632] The device collects biometric data such as heart rate, acceleration, and electromyogram in real time from sensors worn by athletes. It also collects facial expression and voice data from facial recognition sensors and a voice recognition microphone for emotion recognition. This collected data is temporarily stored on the device.

[0633] Step 2:

[0634] The device transmits all collected biometric and emotional data to a server periodically, delivering the data in near real time.

[0635] Step 3:

[0636] The server receives the data sent from the device, which is first cleaned to remove noise and outliers and fill in missing data, improving the accuracy of the data.

[0637] Step 4:

[0638] The server normalizes the cleaned data. Normalization is the process of converting data from different scales into a unified scale to make it easier to analyze.

[0639] Step 5:

[0640] The server analyzes the normalized data with an emotion engine, which identifies the athlete's emotional state (e.g., joy, sadness, anger, stress, etc.) based on facial and voice data.

[0641] Step 6:

[0642] The server uses the emotion engine results and biological data for biomechanical analysis, which identifies abnormalities in the athlete's movements, loads, and fatigue.

[0643] Step 7:

[0644] Based on the analysis results, the server generates a training program optimized for the athlete's characteristics and emotional state. The program includes details such as exercise content, intensity, number of repetitions, and rest periods. For example, if an athlete is in a high stress state, relaxation exercises will be added.

[0645] Step 8:

[0646] The server transmits the generated training program to the terminal, which receives it and displays it to the user.

[0647] Step 9:

[0648] The user checks the training program presented and makes a training plan for the day. The terminal records the user's operations and transmits the necessary data to the server.

[0649] Step 10:

[0650] During training, the device continues to collect real-time biometric and emotional data and transmits it to the server, which is used to monitor the training progress in real time.

[0651] Step 11:

[0652] The server analyzes the data received in real time to detect the athlete's fatigue, abnormalities in their movements, and emotional changes. For example, if an athlete's heart rate spikes or stress is detected in their facial expressions, the server generates appropriate feedback.

[0653] Step 12:

[0654] The server generates real-time advice and care based on the analysis results and notifies the device. For example, it suggests resting if fatigue suddenly increases, instructs corrective actions if abnormal behavior is detected, and sends instructions for relaxation if emotional stress increases.

[0655] Step 13:

[0656] The device displays real-time advice and care notifications from the server to the user, who then checks these notifications and acts accordingly, for example, accepting suggestions for rest or modifying their behavior.

[0657] In this way, the system comprehensively analyzes biometric and emotional data and provides optimal training programs and real-time advice tailored to the athlete's condition, thereby improving their performance and preventing injuries.

[0658] Example 2

[0659] 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."

[0660] Conventional training systems for athletes focus on collecting and analyzing only biological data, and lack comprehensive evaluation and advice that takes into account the athlete's emotional state. This often leaves them inadequate for maximizing athletes' performance and preventing injuries. Real-time feedback and immediate care during training are also limited. To address this situation, a system is needed that can comprehensively analyze athletes' biological and emotional data and provide optimal training programs and real-time advice tailored to their individual characteristics.

[0661] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting the athlete's biological data and emotional data, means for cleaning and normalizing the collected data, means for identifying the athlete's emotions using an emotion engine, means for performing biomechanics analysis and identifying abnormalities in movement and load, means for generating a training program optimal for the athlete's characteristics and emotional state based on the analysis results, and means for providing advice and care to the athlete in real time. This makes it possible to comprehensively evaluate the athlete's physical and emotional state and propose more accurate training programs and provide real-time advice.

[0662] "Biometric data" refers to data that indicates the physiological state of the body, such as an athlete's heart rate, acceleration, and electromyogram.

[0663] "Emotional data" is data that indicates the emotional state of an athlete, obtained from facial expressions, voice, etc.

[0664] An "emotion engine" is software or algorithm that identifies an athlete's emotions from collected facial and voice data.

[0665] "Biomechanics analysis" is an analytical method that analyzes an athlete's movements and loads to identify abnormalities.

[0666] A "training program" is a program that includes the optimal exercise content, intensity, number of repetitions, rest time, etc., according to the athlete's characteristics and emotional state.

[0667] "Real-time advice" refers to instructions and advice provided to athletes instantly based on collected biometric and emotional data.

[0668] "Care" means the instruction and support to maintain and promote the athlete's physical and mental health.

[0669] "Cleaning" is the process of removing noise from collected data and preparing it in a form that can be analyzed.

[0670] "Normalization" is the process of converting data into a consistent format that makes it easier to analyze.

[0671] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries. Furthermore, this invention provides a system that combines an emotion engine that recognizes athletes' emotions to achieve comprehensive performance improvement and injury prevention for athletes.

[0672] The system consists of the following main components:

[0673] 1. Data Collection Methods

[0674] The device collects biometric data such as heart rate, acceleration, and electromyogram in real time from sensors or smartwatches worn by athletes. The device also collects facial expression and voice data using a camera and voice recognition microphone. For example, when an athlete is running, the device collects not only heart rate and electromyogram data, but also facial expressions while running and comments on training in real time.

[0675] 2. Emotion recognition means

[0676] The server inputs the collected facial and voice data into an emotion engine to identify the athlete's emotions. The emotion engine utilizes machine learning models to assess the athlete's emotional state in real time. For example, it can analyze whether the athlete is feeling stressed based on facial expressions and tone of voice.

[0677] 3. Data Analysis Methods

[0678] The server cleans the collected biometric and emotional data to remove noise. It then normalizes the data to make it easier to analyze. It then performs biomechanical analysis to identify abnormalities in movement and load. For example, it can detect an anomaly if an athlete takes a stride that differs from their normal walking style.

[0679] 4. Training program proposal methods

[0680] Based on the analysis results, the server generates a training program optimized for the athlete's characteristics and emotional state. This program includes details such as exercise content, intensity, number of repetitions, and rest periods. For example, if the athlete is feeling stressed, it will suggest relaxation exercises.

[0681] 5. Real-time advice and care delivery methods

[0682] During training, the device continuously collects and transmits real-time biometric and emotional data to the server, which analyzes it and generates immediate feedback as needed. For example, if your heart rate spikes, the device will prompt you to take a short break.

[0683] To use the system, the generative AI model might be fed prompts like the following example:

[0684] "Please explain how an AI system that analyzes athletes' performance and emotional data and proposes optimal training programs works from the perspectives of the server, device, and user."

[0685] This system will enable a comprehensive assessment of an athlete's physical and emotional state, providing more accurate training program suggestions and real-time advice.

[0686] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0687] Step 1:

[0688] Data collection

[0689] The device collects biometric data in real time from sensors or smartwatches worn by athletes. For example, it acquires heart rate (collected data) and electromyograms. The input data is the athlete's real-time heart rate and electromyogram, and the output is a stream of collected biometric data.

[0690] The device uses a camera and a voice recognition microphone to collect facial and voice data of the athlete. For example, it captures the athlete's smile and tone of voice (emotion data). The input data is real-time captured information from the camera and microphone, and the output is a stream of emotion data.

[0691] Step 2:

[0692] Data Preprocessing

[0693] The server receives the biometric data and emotion data sent from the terminal, and the input data is the collected biometric data and emotion data.

[0694] The server cleans (denoises) and normalizes the data to make it easier to analyze. For example, it removes outliers from heart rate data and aligns them along a time axis. The output is cleaned and normalized biometric and emotion data.

[0695] Step 3:

[0696] emotion recognition

[0697] The server inputs the cleaned and normalized emotion data into the emotion engine to identify emotions. The input data is the preprocessed facial expression data and speech data.

[0698] The server uses an emotion engine to analyze emotions such as stress, joy, anger, etc. For example, a smiling face can be recognized as joy, and a low voice as stress. The output is data indicating the emotional state.

[0699] Step 4:

[0700] Data analysis

[0701] The server performs biomechanics analysis using the biometric data and emotion data, and the input data is the preprocessed biometric data and emotion data.

[0702] The server uses machine learning algorithms to identify abnormalities in movement and load, for example, detecting unusual running form. The output is an analysis result that includes the abnormal movement and load.

[0703] Step 5:

[0704] Generate a training program

[0705] The server generates a training program that is optimal for the athlete's characteristics and emotional state based on the analysis results. The input data are the biological data, the emotional data, and the analysis results.

[0706] The server automatically generates a training program including exercise type, intensity, number of repetitions, and rest time. For example, it suggests relaxation exercises when stress is high, and high-intensity training when energy is high. The output is a customized training program.

[0707] Step 6:

[0708] Training Program Notification

[0709] The server sends the generated training program to the terminal, and the input data is the generated training program.

[0710] The device displays the information to the athlete and notifies them of the next action. For example, specific instructions such as "Next, stretch after 10 minutes of running" are displayed. The output is the notification to the athlete.

[0711] Step 7:

[0712] Real-time monitoring and feedback

[0713] The device continuously transmits the biological data and emotional data collected in real time during training to the server. The input data is the data collected in real time.

[0714] The server analyzes the data received in real time and generates immediate feedback if necessary. For example, if your heart rate spikes, it will generate a prompt to "take a short break." The output is real-time feedback.

[0715] The device provides real-time advice to the athlete based on feedback from the server. For example, if there is an abnormality in movement, specific advice such as "Check your right foot step" is displayed. The output is real-time advice to the athlete.

[0716] Through these steps, the system will be able to perform detailed analysis of athletes' biometric and emotional data, and provide training programs and real-time advice tailored to their individual characteristics.

[0717] (Application example 2)

[0718] 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."

[0719] Previous systems have focused on improving athletes' performance and managing their workload, but few systems have considered the influence of emotions. Furthermore, technology for managing passenger emotions and comfort levels in real time in autonomous vehicles is still immature, and a method to improve the overall passenger experience is needed. Therefore, a new system that utilizes emotion data is needed in the context of both athletes and autonomous vehicles.

[0720] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting athlete performance data, means for performing biomechanics analysis to identify abnormal movements and loads, means for proposing an individual training program based on the analysis results, means for providing advice and care to the athlete in real time, means for collecting passenger emotional data, means for analyzing the collected emotional data and evaluating comfort levels, means for automatically adjusting the in-vehicle environment based on the evaluation results, and means for suggesting entertainment and relaxation to passengers based on their emotional states. This makes it possible to optimize athlete performance while preventing injuries and managing loads, and enables real-time management of passenger emotions and comfort levels in autonomous vehicles.

[0721] "Means for collecting athlete performance data" refers to equipment that uses sensors or devices worn by athletes to obtain biometric data such as heart rate, electromyogram, and acceleration.

[0722] "Means for conducting biomechanical analysis and identifying abnormal movements and loads" refers to algorithms and programs that analyze collected biometric data and identify any abnormalities in an athlete's movements or loads.

[0723] The "means for proposing individual training programs based on the analysis results" is a system for generating training programs specifically for athletes based on the results of data analysis.

[0724] "Means for providing athletes with real-time advice and care" refers to applications that provide athletes with immediate feedback and care instructions based on data collected during training.

[0725] The "means for collecting passenger emotional data" is a device that uses a camera or microphone to capture passenger facial expressions and voices and collect emotional data based on them.

[0726] The "means for analyzing collected emotion data and evaluating the comfort level" is a system that analyzes the acquired emotion data and evaluates the comfort level of passengers using the analysis results.

[0727] The "means for automatically adjusting the in-car environment based on the evaluation results" is a device that automatically sets and changes the in-car environment, such as temperature, lighting, and music, based on the evaluation results of emotional data.

[0728] The "means for suggesting entertainment and relaxation methods to passengers based on their emotional state" is a system that presents entertainment content and relaxation methods appropriate for passengers based on the results of analyzing their emotions.

[0729] This invention relates to an AI system for improving athletic performance and injury prevention, and a passenger comfort management system for autonomous vehicles. The system includes the following main components and processes:

[0730] Data collection

[0731] The server uses sensors and devices to collect biometric data from athletes and emotional data from passengers. Specifically, it uses devices such as smartwatches worn by athletes, accelerometers, electromyogram sensors, cameras, and microphones to collect heart rate, electromyogram, acceleration, facial expression data, and voice data. To collect emotional data from passengers in the in-car environment, it uses cameras and microphones installed in the vehicle.

[0732] Data preprocessing and emotion recognition

[0733] The server cleans the collected data and removes noise. It uses Python and R libraries to normalize the data and make it easier to analyze. For emotion recognition, it uses emotion recognition models built with TensorFlow and Keras. For example, if a passenger is not smiling, their facial expression data is also collected and analyzed along with the voice data.

[0734] Data analysis and evaluation

[0735] The server performs biomechanics analysis using normalized biometric and emotional data. It uses machine learning algorithms, such as scikit-learn and TensorFlow, to identify abnormalities in movement and load. To assess passenger comfort, it generates a comfort score based on the emotional data.

[0736] Training program suggestions and automatic adjustment of the in-car environment

[0737] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics and emotional state. The program includes details such as exercise type, intensity, number of repetitions, and rest periods. Inside the autonomous vehicle, a control program is executed that automatically adjusts the in-car environment, including temperature, lighting, and music, based on the evaluation results of the emotional data.

[0738] Real-time advice and care

[0739] During training or while the vehicle is in operation, the device continuously collects real-time biometric and emotional data and transmits it to the server. The server analyzes this data and provides immediate feedback. For example, if fatigue or abnormal movements are detected, the device will instruct the athlete to rest or correct their movements. It will also suggest relaxation and entertainment options based on the passenger's emotional state.

[0740] Examples of specific examples and prompts

[0741] For example, when an athlete is training, the system can detect their fatigue level in real time using electromyograms and heart rate data and immediately instruct them to rest. Based on passenger emotional data, the in-car environment can be optimally adjusted to provide a comfortable travel experience.

[0742] Example prompts to input to a generative AI model:

[0743] 1. "Suggest a list of music to play when passengers are happy."

[0744] 2. "Decide on environmental settings for passengers experiencing stress and adjust temperature and lighting settings for accountability."

[0745] 3. "Analyze real-time sentiment data and show passengers the entertainment they want."

[0746] In this way, the system, combined with the emotion engine, can comprehensively assess the athlete's physical and emotional state, improving passenger comfort in autonomous vehicles.

[0747] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0748] Step 1:

[0749] The device collects biometric and emotional data from athletes or passengers. Specifically, it uses devices such as smartwatches worn by athletes, accelerometers, electromyogram sensors, cameras, and microphones to obtain heart rate, electromyogram, acceleration, facial expression data, and voice data in real time. The device then transmits this data to a server.

[0750] Step 2:

[0751] The server cleans the received data and removes noise. Specifically, it uses data preprocessing libraries in Python and R to impute missing values ​​and remove outliers from the collected biometric and emotional data. The input data includes biometric signals from biometric sensors and camera and microphone data, and the output data is clean data.

[0752] Step 3:

[0753] The server normalizes the cleaned data and prepares it for easier analysis. Specifically, it scales and standardizes the biometric and emotional data. Here, the input data is the cleaned biometric and emotional data, and the output data is the normalized data.

[0754] Step 4:

[0755] The server uses the normalized data to perform emotion recognition. Specifically, it inputs the data into an emotion recognition model built using TensorFlow and Keras to analyze the emotional state. The input data includes normalized facial expression data and voice data, and the output data is the emotional state (happiness, sadness, anger, stress, etc.).

[0756] Step 5:

[0757] The server performs biomechanics analysis using normalized biometric and emotional data. It uses machine learning algorithms to identify abnormalities in movement and stress. Specifically, it uses scikit-learn and TensorFlow to apply a motion analysis model to detect abnormal movements and overload. The input data is normalized biometric and emotional data, and the output data includes abnormal movements and stress.

[0758] Step 6:

[0759] The server generates a training program that matches the athlete's characteristics and emotional state based on the analysis results. Specifically, if overload or abnormal movement is detected, it provides a program that includes appropriate exercise content, intensity, number of repetitions, rest periods, etc. The input data are the biomechanics analysis results and emotion analysis results, and the output data includes a training program.

[0760] Step 7:

[0761] The server evaluates the passenger's comfort level based on emotional data in the autonomous vehicle and automatically adjusts the in-car environment. Specifically, if the emotional state indicates stress, it adjusts the temperature and lighting and plays relaxation music. The input data is the emotion analysis results, and the output data includes the in-car environment settings.

[0762] Step 8:

[0763] The terminal continuously transmits the data collected in real time to the server, which then provides immediate feedback. Specifically, it displays rest instructions and movement modification advice to athletes, and relaxation and entertainment suggestions to passengers. The input data is real-time biometric and emotional data, and the output data includes the content of the feedback.

[0764] This way, proper care and feedback can be provided to both the athlete and the passengers at each step.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] [Third embodiment]

[0769] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0770] 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.

[0771] 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).

[0772] 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.

[0773] 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.

[0774] 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).

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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."

[0781] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries. This system collects and analyzes performance data, proposes optimal training programs for athletes, and provides advice and care in real time.

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

[0783] 1. Data Collection Methods

[0784] Sensors or smartwatches worn by athletes collect biometric data such as heart rate, acceleration, and electromyogram in real time. The devices receive this data and send it to a server.

[0785] 2. Data analysis methods

[0786] The server preprocesses the received biometric data, removing noise and normalizing it. It then performs biomechanics analysis to detect abnormalities in movement and load. It also simultaneously evaluates fatigue levels and predicts injury risk.

[0787] 3. Training program proposal methods

[0788] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics. The program includes details such as exercise content, intensity, number of repetitions, and rest periods. The terminal displays the generated program to the athlete.

[0789] 4. Real-time advice and care delivery tools

[0790] During training, the device continuously collects and transmits real-time data to the server, which analyzes it and generates immediate feedback as needed. If signs of fatigue or abnormal movements are detected, the device will notify the athlete and advise them to rest or modify their movements.

[0791] Specific flow and examples of program processing

[0792] To concretely explain how this system works, let's describe the program's processing in natural language:

[0793] 1. Data collection

[0794] The device collects heart rate and electromyogram data from the athlete in real time. For example, if the athlete's heart rate spikes during training, the device sends that data to a server.

[0795] 2. Data Preprocessing and Analysis

[0796] The server cleans the collected data, removes noise, and normalizes it to make it easier to analyze.

[0797] The server then performs an analysis and, if it determines that, for example, the athlete's heart rate fluctuations are abnormal, it records the abnormality.

[0798] 3. Training program proposals

[0799] Based on the results of the biomechanics analysis, the server generates a training program optimized for the athlete's characteristics, providing detailed guidelines such as specific exercises to strengthen muscles, as well as the number of repetitions and intensity of those exercises.

[0800] The terminal displays the generated training program to the athlete, and the user confirms the training plan for the day.

[0801] 4. Real-time advice and care

[0802] During training, the device continuously collects and transmits real-time data to a server that analyzes the data and, if it detects signs of fatigue, for example, sends instructions to the athlete to rest.

[0803] If the movement is determined to be abnormal, the server will provide advice to the athlete in real time via the device, such as "Pay attention to the position of your toes to correct your running form."

[0804] In this way, this system will improve athletes' performance and prevent injuries by consistently collecting and analyzing data, creating training programs, and providing real-time feedback.

[0805] The processing flow will be explained below.

[0806] Step 1:

[0807] The device collects biometric data such as heart rate, acceleration, and electromyogram in real time from sensors worn by athletes, and the collected data is temporarily stored on the device.

[0808] Step 2:

[0809] The device transmits the collected biometric data to the server. This communication occurs periodically to ensure that real-time data is transmitted to the server.

[0810] Step 3:

[0811] The server receives the data sent from the terminal. The received data is first cleaned. Cleaning is a process in which noise and outliers are removed and missing data is filled in.

[0812] Step 4:

[0813] The server normalizes the cleaned data. Normalization refers to converting data from different scales into a unified scale to make it easier to analyze.

[0814] Step 5:

[0815] The server uses the normalized data for biomechanical analysis, including machine learning algorithms, to identify abnormal movements and loads.

[0816] Step 6:

[0817] The server uses data analysis to assess an athlete's fatigue state and predict injury risk, integrating past and current data to make a comprehensive judgment.

[0818] Step 7:

[0819] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics, including exercise content, intensity, number of repetitions, and rest periods.

[0820] Step 8:

[0821] The server transmits the generated training program to the terminal, which receives it and displays it to the user.

[0822] Step 9:

[0823] The user checks the training program presented and makes a training plan for the day. The terminal records the user's operations and transmits the necessary data to the server.

[0824] Step 10:

[0825] During training, the device continuously collects biometric data in real time and transmits it to a server, which then analyzes the data to detect fatigue and abnormalities in real time.

[0826] Step 11:

[0827] The server generates real-time advice and care based on the analysis results and notifies the device. For example, if fatigue is detected, it will instruct the user to rest, and if abnormal behavior is detected, it will send advice for correction.

[0828] Step 12:

[0829] The terminal displays real-time advice and care notifications from the server to the user, who then checks these notifications and acts according to the instructions.

[0830] In this way, the system efficiently collects and analyzes athletes' performance data, creates optimal training programs, and provides advice and care in real time, thereby improving athletes' performance and preventing injuries.

[0831] Example 1

[0832] 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."

[0833] Conventional training systems for athletes have struggled to comprehensively and centrally manage the collection and analysis of real-time biometric data, as well as the proposal of training programs based on the analysis results. It has been particularly difficult to provide fast and accurate advice in situations where real-time feedback during training or immediate action is required to prevent injury. Furthermore, insufficient pre-processing, such as data noise removal and normalization, can reduce the accuracy of the analysis, potentially resulting in a decline in the quality of the training program.

[0834] 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.

[0835] In this invention, the server includes means for collecting athlete performance data, means for transmitting the data to the server, means for preprocessing, cleaning, and normalizing the collected data, means for performing biomechanics analysis to identify abnormal movements and loads, means for generating an individual training program based on the analysis results, means for displaying the generated training program on a terminal, means for providing advice and care to the athlete in real time, and means for collecting data in real time during training and transmitting it to the server. This enables a system that can perform all processes from collection to analysis, generation of a training program, and provision of real-time feedback.

[0836] "Athlete" refers to a person who participates in competitive activities in sports or athletic competitions.

[0837] "Performance data" refers to biometric information that indicates an athlete's physical ability, physical condition, exercise status, etc. Specifically, it includes data such as heart rate, acceleration, and electromyogram.

[0838] "Data Collection Instruments" refers to devices or equipment used to obtain real-time performance data from athletes, including, for example, sensors and smartwatches.

[0839] "Server" refers to a data processing device accessible via the Internet or a local network that analyzes data and generates training programs.

[0840] "Preprocessing" refers to the process carried out before data analysis, such as removing noise and normalizing the data. This process improves the quality of the data and increases the accuracy of the analysis.

[0841] "Cleaning" refers to the process of removing unnecessary noise and outliers from acquired performance data.

[0842] "Normalization" is a process of constraining data variation within a certain range, and is performed to ensure consistency between different data sets.

[0843] "Biomechanics analysis" refers to a data-based method of analyzing an athlete's physical movements and stress conditions. This analysis can detect abnormalities in movement and excessive stress.

[0844] A "training program" is a plan that specifically outlines the exercises and training that an athlete should perform, including the content, intensity, number of repetitions, and rest times.

[0845] "Real-time advice and care delivery tools" refer to tools that provide immediate feedback and instruction based on data collected during training.

[0846] "Terminal" refers to a device that an athlete can operate and view displayed information, including, specifically, a smartphone or tablet.

[0847] "Analysis results" refers to the evaluation and diagnostic results of data obtained through preprocessing and biomechanics analysis.

[0848] "Abnormal movements or loads" refers to conditions that exceed normal movement patterns or physical load ranges, and indicates movements or excessive loads that may have adverse effects on the body.

[0849] MODE FOR CARRYING OUT THE INVENTION

[0850] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries. This system collects and analyzes performance data to propose optimal training programs for athletes and provides advice and care in real time. Specific embodiments of this system are described below.

[0851] The system consists of the following main components:

[0852] 1. Data Collection Methods

[0853] Sensors, smartwatches, and other devices collect biometric data, such as heart rate, acceleration, and electromyograms, in real time. Users wear these devices. The device receives this data and transmits it to a server. For example, if a user's heart rate spikes while running, the device sends that data to the server.

[0854] 2. Data Preprocessing and Analysis

[0855] The server first cleans the biometric data received from the device to remove noise. Then, it normalizes the data to make it easier to analyze. The server then uses the normalized data to perform biomechanics analysis and detect abnormalities in movement and load. For example, if a sudden change in heart rate is detected, the server records the abnormality and considers countermeasures.

[0856] 3. Training program proposals

[0857] The server generates a training program optimized for the athlete's characteristics based on the analysis results. The program includes details such as exercise content, intensity, number of repetitions, and rest time. For example, if it is determined that muscle strengthening is necessary, detailed guidelines such as "3 sets of 12 squats, with a load of 50% of body weight, with 90 seconds of rest between sets" will be generated. The device displays the generated training program to the user.

[0858] 4. Real-time advice and care delivery tools

[0859] During training, the device continuously transmits collected real-time data to the server, which immediately analyzes it and generates immediate feedback as needed. For example, if signs of fatigue are detected, the device will instruct the user to rest. If abnormal movements are detected, specific advice such as "Pay attention to the position of your toes to correct your running form" will be provided.

[0860] Specific examples

[0861] For example, to generate an optimal training program for Athlete A to improve muscle strength and prevent injury based on their heart rate, EMG data, and training history from the past week, the prompt would be:

[0862] Based on Athlete A's heart rate, EMG data, and training history from the past week, please generate an optimal training program for improving muscle strength and preventing injury. Please recommend specific exercises, number of repetitions, intensity, and rest periods.

[0863] An example of the output produced is:

[0864] Strength Training Program:

[0865] Exercise: Squats

[0866] Reps: 3 sets x 12 reps

[0867] Intensity: 50% of body weight

[0868] Rest Time: 90 seconds rest between sets

[0869] Additional tips: Focus on form, foot position and knee movement. After this exercise, do some gentle stretching to loosen up your muscles.

[0870] In this way, this system starts with collecting data from the device worn by the user, then analyzes the data on the server, creates training programs, and provides real-time feedback, all in an integrated manner, effectively supporting athletes in improving their performance and preventing injuries.

[0871] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0872] Step 1: Collect data

[0873] How it works: The user wears a smartwatch and sensors, which collect biometric data such as heart rate, acceleration, and electromyogram in real time. The smartwatch measures heart rate every 10 seconds and sends the data to the device.

[0874] Input: Biometric data from smartwatches and sensors.

[0875] Output: Real-time biometric data sent to the device.

[0876] Step 2: Sending data

[0877] Specific operation: The device sends the collected biometric data to the server at any time. The data is securely transmitted via the Internet.

[0878] Input: Biometric data collected on the device.

[0879] Output: Biometric data sent to the server.

[0880] Step 3: Preprocessing the data

[0881] Specific operation: The server first cleans the received biometric data, removes noise if it is present, and corrects outliers. Then, it normalizes the data and converts it into a unified format.

[0882] Input: Biometric data sent to the server.

[0883] Output: Cleaned and normalized biometric data.

[0884] Step 4: Analyze the data

[0885] Specific actions: The server performs biomechanical analysis based on the normalized data. This determines whether the athlete's movements and loads are appropriate. If abnormal movements or excessive loads are detected, they are recorded and countermeasures are considered.

[0886] Input: Cleaned and normalized biometric data.

[0887] Output: Biomechanical analysis results, assessment of abnormalities and loads.

[0888] Step 5: Generate a training program

[0889] Specific actions: Based on the analysis results, the server generates a training program that is optimal for the athlete's characteristics. The program includes details such as exercise content, intensity, number of repetitions, and rest time. For example, it creates guidelines such as "3 sets of 12 squats, with a load of 50% of body weight, and 90 seconds of rest between sets."

[0890] Input: Biomechanical analysis results.

[0891] Output: Training program details.

[0892] Step 6: View your training program

[0893] Specific operation: The device displays the generated training program to the athlete, who can then check the training plan for the day through the device.

[0894] Input: Training program details.

[0895] Output: The training program displayed on the terminal.

[0896] Step 7: Collect real-time data

[0897] Specific operation: During training, the device continues to collect biometric data in real time and transmits it to the server.

[0898] Input: Real-time biometric data during training.

[0899] Output: Real-time biometric data sent to the server.

[0900] Step 8: Real-time feedback

[0901] Specific operation: The server immediately analyzes the data received in real time and generates immediate feedback as needed. If signs of fatigue or abnormal movements are detected, the server notifies the athlete via the device with appropriate instructions. For example, it gives advice such as "You are showing signs of fatigue. Please take a break" or "Pay attention to the position of your toes to correct your running form."

[0902] Input: Biometric data received in real time.

[0903] Output: Real-time feedback displayed on the device.

[0904] These steps enable the system to consistently collect and analyze data, generate training programs, and provide real-time feedback, thereby effectively supporting athletes in improving their performance and preventing injuries.

[0905] (Application example 1)

[0906] 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."

[0907] Conventional industrial equipment does not adequately collect and analyze operational data, making it difficult to detect signs of abnormal operation early. As a result, abnormalities are often not noticed until a failure occurs, leading to sudden machine shutdowns and production delays. Furthermore, even when an abnormality is detected, there is a lack of means to provide immediate, appropriate feedback, making it difficult to operate industrial equipment efficiently. A new system is needed to solve these issues, improve operational performance, and prevent failures.

[0908] 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.

[0909] In this invention, the server includes means for collecting operational data of industrial equipment, means for performing machine operation analysis and identifying abnormal operations and loads, means for proposing individual operation schedules based on the analysis results, means for providing advice and correction instructions to the industrial equipment in real time, means for evaluating the fatigue state and predicting the risk of failure, and means for preprocessing, cleaning, and normalizing the collected data, thereby improving the operational performance of the industrial equipment, reducing the risk of failure, and enabling stable operation.

[0910] "Industrial equipment" is a general term for machines and devices used in factories and manufacturing facilities to automate, streamline, or support the production process.

[0911] "Operational data" refers to information relating to the movement of a device, including measurements such as position, speed, temperature, and vibration.

[0912] "Machine operation analysis" is a technology that analyzes the operating status of equipment based on collected operation data and distinguishes between normal and abnormal operation.

[0913] "Abnormal operation" refers to the occurrence of behavior that is different from normal in the operation of equipment, which may cause a malfunction if it continues.

[0914] "Load" refers to external factors such as force, pressure, and temperature that are applied to equipment when it is operating, and if this load becomes excessive it can have a negative effect on the equipment.

[0915] An "operation schedule" is a timetable for systematically managing the operation and running of equipment, and lists optimal operating times and maintenance timings.

[0916] "Advice" means appropriate instructions or suggestions regarding the operation of equipment, intended to facilitate adjustments to operation or maintenance.

[0917] "Correction instructions" refer to instructions on specific operating methods or changes to be made to deal with abnormal equipment operation or load.

[0918] "Fatigue" refers to a state in which equipment parts or systems begin to deteriorate due to prolonged or excessive use.

[0919] "Failure risk" is the probability of a failure occurring that can be predicted from the operation and condition of equipment, and by predicting this, it is possible to take measures in advance.

[0920] "Data preprocessing" refers to the process of preparing collected raw data in a form that is easier to analyze, and includes processes such as removing noise and normalizing the data.

[0921] "Cleaning" is the process of removing unnecessary information and errors from collected data.

[0922] "Normalization" is a process of standardizing data values ​​to a certain scale, and is performed to improve the accuracy of analysis.

[0923] This invention relates to an AI system aimed at improving the operational performance and preventing breakdowns of industrial equipment. This system collects and analyzes operational data, proposes optimal operation schedules for industrial equipment, and provides advice and correction instructions in real time. The system consists of the following main components:

[0924] Data collection methods

[0925] Sensors attached to industrial equipment collect operational data such as position, speed, temperature, and vibration in real time, and the collected data is sent to a server via the terminal.

[0926] Data Analysis Methods

[0927] The server preprocesses the collected operational data, removing noise and normalizing the data, and performs machine operation analysis to detect abnormalities in operation and load. It also evaluates fatigue status and predicts failure risk.

[0928] Operation schedule suggestion means

[0929] Based on the analysis results, the server generates an optimal operation schedule tailored to the characteristics of the industrial equipment. The schedule includes details such as operating hours, load balancing, and maintenance periods. The terminal displays the generated schedule to the industrial equipment operator.

[0930] Real-time advice and corrective action methods

[0931] During operation, the terminal continuously transmits real-time collected data to the server, which analyzes the data and generates immediate feedback as needed. If abnormal behavior or excessive load is detected, the terminal will notify the operator with appropriate corrective instructions.

[0932] System Operation

[0933] 1. Data collection: Sensors attached to industrial equipment continuously collect operational data in real time, such as position, speed, temperature, and vibration. For example, if a robot arm experiences a sudden rise in temperature while in operation, the data is sent to a server via the terminal.

[0934] 2. Data preprocessing and analysis: The server cleans the collected data and removes noise. It also normalizes the data to make it easier to analyze. Next, the server analyzes the machine's operation to detect abnormal behavior or excessive loads. For example, if analysis of vibration data reveals that a particular part is wearing out, the server records that information.

[0935] 3. Proposing an operation schedule: Based on the analysis results, the server generates an optimal operation schedule tailored to the characteristics of the industrial equipment. As a specific example, it proposes a short-term maintenance schedule taking into account parts that are deteriorating. The terminal displays the generated schedule to the operator, who then confirms the plan.

[0936] 4. Real-time advice and correction instructions: If an abnormality is detected during operation, the server immediately analyzes it and generates appropriate correction instructions. For example, specific advice such as "Please reduce the operating speed" or "A specific part needs to be replaced" is provided in real time via the terminal.

[0937] Hardware and software used

[0938] To implement the present invention, the following hardware and software are used:

[0939] Hardware: Industrial equipment, accelerometers, temperature sensors, vibration sensors.

[0940] Software: Python, TensorFlow, SQL Server, GUI development frameworks (such as Tkinter).

[0941] Examples and prompts

[0942] Specific examples

[0943] 1. Example 1: If the motor temperature suddenly rises while an industrial robot is operating, the system will issue a warning saying "Motor temperature is too high. Please reduce speed."

[0944] 2. Example 2: If abnormal vibration is detected, notify the user that "Abnormal vibration has been detected. Please change the operation route."

[0945] Prompt statement

[0946] Example prompts to enter into the Data Analysis module:

[0947] Check for motor temperature spikes and display warnings if necessary. Use temperature data from the past 24 hours.

[0948] Example prompts for the optimization algorithm:

[0949] "Optimize the operating schedule of industrial equipment and distribute the load to specific time periods. Consider detailed load data and operating history."

[0950] As described above, this system performs all processes from data collection and analysis to generating operation schedules and providing real-time feedback, thereby improving the operational performance of industrial equipment and preventing breakdowns.

[0951] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0952] Step 1:

[0953] Sensors collect operational data

[0954] Sensors attached to industrial equipment collect operational data such as position, speed, temperature, and vibration in real time. This data is sent to a server via a terminal. The input data is the measurement value from the sensor, and the output is the raw data sent to the server. For example, the temperature and vibration data of a robot arm in operation is constantly recorded and transferred to the terminal.

[0955] Step 2:

[0956] Data Preprocessing

[0957] The server cleans the received motion data, removes noise, and normalizes it to make it easier to analyze. The input data is raw data sent from the sensors, and the output is cleaned and normalized data. Specific operations include missing value imputation, outlier removal, and range scaling.

[0958] Step 3:

[0959] Data analysis

[0960] The server uses the preprocessed data to analyze machine operation to identify abnormal behavior and loads. A generative AI model is used for the analysis to detect anomalies and evaluate failure risks. The input data is preprocessed data, and the output is the analysis results, including abnormal behavior detection results and risk assessment data. Specifically, the AI ​​model analyzes sensor data to detect abnormal temperature increases and excessive vibrations.

[0961] Step 4:

[0962] Generate an operation schedule

[0963] Based on the analysis results, the server generates an optimal operation schedule tailored to the characteristics of the industrial equipment. The input data are the analysis results, and the output is a recommended operation schedule. In terms of specific operations, the system generates plans for maintenance periods and load balancing based on the analysis results and presents them to the operator.

[0964] Step 5:

[0965] Viewing Schedules

[0966] The terminal displays the generated operation schedule to the industrial equipment operator. The input data is the operation schedule sent from the server, and the output is data in a display format that can be checked by the operator. In concrete terms, the operation schedule is displayed on the terminal display, and the operator checks it.

[0967] Step 6:

[0968] Real-time data monitoring and feedback

[0969] During operation, the terminal continuously collects and transmits real-time operational data to the server. The server analyzes this data and generates immediate feedback as needed. The input data is real-time operational data, and the output is feedback such as advice and correction instructions. Specifically, if abnormal movement or excessive load is detected, instructions such as "Please reduce speed" are displayed in real time on the operator's terminal.

[0970] 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.

[0971] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries, and also provides a system that combines an emotion engine that recognizes athletes' emotions. This system collects and analyzes performance and emotion data, proposes optimal training programs for athletes, and provides advice and care in real time, thereby achieving overall performance improvement and injury prevention for athletes.

[0972] The system consists of the following main components:

[0973] 1. Data Collection Methods

[0974] The sensors and smartwatches worn by athletes collect biometric data such as heart rate, acceleration, and electromyograms, as well as emotional data from the athletes' facial expressions and voice. The devices receive this data and send it to a server.

[0975] 2. Emotion recognition means

[0976] The server uses the collected facial and voice data to analyze the athlete's emotional state using an emotion engine, which identifies emotions such as joy, sadness, anger, and stress.

[0977] 3. Data Analysis Methods

[0978] The server preprocesses the received biometric and emotional data, cleansing and normalizing them, and then performs biomechanics analysis to comprehensively evaluate abnormalities in movement and load, as well as emotional states.

[0979] 4. Training program proposal methods

[0980] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics and emotional state. The program includes details such as exercise content, intensity, number of repetitions, and rest periods. The terminal displays the generated program to the athlete.

[0981] 5. Real-time advice and care delivery methods

[0982] During training, the device continuously collects and transmits real-time biometric and emotional data to the server, which analyzes it and generates immediate feedback as needed. If signs of fatigue, abnormal movements, or emotional stress are detected, the device will notify the athlete and advise them to rest or modify their movements.

[0983] Specific flow and examples of program processing

[0984] To concretely explain how this system works, let's describe the program's processing in natural language:

[0985] 1. Data collection

[0986] The device collects real-time data from athletes, including their heart rate, electromyogram, facial expression data from a facial recognition sensor, and audio data from a voice recognition microphone. For example, if an athlete does not smile during training, their facial expression and audio data will also be collected.

[0987] 2. Data Preprocessing and Emotion Recognition

[0988] The server cleans the collected data, removes noise, and normalizes it to make it easier to analyze.

[0989] The emotion engine identifies the athlete's emotions from facial and voice data. For example, if a high level of stress or fatigue is detected, the emotion data is recorded.

[0990] 3. Data analysis and evaluation

[0991] The server uses normalized biometric and emotional data for biomechanical analysis, using machine learning algorithms to identify abnormalities in movement and stress.

[0992] The server uses data analysis to comprehensively assess an athlete's fatigue and emotional state, adjusting the intensity of specific training sessions if, for example, emotional stress is high.

[0993] 4. Training program proposals

[0994] Based on the analysis results, the server generates a training program that is optimal for the athlete's characteristics and emotional state. For example, it adds relaxation exercises when stress levels are high, and suggests high-intensity training when joy levels are high.

[0995] 5. Real-time advice and care

[0996] During training, the device continuously collects biometric and emotional data in real time and transmits it to a server, which then analyzes the data to detect fatigue, abnormalities in movement, and emotional changes in real time.

[0997] Based on the analysis results, real-time advice and care is provided. For example, if emotional stress is detected, it will suggest ways to relax, and if abnormal movements are detected, it will advise on the correct way to move.

[0998] In this way, by combining this system with an emotion engine, it is possible to comprehensively evaluate an athlete's physical and emotional state, suggest more accurate training programs, and provide real-time advice, thereby improving athlete performance and preventing injuries.

[0999] The processing flow will be explained below.

[1000] Step 1:

[1001] The device collects biometric data such as heart rate, acceleration, and electromyogram in real time from sensors worn by athletes. It also collects facial expression and voice data from facial recognition sensors and a voice recognition microphone for emotion recognition. This collected data is temporarily stored on the device.

[1002] Step 2:

[1003] The device transmits all collected biometric and emotional data to a server periodically, delivering the data in near real time.

[1004] Step 3:

[1005] The server receives the data sent from the device, which is first cleaned to remove noise and outliers and fill in missing data, improving the accuracy of the data.

[1006] Step 4:

[1007] The server normalizes the cleaned data. Normalization is the process of converting data from different scales into a unified scale to make it easier to analyze.

[1008] Step 5:

[1009] The server analyzes the normalized data with an emotion engine, which identifies the athlete's emotional state (e.g., joy, sadness, anger, stress, etc.) based on facial and voice data.

[1010] Step 6:

[1011] The server uses the emotion engine results and biological data for biomechanical analysis, which identifies abnormalities in the athlete's movements, loads, and fatigue.

[1012] Step 7:

[1013] Based on the analysis results, the server generates a training program optimized for the athlete's characteristics and emotional state. The program includes details such as exercise content, intensity, number of repetitions, and rest periods. For example, if an athlete is in a high stress state, relaxation exercises will be added.

[1014] Step 8:

[1015] The server transmits the generated training program to the terminal, which receives it and displays it to the user.

[1016] Step 9:

[1017] The user checks the training program presented and makes a training plan for the day. The terminal records the user's operations and transmits the necessary data to the server.

[1018] Step 10:

[1019] During training, the device continues to collect real-time biometric and emotional data and transmits it to the server, which is used to monitor the training progress in real time.

[1020] Step 11:

[1021] The server analyzes the data received in real time to detect the athlete's fatigue, abnormalities in their movements, and emotional changes. For example, if an athlete's heart rate spikes or stress is detected in their facial expressions, the server generates appropriate feedback.

[1022] Step 12:

[1023] The server generates real-time advice and care based on the analysis results and notifies the device. For example, it suggests resting if fatigue suddenly increases, instructs corrective actions if abnormal behavior is detected, and sends instructions for relaxation if emotional stress increases.

[1024] Step 13:

[1025] The device displays real-time advice and care notifications from the server to the user, who then checks these notifications and acts accordingly, for example, accepting suggestions for rest or modifying their behavior.

[1026] In this way, the system comprehensively analyzes biometric and emotional data and provides optimal training programs and real-time advice tailored to the athlete's condition, thereby improving their performance and preventing injuries.

[1027] Example 2

[1028] 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."

[1029] Conventional training systems for athletes focus on collecting and analyzing only biological data, and lack comprehensive evaluation and advice that takes into account the athlete's emotional state. This often leaves them inadequate for maximizing athletes' performance and preventing injuries. Real-time feedback and immediate care during training are also limited. To address this situation, a system is needed that can comprehensively analyze athletes' biological and emotional data and provide optimal training programs and real-time advice tailored to their individual characteristics.

[1030] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting the athlete's biological data and emotional data, means for cleaning and normalizing the collected data, means for identifying the athlete's emotions using an emotion engine, means for performing biomechanics analysis and identifying abnormalities in movement and load, means for generating a training program optimal for the athlete's characteristics and emotional state based on the analysis results, and means for providing advice and care to the athlete in real time. This makes it possible to comprehensively evaluate the athlete's physical and emotional state and propose more accurate training programs and provide real-time advice.

[1031] "Biometric data" refers to data that indicates the physiological state of the body, such as an athlete's heart rate, acceleration, and electromyogram.

[1032] "Emotional data" is data that indicates the emotional state of an athlete, obtained from facial expressions, voice, etc.

[1033] An "emotion engine" is software or algorithm that identifies an athlete's emotions from collected facial and voice data.

[1034] "Biomechanics analysis" is an analytical method that analyzes an athlete's movements and loads to identify abnormalities.

[1035] A "training program" is a program that includes the optimal exercise content, intensity, number of repetitions, rest time, etc., according to the athlete's characteristics and emotional state.

[1036] "Real-time advice" refers to instructions and advice provided to athletes instantly based on collected biometric and emotional data.

[1037] "Care" means the instruction and support to maintain and promote the athlete's physical and mental health.

[1038] "Cleaning" is the process of removing noise from collected data and preparing it in a form that can be analyzed.

[1039] "Normalization" is the process of converting data into a consistent format that makes it easier to analyze.

[1040] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries. Furthermore, this invention provides a system that combines an emotion engine that recognizes athletes' emotions to achieve comprehensive performance improvement and injury prevention for athletes.

[1041] The system consists of the following main components:

[1042] 1. Data Collection Methods

[1043] The device collects biometric data such as heart rate, acceleration, and electromyogram in real time from sensors or smartwatches worn by athletes. The device also collects facial expression and voice data using a camera and voice recognition microphone. For example, when an athlete is running, the device collects not only heart rate and electromyogram data, but also facial expressions while running and comments on training in real time.

[1044] 2. Emotion recognition means

[1045] The server inputs the collected facial and voice data into an emotion engine to identify the athlete's emotions. The emotion engine utilizes machine learning models to assess the athlete's emotional state in real time. For example, it can analyze whether the athlete is feeling stressed based on facial expressions and tone of voice.

[1046] 3. Data Analysis Methods

[1047] The server cleans the collected biometric and emotional data to remove noise. It then normalizes the data to make it easier to analyze. It then performs biomechanical analysis to identify abnormalities in movement and load. For example, it can detect an anomaly if an athlete takes a stride that differs from their normal walking style.

[1048] 4. Training program proposal methods

[1049] Based on the analysis results, the server generates a training program optimized for the athlete's characteristics and emotional state. This program includes details such as exercise content, intensity, number of repetitions, and rest periods. For example, if the athlete is feeling stressed, it will suggest relaxation exercises.

[1050] 5. Real-time advice and care delivery methods

[1051] During training, the device continuously collects and transmits real-time biometric and emotional data to the server, which analyzes it and generates immediate feedback as needed. For example, if your heart rate spikes, the device will prompt you to take a short break.

[1052] To use the system, the generative AI model might be fed prompts like the following example:

[1053] "Please explain how an AI system that analyzes athletes' performance and emotional data and proposes optimal training programs works from the perspectives of the server, device, and user."

[1054] This system will enable a comprehensive assessment of an athlete's physical and emotional state, providing more accurate training program suggestions and real-time advice.

[1055] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1056] Step 1:

[1057] Data collection

[1058] The device collects biometric data in real time from sensors or smartwatches worn by athletes. For example, it acquires heart rate (collected data) and electromyograms. The input data is the athlete's real-time heart rate and electromyogram, and the output is a stream of collected biometric data.

[1059] The device uses a camera and a voice recognition microphone to collect facial and voice data of the athlete. For example, it captures the athlete's smile and tone of voice (emotion data). The input data is real-time captured information from the camera and microphone, and the output is a stream of emotion data.

[1060] Step 2:

[1061] Data Preprocessing

[1062] The server receives the biometric data and emotion data sent from the terminal, and the input data is the collected biometric data and emotion data.

[1063] The server cleans (denoises) and normalizes the data to make it easier to analyze. For example, it removes outliers from heart rate data and aligns them along a time axis. The output is cleaned and normalized biometric and emotion data.

[1064] Step 3:

[1065] emotion recognition

[1066] The server inputs the cleaned and normalized emotion data into the emotion engine to identify emotions. The input data is the preprocessed facial expression data and speech data.

[1067] The server uses an emotion engine to analyze emotions such as stress, joy, anger, etc. For example, a smiling face can be recognized as joy, and a low voice as stress. The output is data indicating the emotional state.

[1068] Step 4:

[1069] Data analysis

[1070] The server performs biomechanics analysis using the biometric data and emotion data, and the input data is the preprocessed biometric data and emotion data.

[1071] The server uses machine learning algorithms to identify abnormalities in movement and load, for example, detecting unusual running form. The output is an analysis result that includes the abnormal movement and load.

[1072] Step 5:

[1073] Generate a training program

[1074] The server generates a training program that is optimal for the athlete's characteristics and emotional state based on the analysis results. The input data are the biological data, the emotional data, and the analysis results.

[1075] The server automatically generates a training program including exercise type, intensity, number of repetitions, and rest time. For example, it suggests relaxation exercises when stress is high, and high-intensity training when energy is high. The output is a customized training program.

[1076] Step 6:

[1077] Training Program Notification

[1078] The server sends the generated training program to the terminal, and the input data is the generated training program.

[1079] The device displays the information to the athlete and notifies them of the next action. For example, specific instructions such as "Next, stretch after 10 minutes of running" are displayed. The output is the notification to the athlete.

[1080] Step 7:

[1081] Real-time monitoring and feedback

[1082] The device continuously transmits the biological data and emotional data collected in real time during training to the server. The input data is the data collected in real time.

[1083] The server analyzes the data received in real time and generates immediate feedback if necessary. For example, if your heart rate spikes, it will generate a prompt to "take a short break." The output is real-time feedback.

[1084] The device provides real-time advice to the athlete based on feedback from the server. For example, if there is an abnormality in movement, specific advice such as "Check your right foot step" is displayed. The output is real-time advice to the athlete.

[1085] Through these steps, the system will be able to perform detailed analysis of athletes' biometric and emotional data, and provide training programs and real-time advice tailored to their individual characteristics.

[1086] (Application example 2)

[1087] 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."

[1088] Previous systems have focused on improving athletes' performance and managing their workload, but few systems have considered the influence of emotions. Furthermore, technology for managing passenger emotions and comfort levels in real time in autonomous vehicles is still immature, and a method to improve the overall passenger experience is needed. Therefore, a new system that utilizes emotion data is needed in the context of both athletes and autonomous vehicles.

[1089] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting athlete performance data, means for performing biomechanics analysis to identify abnormal movements and loads, means for proposing an individual training program based on the analysis results, means for providing advice and care to the athlete in real time, means for collecting passenger emotional data, means for analyzing the collected emotional data and evaluating comfort levels, means for automatically adjusting the in-vehicle environment based on the evaluation results, and means for suggesting entertainment and relaxation to passengers based on their emotional states. This makes it possible to optimize athlete performance while preventing injuries and managing loads, and enables real-time management of passenger emotions and comfort levels in autonomous vehicles.

[1090] "Means for collecting athlete performance data" refers to equipment that uses sensors or devices worn by athletes to obtain biometric data such as heart rate, electromyogram, and acceleration.

[1091] "Means for conducting biomechanical analysis and identifying abnormal movements and loads" refers to algorithms and programs that analyze collected biometric data and identify any abnormalities in an athlete's movements or loads.

[1092] The "means for proposing individual training programs based on the analysis results" is a system for generating training programs specifically for athletes based on the results of data analysis.

[1093] "Means for providing athletes with real-time advice and care" refers to applications that provide athletes with immediate feedback and care instructions based on data collected during training.

[1094] The "means for collecting passenger emotional data" is a device that uses a camera or microphone to capture passenger facial expressions and voices and collect emotional data based on them.

[1095] The "means for analyzing collected emotion data and evaluating the comfort level" is a system that analyzes the acquired emotion data and evaluates the comfort level of passengers using the analysis results.

[1096] The "means for automatically adjusting the in-car environment based on the evaluation results" is a device that automatically sets and changes the in-car environment, such as temperature, lighting, and music, based on the evaluation results of emotional data.

[1097] The "means for suggesting entertainment and relaxation methods to passengers based on their emotional state" is a system that presents entertainment content and relaxation methods appropriate for passengers based on the results of analyzing their emotions.

[1098] This invention relates to an AI system for improving athletic performance and injury prevention, and a passenger comfort management system for autonomous vehicles. The system includes the following main components and processes:

[1099] Data collection

[1100] The server uses sensors and devices to collect biometric data from athletes and emotional data from passengers. Specifically, it uses devices such as smartwatches worn by athletes, accelerometers, electromyogram sensors, cameras, and microphones to collect heart rate, electromyogram, acceleration, facial expression data, and voice data. To collect emotional data from passengers in the in-car environment, it uses cameras and microphones installed in the vehicle.

[1101] Data preprocessing and emotion recognition

[1102] The server cleans the collected data and removes noise. It uses Python and R libraries to normalize the data and make it easier to analyze. For emotion recognition, it uses emotion recognition models built with TensorFlow and Keras. For example, if a passenger is not smiling, their facial expression data is also collected and analyzed along with the voice data.

[1103] Data analysis and evaluation

[1104] The server performs biomechanics analysis using normalized biometric and emotional data. It uses machine learning algorithms, such as scikit-learn and TensorFlow, to identify abnormalities in movement and load. To assess passenger comfort, it generates a comfort score based on the emotional data.

[1105] Training program suggestions and automatic adjustment of the in-car environment

[1106] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics and emotional state. The program includes details such as exercise type, intensity, number of repetitions, and rest periods. Inside the autonomous vehicle, a control program is executed that automatically adjusts the in-car environment, including temperature, lighting, and music, based on the evaluation results of the emotional data.

[1107] Real-time advice and care

[1108] During training or while the vehicle is in operation, the device continuously collects real-time biometric and emotional data and transmits it to the server. The server analyzes this data and provides immediate feedback. For example, if fatigue or abnormal movements are detected, the device will instruct the athlete to rest or correct their movements. It will also suggest relaxation and entertainment options based on the passenger's emotional state.

[1109] Examples of specific examples and prompts

[1110] For example, when an athlete is training, the system can detect their fatigue level in real time using electromyograms and heart rate data and immediately instruct them to rest. Based on passenger emotional data, the in-car environment can be optimally adjusted to provide a comfortable travel experience.

[1111] Example prompts to input to a generative AI model:

[1112] 1. "Suggest a list of music to play when passengers are happy."

[1113] 2. "Decide on environmental settings for passengers experiencing stress and adjust temperature and lighting settings for accountability."

[1114] 3. "Analyze real-time sentiment data and show passengers the entertainment they want."

[1115] In this way, the system, combined with the emotion engine, can comprehensively assess the athlete's physical and emotional state, improving passenger comfort in autonomous vehicles.

[1116] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1117] Step 1:

[1118] The device collects biometric and emotional data from athletes or passengers. Specifically, it uses devices such as smartwatches worn by athletes, accelerometers, electromyogram sensors, cameras, and microphones to obtain heart rate, electromyogram, acceleration, facial expression data, and voice data in real time. The device then transmits this data to a server.

[1119] Step 2:

[1120] The server cleans the received data and removes noise. Specifically, it uses data preprocessing libraries in Python and R to impute missing values ​​and remove outliers from the collected biometric and emotional data. The input data includes biometric signals from biometric sensors and camera and microphone data, and the output data is clean data.

[1121] Step 3:

[1122] The server normalizes the cleaned data and prepares it for easier analysis. Specifically, it scales and standardizes the biometric and emotional data. Here, the input data is the cleaned biometric and emotional data, and the output data is the normalized data.

[1123] Step 4:

[1124] The server uses the normalized data to perform emotion recognition. Specifically, it inputs the data into an emotion recognition model built using TensorFlow and Keras to analyze the emotional state. The input data includes normalized facial expression data and voice data, and the output data is the emotional state (happiness, sadness, anger, stress, etc.).

[1125] Step 5:

[1126] The server performs biomechanics analysis using normalized biometric and emotional data. It uses machine learning algorithms to identify abnormalities in movement and stress. Specifically, it uses scikit-learn and TensorFlow to apply a motion analysis model to detect abnormal movements and overload. The input data is normalized biometric and emotional data, and the output data includes abnormal movements and stress.

[1127] Step 6:

[1128] The server generates a training program that matches the athlete's characteristics and emotional state based on the analysis results. Specifically, if overload or abnormal movement is detected, it provides a program that includes appropriate exercise content, intensity, number of repetitions, rest periods, etc. The input data are the biomechanics analysis results and emotion analysis results, and the output data includes a training program.

[1129] Step 7:

[1130] The server evaluates the passenger's comfort level based on emotional data in the autonomous vehicle and automatically adjusts the in-car environment. Specifically, if the emotional state indicates stress, it adjusts the temperature and lighting and plays relaxation music. The input data is the emotion analysis results, and the output data includes the in-car environment settings.

[1131] Step 8:

[1132] The terminal continuously transmits the data collected in real time to the server, which then provides immediate feedback. Specifically, it displays rest instructions and movement modification advice to athletes, and relaxation and entertainment suggestions to passengers. The input data is real-time biometric and emotional data, and the output data includes the content of the feedback.

[1133] This way, proper care and feedback can be provided to both the athlete and the passengers at each step.

[1134] 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.

[1135] 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.

[1136] 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.

[1137] [Fourth embodiment]

[1138] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1139] 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.

[1140] 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).

[1141] 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.

[1142] 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.

[1143] 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).

[1144] 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.

[1145] 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.

[1146] 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.

[1147] 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.

[1148] 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.

[1149] 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.

[1150] 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."

[1151] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries. This system collects and analyzes performance data, proposes optimal training programs for athletes, and provides advice and care in real time.

[1152] The system consists of the following main components:

[1153] 1. Data Collection Methods

[1154] Sensors or smartwatches worn by athletes collect biometric data such as heart rate, acceleration, and electromyogram in real time. The devices receive this data and send it to a server.

[1155] 2. Data analysis methods

[1156] The server preprocesses the received biometric data, removing noise and normalizing it. It then performs biomechanics analysis to detect abnormalities in movement and load. It also simultaneously evaluates fatigue levels and predicts injury risk.

[1157] 3. Training program proposal methods

[1158] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics. The program includes details such as exercise content, intensity, number of repetitions, and rest periods. The terminal displays the generated program to the athlete.

[1159] 4. Real-time advice and care delivery tools

[1160] During training, the device continuously collects and transmits real-time data to the server, which analyzes it and generates immediate feedback as needed. If signs of fatigue or abnormal movements are detected, the device will notify the athlete and advise them to rest or modify their movements.

[1161] Specific flow and examples of program processing

[1162] To concretely explain how this system works, let's describe the program's processing in natural language:

[1163] 1. Data collection

[1164] The device collects heart rate and electromyogram data from the athlete in real time. For example, if the athlete's heart rate spikes during training, the device sends that data to a server.

[1165] 2. Data Preprocessing and Analysis

[1166] The server cleans the collected data, removes noise, and normalizes it to make it easier to analyze.

[1167] The server then performs an analysis and, if it determines that, for example, the athlete's heart rate fluctuations are abnormal, it records the abnormality.

[1168] 3. Training program proposals

[1169] Based on the results of the biomechanics analysis, the server generates a training program optimized for the athlete's characteristics, providing detailed guidelines such as specific exercises to strengthen muscles, as well as the number of repetitions and intensity of those exercises.

[1170] The terminal displays the generated training program to the athlete, and the user confirms the training plan for the day.

[1171] 4. Real-time advice and care

[1172] During training, the device continuously collects and transmits real-time data to a server that analyzes the data and, if it detects signs of fatigue, for example, sends instructions to the athlete to rest.

[1173] If the movement is determined to be abnormal, the server will provide advice to the athlete in real time via the device, such as "Pay attention to the position of your toes to correct your running form."

[1174] In this way, this system will improve athletes' performance and prevent injuries by consistently collecting and analyzing data, creating training programs, and providing real-time feedback.

[1175] The processing flow will be explained below.

[1176] Step 1:

[1177] The device collects biometric data such as heart rate, acceleration, and electromyogram in real time from sensors worn by athletes, and the collected data is temporarily stored on the device.

[1178] Step 2:

[1179] The device transmits the collected biometric data to the server. This communication occurs periodically to ensure that real-time data is transmitted to the server.

[1180] Step 3:

[1181] The server receives the data sent from the terminal. The received data is first cleaned. Cleaning is a process in which noise and outliers are removed and missing data is filled in.

[1182] Step 4:

[1183] The server normalizes the cleaned data. Normalization refers to converting data from different scales into a unified scale to make it easier to analyze.

[1184] Step 5:

[1185] The server uses the normalized data for biomechanical analysis, including machine learning algorithms, to identify abnormal movements and loads.

[1186] Step 6:

[1187] The server uses data analysis to assess an athlete's fatigue state and predict injury risk, integrating past and current data to make a comprehensive judgment.

[1188] Step 7:

[1189] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics, including exercise content, intensity, number of repetitions, and rest periods.

[1190] Step 8:

[1191] The server transmits the generated training program to the terminal, which receives it and displays it to the user.

[1192] Step 9:

[1193] The user checks the training program presented and makes a training plan for the day. The terminal records the user's operations and transmits the necessary data to the server.

[1194] Step 10:

[1195] During training, the device continuously collects biometric data in real time and transmits it to a server, which then analyzes the data to detect fatigue and abnormalities in real time.

[1196] Step 11:

[1197] The server generates real-time advice and care based on the analysis results and notifies the device. For example, if fatigue is detected, it will instruct the user to rest, and if abnormal behavior is detected, it will send advice for correction.

[1198] Step 12:

[1199] The terminal displays real-time advice and care notifications from the server to the user, who then checks these notifications and acts according to the instructions.

[1200] In this way, the system efficiently collects and analyzes athletes' performance data, creates optimal training programs, and provides advice and care in real time, thereby improving athletes' performance and preventing injuries.

[1201] Example 1

[1202] 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."

[1203] Conventional training systems for athletes have struggled to comprehensively and centrally manage the collection and analysis of real-time biometric data, as well as the proposal of training programs based on the analysis results. It has been particularly difficult to provide fast and accurate advice in situations where real-time feedback during training or immediate action is required to prevent injury. Furthermore, insufficient pre-processing, such as data noise removal and normalization, can reduce the accuracy of the analysis, potentially resulting in a decline in the quality of the training program.

[1204] 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.

[1205] In this invention, the server includes means for collecting athlete performance data, means for transmitting the data to the server, means for preprocessing, cleaning, and normalizing the collected data, means for performing biomechanics analysis to identify abnormal movements and loads, means for generating an individual training program based on the analysis results, means for displaying the generated training program on a terminal, means for providing advice and care to the athlete in real time, and means for collecting data in real time during training and transmitting it to the server. This enables a system that can perform all processes from collection to analysis, generation of a training program, and provision of real-time feedback.

[1206] "Athlete" refers to a person who participates in competitive activities in sports or athletic competitions.

[1207] "Performance data" refers to biometric information that indicates an athlete's physical ability, physical condition, exercise status, etc. Specifically, it includes data such as heart rate, acceleration, and electromyogram.

[1208] "Data Collection Instruments" refers to devices or equipment used to obtain real-time performance data from athletes, including, for example, sensors and smartwatches.

[1209] "Server" refers to a data processing device accessible via the Internet or a local network that analyzes data and generates training programs.

[1210] "Preprocessing" refers to the process carried out before data analysis, such as removing noise and normalizing the data. This process improves the quality of the data and increases the accuracy of the analysis.

[1211] "Cleaning" refers to the process of removing unnecessary noise and outliers from acquired performance data.

[1212] "Normalization" is a process of constraining data variation within a certain range, and is performed to ensure consistency between different data sets.

[1213] "Biomechanics analysis" refers to a data-based method of analyzing an athlete's physical movements and stress conditions. This analysis can detect abnormalities in movement and excessive stress.

[1214] A "training program" is a plan that specifically outlines the exercises and training that an athlete should perform, including the content, intensity, number of repetitions, and rest times.

[1215] "Real-time advice and care delivery tools" refer to tools that provide immediate feedback and instruction based on data collected during training.

[1216] "Terminal" refers to a device that an athlete can operate and view displayed information, including, specifically, a smartphone or tablet.

[1217] "Analysis results" refers to the evaluation and diagnostic results of data obtained through preprocessing and biomechanics analysis.

[1218] "Abnormal movements or loads" refers to conditions that exceed normal movement patterns or physical load ranges, and indicates movements or excessive loads that may have adverse effects on the body.

[1219] MODE FOR CARRYING OUT THE INVENTION

[1220] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries. This system collects and analyzes performance data to propose optimal training programs for athletes and provides advice and care in real time. Specific embodiments of this system are described below.

[1221] The system consists of the following main components:

[1222] 1. Data Collection Methods

[1223] Sensors, smartwatches, and other devices collect biometric data, such as heart rate, acceleration, and electromyograms, in real time. Users wear these devices. The device receives this data and transmits it to a server. For example, if a user's heart rate spikes while running, the device sends that data to the server.

[1224] 2. Data Preprocessing and Analysis

[1225] The server first cleans the biometric data received from the device to remove noise. Then, it normalizes the data to make it easier to analyze. The server then uses the normalized data to perform biomechanics analysis and detect abnormalities in movement and load. For example, if a sudden change in heart rate is detected, the server records the abnormality and considers countermeasures.

[1226] 3. Training program proposals

[1227] The server generates a training program optimized for the athlete's characteristics based on the analysis results. The program includes details such as exercise content, intensity, number of repetitions, and rest time. For example, if it is determined that muscle strengthening is necessary, detailed guidelines such as "3 sets of 12 squats, with a load of 50% of body weight, with 90 seconds of rest between sets" will be generated. The device displays the generated training program to the user.

[1228] 4. Real-time advice and care delivery tools

[1229] During training, the device continuously transmits collected real-time data to the server, which immediately analyzes it and generates immediate feedback as needed. For example, if signs of fatigue are detected, the device will instruct the user to rest. If abnormal movements are detected, specific advice such as "Pay attention to the position of your toes to correct your running form" will be provided.

[1230] Specific examples

[1231] For example, to generate an optimal training program for Athlete A to improve muscle strength and prevent injury based on their heart rate, EMG data, and training history from the past week, the prompt would be:

[1232] Based on Athlete A's heart rate, EMG data, and training history from the past week, please generate an optimal training program for improving muscle strength and preventing injury. Please recommend specific exercises, number of repetitions, intensity, and rest periods.

[1233] An example of the output produced is:

[1234] Strength Training Program:

[1235] Exercise: Squats

[1236] Reps: 3 sets x 12 reps

[1237] Intensity: 50% of body weight

[1238] Rest Time: 90 seconds rest between sets

[1239] Additional tips: Focus on form, foot position and knee movement. After this exercise, do some gentle stretching to loosen up your muscles.

[1240] In this way, this system starts with collecting data from the device worn by the user, then analyzes the data on the server, creates training programs, and provides real-time feedback, all in an integrated manner, effectively supporting athletes in improving their performance and preventing injuries.

[1241] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1242] Step 1: Collect data

[1243] How it works: The user wears a smartwatch and sensors, which collect biometric data such as heart rate, acceleration, and electromyogram in real time. The smartwatch measures heart rate every 10 seconds and sends the data to the device.

[1244] Input: Biometric data from smartwatches and sensors.

[1245] Output: Real-time biometric data sent to the device.

[1246] Step 2: Sending data

[1247] Specific operation: The device sends the collected biometric data to the server at any time. The data is securely transmitted via the Internet.

[1248] Input: Biometric data collected on the device.

[1249] Output: Biometric data sent to the server.

[1250] Step 3: Preprocessing the data

[1251] Specific operation: The server first cleans the received biometric data, removes noise if it is present, and corrects outliers. Then, it normalizes the data and converts it into a unified format.

[1252] Input: Biometric data sent to the server.

[1253] Output: Cleaned and normalized biometric data.

[1254] Step 4: Analyze the data

[1255] Specific actions: The server performs biomechanical analysis based on the normalized data. This determines whether the athlete's movements and loads are appropriate. If abnormal movements or excessive loads are detected, they are recorded and countermeasures are considered.

[1256] Input: Cleaned and normalized biometric data.

[1257] Output: Biomechanical analysis results, assessment of abnormalities and loads.

[1258] Step 5: Generate a training program

[1259] Specific actions: Based on the analysis results, the server generates a training program that is optimal for the athlete's characteristics. The program includes details such as exercise content, intensity, number of repetitions, and rest time. For example, it creates guidelines such as "3 sets of 12 squats, with a load of 50% of body weight, and 90 seconds of rest between sets."

[1260] Input: Biomechanical analysis results.

[1261] Output: Training program details.

[1262] Step 6: View your training program

[1263] Specific operation: The device displays the generated training program to the athlete, who can then check the training plan for the day through the device.

[1264] Input: Training program details.

[1265] Output: The training program displayed on the terminal.

[1266] Step 7: Collect real-time data

[1267] Specific operation: During training, the device continues to collect biometric data in real time and transmits it to the server.

[1268] Input: Real-time biometric data during training.

[1269] Output: Real-time biometric data sent to the server.

[1270] Step 8: Real-time feedback

[1271] Specific operation: The server immediately analyzes the data received in real time and generates immediate feedback as needed. If signs of fatigue or abnormal movements are detected, the server notifies the athlete via the device with appropriate instructions. For example, it gives advice such as "You are showing signs of fatigue. Please take a break" or "Pay attention to the position of your toes to correct your running form."

[1272] Input: Biometric data received in real time.

[1273] Output: Real-time feedback displayed on the device.

[1274] These steps enable the system to consistently collect and analyze data, generate training programs, and provide real-time feedback, thereby effectively supporting athletes in improving their performance and preventing injuries.

[1275] (Application example 1)

[1276] 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."

[1277] Conventional industrial equipment does not adequately collect and analyze operational data, making it difficult to detect signs of abnormal operation early. As a result, abnormalities are often not noticed until a failure occurs, leading to sudden machine shutdowns and production delays. Furthermore, even when an abnormality is detected, there is a lack of means to provide immediate, appropriate feedback, making it difficult to operate industrial equipment efficiently. A new system is needed to solve these issues, improve operational performance, and prevent failures.

[1278] 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.

[1279] In this invention, the server includes means for collecting operational data of industrial equipment, means for performing machine operation analysis and identifying abnormal operations and loads, means for proposing individual operation schedules based on the analysis results, means for providing advice and correction instructions to the industrial equipment in real time, means for evaluating the fatigue state and predicting the risk of failure, and means for preprocessing, cleaning, and normalizing the collected data, thereby improving the operational performance of the industrial equipment, reducing the risk of failure, and enabling stable operation.

[1280] "Industrial equipment" is a general term for machines and devices used in factories and manufacturing facilities to automate, streamline, or support the production process.

[1281] "Operational data" refers to information relating to the movement of a device, including measurements such as position, speed, temperature, and vibration.

[1282] "Machine operation analysis" is a technology that analyzes the operating status of equipment based on collected operation data and distinguishes between normal and abnormal operation.

[1283] "Abnormal operation" refers to the occurrence of behavior that is different from normal in the operation of equipment, which may cause a malfunction if it continues.

[1284] "Load" refers to external factors such as force, pressure, and temperature that are applied to equipment when it is operating, and if this load becomes excessive it can have a negative effect on the equipment.

[1285] An "operation schedule" is a timetable for systematically managing the operation and running of equipment, and lists optimal operating times and maintenance timings.

[1286] "Advice" means appropriate instructions or suggestions regarding the operation of equipment, intended to facilitate adjustments to operation or maintenance.

[1287] "Correction instructions" refer to instructions on specific operating methods or changes to be made to deal with abnormal equipment operation or load.

[1288] "Fatigue" refers to a state in which equipment parts or systems begin to deteriorate due to prolonged or excessive use.

[1289] "Failure risk" is the probability of a failure occurring that can be predicted from the operation and condition of equipment, and by predicting this, it is possible to take measures in advance.

[1290] "Data preprocessing" refers to the process of preparing collected raw data in a form that is easier to analyze, and includes processes such as removing noise and normalizing the data.

[1291] "Cleaning" is the process of removing unnecessary information and errors from collected data.

[1292] "Normalization" is a process of standardizing data values ​​to a certain scale, and is performed to improve the accuracy of analysis.

[1293] This invention relates to an AI system aimed at improving the operational performance and preventing breakdowns of industrial equipment. This system collects and analyzes operational data, proposes optimal operation schedules for industrial equipment, and provides advice and correction instructions in real time. The system consists of the following main components:

[1294] Data collection methods

[1295] Sensors attached to industrial equipment collect operational data such as position, speed, temperature, and vibration in real time, and the collected data is sent to a server via the terminal.

[1296] Data Analysis Methods

[1297] The server preprocesses the collected operational data, removing noise and normalizing the data, and performs machine operation analysis to detect abnormalities in operation and load. It also evaluates fatigue status and predicts failure risk.

[1298] Operation schedule suggestion means

[1299] Based on the analysis results, the server generates an optimal operation schedule tailored to the characteristics of the industrial equipment. The schedule includes details such as operating hours, load balancing, and maintenance periods. The terminal displays the generated schedule to the industrial equipment operator.

[1300] Real-time advice and corrective action methods

[1301] During operation, the terminal continuously transmits real-time collected data to the server, which analyzes the data and generates immediate feedback as needed. If abnormal behavior or excessive load is detected, the terminal will notify the operator with appropriate corrective instructions.

[1302] System Operation

[1303] 1. Data collection: Sensors attached to industrial equipment continuously collect operational data in real time, such as position, speed, temperature, and vibration. For example, if a robot arm experiences a sudden rise in temperature while in operation, the data is sent to a server via the terminal.

[1304] 2. Data preprocessing and analysis: The server cleans the collected data and removes noise. It also normalizes the data to make it easier to analyze. Next, the server analyzes the machine's operation to detect abnormal behavior or excessive loads. For example, if analysis of vibration data reveals that a particular part is wearing out, the server records that information.

[1305] 3. Proposing an operation schedule: Based on the analysis results, the server generates an optimal operation schedule tailored to the characteristics of the industrial equipment. As a specific example, it proposes a short-term maintenance schedule taking into account parts that are deteriorating. The terminal displays the generated schedule to the operator, who then confirms the plan.

[1306] 4. Real-time advice and correction instructions: If an abnormality is detected during operation, the server immediately analyzes it and generates appropriate correction instructions. For example, specific advice such as "Please reduce the operating speed" or "A specific part needs to be replaced" is provided in real time via the terminal.

[1307] Hardware and software used

[1308] To implement the present invention, the following hardware and software are used:

[1309] Hardware: Industrial equipment, accelerometers, temperature sensors, vibration sensors.

[1310] Software: Python, TensorFlow, SQL Server, GUI development frameworks (such as Tkinter).

[1311] Examples and prompts

[1312] Specific examples

[1313] 1. Example 1: If the motor temperature suddenly rises while an industrial robot is operating, the system will issue a warning saying "Motor temperature is too high. Please reduce speed."

[1314] 2. Example 2: If abnormal vibration is detected, notify the user that "Abnormal vibration has been detected. Please change the operation route."

[1315] Prompt statement

[1316] Example prompts to enter into the Data Analysis module:

[1317] Check for motor temperature spikes and display warnings if necessary. Use temperature data from the past 24 hours.

[1318] Example prompts for the optimization algorithm:

[1319] "Optimize the operating schedule of industrial equipment and distribute the load to specific time periods. Consider detailed load data and operating history."

[1320] As described above, this system performs all processes from data collection and analysis to generating operation schedules and providing real-time feedback, thereby improving the operational performance of industrial equipment and preventing breakdowns.

[1321] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1322] Step 1:

[1323] Sensors collect operational data

[1324] Sensors attached to industrial equipment collect operational data such as position, speed, temperature, and vibration in real time. This data is sent to a server via a terminal. The input data is the measurement value from the sensor, and the output is the raw data sent to the server. For example, the temperature and vibration data of a robot arm in operation is constantly recorded and transferred to the terminal.

[1325] Step 2:

[1326] Data Preprocessing

[1327] The server cleans the received motion data, removes noise, and normalizes it to make it easier to analyze. The input data is raw data sent from the sensors, and the output is cleaned and normalized data. Specific operations include missing value imputation, outlier removal, and range scaling.

[1328] Step 3:

[1329] Data analysis

[1330] The server uses the preprocessed data to analyze machine operation to identify abnormal behavior and loads. A generative AI model is used for the analysis to detect anomalies and evaluate failure risks. The input data is preprocessed data, and the output is the analysis results, including abnormal behavior detection results and risk assessment data. Specifically, the AI ​​model analyzes sensor data to detect abnormal temperature increases and excessive vibrations.

[1331] Step 4:

[1332] Generate an operation schedule

[1333] Based on the analysis results, the server generates an optimal operation schedule tailored to the characteristics of the industrial equipment. The input data are the analysis results, and the output is a recommended operation schedule. In terms of specific operations, the system generates plans for maintenance periods and load balancing based on the analysis results and presents them to the operator.

[1334] Step 5:

[1335] Viewing Schedules

[1336] The terminal displays the generated operation schedule to the industrial equipment operator. The input data is the operation schedule sent from the server, and the output is data in a display format that can be checked by the operator. In concrete terms, the operation schedule is displayed on the terminal display, and the operator checks it.

[1337] Step 6:

[1338] Real-time data monitoring and feedback

[1339] During operation, the terminal continuously collects and transmits real-time operational data to the server. The server analyzes this data and generates immediate feedback as needed. The input data is real-time operational data, and the output is feedback such as advice and correction instructions. Specifically, if abnormal movement or excessive load is detected, instructions such as "Please reduce speed" are displayed in real time on the operator's terminal.

[1340] 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.

[1341] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries, and also provides a system that combines an emotion engine that recognizes athletes' emotions. This system collects and analyzes performance and emotion data, proposes optimal training programs for athletes, and provides advice and care in real time, thereby achieving overall performance improvement and injury prevention for athletes.

[1342] The system consists of the following main components:

[1343] 1. Data Collection Methods

[1344] The sensors and smartwatches worn by athletes collect biometric data such as heart rate, acceleration, and electromyograms, as well as emotional data from the athletes' facial expressions and voice. The devices receive this data and send it to a server.

[1345] 2. Emotion recognition means

[1346] The server uses the collected facial and voice data to analyze the athlete's emotional state using an emotion engine, which identifies emotions such as joy, sadness, anger, and stress.

[1347] 3. Data Analysis Methods

[1348] The server preprocesses the received biometric and emotional data, cleansing and normalizing them, and then performs biomechanics analysis to comprehensively evaluate abnormalities in movement and load, as well as emotional states.

[1349] 4. Training program proposal methods

[1350] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics and emotional state. The program includes details such as exercise content, intensity, number of repetitions, and rest periods. The terminal displays the generated program to the athlete.

[1351] 5. Real-time advice and care delivery methods

[1352] During training, the device continuously collects and transmits real-time biometric and emotional data to the server, which analyzes it and generates immediate feedback as needed. If signs of fatigue, abnormal movements, or emotional stress are detected, the device will notify the athlete and advise them to rest or modify their movements.

[1353] Specific flow and examples of program processing

[1354] To concretely explain how this system works, let's describe the program's processing in natural language:

[1355] 1. Data collection

[1356] The device collects real-time data from athletes, including their heart rate, electromyogram, facial expression data from a facial recognition sensor, and audio data from a voice recognition microphone. For example, if an athlete does not smile during training, their facial expression and audio data will also be collected.

[1357] 2. Data Preprocessing and Emotion Recognition

[1358] The server cleans the collected data, removes noise, and normalizes it to make it easier to analyze.

[1359] The emotion engine identifies the athlete's emotions from facial and voice data. For example, if a high level of stress or fatigue is detected, the emotion data is recorded.

[1360] 3. Data analysis and evaluation

[1361] The server uses normalized biometric and emotional data for biomechanical analysis, using machine learning algorithms to identify abnormalities in movement and stress.

[1362] The server uses data analysis to comprehensively assess an athlete's fatigue and emotional state, adjusting the intensity of specific training sessions if, for example, emotional stress is high.

[1363] 4. Training program proposals

[1364] Based on the analysis results, the server generates a training program that is optimal for the athlete's characteristics and emotional state. For example, it adds relaxation exercises when stress levels are high, and suggests high-intensity training when joy levels are high.

[1365] 5. Real-time advice and care

[1366] During training, the device continuously collects biometric and emotional data in real time and transmits it to a server, which then analyzes the data to detect fatigue, abnormalities in movement, and emotional changes in real time.

[1367] Based on the analysis results, real-time advice and care is provided. For example, if emotional stress is detected, it will suggest ways to relax, and if abnormal movements are detected, it will advise on the correct way to move.

[1368] In this way, by combining this system with an emotion engine, it is possible to comprehensively evaluate an athlete's physical and emotional state, suggest more accurate training programs, and provide real-time advice, thereby improving athlete performance and preventing injuries.

[1369] The processing flow will be explained below.

[1370] Step 1:

[1371] The device collects biometric data such as heart rate, acceleration, and electromyogram in real time from sensors worn by athletes. It also collects facial expression and voice data from facial recognition sensors and a voice recognition microphone for emotion recognition. This collected data is temporarily stored on the device.

[1372] Step 2:

[1373] The device transmits all collected biometric and emotional data to a server periodically, delivering the data in near real time.

[1374] Step 3:

[1375] The server receives the data sent from the device, which is first cleaned to remove noise and outliers and fill in missing data, improving the accuracy of the data.

[1376] Step 4:

[1377] The server normalizes the cleaned data. Normalization is the process of converting data from different scales into a unified scale to make it easier to analyze.

[1378] Step 5:

[1379] The server analyzes the normalized data with an emotion engine, which identifies the athlete's emotional state (e.g., joy, sadness, anger, stress, etc.) based on facial and voice data.

[1380] Step 6:

[1381] The server uses the emotion engine results and biological data for biomechanical analysis, which identifies abnormalities in the athlete's movements, loads, and fatigue.

[1382] Step 7:

[1383] Based on the analysis results, the server generates a training program optimized for the athlete's characteristics and emotional state. The program includes details such as exercise content, intensity, number of repetitions, and rest periods. For example, if an athlete is in a high stress state, relaxation exercises will be added.

[1384] Step 8:

[1385] The server transmits the generated training program to the terminal, which receives it and displays it to the user.

[1386] Step 9:

[1387] The user checks the training program presented and makes a training plan for the day. The terminal records the user's operations and transmits the necessary data to the server.

[1388] Step 10:

[1389] During training, the device continues to collect real-time biometric and emotional data and transmits it to the server, which is used to monitor the training progress in real time.

[1390] Step 11:

[1391] The server analyzes the data received in real time to detect the athlete's fatigue, abnormalities in their movements, and emotional changes. For example, if an athlete's heart rate spikes or stress is detected in their facial expressions, the server generates appropriate feedback.

[1392] Step 12:

[1393] The server generates real-time advice and care based on the analysis results and notifies the device. For example, it suggests resting if fatigue suddenly increases, instructs corrective actions if abnormal behavior is detected, and sends instructions for relaxation if emotional stress increases.

[1394] Step 13:

[1395] The device displays real-time advice and care notifications from the server to the user, who then checks these notifications and acts accordingly, for example, accepting suggestions for rest or modifying their behavior.

[1396] In this way, the system comprehensively analyzes biometric and emotional data and provides optimal training programs and real-time advice tailored to the athlete's condition, thereby improving their performance and preventing injuries.

[1397] Example 2

[1398] 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."

[1399] Conventional training systems for athletes focus on collecting and analyzing only biological data, and lack comprehensive evaluation and advice that takes into account the athlete's emotional state. This often leaves them inadequate for maximizing athletes' performance and preventing injuries. Real-time feedback and immediate care during training are also limited. To address this situation, a system is needed that can comprehensively analyze athletes' biological and emotional data and provide optimal training programs and real-time advice tailored to their individual characteristics.

[1400] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting the athlete's biological data and emotional data, means for cleaning and normalizing the collected data, means for identifying the athlete's emotions using an emotion engine, means for performing biomechanics analysis and identifying abnormalities in movement and load, means for generating a training program optimal for the athlete's characteristics and emotional state based on the analysis results, and means for providing advice and care to the athlete in real time. This makes it possible to comprehensively evaluate the athlete's physical and emotional state and propose more accurate training programs and provide real-time advice.

[1401] "Biometric data" refers to data that indicates the physiological state of the body, such as an athlete's heart rate, acceleration, and electromyogram.

[1402] "Emotional data" is data that indicates the emotional state of an athlete, obtained from facial expressions, voice, etc.

[1403] An "emotion engine" is software or algorithm that identifies an athlete's emotions from collected facial and voice data.

[1404] "Biomechanics analysis" is an analytical method that analyzes an athlete's movements and loads to identify abnormalities.

[1405] A "training program" is a program that includes the optimal exercise content, intensity, number of repetitions, rest time, etc., according to the athlete's characteristics and emotional state.

[1406] "Real-time advice" refers to instructions and advice provided to athletes instantly based on collected biometric and emotional data.

[1407] "Care" means the instruction and support to maintain and promote the athlete's physical and mental health.

[1408] "Cleaning" is the process of removing noise from collected data and preparing it in a form that can be analyzed.

[1409] "Normalization" is the process of converting data into a consistent format that makes it easier to analyze.

[1410] This invention relates to an AI system aimed at improving athletes' performance and preventing injuries. Furthermore, this invention provides a system that combines an emotion engine that recognizes athletes' emotions to achieve comprehensive performance improvement and injury prevention for athletes.

[1411] The system consists of the following main components:

[1412] 1. Data Collection Methods

[1413] The device collects biometric data such as heart rate, acceleration, and electromyogram in real time from sensors or smartwatches worn by athletes. The device also collects facial expression and voice data using a camera and voice recognition microphone. For example, when an athlete is running, the device collects not only heart rate and electromyogram data, but also facial expressions while running and comments on training in real time.

[1414] 2. Emotion recognition means

[1415] The server inputs the collected facial and voice data into an emotion engine to identify the athlete's emotions. The emotion engine utilizes machine learning models to assess the athlete's emotional state in real time. For example, it can analyze whether the athlete is feeling stressed based on facial expressions and tone of voice.

[1416] 3. Data Analysis Methods

[1417] The server cleans the collected biometric and emotional data to remove noise. It then normalizes the data to make it easier to analyze. It then performs biomechanical analysis to identify abnormalities in movement and load. For example, it can detect an anomaly if an athlete takes a stride that differs from their normal walking style.

[1418] 4. Training program proposal methods

[1419] Based on the analysis results, the server generates a training program optimized for the athlete's characteristics and emotional state. This program includes details such as exercise content, intensity, number of repetitions, and rest periods. For example, if the athlete is feeling stressed, it will suggest relaxation exercises.

[1420] 5. Real-time advice and care delivery methods

[1421] During training, the device continuously collects and transmits real-time biometric and emotional data to the server, which analyzes it and generates immediate feedback as needed. For example, if your heart rate spikes, the device will prompt you to take a short break.

[1422] To use the system, the generative AI model might be fed prompts like the following example:

[1423] "Please explain how an AI system that analyzes athletes' performance and emotional data and proposes optimal training programs works from the perspectives of the server, device, and user."

[1424] This system will enable a comprehensive assessment of an athlete's physical and emotional state, providing more accurate training program suggestions and real-time advice.

[1425] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1426] Step 1:

[1427] Data collection

[1428] The device collects biometric data in real time from sensors or smartwatches worn by athletes. For example, it acquires heart rate (collected data) and electromyograms. The input data is the athlete's real-time heart rate and electromyogram, and the output is a stream of collected biometric data.

[1429] The device uses a camera and a voice recognition microphone to collect facial and voice data of the athlete. For example, it captures the athlete's smile and tone of voice (emotion data). The input data is real-time captured information from the camera and microphone, and the output is a stream of emotion data.

[1430] Step 2:

[1431] Data Preprocessing

[1432] The server receives the biometric data and emotion data sent from the terminal, and the input data is the collected biometric data and emotion data.

[1433] The server cleans (denoises) and normalizes the data to make it easier to analyze. For example, it removes outliers from heart rate data and aligns them along a time axis. The output is cleaned and normalized biometric and emotion data.

[1434] Step 3:

[1435] emotion recognition

[1436] The server inputs the cleaned and normalized emotion data into the emotion engine to identify emotions. The input data is the preprocessed facial expression data and speech data.

[1437] The server uses an emotion engine to analyze emotions such as stress, joy, anger, etc. For example, a smiling face can be recognized as joy, and a low voice as stress. The output is data indicating the emotional state.

[1438] Step 4:

[1439] Data analysis

[1440] The server performs biomechanics analysis using the biometric data and emotion data, and the input data is the preprocessed biometric data and emotion data.

[1441] The server uses machine learning algorithms to identify abnormalities in movement and load, for example, detecting unusual running form. The output is an analysis result that includes the abnormal movement and load.

[1442] Step 5:

[1443] Generate a training program

[1444] The server generates a training program that is optimal for the athlete's characteristics and emotional state based on the analysis results. The input data are the biological data, the emotional data, and the analysis results.

[1445] The server automatically generates a training program including exercise type, intensity, number of repetitions, and rest time. For example, it suggests relaxation exercises when stress is high, and high-intensity training when energy is high. The output is a customized training program.

[1446] Step 6:

[1447] Training Program Notification

[1448] The server sends the generated training program to the terminal, and the input data is the generated training program.

[1449] The device displays the information to the athlete and notifies them of the next action. For example, specific instructions such as "Next, stretch after 10 minutes of running" are displayed. The output is the notification to the athlete.

[1450] Step 7:

[1451] Real-time monitoring and feedback

[1452] The device continuously transmits the biological data and emotional data collected in real time during training to the server. The input data is the data collected in real time.

[1453] The server analyzes the data received in real time and generates immediate feedback if necessary. For example, if your heart rate spikes, it will generate a prompt to "take a short break." The output is real-time feedback.

[1454] The device provides real-time advice to the athlete based on feedback from the server. For example, if there is an abnormality in movement, specific advice such as "Check your right foot step" is displayed. The output is real-time advice to the athlete.

[1455] Through these steps, the system will be able to perform detailed analysis of athletes' biometric and emotional data, and provide training programs and real-time advice tailored to their individual characteristics.

[1456] (Application example 2)

[1457] 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."

[1458] Previous systems have focused on improving athletes' performance and managing their workload, but few systems have considered the influence of emotions. Furthermore, technology for managing passenger emotions and comfort levels in real time in autonomous vehicles is still immature, and a method to improve the overall passenger experience is needed. Therefore, a new system that utilizes emotion data is needed in the context of both athletes and autonomous vehicles.

[1459] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting athlete performance data, means for performing biomechanics analysis to identify abnormal movements and loads, means for proposing an individual training program based on the analysis results, means for providing advice and care to the athlete in real time, means for collecting passenger emotional data, means for analyzing the collected emotional data and evaluating comfort levels, means for automatically adjusting the in-vehicle environment based on the evaluation results, and means for suggesting entertainment and relaxation to passengers based on their emotional states. This makes it possible to optimize athlete performance while preventing injuries and managing loads, and enables real-time management of passenger emotions and comfort levels in autonomous vehicles.

[1460] "Means for collecting athlete performance data" refers to equipment that uses sensors or devices worn by athletes to obtain biometric data such as heart rate, electromyogram, and acceleration.

[1461] "Means for conducting biomechanical analysis and identifying abnormal movements and loads" refers to algorithms and programs that analyze collected biometric data and identify any abnormalities in an athlete's movements or loads.

[1462] The "means for proposing individual training programs based on the analysis results" is a system for generating training programs specifically for athletes based on the results of data analysis.

[1463] "Means for providing athletes with real-time advice and care" refers to applications that provide athletes with immediate feedback and care instructions based on data collected during training.

[1464] The "means for collecting passenger emotional data" is a device that uses a camera or microphone to capture passenger facial expressions and voices and collect emotional data based on them.

[1465] The "means for analyzing collected emotion data and evaluating the comfort level" is a system that analyzes the acquired emotion data and evaluates the comfort level of passengers using the analysis results.

[1466] The "means for automatically adjusting the in-car environment based on the evaluation results" is a device that automatically sets and changes the in-car environment, such as temperature, lighting, and music, based on the evaluation results of emotional data.

[1467] The "means for suggesting entertainment and relaxation methods to passengers based on their emotional state" is a system that presents entertainment content and relaxation methods appropriate for passengers based on the results of analyzing their emotions.

[1468] This invention relates to an AI system for improving athletic performance and injury prevention, and a passenger comfort management system for autonomous vehicles. The system includes the following main components and processes:

[1469] Data collection

[1470] The server uses sensors and devices to collect biometric data from athletes and emotional data from passengers. Specifically, it uses devices such as smartwatches worn by athletes, accelerometers, electromyogram sensors, cameras, and microphones to collect heart rate, electromyogram, acceleration, facial expression data, and voice data. To collect emotional data from passengers in the in-car environment, it uses cameras and microphones installed in the vehicle.

[1471] Data preprocessing and emotion recognition

[1472] The server cleans the collected data and removes noise. It uses Python and R libraries to normalize the data and make it easier to analyze. For emotion recognition, it uses emotion recognition models built with TensorFlow and Keras. For example, if a passenger is not smiling, their facial expression data is also collected and analyzed along with the voice data.

[1473] Data analysis and evaluation

[1474] The server performs biomechanics analysis using normalized biometric and emotional data. It uses machine learning algorithms, such as scikit-learn and TensorFlow, to identify abnormalities in movement and load. To assess passenger comfort, it generates a comfort score based on the emotional data.

[1475] Training program suggestions and automatic adjustment of the in-car environment

[1476] Based on the analysis results, the server generates an optimal training program tailored to the athlete's characteristics and emotional state. The program includes details such as exercise type, intensity, number of repetitions, and rest periods. Inside the autonomous vehicle, a control program is executed that automatically adjusts the in-car environment, including temperature, lighting, and music, based on the evaluation results of the emotional data.

[1477] Real-time advice and care

[1478] During training or while the vehicle is in operation, the device continuously collects real-time biometric and emotional data and transmits it to the server. The server analyzes this data and provides immediate feedback. For example, if fatigue or abnormal movements are detected, the device will instruct the athlete to rest or correct their movements. It will also suggest relaxation and entertainment options based on the passenger's emotional state.

[1479] Examples of specific examples and prompts

[1480] For example, when an athlete is training, the system can detect their fatigue level in real time using electromyograms and heart rate data and immediately instruct them to rest. Based on passenger emotional data, the in-car environment can be optimally adjusted to provide a comfortable travel experience.

[1481] Example prompts to input to a generative AI model:

[1482] 1. "Suggest a list of music to play when passengers are happy."

[1483] 2. "Decide on environmental settings for passengers experiencing stress and adjust temperature and lighting settings for accountability."

[1484] 3. "Analyze real-time sentiment data and show passengers the entertainment they want."

[1485] In this way, the system, combined with the emotion engine, can comprehensively assess the athlete's physical and emotional state, improving passenger comfort in autonomous vehicles.

[1486] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1487] Step 1:

[1488] The device collects biometric and emotional data from athletes or passengers. Specifically, it uses devices such as smartwatches worn by athletes, accelerometers, electromyogram sensors, cameras, and microphones to obtain heart rate, electromyogram, acceleration, facial expression data, and voice data in real time. The device then transmits this data to a server.

[1489] Step 2:

[1490] The server cleans the received data and removes noise. Specifically, it uses data preprocessing libraries in Python and R to impute missing values ​​and remove outliers from the collected biometric and emotional data. The input data includes biometric signals from biometric sensors and camera and microphone data, and the output data is clean data.

[1491] Step 3:

[1492] The server normalizes the cleaned data and prepares it for easier analysis. Specifically, it scales and standardizes the biometric and emotional data. Here, the input data is the cleaned biometric and emotional data, and the output data is the normalized data.

[1493] Step 4:

[1494] The server uses the normalized data to perform emotion recognition. Specifically, it inputs the data into an emotion recognition model built using TensorFlow and Keras to analyze the emotional state. The input data includes normalized facial expression data and voice data, and the output data is the emotional state (happiness, sadness, anger, stress, etc.).

[1495] Step 5:

[1496] The server performs biomechanics analysis using normalized biometric and emotional data. It uses machine learning algorithms to identify abnormalities in movement and stress. Specifically, it uses scikit-learn and TensorFlow to apply a motion analysis model to detect abnormal movements and overload. The input data is normalized biometric and emotional data, and the output data includes abnormal movements and stress.

[1497] Step 6:

[1498] The server generates a training program that matches the athlete's characteristics and emotional state based on the analysis results. Specifically, if overload or abnormal movement is detected, it provides a program that includes appropriate exercise content, intensity, number of repetitions, rest periods, etc. The input data are the biomechanics analysis results and emotion analysis results, and the output data includes a training program.

[1499] Step 7:

[1500] The server evaluates the passenger's comfort level based on emotional data in the autonomous vehicle and automatically adjusts the in-car environment. Specifically, if the emotional state indicates stress, it adjusts the temperature and lighting and plays relaxation music. The input data is the emotion analysis results, and the output data includes the in-car environment settings.

[1501] Step 8:

[1502] The terminal continuously transmits the data collected in real time to the server, which then provides immediate feedback. Specifically, it displays rest instructions and movement modification advice to athletes, and relaxation and entertainment suggestions to passengers. The input data is real-time biometric and emotional data, and the output data includes the content of the feedback.

[1503] This way, proper care and feedback can be provided to both the athlete and the passengers at each step.

[1504] 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.

[1505] 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.

[1506] 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 robot 414.

[1507] 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.

[1508] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1509] 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.

[1510] 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).

[1511] 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.

[1512] 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."

[1513] 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.

[1514] 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).

[1515] 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.

[1516] 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.

[1517] 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.

[1518] 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.

[1519] 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.

[1520] 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.

[1521] 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.

[1522] 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.

[1523] 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.

[1524] 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.

[1525] The following is further disclosed regarding the above embodiment.

[1526] (Claim 1)

[1527] A means of collecting athlete performance data;

[1528] A means of performing biomechanical analysis to identify abnormal movements and loads;

[1529] A means for proposing individual training programs based on the analysis results;

[1530] a means to provide real-time advice and care to athletes;

[1531] A system including:

[1532] (Claim 2)

[1533] 10. The system of claim 1, further comprising means for assessing fatigue state and predicting injury risk.

[1534] (Claim 3)

[1535] 10. The system of claim 1, further comprising means for pre-processing, cleaning and normalizing the collected data.

[1536] "Example 1"

[1537] (Claim 1)

[1538] A means of collecting athlete performance data;

[1539] means for transmitting data to a server;

[1540] A means of preprocessing, cleaning and normalizing the collected data;

[1541] A means of performing biomechanical analysis to identify abnormal movements and loads;

[1542] means for generating an individual training program based on the analysis results;

[1543] a means for displaying the generated training program on a terminal;

[1544] a means to provide real-time advice and care to athletes;

[1545] A system including:

[1546] (Claim 2)

[1547] 10. The system of claim 1, further comprising means for assessing fatigue state and predicting injury risk.

[1548] (Claim 3)

[1549] 10. The system of claim 1, further comprising means for collecting and transmitting data to a server in real time during training.

[1550] "Application Example 1"

[1551] (Claim 1)

[1552] means for collecting operational data of the industrial equipment;

[1553] A means of performing machine motion analysis to identify abnormal motions and loads;

[1554] A means for proposing an individual operation schedule based on the analysis results;

[1555] a means of providing real-time advice and corrective instructions to industrial equipment;

[1556] A system including:

[1557] (Claim 2)

[1558] 10. The system of claim 1, further comprising means for assessing fatigue state and predicting risk of failure.

[1559] (Claim 3)

[1560] 10. The system of claim 1, further comprising means for pre-processing, cleaning and normalizing the collected data.

[1561] "Example 2: Combining Emotion Engines"

[1562] (Claim 1)

[1563] a means for collecting biometric and emotional data of the athlete;

[1564] A means of cleaning and normalizing the collected data;

[1565] a means for identifying an emotion of the athlete using an emotion engine;

[1566] A means of performing biomechanical analysis to identify abnormalities in movement and load,

[1567] A means for generating a training program that is optimal for the characteristics and emotional state of the athlete based on the analysis results;

[1568] a means to provide real-time advice and care to athletes;

[1569] A system including:

[1570] (Claim 2)

[1571] 10. The system of claim 1, further comprising means for assessing fatigue state and predicting injury risk.

[1572] (Claim 3)

[1573] 10. The system of claim 1, further comprising means for collecting and continuously analyzing biometric and emotional data in real time.

[1574] "Application example 2 when combining emotion engines"

[1575] (Claim 1)

[1576] A means of collecting athlete performance data;

[1577] A means of performing biomechanical analysis to identify abnormal movements and loads;

[1578] A means for proposing individual training programs based on the analysis results;

[1579] a means to provide real-time advice and care to athletes;

[1580] a means for collecting passenger sentiment data;

[1581] A means for analyzing the collected emotional data and evaluating the comfort level;

[1582] A means for automatically adjusting the in-vehicle environment based on the evaluation results;

[1583] a means of suggesting entertainment or relaxation to passengers based on their emotional state;

[1584] A system including:

[1585] (Claim 2)

[1586] 10. The system of claim 1, further comprising means for assessing fatigue state and predicting injury risk.

[1587] (Claim 3)

[1588] 10. The system of claim 1, further comprising means for pre-processing, cleaning and normalizing the collected data. [Explanation of symbols]

[1589] 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 performance data; A means of performing biomechanical analysis to identify abnormal movements and loads; A means for proposing individual training programs based on the analysis results; a means to provide real-time advice and care to athletes; A system including:

2. The system of claim 1 , further comprising means for assessing fatigue state and predicting injury risk.

3. The system of claim 1 further comprising means for pre-processing, cleaning and normalizing the collected data.

Images