system

Abstract

Provide a system. [Solution] means for receiving training data, nutritional data, and physical information from a user; A means to collect and store training data, nutrition data, and form data of top athletes, A means for analyzing the accumulated data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for users; a means for transmitting the generated training method, nutritional intake method, and form correction points to a user terminal; The system includes a means for analyzing feedback received from users and updating the recommendations.

Description

[Technical Field]

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

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

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

[0004] One of the challenges faced by children aiming to become top athletes and their parents is the inability to accurately grasp appropriate training methods, nutritional intake methods, and form corrections. In particular, coaches often rely on their experience and intuition, and instruction tends to be unbased on scientific evidence. This can lead to injuries and poor physical condition due to excessive practice and inadequate nutritional intake. Furthermore, access to the knowledge and data of top-level athletes is limited, and there is a lack of information on standard training and nutritional intake methods. A new system to solve this problem is needed. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes a means for receiving training data, nutritional data, and physical information from users, a means for collecting and storing training data, nutritional data, and form data of top athletes, a means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for users, a means for transmitting the generated training methods, nutritional intake methods, and form correction points to a user terminal, and a means for analyzing feedback received from users and updating the suggestions.Furthermore, a system is constructed that analyzes data input from the user terminal, receives advertising data from sporting goods manufacturers and nutritional food manufacturers, and displays it on the user terminal to provide specific suggestions and product information for training and nutritional intake.

[0006] "User" means an individual or their guardian who uses the system and provides training data, nutritional data, and physical information.

[0007] "Training data" refers to information such as the content, frequency, and intensity of the exercise or training the user has performed.

[0008] "Nutrition data" is information about the meals and nutritional supplements a user consumes.

[0009] "Physical information" refers to information about the user's weight, height, body fat percentage, muscle mass, and other physical characteristics.

[0010] A "top athlete" is an athlete who has achieved outstanding results at a competitive level.

[0011] "Form data" refers to videos and still images of top athletes' athletic form, as well as numerical data analyzed from these.

[0012] A "generative AI model" is an artificial intelligence model that generates optimal training methods, nutritional intake methods, and form correction points based on given data.

[0013] A "user terminal" is a device that allows a user to access the system and input or output data.

[0014] "Feedback" is data that users send back to the system by providing their results and impressions of implementing the suggestions.

[0015] "Advertising data" refers to product information and advertising content provided by sporting goods manufacturers and nutritional food manufacturers and presented to users. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention relates to a system that enables users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, and form correction points. Specific examples of the present invention are described below.

[0038] 1. Server system overview:

[0039] The server has the function of collecting and storing training data, nutritional data, and form data of top athletes. This data is stored in a database and used for analysis. The server also has the function of receiving data entered by users (training data, nutritional data, physical information) and analyzing it using a generative AI model. Based on the analysis results, the generative AI model generates optimal training methods, nutritional intake methods, and form correction points for the user. The generated suggestions are then sent to the user's device.

[0040] 2. Device Features:

[0041] The user terminal has the function of inputting data from the user via an input interface and sending it to the server. This data includes the user's training history, dietary content, and physical information. The user terminal also has the function of receiving suggestions sent from the server and displaying them. Furthermore, the user can input the results and impressions of their training and nutritional intake as feedback and send it to the server.

[0042] 3. User Action:

[0043] The user first enters their physical information, training history, and dietary details into the user device. The device then sends this data to the server, which receives it and begins analysis. Using a generative AI model, the system generates training methods, nutritional intake methods, and form correction points suited to the user, and sends these suggestions to the user's device. The user then performs training and nutritional intake based on the suggestions, and enters the results and impressions into the device to send feedback to the server. The server then reanalyzes the data based on the received feedback and updates the suggestions.

[0044] 4. Example:

[0045] High school athlete users input their weight, height, dietary habits, and training history into their device and send it. The server receives this data and analyzes it by comparing it with a database of top athletes. As a result, it generates an optimal training menu for the user (e.g., running and strength training five times a week), a nutritional intake plan (e.g., a high-protein, low-fat diet), and form corrections (e.g., improving arm swing), and sends these to the user's device. The user follows these suggestions to train and consume nutritional information, and then provides feedback on the results to the server. By repeating this cycle, the system continuously supports the user's growth.

[0046] In this way, the present invention allows users to obtain scientifically based optimal training methods, nutritional intake methods, and form corrections, thereby improving their competitive level. Furthermore, as the generative AI model continuously learns based on feedback, the accuracy of its suggestions improves, allowing it to provide support that is even more tailored to the individual needs of the user.

[0047] The processing flow will be explained below.

[0048] Step 1:

[0049] The user inputs physical information such as weight, height, training history, dietary details, and activity data into the user terminal.

[0050] Step 2:

[0051] The terminal transmits the input data to the server.

[0052] Step 3:

[0053] The server receives the data sent by the user and stores it in a database.

[0054] Step 4:

[0055] The server collects training data, nutritional data, and form data of top athletes and stores it in a database.

[0056] Step 5:

[0057] The server performs preprocessing to analyze the accumulated data, for example, extracting form keyframes from video data and converting them into numerical data.

[0058] Step 6:

[0059] The server inputs the preprocessed data into a generative AI model, which learns the successful patterns of top athletes.

[0060] Step 7:

[0061] The server uses the received user data and a trained AI model to generate optimal training methods, nutritional intake methods, and form corrections for the user.

[0062] Step 8:

[0063] The server transmits the generated proposal content to the user terminal.

[0064] Step 9:

[0065] The terminal displays the suggestions received from the server to the user, who then checks the suggested training method, nutrition plan, and form correction points.

[0066] Step 10:

[0067] The user follows the suggestions to train and take in nutrients, and then enters the results and impressions into the device.

[0068] Step 11:

[0069] The terminal transmits the input feedback data to the server.

[0070] Step 12:

[0071] The server analyzes the received feedback and retrains the generative AI model to improve the accuracy of the suggestions.

[0072] Step 13:

[0073] The server receives advertising data from sporting goods manufacturers and nutritional food manufacturers and generates optimal advertisements to display on user terminals.

[0074] Step 14:

[0075] The device displays the advertisements and recommended product information received from the server to the user, who can then select the products they are interested in and proceed with the purchase.

[0076] Example 1

[0077] 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."

[0078] Conventional systems were not sufficient for users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, and form correction points. In particular, it was difficult to efficiently reflect user feedback and provide suggestions for continuous improvement. There was also a need to quickly and accurately transmit user-entered data to the server and improve the accuracy of analysis.

[0079] 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.

[0080] In this invention, the server includes a means for receiving training data, nutritional data, and physical information from the user, a means for collecting and storing training data, nutritional data, and form data of top athletes, and a means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user. This allows the user to obtain optimal training methods, nutritional intake methods, and form correction points based on scientific evidence in a timely manner. In addition, data entered through the user's terminal can be quickly sent to the server, allowing for continuous improvement in the accuracy of the analysis.

[0081] A "user" is an individual who aims to become a top athlete by using this system to improve their own training methods, nutritional intake methods, and form correction points.

[0082] "Training data" refers to a record of the type, frequency, intensity, duration, etc. of exercise a user is performing.

[0083] "Nutrition data" refers to information such as the user's daily diet, calorie intake, and nutrient ratios.

[0084] "Physical information" refers to basic data about the user's body, such as height, weight, and body fat percentage.

[0085] "Server" means a central data processing unit that collects, stores, and analyzes data received from users, and generates and transmits proposals.

[0086] The "generative AI model" is an artificial intelligence model that analyzes accumulated data and automatically generates optimal training methods, nutritional intake methods, and form correction points for each user.

[0087] "Training method" refers to the individual exercises or programs that a user performs, including the frequency of exercise per week and the type of exercise.

[0088] "Nutrition method" refers to the dietary content and nutrient intake balance that a user should have.

[0089] "Form correction points" refer to areas where the user can improve their body movements and posture during exercise.

[0090] "Feedback" refers to the results and impressions of the user when they carry out the suggested training and nutritional intake methods.

[0091] A "user terminal" is an electronic device that a user uses to input data and communicate with a server.

[0092] The present invention relates to a system that enables users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, and form correction points. Specific embodiments of the present invention are described below.

[0093] Server Configuration

[0094] The server is equipped with a high-performance processor (e.g., Intel Xeon), large memory capacity (128 GB RAM), and high-speed storage (2 TB SSD). A database management system (e.g., MySQL®) and a generative AI model (e.g., TENSORFLOW®) are installed on the server. The server has the following main functions:

[0095] 1. Receive training data, nutrition data, and physical information from the user.

[0096] 2. Collect training data, nutritional data, and form data of top athletes and store it in a database.

[0097] 3. Analyze the received and accumulated data and use a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user.

[0098] 4. The generated proposal is sent to the user's device.

[0099] 5. Analyze the feedback received from users and update the suggestions.

[0100] Device configuration

[0101] The user device is a mobile information terminal such as a smartphone or tablet, equipped with an input interface. A dedicated mobile application (e.g., an app developed with React Native) is installed on the device, and has the following main functions:

[0102] 1. The user enters their physical information, training history, and dietary information.

[0103] 2. Send the entered data to the server.

[0104] 3. Receive and display the proposal sent from the server.

[0105] 4. The user inputs the results and impressions of their training and nutritional intake as feedback and sends it to the server.

[0106] User operations

[0107] First, the user enters their physical information (e.g., height, weight), training history (e.g., weekly exercise frequency, type of exercise), and dietary details into the user device. The entered data is sent to the server via the device. The server receives the data and stores it in a database. The data is then analyzed using a generative AI model to generate the optimal training method, nutritional intake method, and form correction points for the user. The generated suggestions are sent to the user's device and presented to the user. The user then performs training and nutritional intake based on the presented suggestions. The results and impressions are entered into the user device and fed back to the server. The server re-analyzes the feedback and updates the suggestions.

[0108] Specific examples

[0109] For example, a high school athlete enters their weight, height, diet, and training history into a form on a smartphone app. An example input might be "height 180 cm, weight 75 kg, breakfast: salad and yogurt, training: 30 minutes of running." When this information is sent to the server, it is saved in a database and analyzed using a generative AI model. As a result, recommendations are generated for the user, such as "strength training five times a week, high-protein, low-fat diet, form correction: arm swing," and sent to the user's device. The user then trains and takes in nutrients based on the recommendations, and as a result, provides feedback such as "I feel like my muscle strength has improved in a week," which is then sent to the server. Based on this feedback, the server performs further analysis to improve the accuracy of the recommendations.

[0110] Prompt Sentence Examples

[0111] "Generate a suitable workout schedule for a user who is 180cm tall, weighs 75kg, and trains four times a week."

[0112] The above is an embodiment of the present invention. This system allows users to obtain optimal training methods, nutritional intake methods, and form corrections based on scientific evidence. In addition, the generative AI model continuously learns based on user feedback, improving the accuracy of its suggestions.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1:

[0115] User data entry and submission

[0116] The user uses the device to input their physical information, training history, and dietary details. Data input by the user may include, for example, "height 180 cm, weight 75 kg, diet: salad and yogurt for breakfast, 30 minutes of running for training." After completing the input, the device formats the user data and sends it to the server. The input at this stage is all the personal data the user provides to the device, and the output is the formatted user data and its transmission to the server.

[0117] Step 2:

[0118] Receiving and storing data

[0119] The server immediately receives the user data from the terminal. The received data is stored in a database system (e.g., MySQL) on the server. Specifically, the server stores the data in the database as "User ID 123, height 180 cm, weight 75 kg, diet: salad and yogurt for breakfast, 30 minutes of running for training." The input is the user data from the terminal, and the output is the data stored in the database on the server.

[0120] Step 3:

[0121] Data analysis

[0122] The server retrieves the saved user data from the database and passes it to a generative AI model (example of use: TensorFlow). The generative AI model performs analysis based on the user data and accumulated data on top athletes. As a result, it generates the optimal training method, nutritional intake method, and form correction points for the user. For example, analysis of the input user data may generate suggestions such as "strength training five times a week, a high-protein, low-fat diet, and form correction points: arm swing." The input is the user data retrieved from the database, and the output is the optimal suggestion from the generative AI model.

[0123] Step 4:

[0124] Submit your proposal

[0125] The server sends the suggestions output from the generative AI model to the user's device. For example, suggestions such as "strength training five times a week, high-protein, low-fat diet, and form corrections: arm swing" are sent to the user's device. The input is the generated suggestions, and the output is the data sent to the user's device.

[0126] Step 5:

[0127] User execution and feedback

[0128] The user checks the suggestions sent from the server and performs the training and diet based on them. The results and impressions of the training are input into the user's device. For example, the user may input their impressions after training, such as "I feel like my muscle strength has improved in a week," and send the feedback to the server via the device. The input is the user's results and impressions, and the output is the feedback data sent to the server.

[0129] Step 6:

[0130] Analyzing feedback and updating suggestions

[0131] The server receives feedback sent by the user and stores it in a database. Based on the stored feedback, the generative AI model is used again to analyze it and improve the accuracy of the suggestions. The updated suggestions are then sent back to the user's device. For example, as a result of analyzing the feedback "I feel like my muscle strength has improved," a new suggestion "Slightly increase the load of your strength training" is generated and sent to the user's device. The input is the feedback data, and the output is the updated suggestions.

[0132] keyword

[0133] Generative AI model, prompt sentence

[0134] (Application example 1)

[0135] 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."

[0136] Previous user training systems and factory robot motion optimization systems lacked a way to efficiently provide optimal training methods or correction points for robot motion. Furthermore, they lacked a system for quickly updating suggestions based on user feedback, making it difficult to provide support that met individual needs.

[0137] 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.

[0138] In this invention, the server includes means for receiving training data, nutritional data, and physical information from users, means for collecting and storing training data, nutritional data, and form data of top athletes, means for collecting and storing factory robot motion data, means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, form correction points, and robot motion correction points for users, means for transmitting the generated training methods, nutritional intake methods, form correction points, and robot motion correction points to a user terminal, and means for analyzing feedback received from users and updating the suggested content, thereby making it possible to provide optimal training methods and motion correction points based on individual needs.

[0139] "User" is the person providing the training data, nutritional data, and physical information or the operator of the equipment.

[0140] "Training data" refers to information that refers to the history and details of the exercises and practices that a user has performed.

[0141] "Nutrition data" refers to information about the dietary content and nutrients that a user has consumed.

[0142] "Physical information" refers to physical data such as the user's weight, height, and body fat percentage.

[0143] A "top athlete" is an athlete who performs at the highest level in their field.

[0144] "Form data" is data that includes details of posture and movement during exercise or movement.

[0145] "Factory robot" refers to automated machinery used in factories and manufacturing environments.

[0146] "Operation data" refers to the history and performance data of the operations performed by factory robots.

[0147] A "generative AI model" is an artificial intelligence algorithm that analyzes accumulated data and calculates optimal training methods and movement correction points.

[0148] "Feedback" refers to information provided by the user about the results and impressions of training and nutritional intake.

[0149] "Analysis" is the process of examining data in detail and extracting meaningful information.

[0150] "Suggested content" refers to training methods, nutritional intake methods, form correction points, or robot movement correction points that are shown to the user by the generative AI model.

[0151] This invention relates to a system that enables users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, form correction points, or factory robot movement correction points. This system collects various data from users, analyzes it using a generative AI model, and provides appropriate suggestions to the users.

[0152] 1. System configuration:

[0153] server:

[0154] The server mainly collects, stores, and analyzes data, and transmits the results. Specifically, it runs a generative AI model using Python and TensorFlow, and stores the data in a PostgreSQL database. The MQTT protocol is used for data transmission and reception.

[0155] User device:

[0156] The user device receives training data, nutritional data, physical information, and feedback from the user via an input interface. This data is then sent to the server using the MQTT protocol. The server also displays the optimal training method, nutritional intake method, and form correction points sent from the server.

[0157] Factory robots:

[0158] Factory robots use sensors to collect operational data and send it to a server. They then execute the operational correction points sent from the server, collect operational data again, and send it to the server to optimize their operations.

[0159] 2. Data flow:

[0160] Data collection:

[0161] Users use the device's input interface to input data such as physical information, training history, and dietary details, while factory robots equipped with sensors collect movement data.

[0162] Data transmission:

[0163] The user terminal and the factory robot send the collected data to the server via the MQTT protocol.

[0164] Data Analysis:

[0165] The server uses Python and TensorFlow to analyze the received data and calculates optimal training methods, nutritional intake methods, form corrections, or robot movement corrections using a generative AI model. The analysis results are stored in a PostgreSQL database.

[0166] Generate and submit a proposal:

[0167] The optimization proposals generated by the server are sent to the user terminal and factory robot via the MQTT protocol.

[0168] 3. Example:

[0169] For example, when a high school athlete inputs and sends their weight, height, dietary habits, and training history to a device, this data is compared with that of top athletes and analyzed by the server. As a result, an optimal training menu and nutrition plan for the user is generated and sent to the user's device. Similarly, the operation data of a factory robot can be sent to the server, and optimal operation correction points can be received.

[0170] An example of a prompt would be, "Use a generative AI model to analyze the operation data of a factory robot and suggest optimized operation patterns and error correction points."

[0171] This allows users to efficiently obtain optimal training methods and movement corrections tailored to their individual needs.In addition, the generative AI model continuously learns based on user feedback and newly collected data, enabling it to improve the accuracy of its suggestions.

[0172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0173] Step 1:

[0174] The user device uses an input interface to collect data from the user, such as physical information, training history, and dietary details. The input data includes the user's weight, height, exercise details, and dietary details. This data is formatted to be stored in a database and then sent to the server using the MQTT protocol.

[0175] Step 2:

[0176] The server receives data sent from the user's device, including physical information, training history, and dietary details. The server stores this data in a PostgreSQL database.

[0177] Step 3:

[0178] Factory robots use sensors to collect operational data, including the robot's movement patterns, speed, error rate, etc. This data is also sent to a server using the MQTT protocol.

[0179] Step 4:

[0180] The server receives operation data sent from the factory robots and stores it in a PostgreSQL database, allowing for centralized management of both user data and robot data.

[0181] Step 5:

[0182] The server uses Python and TensorFlow to analyze data stored in PostgreSQL. Specifically, it uses a generative AI model to generate optimal training methods, nutritional intake methods, form corrections, and factory robot operation corrections for each user. The analysis uses data from past top athletes and existing optimization algorithms.

[0183] Step 6:

[0184] The server transmits the generated training methods, nutritional intake methods, form correction points, and factory robot operation correction points to the user terminal and the factory robot again via the MQTT protocol.

[0185] Step 7:

[0186] The user terminal receives the suggestions sent from the server and displays them to the user, who then performs training and nutritional intake based on them.

[0187] Step 8:

[0188] The factory robot receives the operation correction points sent from the server and corrects and optimizes its operation. The robot collects the corrected operation data again and sends it to the server.

[0189] Step 9:

[0190] The results and impressions obtained by the user and the factory robot are entered as feedback into the input interface of the user terminal and the robot, and sent to the server. The server analyzes the received feedback and stores and updates it in the PostgreSQL database.

[0191] Step 10:

[0192] The server updates the generative AI model based on the received feedback and newly collected data, and performs re-analysis to improve the accuracy of the suggestions, thereby repeatedly providing optimal suggestions for the user and the robot, enabling continuous performance improvement.

[0193] 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.

[0194] The present invention relates to a system that supports a user in more effectively managing their training and nutrition, enabling them to perform at the level of a top athlete. Specific examples of the present invention are described below.

[0195] 1. Server system overview:

[0196] The server has the ability to receive training data, nutritional data, and physical information from users and store it in a database. The server also collects training data, nutritional data, and form data from top athletes and stores it in a database. The server then uses a generative AI model to analyze the accumulated data and generate optimal training menus, nutrition plans, and form correction suggestions for each user. It also has the ability to send suggestions to the user's device and update the suggestions based on feedback received from the user.

[0197] 2. Emotion engine feature additions:

[0198] The system also incorporates an emotion engine, which has the ability to collect and analyze emotional data from the user's facial expressions, voice tone, text input, etc. The emotional data is used to understand the user's current psychological state and reflect it in training and nutrition plan suggestions.

[0199] 3. Device Features:

[0200] The user terminal has the function of inputting data from the user via an input interface and sending it to the server. This data includes the user's training history, dietary content, and physical information. The user terminal also has the function of receiving suggestions sent from the server and displaying them. Furthermore, the user can input the results and impressions of their training and nutritional intake as feedback and send them to the server. It also has an interface for collecting emotional data.

[0201] 4. User Action:

[0202] The user first enters their physical information, training history, and dietary details into the user device. The device sends this data to the server, which receives it and begins analysis. A generative AI model is used to generate training methods, nutritional intake methods, and form correction points that are suitable for the user. An emotion engine is also used to collect and analyze the user's emotional data and reflect this in the suggestions. The generated suggestions are sent to the user device. The user then performs training and nutritional intake based on the suggestions, and enters the results and impressions into the device, sending feedback to the server. The server analyzes the received feedback and emotional data to improve the accuracy of the suggestions.

[0203] 5. Examples:

[0204] A high school athlete user inputs and sends their weight, height, dietary habits, and training history into their device. The server receives this data and analyzes it by comparing it with a database of top athletes. At the same time, an emotion engine analyzes the user's psychological state. As a result, an optimal training menu (five times a week of running and strength training), nutrition plan (high-protein, low-fat diet), and form correction points (improvement of arm swing) are generated and sent to the user's device. The user trains and takes in nutrients according to these suggestions, and then feeds the results and emotional data back to the server. The server analyzes the feedback and emotional data, retrains the generative AI model, and updates the suggestions.

[0205] In this way, the present invention allows users to obtain optimal training methods, nutritional intake methods, and form correction points based on scientific evidence, thereby enabling them to improve their competitive level. Furthermore, by using emotional data, flexible suggestions can be made based on the user's psychological state, which can lead to better results.

[0206] The processing flow will be explained below.

[0207] Step 1:

[0208] The user inputs their physical information (weight, height, etc.), training history, and dietary details into the user terminal.

[0209] Step 2:

[0210] The terminal transmits the input data to the server.

[0211] Step 3:

[0212] The server receives the data sent by the user and stores it in a database.

[0213] Step 4:

[0214] The server collects training data, nutrition data, and form data of top athletes and stores it in a database.

[0215] Step 5:

[0216] The device collects emotion data from the user's facial expressions and voice and sends it to the server. In this step, the emotion engine performs facial expression recognition and voice analysis to extract the user's emotion as numerical data.

[0217] Step 6:

[0218] The server receives the emotion data and stores it in a database.

[0219] Step 7:

[0220] The server preprocesses the accumulated data (user data and top athlete data) and generates a dataset for analysis.

[0221] Step 8:

[0222] The server uses a generative AI model to analyze the pre-processed data and generate optimal training methods, nutritional intake methods, and form correction points for the user.

[0223] Step 9:

[0224] The server dynamically adjusts the difficulty and intensity of the suggested content based on the emotional data, creating a flexible training plan that suits the user's psychological state.

[0225] Step 10:

[0226] The server transmits the generated training method, nutritional intake method, and form correction points to the user terminal.

[0227] Step 11:

[0228] The device displays the suggestions received from the server to the user, who then checks the suggestions and carries out the actual training and meal plan.

[0229] Step 12:

[0230] The user performs training and nutritional intake based on the suggestions, and then inputs the results and impressions into the terminal.

[0231] Step 13:

[0232] The terminal transmits the input feedback data to the server.

[0233] Step 14:

[0234] The server analyzes the received feedback and retrains the generative AI model to improve the accuracy of the suggestions. It also analyzes newly collected emotion data and incorporates it into the next suggestions.

[0235] Step 15:

[0236] The server receives advertising data from sporting goods manufacturers and nutritional food manufacturers and generates optimal advertisements to display on user terminals.

[0237] Step 16:

[0238] The device displays the advertisements and recommended product information received from the server to the user, who can then select the products they are interested in and proceed with the purchase.

[0239] Example 2

[0240] 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."

[0241] Conventional training support systems support users' training and nutritional management, but they are unable to make suggestions that take into account each individual's psychological state, making it difficult to achieve effective training and nutritional management. Furthermore, systems that dynamically update suggestions based on user feedback are also lacking. This results in insufficient support for users to achieve high performance.

[0242] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0243] In this invention, the server includes means for receiving training data, nutritional data, and physical information from a user, means for collecting and storing exercise data, nutritional data, and form data of top athletes, means for analyzing the stored data and using a generative AI model to generate an optimal training method, nutritional intake method, and form correction points for the user, means for transmitting the generated training method, nutritional intake method, and form correction points to a user terminal, means for collecting and analyzing emotional data from the user terminal, means for generating training method and nutritional intake method suggestions that reflect the emotional data, and means for analyzing feedback received from the user and updating the suggestions. This enables flexible suggestions that take the user's emotional data into consideration, and makes it possible to provide optimal training methods and nutritional intake methods that are dynamically updated.

[0244] "User" means an individual who wishes to use the System to improve their own training and nutritional management.

[0245] "Training data" refers to a record of the type, duration, intensity, etc. of exercise performed by the user.

[0246] "Nutrition data" refers to information such as the type and amount of food consumed by the user, calories, nutrients, etc.

[0247] "Physical information" refers to data that indicates the user's physical characteristics, such as weight, height, and body fat percentage.

[0248] A "top athlete" is a competitor who has demonstrated great skill and achievement in a particular sporting field.

[0249] "Athletic data" refers to information about training content and performance recorded by top athletes.

[0250] "Form data" refers to detailed information that records the physical movements of top athletes during exercise.

[0251] A "generative AI model" is an artificial intelligence used to generate optimal training and nutrition plans based on large amounts of data.

[0252] "Emotion data" refers to information about a user's psychological state that can be inferred from facial expressions, voice tone, text input, and the like.

[0253] A "user terminal" refers to a device such as a computer or smartphone used by a user.

[0254] "Feedback" refers to information that a user provides to the system regarding the results and impressions of their training and nutritional intake.

[0255] "Suggestions" refer to training methods, nutritional intake methods, and form correction points provided to users based on the results of analysis of the generative AI model and emotional data.

[0256] The present invention relates to a system that supports users in more effectively managing their training and nutrition, enabling them to perform at the level of a top athlete. A specific example of this system is described below.

[0257] The system consists of a server, a user device, an emotion engine, and a generative AI model. The server receives training data, nutritional data, and physical information from the user and stores this data in a database. The software used includes a database management system and a generative AI model. It also collects exercise data, nutritional data, and form data from top athletes and stores this in the database. The server analyzes the accumulated data and uses the generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user.

[0258] The user terminal has the function of inputting data from the user via an input interface and sending it to the server. This data includes the user's training history, dietary content, and physical information. The user terminal also has the function of receiving and displaying suggestions sent from the server. Furthermore, the user can input the results and impressions of their training and nutritional intake as feedback and send it to the server. It also has an interface for collecting emotional data. This emotion engine has the function of collecting and analyzing emotional data from the user's facial expressions, voice tone, text input, etc. Emotional data is used to understand the user's current psychological state and reflect it in training and nutrition plan suggestions.

[0259] As a specific use case, consider the case where a high school athlete inputs and sends their weight, height, dietary habits, and training history into their device. The server receives this data and analyzes it by comparing it with a database of top athletes. At the same time, the emotion engine analyzes the user's psychological state. As a result, the system generates an optimal training menu for the user (e.g., running and strength training five times a week), a nutrition plan (e.g., a high-protein, low-fat diet), and form corrections (e.g., improving arm swing), and sends these suggestions to the user's device. The user then trains and takes in nutrients according to these suggestions, and provides feedback on the results and emotional data to the server. The server analyzes the feedback and emotional data, retrains the generative AI model, and updates the suggestions.

[0260] A unique feature of this system is that it can propose flexible training and nutrition plans that reflect the user's emotional data, allowing users to find training and nutritional methods that are optimal for their own psychological state, thereby improving their sports performance.

[0261] Examples of prompts to be used in this system include, "Generate the optimal training menu and nutrition plan based on the user's training data, nutrition data, and physical information. Also, make suggestions for improvements taking the user's emotional data into consideration," "Output the results of an analysis of the user's training menu compared with data from top athletes," and "Update the suggestions based on the user's real-time feedback to provide a more accurate training menu."

[0262] In this way, the present invention allows users to obtain optimal training methods, nutritional intake methods, and form corrections based on scientific evidence, thereby enabling them to improve their competitive level. Furthermore, by using emotional data, flexible suggestions can be made based on the user's psychological state, which can lead to better results.

[0263] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0264] Step 1: Enter and submit data

[0265] The user inputs their weight, height, dietary habits, training history, etc. into the user terminal. This data is collected through an input interface installed on the user terminal. When the user presses the "send" button, the user terminal sends this data to the server.

[0266] Input: Weight, height, diet, training history

[0267] Output: Data sent from the user device to the server

[0268] Specific action: The user enters data into a smartphone application and presses the "Submit" button.

[0269] Step 2: Receiving and storing data

[0270] The server receives the data sent from the user terminal and stores the received data in a database.

[0271] Input: Data sent from the user's device

[0272] Output: User data stored in the database

[0273] What it does: The server listens on a specific port and automatically stores the received data in a MySQL database.

[0274] Step 3: Collecting and storing top athlete data

[0275] The server collects the exercise data, nutrition data, and form data of top athletes and stores them in a database.

[0276] Input: Top athletes' exercise data, nutrition data, and form data

[0277] Output: Top athlete data stored in a database

[0278] Specific operation: Automatically collect data from various data sources using APIs and store it in a database.

[0279] Step 4: Data analysis and proposal generation

[0280] The server compares the user data stored in the database with the data of top athletes and uses a generative AI model to generate optimal training methods, nutritional intake methods, and form corrections for the user. In this process, the generative AI model runs on frameworks such as TensorFlow.

[0281] Input: User data and top athlete data stored in the database

[0282] Output: Optimal training methods, nutritional intake methods, and form correction points

[0283] Specific operation: The generative AI model analyzes the data and outputs the results in JSON format, and the server generates suggestions based on this.

[0284] Step 5: Submit and view your proposal

[0285] The server sends the generated training methods, nutritional intake methods, and form correction suggestions to the user's device. The user's device receives the suggestions and displays them to the user. They are displayed in the form of a notification, allowing the user to check the details.

[0286] Input: Optimal training methods, nutritional intake methods, form correction points

[0287] Output: Proposal content notified to the user's device

[0288] Specific operation: The proposal is displayed in the form of a notification in the application on the user's device.

[0289] Step 6: Collect and analyze emotion data

[0290] The user terminal collects emotion data from facial expressions, voice tones, and text input. The emotion engine analyzes the emotion data and sends the results to the server.

[0291] Input: Facial expressions, voice tone, text input

[0292] Output: Emotion data analysis results sent to the server

[0293] How it works: The facial expression recognition software uses OpenCV to analyze the user's facial expressions in real time and sends the results to the server.

[0294] Step 7: Update suggestions taking into account sentiment data

[0295] The server reflects the emotional data obtained from the emotion engine and generates suggestions for training methods and nutritional intake methods.

[0296] Input: Emotion data analysis results

[0297] Output: Suggestions for training and nutritional intake methods that reflect emotional data

[0298] Specific operation: The generative AI model is run again based on the results of emotion data analysis to generate new suggestions.

[0299] Step 8: Send and analyze feedback

[0300] The user follows the suggested training menu and nutrition plan, inputs the results and impressions into the user's device, and sends them to the server. The server receives and analyzes the feedback, and based on the results, retrains the generative AI model and updates the suggestions.

[0301] Input: Training execution results, feedback

[0302] Output: Updated proposal

[0303] Specific operation: The user enters details of their training and diet into the application, and by pressing the "Feedback" button, the information is sent to the server. The server analyzes the feedback and reflects it in the generative AI model.

[0304] This will enable the system to dynamically provide optimal training and nutritional intake methods that take into account the user's emotional data, thereby supporting high sports performance.

[0305] (Application example 2)

[0306] 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."

[0307] While conventional training support systems can collect and analyze users' training and nutritional data, they have difficulty personalizing training and nutritional management by taking into account the user's psychological state and emotions. Furthermore, due to a lack of provision of personalized meal plans based on this data and collaboration with food delivery companies, it has been difficult for users to achieve consistent training and nutritional management.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0309] In this invention, the server includes a means for receiving training data, nutritional data, and physical information from the user, a means for collecting and storing training data, nutritional data, and form data of top athletes, and a means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user. This makes it possible to generate optimal training methods and personalized meal plans based on the individual health and psychological state of the user, and to support their implementation.

[0310] The "means for receiving training data, nutritional data, and physical information from the user" refers to an interface that allows the user to input their own training history, dietary content, and physical information such as weight and height, and transmit this information in digital form to the server.

[0311] "Means for collecting and storing training data, nutritional data, and form data of top athletes" refers to a system for compiling and storing information on the training methods, nutritional intake patterns, and movement form of outstanding athletes in a database.

[0312] "Means of analyzing accumulated data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for each user" refers to technology that analyzes the vast amount of data accumulated on a server and utilizes artificial intelligence to generate training plans, nutritional intake plans, and movement improvement points that are customized for each individual user.

[0313] "Means for transmitting the generated training methods, nutritional intake methods, and form correction points to the user's terminal" refers to a communication technology that sends the suggestions and plans generated by the server to the user's terminal, such as a smartphone or PC, and displays them.

[0314] The "means for analyzing feedback received from users and updating the content of suggestions" refers to a system that collects the results and impressions of the user's training and diet, analyzes them, and updates the next suggestions to make them more accurate.

[0315] "Means for collecting and analyzing emotional data" refers to technology that reads the user's emotional state from their facial expressions and vocal tone, and analyzes that data to understand the user's psychological state.

[0316] "Means for generating personalized meal menus based on a user's training history, nutritional data, and emotional data, and sending orders to food delivery companies" refers to a system that plans individually optimized meal menus taking into account a user's past training, dietary history, and emotional state, and automatically places orders with a food delivery service.

[0317] The present invention provides a system that allows a user to perform training and nutritional management more effectively. Specific embodiments for carrying out the invention are described below.

[0318] 1. System Overview

[0319] The server has the function of receiving training data, nutritional data, and physical information from the user's device. This includes an interface for users to input their own data and communication technology for transmitting that data to the server. Users input data using devices such as smartphones or PCs.

[0320] 2. Data collection and storage

[0321] The server collects training data, nutrition data, and form data from top athletes and stores them in a database. Data on outstanding athletes is obtained from books, the internet, and specialist institutions, and then categorized and stored in the database. This data serves as the basis for optimal recommendations to users.

[0322] 3. Analysis using generative AI models

[0323] The server analyzes the accumulated data and uses a generative AI model to generate optimal training methods, nutritional intake methods, and form corrections for the user. The generated suggestions are based on customized and pre-programmed algorithms.

[0324] 4. Submit your proposal

[0325] The server then sends the generated training methods, nutritional intake methods, and form correction points to the user's device. The communication protocol uses an internet connection, allowing the user to act on this information and plan their next training and meal plans.

[0326] 5. Analyzing feedback and updating suggestions

[0327] The server analyzes the feedback received from the user and updates the suggestions. This feedback includes the results and thoughts of the user on their training and diet. Based on the feedback, the generative AI model retrains and improves the accuracy of the suggestions.

[0328] 6. Emotional Data Collection and Analysis

[0329] The server uses an emotion engine to collect and analyze emotional data from the user's facial expressions, voice tone, text input, etc. This allows the server to understand the user's psychological state and reflect this in training and nutrition plan suggestions.

[0330] 7. Generate personalized meal menus and order from food delivery providers

[0331] The server generates a personalized meal menu based on the user's training history, nutritional data, and emotional data, and automatically sends the generated menu to a food delivery company, allowing the user to receive the optimal meal at the right time.

[0332] Hardware and software used

[0333] Hardware:

[0334] Smartphone: A device equipped with a camera and microphone.

[0335] Server: A high-performance server for receiving, analyzing, and sending data.

[0336] software:

[0337] Python scripting: Used to process data, analyze, and operate generative AI models.

[0338] Emotion Recognition API: An external API for analyzing user emotion data.

[0339] Generative AI model API: Used to generate training methods and nutrition plans.

[0340] Database system: Used to store data (e.g. PostgreSQL).

[0341] Specific examples

[0342] High school athlete users enter their weight, height, dietary habits, and training history into a smartphone app and send it to a server. The server receives this data and analyzes it by comparing it with a database of top athletes. At the same time, it analyzes the user's psychological state using an emotion engine. As a result, it generates an optimal training menu for the user (running five times a week and strength training), a nutrition plan (high-protein, low-fat diet), and form correction points (improving arm swing), and sends these to the user's device. The user trains and takes in nutrients according to these suggestions, and then feeds the results and emotional data back to the server. The server analyzes the feedback and emotional data, retrains the generative AI model, and updates the suggestions.

[0343] Prompt Sentence Examples

[0344] "Recommend optimal training and nutrition plans based on the user's training history and nutrition data. Also consider the user's emotional state and include elements that help reduce stress."

[0345] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0346] Step 1:

[0347] Input: The user enters training data, nutrition data, and physical information into the smartphone device and presses the send button.

[0348] Processing: The terminal sends the entered data to the server.

[0349] Output: The server receives the user's training data, nutrition data, and physical information and stores them in a database.

[0350] Specific operation: The user enters information such as weight, height, dietary habits, and training history into the input form and presses the "Submit" button. The device converts the data into JSON format and sends an HTTP request to the server. The server receives this and stores it in a database.

[0351] Step 2:

[0352] Input: The server reads the accumulated training, nutrition, and form data of top athletes.

[0353] Processing: The server prepares the user data and top athlete data for comparison and analysis.

[0354] Output: The top athlete data and user data are ready and we move on to the analysis phase.

[0355] Specific operation: The server queries the necessary items from the database of top athletes and converts them into a format that can be integrated with user data.

[0356] Step 3:

[0357] Input: User data and top athlete data.

[0358] Processing: The server uses the generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user.

[0359] Output: Generates a personalized training plan, nutrition plan, and form corrections.

[0360] How it works: Enter a prompt into the generative AI model, such as, "Based on the user's training history and nutrition data, suggest the optimal training menu and nutrition plan. Include elements that will help reduce stress, taking into account the user's emotional state." The model then analyzes the data and generates the optimal suggestion.

[0361] Step 4:

[0362] Input: Training plan, nutrition plan, and form correction points generated by a generative AI model.

[0363] Processing: The server sends the generated proposal to the user terminal.

[0364] Output: Training plan, nutrition plan, and form correction points are displayed on the user's device.

[0365] Specific operation: The server sends the generated proposal content to the user's device as an HTTP response. The user's device displays the received data in a format that is easy for the user to view.

[0366] Step 5:

[0367] Input: User feedback.

[0368] Processing: The server receives the feedback and uses it for analysis.

[0369] Output: Feedback data parsed by the server.

[0370] Specific operation: The user inputs the results of their training and diet and their thoughts on the device, and presses the "Send Feedback" button. The device then sends the data to the server, which receives and analyzes it.

[0371] Step 6:

[0372] Input: User feedback and sentiment data.

[0373] Processing: The server analyzes the feedback data and sentiment data and updates the suggestions using the generative AI model.

[0374] Output: Updated training plan, nutrition plan.

[0375] How it works: The server analyzes the feedback and emotion data and retrains the generative AI model. The updated model generates new optimized training and nutrition plans.

[0376] Step 7:

[0377] Input: User emotion data.

[0378] Processing: The server analyzes the emotion data using the emotion engine.

[0379] Output: Data based on the user's emotional state.

[0380] Specific operation: The server analyzes the user's facial expressions and voice data and obtains emotion data using the emotion engine API. This emotion data is used as input data for the generative AI model.

[0381] Step 8:

[0382] Input: User's training history, nutritional data, and emotional data.

[0383] Processing: The server generates a personalized meal menu based on this data and sends the order to the food delivery company.

[0384] Output: A personalized meal menu and the order data generated based on it.

[0385] How it works: The server uses a generative AI model to analyze user data and generate an optimal meal menu, which is then automatically sent as an order to a food delivery service.

[0386] 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.

[0387] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0388] 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.

[0389] [Second embodiment]

[0390] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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."

[0402] The present invention relates to a system that enables users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, and form correction points. Specific examples of the present invention are described below.

[0403] 1. Server system overview:

[0404] The server has the function of collecting and storing training data, nutritional data, and form data of top athletes. This data is stored in a database and used for analysis. The server also has the function of receiving data entered by users (training data, nutritional data, physical information) and analyzing it using a generative AI model. Based on the analysis results, the generative AI model generates optimal training methods, nutritional intake methods, and form correction points for the user. The generated suggestions are then sent to the user's device.

[0405] 2. Device Features:

[0406] The user terminal has the function of inputting data from the user via an input interface and sending it to the server. This data includes the user's training history, dietary content, and physical information. The user terminal also has the function of receiving suggestions sent from the server and displaying them. Furthermore, the user can input the results and impressions of their training and nutritional intake as feedback and send it to the server.

[0407] 3. User Action:

[0408] The user first enters their physical information, training history, and dietary details into the user device. The device then sends this data to the server, which receives it and begins analysis. Using a generative AI model, the system generates training methods, nutritional intake methods, and form correction points suited to the user, and sends these suggestions to the user's device. The user then performs training and nutritional intake based on the suggestions, and enters the results and impressions into the device to send feedback to the server. The server then reanalyzes the data based on the received feedback and updates the suggestions.

[0409] 4. Example:

[0410] High school athlete users input their weight, height, dietary habits, and training history into their device and send it. The server receives this data and analyzes it by comparing it with a database of top athletes. As a result, it generates an optimal training menu for the user (e.g., running and strength training five times a week), a nutritional intake plan (e.g., a high-protein, low-fat diet), and form corrections (e.g., improving arm swing), and sends these to the user's device. The user follows these suggestions to train and consume nutritional information, and then provides feedback on the results to the server. By repeating this cycle, the system continuously supports the user's growth.

[0411] In this way, the present invention allows users to obtain scientifically based optimal training methods, nutritional intake methods, and form corrections, thereby improving their competitive level. Furthermore, as the generative AI model continuously learns based on feedback, the accuracy of its suggestions improves, allowing it to provide support that is even more tailored to the individual needs of the user.

[0412] The processing flow will be explained below.

[0413] Step 1:

[0414] The user inputs physical information such as weight, height, training history, dietary details, and activity data into the user terminal.

[0415] Step 2:

[0416] The terminal transmits the input data to the server.

[0417] Step 3:

[0418] The server receives the data sent by the user and stores it in a database.

[0419] Step 4:

[0420] The server collects training data, nutritional data, and form data of top athletes and stores it in a database.

[0421] Step 5:

[0422] The server performs preprocessing to analyze the accumulated data, for example, extracting form keyframes from video data and converting them into numerical data.

[0423] Step 6:

[0424] The server inputs the preprocessed data into a generative AI model, which learns the successful patterns of top athletes.

[0425] Step 7:

[0426] The server uses the received user data and a trained AI model to generate optimal training methods, nutritional intake methods, and form corrections for the user.

[0427] Step 8:

[0428] The server transmits the generated proposal content to the user terminal.

[0429] Step 9:

[0430] The terminal displays the suggestions received from the server to the user, who then checks the suggested training method, nutrition plan, and form correction points.

[0431] Step 10:

[0432] The user follows the suggestions to train and take in nutrients, and then enters the results and impressions into the device.

[0433] Step 11:

[0434] The terminal transmits the input feedback data to the server.

[0435] Step 12:

[0436] The server analyzes the received feedback and retrains the generative AI model to improve the accuracy of the suggestions.

[0437] Step 13:

[0438] The server receives advertising data from sporting goods manufacturers and nutritional food manufacturers and generates optimal advertisements to display on user terminals.

[0439] Step 14:

[0440] The device displays the advertisements and recommended product information received from the server to the user, who can then select the products they are interested in and proceed with the purchase.

[0441] Example 1

[0442] 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."

[0443] Conventional systems were not sufficient for users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, and form correction points. In particular, it was difficult to efficiently reflect user feedback and provide suggestions for continuous improvement. There was also a need to quickly and accurately transmit user-entered data to the server and improve the accuracy of analysis.

[0444] 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.

[0445] In this invention, the server includes a means for receiving training data, nutritional data, and physical information from the user, a means for collecting and storing training data, nutritional data, and form data of top athletes, and a means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user. This allows the user to obtain optimal training methods, nutritional intake methods, and form correction points based on scientific evidence in a timely manner. In addition, data entered through the user's terminal can be quickly sent to the server, allowing for continuous improvement in the accuracy of the analysis.

[0446] A "user" is an individual who aims to become a top athlete by using this system to improve their own training methods, nutritional intake methods, and form correction points.

[0447] "Training data" refers to a record of the type, frequency, intensity, duration, etc. of exercise a user is performing.

[0448] "Nutrition data" refers to information such as the user's daily diet, calorie intake, and nutrient ratios.

[0449] "Physical information" refers to basic data about the user's body, such as height, weight, and body fat percentage.

[0450] "Server" means a central data processing unit that collects, stores, and analyzes data received from users, and generates and transmits proposals.

[0451] The "generative AI model" is an artificial intelligence model that analyzes accumulated data and automatically generates optimal training methods, nutritional intake methods, and form correction points for each user.

[0452] "Training method" refers to the individual exercises or programs that a user performs, including the frequency of exercise per week and the type of exercise.

[0453] "Nutrition method" refers to the dietary content and nutrient intake balance that a user should have.

[0454] "Form correction points" refer to areas where the user can improve their body movements and posture during exercise.

[0455] "Feedback" refers to the results and impressions of the user when they carry out the suggested training and nutritional intake methods.

[0456] A "user terminal" is an electronic device that a user uses to input data and communicate with a server.

[0457] The present invention relates to a system that enables users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, and form correction points. Specific embodiments of the present invention are described below.

[0458] Server Configuration

[0459] The server is equipped with a high-performance processor (e.g., Intel Xeon), a large amount of memory (128 GB RAM), and high-speed storage (2 TB SSD). A database management system (e.g., MySQL) and a generative AI model (e.g., TensorFlow) are installed on the server. The server has the following main functions:

[0460] 1. Receive training data, nutrition data, and physical information from the user.

[0461] 2. Collect training data, nutritional data, and form data of top athletes and store it in a database.

[0462] 3. Analyze the received and accumulated data and use a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user.

[0463] 4. The generated proposal is sent to the user's device.

[0464] 5. Analyze the feedback received from users and update the suggestions.

[0465] Device configuration

[0466] The user device is a mobile information terminal such as a smartphone or tablet, equipped with an input interface. A dedicated mobile application (e.g., an app developed with React Native) is installed on the device, and has the following main functions:

[0467] 1. The user enters their physical information, training history, and dietary information.

[0468] 2. Send the entered data to the server.

[0469] 3. Receive and display the proposal sent from the server.

[0470] 4. The user inputs the results and impressions of their training and nutritional intake as feedback and sends it to the server.

[0471] User operations

[0472] First, the user enters their physical information (e.g., height, weight), training history (e.g., weekly exercise frequency, type of exercise), and dietary details into the user device. The entered data is sent to the server via the device. The server receives the data and stores it in a database. The data is then analyzed using a generative AI model to generate the optimal training method, nutritional intake method, and form correction points for the user. The generated suggestions are sent to the user's device and presented to the user. The user then performs training and nutritional intake based on the presented suggestions. The results and impressions are entered into the user device and fed back to the server. The server re-analyzes the feedback and updates the suggestions.

[0473] Specific examples

[0474] For example, a high school athlete enters their weight, height, diet, and training history into a form on a smartphone app. An example input might be "height 180 cm, weight 75 kg, breakfast: salad and yogurt, training: 30 minutes of running." When this information is sent to the server, it is saved in a database and analyzed using a generative AI model. As a result, recommendations are generated for the user, such as "strength training five times a week, high-protein, low-fat diet, form correction: arm swing," and sent to the user's device. The user then trains and takes in nutrients based on the recommendations, and as a result, provides feedback such as "I feel like my muscle strength has improved in a week," which is then sent to the server. Based on this feedback, the server performs further analysis to improve the accuracy of the recommendations.

[0475] Prompt Sentence Examples

[0476] "Generate a suitable workout schedule for a user who is 180cm tall, weighs 75kg, and trains four times a week."

[0477] The above is an embodiment of the present invention. This system allows users to obtain optimal training methods, nutritional intake methods, and form corrections based on scientific evidence. In addition, the generative AI model continuously learns based on user feedback, improving the accuracy of its suggestions.

[0478] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0479] Step 1:

[0480] User data entry and submission

[0481] The user uses the device to input their physical information, training history, and dietary details. Data input by the user may include, for example, "height 180 cm, weight 75 kg, diet: salad and yogurt for breakfast, 30 minutes of running for training." After completing the input, the device formats the user data and sends it to the server. The input at this stage is all the personal data the user provides to the device, and the output is the formatted user data and its transmission to the server.

[0482] Step 2:

[0483] Receiving and storing data

[0484] The server immediately receives the user data from the terminal. The received data is stored in a database system (e.g., MySQL) on the server. Specifically, the server stores the data in the database as "User ID 123, height 180 cm, weight 75 kg, diet: salad and yogurt for breakfast, 30 minutes of running for training." The input is the user data from the terminal, and the output is the data stored in the database on the server.

[0485] Step 3:

[0486] Data analysis

[0487] The server retrieves the saved user data from the database and passes it to a generative AI model (example of use: TensorFlow). The generative AI model performs analysis based on the user data and accumulated data on top athletes. As a result, it generates the optimal training method, nutritional intake method, and form correction points for the user. For example, analysis of the input user data may generate suggestions such as "strength training five times a week, a high-protein, low-fat diet, and form correction points: arm swing." The input is the user data retrieved from the database, and the output is the optimal suggestion from the generative AI model.

[0488] Step 4:

[0489] Submit your proposal

[0490] The server sends the suggestions output from the generative AI model to the user's device. For example, suggestions such as "strength training five times a week, high-protein, low-fat diet, and form corrections: arm swing" are sent to the user's device. The input is the generated suggestions, and the output is the data sent to the user's device.

[0491] Step 5:

[0492] User execution and feedback

[0493] The user checks the suggestions sent from the server and performs the training and diet based on them. The results and impressions of the training are input into the user's device. For example, the user may input their impressions after training, such as "I feel like my muscle strength has improved in a week," and send the feedback to the server via the device. The input is the user's results and impressions, and the output is the feedback data sent to the server.

[0494] Step 6:

[0495] Analyzing feedback and updating suggestions

[0496] The server receives feedback sent by the user and stores it in a database. Based on the stored feedback, the generative AI model is used again to analyze it and improve the accuracy of the suggestions. The updated suggestions are then sent back to the user's device. For example, as a result of analyzing the feedback "I feel like my muscle strength has improved," a new suggestion "Slightly increase the load of your strength training" is generated and sent to the user's device. The input is the feedback data, and the output is the updated suggestions.

[0497] keyword

[0498] Generative AI model, prompt sentence

[0499] (Application example 1)

[0500] 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."

[0501] Previous user training systems and factory robot motion optimization systems lacked a way to efficiently provide optimal training methods or correction points for robot motion. Furthermore, they lacked a system for quickly updating suggestions based on user feedback, making it difficult to provide support that met individual needs.

[0502] 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.

[0503] In this invention, the server includes means for receiving training data, nutritional data, and physical information from users, means for collecting and storing training data, nutritional data, and form data of top athletes, means for collecting and storing factory robot motion data, means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, form correction points, and robot motion correction points for users, means for transmitting the generated training methods, nutritional intake methods, form correction points, and robot motion correction points to a user terminal, and means for analyzing feedback received from users and updating the suggested content, thereby making it possible to provide optimal training methods and motion correction points based on individual needs.

[0504] "User" is the person providing the training data, nutritional data, and physical information or the operator of the equipment.

[0505] "Training data" refers to information that refers to the history and details of the exercises and practices that a user has performed.

[0506] "Nutrition data" refers to information about the dietary content and nutrients that a user has consumed.

[0507] "Physical information" refers to physical data such as the user's weight, height, and body fat percentage.

[0508] A "top athlete" is an athlete who performs at the highest level in their field.

[0509] "Form data" is data that includes details of posture and movement during exercise or movement.

[0510] "Factory robot" refers to automated machinery used in factories and manufacturing environments.

[0511] "Operation data" refers to the history and performance data of the operations performed by factory robots.

[0512] A "generative AI model" is an artificial intelligence algorithm that analyzes accumulated data and calculates optimal training methods and movement correction points.

[0513] "Feedback" refers to information provided by the user about the results and impressions of training and nutritional intake.

[0514] "Analysis" is the process of examining data in detail and extracting meaningful information.

[0515] "Suggested content" refers to training methods, nutritional intake methods, form correction points, or robot movement correction points that are shown to the user by the generative AI model.

[0516] This invention relates to a system that enables users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, form correction points, or factory robot movement correction points. This system collects various data from users, analyzes it using a generative AI model, and provides appropriate suggestions to the users.

[0517] 1. System configuration:

[0518] server:

[0519] The server mainly collects, stores, and analyzes data, and transmits the results. Specifically, it runs a generative AI model using Python and TensorFlow, and stores the data in a PostgreSQL database. The MQTT protocol is used for data transmission and reception.

[0520] User device:

[0521] The user device receives training data, nutritional data, physical information, and feedback from the user via an input interface. This data is then sent to the server using the MQTT protocol. The server also displays the optimal training method, nutritional intake method, and form correction points sent from the server.

[0522] Factory robots:

[0523] Factory robots use sensors to collect operational data and send it to a server. They then execute the operational correction points sent from the server, collect operational data again, and send it to the server to optimize their operations.

[0524] 2. Data flow:

[0525] Data collection:

[0526] Users use the device's input interface to input data such as physical information, training history, and dietary details, while factory robots equipped with sensors collect movement data.

[0527] Data transmission:

[0528] The user terminal and the factory robot send the collected data to the server via the MQTT protocol.

[0529] Data Analysis:

[0530] The server uses Python and TensorFlow to analyze the received data and calculates optimal training methods, nutritional intake methods, form corrections, or robot movement corrections using a generative AI model. The analysis results are stored in a PostgreSQL database.

[0531] Generate and submit a proposal:

[0532] The optimization proposals generated by the server are sent to the user terminal and factory robot via the MQTT protocol.

[0533] 3. Example:

[0534] For example, when a high school athlete inputs and sends their weight, height, dietary habits, and training history to a device, this data is compared with that of top athletes and analyzed by the server. As a result, an optimal training menu and nutrition plan for the user is generated and sent to the user's device. Similarly, the operation data of a factory robot can be sent to the server, and optimal operation correction points can be received.

[0535] An example of a prompt would be, "Use a generative AI model to analyze the operation data of a factory robot and suggest optimized operation patterns and error correction points."

[0536] This allows users to efficiently obtain optimal training methods and movement corrections tailored to their individual needs.In addition, the generative AI model continuously learns based on user feedback and newly collected data, enabling it to improve the accuracy of its suggestions.

[0537] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0538] Step 1:

[0539] The user device uses an input interface to collect data from the user, such as physical information, training history, and dietary details. The input data includes the user's weight, height, exercise details, and dietary details. This data is formatted to be stored in a database and then sent to the server using the MQTT protocol.

[0540] Step 2:

[0541] The server receives data sent from the user's device, including physical information, training history, and dietary details. The server stores this data in a PostgreSQL database.

[0542] Step 3:

[0543] Factory robots use sensors to collect operational data, including the robot's movement patterns, speed, error rate, etc. This data is also sent to a server using the MQTT protocol.

[0544] Step 4:

[0545] The server receives operation data sent from the factory robots and stores it in a PostgreSQL database, allowing for centralized management of both user data and robot data.

[0546] Step 5:

[0547] The server uses Python and TensorFlow to analyze data stored in PostgreSQL. Specifically, it uses a generative AI model to generate optimal training methods, nutritional intake methods, form corrections, and factory robot operation corrections for each user. The analysis uses data from past top athletes and existing optimization algorithms.

[0548] Step 6:

[0549] The server transmits the generated training methods, nutritional intake methods, form correction points, and factory robot operation correction points to the user terminal and the factory robot again via the MQTT protocol.

[0550] Step 7:

[0551] The user terminal receives the suggestions sent from the server and displays them to the user, who then performs training and nutritional intake based on them.

[0552] Step 8:

[0553] The factory robot receives the operation correction points sent from the server and corrects and optimizes its operation. The robot collects the corrected operation data again and sends it to the server.

[0554] Step 9:

[0555] The results and impressions obtained by the user and the factory robot are entered as feedback into the input interface of the user terminal and the robot, and sent to the server. The server analyzes the received feedback and stores and updates it in the PostgreSQL database.

[0556] Step 10:

[0557] The server updates the generative AI model based on the received feedback and newly collected data, and performs re-analysis to improve the accuracy of the suggestions, thereby repeatedly providing optimal suggestions for the user and the robot, enabling continuous performance improvement.

[0558] 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.

[0559] The present invention relates to a system that supports a user in more effectively managing their training and nutrition, enabling them to perform at the level of a top athlete. Specific examples of the present invention are described below.

[0560] 1. Server system overview:

[0561] The server has the ability to receive training data, nutritional data, and physical information from users and store it in a database. The server also collects training data, nutritional data, and form data from top athletes and stores it in a database. The server then uses a generative AI model to analyze the accumulated data and generate optimal training menus, nutrition plans, and form correction suggestions for each user. It also has the ability to send suggestions to the user's device and update the suggestions based on feedback received from the user.

[0562] 2. Emotion engine feature additions:

[0563] The system also incorporates an emotion engine, which has the ability to collect and analyze emotional data from the user's facial expressions, voice tone, text input, etc. The emotional data is used to understand the user's current psychological state and reflect it in training and nutrition plan suggestions.

[0564] 3. Device Features:

[0565] The user terminal has the function of inputting data from the user via an input interface and sending it to the server. This data includes the user's training history, dietary content, and physical information. The user terminal also has the function of receiving suggestions sent from the server and displaying them. Furthermore, the user can input the results and impressions of their training and nutritional intake as feedback and send them to the server. It also has an interface for collecting emotional data.

[0566] 4. User Action:

[0567] The user first enters their physical information, training history, and dietary details into the user device. The device sends this data to the server, which receives it and begins analysis. A generative AI model is used to generate training methods, nutritional intake methods, and form correction points that are suitable for the user. An emotion engine is also used to collect and analyze the user's emotional data and reflect this in the suggestions. The generated suggestions are sent to the user device. The user then performs training and nutritional intake based on the suggestions, and enters the results and impressions into the device, sending feedback to the server. The server analyzes the received feedback and emotional data to improve the accuracy of the suggestions.

[0568] 5. Examples:

[0569] A high school athlete user inputs and sends their weight, height, dietary habits, and training history into their device. The server receives this data and analyzes it by comparing it with a database of top athletes. At the same time, an emotion engine analyzes the user's psychological state. As a result, an optimal training menu (five times a week of running and strength training), nutrition plan (high-protein, low-fat diet), and form correction points (improvement of arm swing) are generated and sent to the user's device. The user trains and takes in nutrients according to these suggestions, and then feeds the results and emotional data back to the server. The server analyzes the feedback and emotional data, retrains the generative AI model, and updates the suggestions.

[0570] In this way, the present invention allows users to obtain optimal training methods, nutritional intake methods, and form correction points based on scientific evidence, thereby enabling them to improve their competitive level. Furthermore, by using emotional data, flexible suggestions can be made based on the user's psychological state, which can lead to better results.

[0571] The processing flow will be explained below.

[0572] Step 1:

[0573] The user inputs their physical information (weight, height, etc.), training history, and dietary details into the user terminal.

[0574] Step 2:

[0575] The terminal transmits the input data to the server.

[0576] Step 3:

[0577] The server receives the data sent by the user and stores it in a database.

[0578] Step 4:

[0579] The server collects training data, nutrition data, and form data of top athletes and stores it in a database.

[0580] Step 5:

[0581] The device collects emotion data from the user's facial expressions and voice and sends it to the server. In this step, the emotion engine performs facial expression recognition and voice analysis to extract the user's emotion as numerical data.

[0582] Step 6:

[0583] The server receives the emotion data and stores it in a database.

[0584] Step 7:

[0585] The server preprocesses the accumulated data (user data and top athlete data) and generates a dataset for analysis.

[0586] Step 8:

[0587] The server uses a generative AI model to analyze the pre-processed data and generate optimal training methods, nutritional intake methods, and form correction points for the user.

[0588] Step 9:

[0589] The server dynamically adjusts the difficulty and intensity of the suggested content based on the emotional data, creating a flexible training plan that suits the user's psychological state.

[0590] Step 10:

[0591] The server transmits the generated training method, nutritional intake method, and form correction points to the user terminal.

[0592] Step 11:

[0593] The device displays the suggestions received from the server to the user, who then checks the suggestions and carries out the actual training and meal plan.

[0594] Step 12:

[0595] The user performs training and nutritional intake based on the suggestions, and then inputs the results and impressions into the terminal.

[0596] Step 13:

[0597] The terminal transmits the input feedback data to the server.

[0598] Step 14:

[0599] The server analyzes the received feedback and retrains the generative AI model to improve the accuracy of the suggestions. It also analyzes newly collected emotion data and incorporates it into the next suggestions.

[0600] Step 15:

[0601] The server receives advertising data from sporting goods manufacturers and nutritional food manufacturers and generates optimal advertisements to display on user terminals.

[0602] Step 16:

[0603] The device displays the advertisements and recommended product information received from the server to the user, who can then select the products they are interested in and proceed with the purchase.

[0604] Example 2

[0605] 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."

[0606] Conventional training support systems support users' training and nutritional management, but they are unable to make suggestions that take into account each individual's psychological state, making it difficult to achieve effective training and nutritional management. Furthermore, systems that dynamically update suggestions based on user feedback are also lacking. This results in insufficient support for users to achieve high performance.

[0607] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0608] In this invention, the server includes means for receiving training data, nutritional data, and physical information from a user, means for collecting and storing exercise data, nutritional data, and form data of top athletes, means for analyzing the stored data and using a generative AI model to generate an optimal training method, nutritional intake method, and form correction points for the user, means for transmitting the generated training method, nutritional intake method, and form correction points to a user terminal, means for collecting and analyzing emotional data from the user terminal, means for generating training method and nutritional intake method suggestions that reflect the emotional data, and means for analyzing feedback received from the user and updating the suggestions. This enables flexible suggestions that take the user's emotional data into consideration, and makes it possible to provide optimal training methods and nutritional intake methods that are dynamically updated.

[0609] "User" means an individual who wishes to use the System to improve their own training and nutritional management.

[0610] "Training data" refers to a record of the type, duration, intensity, etc. of exercise performed by the user.

[0611] "Nutrition data" refers to information such as the type and amount of food consumed by the user, calories, nutrients, etc.

[0612] "Physical information" refers to data that indicates the user's physical characteristics, such as weight, height, and body fat percentage.

[0613] A "top athlete" is a competitor who has demonstrated great skill and achievement in a particular sporting field.

[0614] "Athletic data" refers to information about training content and performance recorded by top athletes.

[0615] "Form data" refers to detailed information that records the physical movements of top athletes during exercise.

[0616] A "generative AI model" is an artificial intelligence used to generate optimal training and nutrition plans based on large amounts of data.

[0617] "Emotion data" refers to information about a user's psychological state that can be inferred from facial expressions, voice tone, text input, and the like.

[0618] A "user terminal" refers to a device such as a computer or smartphone used by a user.

[0619] "Feedback" refers to information that a user provides to the system regarding the results and impressions of their training and nutritional intake.

[0620] "Suggestions" refer to training methods, nutritional intake methods, and form correction points provided to users based on the results of analysis of the generative AI model and emotional data.

[0621] The present invention relates to a system that supports users in more effectively managing their training and nutrition, enabling them to perform at the level of a top athlete. A specific example of this system is described below.

[0622] The system consists of a server, a user device, an emotion engine, and a generative AI model. The server receives training data, nutritional data, and physical information from the user and stores this data in a database. The software used includes a database management system and a generative AI model. It also collects exercise data, nutritional data, and form data from top athletes and stores this in the database. The server analyzes the accumulated data and uses the generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user.

[0623] The user terminal has the function of inputting data from the user via an input interface and sending it to the server. This data includes the user's training history, dietary content, and physical information. The user terminal also has the function of receiving and displaying suggestions sent from the server. Furthermore, the user can input the results and impressions of their training and nutritional intake as feedback and send it to the server. It also has an interface for collecting emotional data. This emotion engine has the function of collecting and analyzing emotional data from the user's facial expressions, voice tone, text input, etc. Emotional data is used to understand the user's current psychological state and reflect it in training and nutrition plan suggestions.

[0624] As a specific use case, consider the case where a high school athlete inputs and sends their weight, height, dietary habits, and training history into their device. The server receives this data and analyzes it by comparing it with a database of top athletes. At the same time, the emotion engine analyzes the user's psychological state. As a result, the system generates an optimal training menu for the user (e.g., running and strength training five times a week), a nutrition plan (e.g., a high-protein, low-fat diet), and form corrections (e.g., improving arm swing), and sends these suggestions to the user's device. The user then trains and takes in nutrients according to these suggestions, and provides feedback on the results and emotional data to the server. The server analyzes the feedback and emotional data, retrains the generative AI model, and updates the suggestions.

[0625] A unique feature of this system is that it can propose flexible training and nutrition plans that reflect the user's emotional data, allowing users to find training and nutritional methods that are optimal for their own psychological state, thereby improving their sports performance.

[0626] Examples of prompts to be used in this system include, "Generate the optimal training menu and nutrition plan based on the user's training data, nutrition data, and physical information. Also, make suggestions for improvements taking the user's emotional data into consideration," "Output the results of an analysis of the user's training menu compared with data from top athletes," and "Update the suggestions based on the user's real-time feedback to provide a more accurate training menu."

[0627] In this way, the present invention allows users to obtain optimal training methods, nutritional intake methods, and form corrections based on scientific evidence, thereby enabling them to improve their competitive level. Furthermore, by using emotional data, flexible suggestions can be made based on the user's psychological state, which can lead to better results.

[0628] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0629] Step 1: Enter and submit data

[0630] The user inputs their weight, height, dietary habits, training history, etc. into the user terminal. This data is collected through an input interface installed on the user terminal. When the user presses the "send" button, the user terminal sends this data to the server.

[0631] Input: Weight, height, diet, training history

[0632] Output: Data sent from the user device to the server

[0633] Specific action: The user enters data into a smartphone application and presses the "Submit" button.

[0634] Step 2: Receiving and storing data

[0635] The server receives the data sent from the user terminal and stores the received data in a database.

[0636] Input: Data sent from the user's device

[0637] Output: User data stored in the database

[0638] What it does: The server listens on a specific port and automatically stores the received data in a MySQL database.

[0639] Step 3: Collecting and storing top athlete data

[0640] The server collects the exercise data, nutrition data, and form data of top athletes and stores them in a database.

[0641] Input: Top athletes' exercise data, nutrition data, and form data

[0642] Output: Top athlete data stored in a database

[0643] Specific operation: Automatically collect data from various data sources using APIs and store it in a database.

[0644] Step 4: Data analysis and proposal generation

[0645] The server compares the user data stored in the database with the data of top athletes and uses a generative AI model to generate optimal training methods, nutritional intake methods, and form corrections for the user. In this process, the generative AI model runs on frameworks such as TensorFlow.

[0646] Input: User data and top athlete data stored in the database

[0647] Output: Optimal training methods, nutritional intake methods, and form correction points

[0648] Specific operation: The generative AI model analyzes the data and outputs the results in JSON format, and the server generates suggestions based on this.

[0649] Step 5: Submit and view your proposal

[0650] The server sends the generated training methods, nutritional intake methods, and form correction suggestions to the user's device. The user's device receives the suggestions and displays them to the user. They are displayed in the form of a notification, allowing the user to check the details.

[0651] Input: Optimal training methods, nutritional intake methods, form correction points

[0652] Output: Proposal content notified to the user's device

[0653] Specific operation: The proposal is displayed in the form of a notification in the application on the user's device.

[0654] Step 6: Collect and analyze emotion data

[0655] The user terminal collects emotion data from facial expressions, voice tones, and text input. The emotion engine analyzes the emotion data and sends the results to the server.

[0656] Input: Facial expressions, voice tone, text input

[0657] Output: Emotion data analysis results sent to the server

[0658] How it works: The facial expression recognition software uses OpenCV to analyze the user's facial expressions in real time and sends the results to the server.

[0659] Step 7: Update suggestions taking into account sentiment data

[0660] The server reflects the emotional data obtained from the emotion engine and generates suggestions for training methods and nutritional intake methods.

[0661] Input: Emotion data analysis results

[0662] Output: Suggestions for training and nutritional intake methods that reflect emotional data

[0663] Specific operation: The generative AI model is run again based on the results of emotion data analysis to generate new suggestions.

[0664] Step 8: Send and analyze feedback

[0665] The user follows the suggested training menu and nutrition plan, inputs the results and impressions into the user's device, and sends them to the server. The server receives and analyzes the feedback, and based on the results, retrains the generative AI model and updates the suggestions.

[0666] Input: Training execution results, feedback

[0667] Output: Updated proposal

[0668] Specific operation: The user enters details of their training and diet into the application, and by pressing the "Feedback" button, the information is sent to the server. The server analyzes the feedback and reflects it in the generative AI model.

[0669] This will enable the system to dynamically provide optimal training and nutritional intake methods that take into account the user's emotional data, thereby supporting high sports performance.

[0670] (Application example 2)

[0671] 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."

[0672] While conventional training support systems can collect and analyze users' training and nutritional data, they have difficulty personalizing training and nutritional management by taking into account the user's psychological state and emotions. Furthermore, due to a lack of provision of personalized meal plans based on this data and collaboration with food delivery companies, it has been difficult for users to achieve consistent training and nutritional management.

[0673] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0674] In this invention, the server includes a means for receiving training data, nutritional data, and physical information from the user, a means for collecting and storing training data, nutritional data, and form data of top athletes, and a means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user. This makes it possible to generate optimal training methods and personalized meal plans based on the individual health and psychological state of the user, and to support their implementation.

[0675] The "means for receiving training data, nutritional data, and physical information from the user" refers to an interface that allows the user to input their own training history, dietary content, and physical information such as weight and height, and transmit this information in digital form to the server.

[0676] "Means for collecting and storing training data, nutritional data, and form data of top athletes" refers to a system for compiling and storing information on the training methods, nutritional intake patterns, and movement form of outstanding athletes in a database.

[0677] "Means of analyzing accumulated data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for each user" refers to technology that analyzes the vast amount of data accumulated on a server and utilizes artificial intelligence to generate training plans, nutritional intake plans, and movement improvement points that are customized for each individual user.

[0678] "Means for transmitting the generated training methods, nutritional intake methods, and form correction points to the user's terminal" refers to a communication technology that sends the suggestions and plans generated by the server to the user's terminal, such as a smartphone or PC, and displays them.

[0679] The "means for analyzing feedback received from users and updating the content of suggestions" refers to a system that collects the results and impressions of the user's training and diet, analyzes them, and updates the next suggestions to make them more accurate.

[0680] "Means for collecting and analyzing emotional data" refers to technology that reads the user's emotional state from their facial expressions and vocal tone, and analyzes that data to understand the user's psychological state.

[0681] "Means for generating personalized meal menus based on a user's training history, nutritional data, and emotional data, and sending orders to food delivery companies" refers to a system that plans individually optimized meal menus taking into account a user's past training, dietary history, and emotional state, and automatically places orders with a food delivery service.

[0682] The present invention provides a system that allows a user to perform training and nutritional management more effectively. Specific embodiments for carrying out the invention are described below.

[0683] 1. System Overview

[0684] The server has the function of receiving training data, nutritional data, and physical information from the user's device. This includes an interface for users to input their own data and communication technology for transmitting that data to the server. Users input data using devices such as smartphones or PCs.

[0685] 2. Data collection and storage

[0686] The server collects training data, nutrition data, and form data from top athletes and stores them in a database. Data on outstanding athletes is obtained from books, the internet, and specialist institutions, and then categorized and stored in the database. This data serves as the basis for optimal recommendations to users.

[0687] 3. Analysis using generative AI models

[0688] The server analyzes the accumulated data and uses a generative AI model to generate optimal training methods, nutritional intake methods, and form corrections for the user. The generated suggestions are based on customized and pre-programmed algorithms.

[0689] 4. Submit your proposal

[0690] The server then sends the generated training methods, nutritional intake methods, and form correction points to the user's device. The communication protocol uses an internet connection, allowing the user to act on this information and plan their next training and meal plans.

[0691] 5. Analyzing feedback and updating suggestions

[0692] The server analyzes the feedback received from the user and updates the suggestions. This feedback includes the results and thoughts of the user on their training and diet. Based on the feedback, the generative AI model retrains and improves the accuracy of the suggestions.

[0693] 6. Emotional Data Collection and Analysis

[0694] The server uses an emotion engine to collect and analyze emotional data from the user's facial expressions, voice tone, text input, etc. This allows the server to understand the user's psychological state and reflect this in training and nutrition plan suggestions.

[0695] 7. Generate personalized meal menus and order from food delivery providers

[0696] The server generates a personalized meal menu based on the user's training history, nutritional data, and emotional data, and automatically sends the generated menu to a food delivery company, allowing the user to receive the optimal meal at the right time.

[0697] Hardware and software used

[0698] Hardware:

[0699] Smartphone: A device equipped with a camera and microphone.

[0700] Server: A high-performance server for receiving, analyzing, and sending data.

[0701] software:

[0702] Python scripting: Used to process data, analyze, and operate generative AI models.

[0703] Emotion Recognition API: An external API for analyzing user emotion data.

[0704] Generative AI model API: Used to generate training methods and nutrition plans.

[0705] Database system: Used to store data (e.g. PostgreSQL).

[0706] Specific examples

[0707] High school athlete users enter their weight, height, dietary habits, and training history into a smartphone app and send it to a server. The server receives this data and analyzes it by comparing it with a database of top athletes. At the same time, it analyzes the user's psychological state using an emotion engine. As a result, it generates an optimal training menu for the user (running five times a week and strength training), a nutrition plan (high-protein, low-fat diet), and form correction points (improving arm swing), and sends these to the user's device. The user trains and takes in nutrients according to these suggestions, and then feeds the results and emotional data back to the server. The server analyzes the feedback and emotional data, retrains the generative AI model, and updates the suggestions.

[0708] Prompt Sentence Examples

[0709] "Recommend optimal training and nutrition plans based on the user's training history and nutrition data. Also consider the user's emotional state and include elements that help reduce stress."

[0710] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0711] Step 1:

[0712] Input: The user enters training data, nutrition data, and physical information into the smartphone device and presses the send button.

[0713] Processing: The terminal sends the entered data to the server.

[0714] Output: The server receives the user's training data, nutrition data, and physical information and stores them in a database.

[0715] Specific operation: The user enters information such as weight, height, dietary habits, and training history into the input form and presses the "Submit" button. The device converts the data into JSON format and sends an HTTP request to the server. The server receives this and stores it in a database.

[0716] Step 2:

[0717] Input: The server reads the accumulated training, nutrition, and form data of top athletes.

[0718] Processing: The server prepares the user data and top athlete data for comparison and analysis.

[0719] Output: The top athlete data and user data are ready and we move on to the analysis phase.

[0720] Specific operation: The server queries the necessary items from the database of top athletes and converts them into a format that can be integrated with user data.

[0721] Step 3:

[0722] Input: User data and top athlete data.

[0723] Processing: The server uses the generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user.

[0724] Output: Generates a personalized training plan, nutrition plan, and form corrections.

[0725] How it works: Enter a prompt into the generative AI model, such as, "Based on the user's training history and nutrition data, suggest the optimal training menu and nutrition plan. Include elements that will help reduce stress, taking into account the user's emotional state." The model then analyzes the data and generates the optimal suggestion.

[0726] Step 4:

[0727] Input: Training plan, nutrition plan, and form correction points generated by a generative AI model.

[0728] Processing: The server sends the generated proposal to the user terminal.

[0729] Output: Training plan, nutrition plan, and form correction points are displayed on the user's device.

[0730] Specific operation: The server sends the generated proposal content to the user's device as an HTTP response. The user's device displays the received data in a format that is easy for the user to view.

[0731] Step 5:

[0732] Input: User feedback.

[0733] Processing: The server receives the feedback and uses it for analysis.

[0734] Output: Feedback data parsed by the server.

[0735] Specific operation: The user inputs the results of their training and diet and their thoughts on the device, and presses the "Send Feedback" button. The device then sends the data to the server, which receives and analyzes it.

[0736] Step 6:

[0737] Input: User feedback and sentiment data.

[0738] Processing: The server analyzes the feedback data and sentiment data and updates the suggestions using the generative AI model.

[0739] Output: Updated training plan, nutrition plan.

[0740] How it works: The server analyzes the feedback and emotion data and retrains the generative AI model. The updated model generates new optimized training and nutrition plans.

[0741] Step 7:

[0742] Input: User emotion data.

[0743] Processing: The server analyzes the emotion data using the emotion engine.

[0744] Output: Data based on the user's emotional state.

[0745] Specific operation: The server analyzes the user's facial expressions and voice data and obtains emotion data using the emotion engine API. This emotion data is used as input data for the generative AI model.

[0746] Step 8:

[0747] Input: User's training history, nutritional data, and emotional data.

[0748] Processing: The server generates a personalized meal menu based on this data and sends the order to the food delivery company.

[0749] Output: A personalized meal menu and the order data generated based on it.

[0750] How it works: The server uses a generative AI model to analyze user data and generate an optimal meal menu, which is then automatically sent as an order to a food delivery service.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] [Third embodiment]

[0755] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0756] 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.

[0757] 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).

[0758] 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.

[0759] 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.

[0760] 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).

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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."

[0767] The present invention relates to a system that enables users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, and form correction points. Specific examples of the present invention are described below.

[0768] 1. Server system overview:

[0769] The server has the function of collecting and storing training data, nutritional data, and form data of top athletes. This data is stored in a database and used for analysis. The server also has the function of receiving data entered by users (training data, nutritional data, physical information) and analyzing it using a generative AI model. Based on the analysis results, the generative AI model generates optimal training methods, nutritional intake methods, and form correction points for the user. The generated suggestions are then sent to the user's device.

[0770] 2. Device Features:

[0771] The user terminal has the function of inputting data from the user via an input interface and sending it to the server. This data includes the user's training history, dietary content, and physical information. The user terminal also has the function of receiving suggestions sent from the server and displaying them. Furthermore, the user can input the results and impressions of their training and nutritional intake as feedback and send it to the server.

[0772] 3. User Action:

[0773] The user first enters their physical information, training history, and dietary details into the user device. The device then sends this data to the server, which receives it and begins analysis. Using a generative AI model, the system generates training methods, nutritional intake methods, and form correction points suited to the user, and sends these suggestions to the user's device. The user then performs training and nutritional intake based on the suggestions, and enters the results and impressions into the device to send feedback to the server. The server then reanalyzes the data based on the received feedback and updates the suggestions.

[0774] 4. Example:

[0775] High school athlete users input their weight, height, dietary habits, and training history into their device and send it. The server receives this data and analyzes it by comparing it with a database of top athletes. As a result, it generates an optimal training menu for the user (e.g., running and strength training five times a week), a nutritional intake plan (e.g., a high-protein, low-fat diet), and form corrections (e.g., improving arm swing), and sends these to the user's device. The user follows these suggestions to train and consume nutritional information, and then provides feedback on the results to the server. By repeating this cycle, the system continuously supports the user's growth.

[0776] In this way, the present invention allows users to obtain scientifically based optimal training methods, nutritional intake methods, and form corrections, thereby improving their competitive level. Furthermore, as the generative AI model continuously learns based on feedback, the accuracy of its suggestions improves, allowing it to provide support that is even more tailored to the individual needs of the user.

[0777] The processing flow will be explained below.

[0778] Step 1:

[0779] The user inputs physical information such as weight, height, training history, dietary details, and activity data into the user terminal.

[0780] Step 2:

[0781] The terminal transmits the input data to the server.

[0782] Step 3:

[0783] The server receives the data sent by the user and stores it in a database.

[0784] Step 4:

[0785] The server collects training data, nutritional data, and form data of top athletes and stores it in a database.

[0786] Step 5:

[0787] The server performs preprocessing to analyze the accumulated data, for example, extracting form keyframes from video data and converting them into numerical data.

[0788] Step 6:

[0789] The server inputs the preprocessed data into a generative AI model, which learns the successful patterns of top athletes.

[0790] Step 7:

[0791] The server uses the received user data and a trained AI model to generate optimal training methods, nutritional intake methods, and form corrections for the user.

[0792] Step 8:

[0793] The server transmits the generated proposal content to the user terminal.

[0794] Step 9:

[0795] The terminal displays the suggestions received from the server to the user, who then checks the suggested training method, nutrition plan, and form correction points.

[0796] Step 10:

[0797] The user follows the suggestions to train and take in nutrients, and then enters the results and impressions into the device.

[0798] Step 11:

[0799] The terminal transmits the input feedback data to the server.

[0800] Step 12:

[0801] The server analyzes the received feedback and retrains the generative AI model to improve the accuracy of the suggestions.

[0802] Step 13:

[0803] The server receives advertising data from sporting goods manufacturers and nutritional food manufacturers and generates optimal advertisements to display on user terminals.

[0804] Step 14:

[0805] The device displays the advertisements and recommended product information received from the server to the user, who can then select the products they are interested in and proceed with the purchase.

[0806] Example 1

[0807] 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."

[0808] Conventional systems were not sufficient for users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, and form correction points. In particular, it was difficult to efficiently reflect user feedback and provide suggestions for continuous improvement. There was also a need to quickly and accurately transmit user-entered data to the server and improve the accuracy of analysis.

[0809] 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.

[0810] In this invention, the server includes a means for receiving training data, nutritional data, and physical information from the user, a means for collecting and storing training data, nutritional data, and form data of top athletes, and a means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user. This allows the user to obtain optimal training methods, nutritional intake methods, and form correction points based on scientific evidence in a timely manner. In addition, data entered through the user's terminal can be quickly sent to the server, allowing for continuous improvement in the accuracy of the analysis.

[0811] A "user" is an individual who aims to become a top athlete by using this system to improve their own training methods, nutritional intake methods, and form correction points.

[0812] "Training data" refers to a record of the type, frequency, intensity, duration, etc. of exercise a user is performing.

[0813] "Nutrition data" refers to information such as the user's daily diet, calorie intake, and nutrient ratios.

[0814] "Physical information" refers to basic data about the user's body, such as height, weight, and body fat percentage.

[0815] "Server" means a central data processing unit that collects, stores, and analyzes data received from users, and generates and transmits proposals.

[0816] The "generative AI model" is an artificial intelligence model that analyzes accumulated data and automatically generates optimal training methods, nutritional intake methods, and form correction points for each user.

[0817] "Training method" refers to the individual exercises or programs that a user performs, including the frequency of exercise per week and the type of exercise.

[0818] "Nutrition method" refers to the dietary content and nutrient intake balance that a user should have.

[0819] "Form correction points" refer to areas where the user can improve their body movements and posture during exercise.

[0820] "Feedback" refers to the results and impressions of the user when they carry out the suggested training and nutritional intake methods.

[0821] A "user terminal" is an electronic device that a user uses to input data and communicate with a server.

[0822] The present invention relates to a system that enables users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, and form correction points. Specific embodiments of the present invention are described below.

[0823] Server Configuration

[0824] The server is equipped with a high-performance processor (e.g., Intel Xeon), a large amount of memory (128 GB RAM), and high-speed storage (2 TB SSD). A database management system (e.g., MySQL) and a generative AI model (e.g., TensorFlow) are installed on the server. The server has the following main functions:

[0825] 1. Receive training data, nutrition data, and physical information from the user.

[0826] 2. Collect training data, nutritional data, and form data of top athletes and store it in a database.

[0827] 3. Analyze the received and accumulated data and use a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user.

[0828] 4. The generated proposal is sent to the user's device.

[0829] 5. Analyze the feedback received from users and update the suggestions.

[0830] Device configuration

[0831] The user device is a mobile information terminal such as a smartphone or tablet, equipped with an input interface. A dedicated mobile application (e.g., an app developed with React Native) is installed on the device, and has the following main functions:

[0832] 1. The user enters their physical information, training history, and dietary information.

[0833] 2. Send the entered data to the server.

[0834] 3. Receive and display the proposal sent from the server.

[0835] 4. The user inputs the results and impressions of their training and nutritional intake as feedback and sends it to the server.

[0836] User operations

[0837] First, the user enters their physical information (e.g., height, weight), training history (e.g., weekly exercise frequency, type of exercise), and dietary details into the user device. The entered data is sent to the server via the device. The server receives the data and stores it in a database. The data is then analyzed using a generative AI model to generate the optimal training method, nutritional intake method, and form correction points for the user. The generated suggestions are sent to the user's device and presented to the user. The user then performs training and nutritional intake based on the presented suggestions. The results and impressions are entered into the user device and fed back to the server. The server re-analyzes the feedback and updates the suggestions.

[0838] Specific examples

[0839] For example, a high school athlete enters their weight, height, diet, and training history into a form on a smartphone app. An example input might be "height 180 cm, weight 75 kg, breakfast: salad and yogurt, training: 30 minutes of running." When this information is sent to the server, it is saved in a database and analyzed using a generative AI model. As a result, recommendations are generated for the user, such as "strength training five times a week, high-protein, low-fat diet, form correction: arm swing," and sent to the user's device. The user then trains and takes in nutrients based on the recommendations, and as a result, provides feedback such as "I feel like my muscle strength has improved in a week," which is then sent to the server. Based on this feedback, the server performs further analysis to improve the accuracy of the recommendations.

[0840] Prompt Sentence Examples

[0841] "Generate a suitable workout schedule for a user who is 180cm tall, weighs 75kg, and trains four times a week."

[0842] The above is an embodiment of the present invention. This system allows users to obtain optimal training methods, nutritional intake methods, and form corrections based on scientific evidence. In addition, the generative AI model continuously learns based on user feedback, improving the accuracy of its suggestions.

[0843] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0844] Step 1:

[0845] User data entry and submission

[0846] The user uses the device to input their physical information, training history, and dietary details. Data input by the user may include, for example, "height 180 cm, weight 75 kg, diet: salad and yogurt for breakfast, 30 minutes of running for training." After completing the input, the device formats the user data and sends it to the server. The input at this stage is all the personal data the user provides to the device, and the output is the formatted user data and its transmission to the server.

[0847] Step 2:

[0848] Receiving and storing data

[0849] The server immediately receives the user data from the terminal. The received data is stored in a database system (e.g., MySQL) on the server. Specifically, the server stores the data in the database as "User ID 123, height 180 cm, weight 75 kg, diet: salad and yogurt for breakfast, 30 minutes of running for training." The input is the user data from the terminal, and the output is the data stored in the database on the server.

[0850] Step 3:

[0851] Data analysis

[0852] The server retrieves the saved user data from the database and passes it to a generative AI model (example of use: TensorFlow). The generative AI model performs analysis based on the user data and accumulated data on top athletes. As a result, it generates the optimal training method, nutritional intake method, and form correction points for the user. For example, analysis of the input user data may generate suggestions such as "strength training five times a week, a high-protein, low-fat diet, and form correction points: arm swing." The input is the user data retrieved from the database, and the output is the optimal suggestion from the generative AI model.

[0853] Step 4:

[0854] Submit your proposal

[0855] The server sends the suggestions output from the generative AI model to the user's device. For example, suggestions such as "strength training five times a week, high-protein, low-fat diet, and form corrections: arm swing" are sent to the user's device. The input is the generated suggestions, and the output is the data sent to the user's device.

[0856] Step 5:

[0857] User execution and feedback

[0858] The user checks the suggestions sent from the server and performs the training and diet based on them. The results and impressions of the training are input into the user's device. For example, the user may input their impressions after training, such as "I feel like my muscle strength has improved in a week," and send the feedback to the server via the device. The input is the user's results and impressions, and the output is the feedback data sent to the server.

[0859] Step 6:

[0860] Analyzing feedback and updating suggestions

[0861] The server receives feedback sent by the user and stores it in a database. Based on the stored feedback, the generative AI model is used again to analyze it and improve the accuracy of the suggestions. The updated suggestions are then sent back to the user's device. For example, as a result of analyzing the feedback "I feel like my muscle strength has improved," a new suggestion "Slightly increase the load of your strength training" is generated and sent to the user's device. The input is the feedback data, and the output is the updated suggestions.

[0862] keyword

[0863] Generative AI model, prompt sentence

[0864] (Application example 1)

[0865] 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."

[0866] Previous user training systems and factory robot motion optimization systems lacked a way to efficiently provide optimal training methods or correction points for robot motion. Furthermore, they lacked a system for quickly updating suggestions based on user feedback, making it difficult to provide support that met individual needs.

[0867] 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.

[0868] In this invention, the server includes means for receiving training data, nutritional data, and physical information from users, means for collecting and storing training data, nutritional data, and form data of top athletes, means for collecting and storing factory robot motion data, means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, form correction points, and robot motion correction points for users, means for transmitting the generated training methods, nutritional intake methods, form correction points, and robot motion correction points to a user terminal, and means for analyzing feedback received from users and updating the suggested content, thereby making it possible to provide optimal training methods and motion correction points based on individual needs.

[0869] "User" is the person providing the training data, nutritional data, and physical information or the operator of the equipment.

[0870] "Training data" refers to information that refers to the history and details of the exercises and practices that a user has performed.

[0871] "Nutrition data" refers to information about the dietary content and nutrients that a user has consumed.

[0872] "Physical information" refers to physical data such as the user's weight, height, and body fat percentage.

[0873] A "top athlete" is an athlete who performs at the highest level in their field.

[0874] "Form data" is data that includes details of posture and movement during exercise or movement.

[0875] "Factory robot" refers to automated machinery used in factories and manufacturing environments.

[0876] "Operation data" refers to the history and performance data of the operations performed by factory robots.

[0877] A "generative AI model" is an artificial intelligence algorithm that analyzes accumulated data and calculates optimal training methods and movement correction points.

[0878] "Feedback" refers to information provided by the user about the results and impressions of training and nutritional intake.

[0879] "Analysis" is the process of examining data in detail and extracting meaningful information.

[0880] "Suggested content" refers to training methods, nutritional intake methods, form correction points, or robot movement correction points that are shown to the user by the generative AI model.

[0881] This invention relates to a system that enables users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, form correction points, or factory robot movement correction points. This system collects various data from users, analyzes it using a generative AI model, and provides appropriate suggestions to the users.

[0882] 1. System configuration:

[0883] server:

[0884] The server mainly collects, stores, and analyzes data, and transmits the results. Specifically, it runs a generative AI model using Python and TensorFlow, and stores the data in a PostgreSQL database. The MQTT protocol is used for data transmission and reception.

[0885] User device:

[0886] The user device receives training data, nutritional data, physical information, and feedback from the user via an input interface. This data is then sent to the server using the MQTT protocol. The server also displays the optimal training method, nutritional intake method, and form correction points sent from the server.

[0887] Factory robots:

[0888] Factory robots use sensors to collect operational data and send it to a server. They then execute the operational correction points sent from the server, collect operational data again, and send it to the server to optimize their operations.

[0889] 2. Data flow:

[0890] Data collection:

[0891] Users use the device's input interface to input data such as physical information, training history, and dietary details, while factory robots equipped with sensors collect movement data.

[0892] Data transmission:

[0893] The user terminal and the factory robot send the collected data to the server via the MQTT protocol.

[0894] Data Analysis:

[0895] The server uses Python and TensorFlow to analyze the received data and calculates optimal training methods, nutritional intake methods, form corrections, or robot movement corrections using a generative AI model. The analysis results are stored in a PostgreSQL database.

[0896] Generate and submit a proposal:

[0897] The optimization proposals generated by the server are sent to the user terminal and factory robot via the MQTT protocol.

[0898] 3. Example:

[0899] For example, when a high school athlete inputs and sends their weight, height, dietary habits, and training history to a device, this data is compared with that of top athletes and analyzed by the server. As a result, an optimal training menu and nutrition plan for the user is generated and sent to the user's device. Similarly, the operation data of a factory robot can be sent to the server, and optimal operation correction points can be received.

[0900] An example of a prompt would be, "Use a generative AI model to analyze the operation data of a factory robot and suggest optimized operation patterns and error correction points."

[0901] This allows users to efficiently obtain optimal training methods and movement corrections tailored to their individual needs.In addition, the generative AI model continuously learns based on user feedback and newly collected data, enabling it to improve the accuracy of its suggestions.

[0902] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0903] Step 1:

[0904] The user device uses an input interface to collect data from the user, such as physical information, training history, and dietary details. The input data includes the user's weight, height, exercise details, and dietary details. This data is formatted to be stored in a database and then sent to the server using the MQTT protocol.

[0905] Step 2:

[0906] The server receives data sent from the user's device, including physical information, training history, and dietary details. The server stores this data in a PostgreSQL database.

[0907] Step 3:

[0908] Factory robots use sensors to collect operational data, including the robot's movement patterns, speed, error rate, etc. This data is also sent to a server using the MQTT protocol.

[0909] Step 4:

[0910] The server receives operation data sent from the factory robots and stores it in a PostgreSQL database, allowing for centralized management of both user data and robot data.

[0911] Step 5:

[0912] The server uses Python and TensorFlow to analyze data stored in PostgreSQL. Specifically, it uses a generative AI model to generate optimal training methods, nutritional intake methods, form corrections, and factory robot operation corrections for each user. The analysis uses data from past top athletes and existing optimization algorithms.

[0913] Step 6:

[0914] The server transmits the generated training methods, nutritional intake methods, form correction points, and factory robot operation correction points to the user terminal and the factory robot again via the MQTT protocol.

[0915] Step 7:

[0916] The user terminal receives the suggestions sent from the server and displays them to the user, who then performs training and nutritional intake based on them.

[0917] Step 8:

[0918] The factory robot receives the operation correction points sent from the server and corrects and optimizes its operation. The robot collects the corrected operation data again and sends it to the server.

[0919] Step 9:

[0920] The results and impressions obtained by the user and the factory robot are entered as feedback into the input interface of the user terminal and the robot, and sent to the server. The server analyzes the received feedback and stores and updates it in the PostgreSQL database.

[0921] Step 10:

[0922] The server updates the generative AI model based on the received feedback and newly collected data, and performs re-analysis to improve the accuracy of the suggestions, thereby repeatedly providing optimal suggestions for the user and the robot, enabling continuous performance improvement.

[0923] 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.

[0924] The present invention relates to a system that supports a user in more effectively managing their training and nutrition, enabling them to perform at the level of a top athlete. Specific examples of the present invention are described below.

[0925] 1. Server system overview:

[0926] The server has the ability to receive training data, nutritional data, and physical information from users and store it in a database. The server also collects training data, nutritional data, and form data from top athletes and stores it in a database. The server then uses a generative AI model to analyze the accumulated data and generate optimal training menus, nutrition plans, and form correction suggestions for each user. It also has the ability to send suggestions to the user's device and update the suggestions based on feedback received from the user.

[0927] 2. Emotion engine feature additions:

[0928] The system also incorporates an emotion engine, which has the ability to collect and analyze emotional data from the user's facial expressions, voice tone, text input, etc. The emotional data is used to understand the user's current psychological state and reflect it in training and nutrition plan suggestions.

[0929] 3. Device Features:

[0930] The user terminal has the function of inputting data from the user via an input interface and sending it to the server. This data includes the user's training history, dietary content, and physical information. The user terminal also has the function of receiving suggestions sent from the server and displaying them. Furthermore, the user can input the results and impressions of their training and nutritional intake as feedback and send them to the server. It also has an interface for collecting emotional data.

[0931] 4. User Action:

[0932] The user first enters their physical information, training history, and dietary details into the user device. The device sends this data to the server, which receives it and begins analysis. A generative AI model is used to generate training methods, nutritional intake methods, and form correction points that are suitable for the user. An emotion engine is also used to collect and analyze the user's emotional data and reflect this in the suggestions. The generated suggestions are sent to the user device. The user then performs training and nutritional intake based on the suggestions, and enters the results and impressions into the device, sending feedback to the server. The server analyzes the received feedback and emotional data to improve the accuracy of the suggestions.

[0933] 5. Examples:

[0934] A high school athlete user inputs and sends their weight, height, dietary habits, and training history into their device. The server receives this data and analyzes it by comparing it with a database of top athletes. At the same time, an emotion engine analyzes the user's psychological state. As a result, an optimal training menu (five times a week of running and strength training), nutrition plan (high-protein, low-fat diet), and form correction points (improvement of arm swing) are generated and sent to the user's device. The user trains and takes in nutrients according to these suggestions, and then feeds the results and emotional data back to the server. The server analyzes the feedback and emotional data, retrains the generative AI model, and updates the suggestions.

[0935] In this way, the present invention allows users to obtain optimal training methods, nutritional intake methods, and form correction points based on scientific evidence, thereby enabling them to improve their competitive level. Furthermore, by using emotional data, flexible suggestions can be made based on the user's psychological state, which can lead to better results.

[0936] The processing flow will be explained below.

[0937] Step 1:

[0938] The user inputs their physical information (weight, height, etc.), training history, and dietary details into the user terminal.

[0939] Step 2:

[0940] The terminal transmits the input data to the server.

[0941] Step 3:

[0942] The server receives the data sent by the user and stores it in a database.

[0943] Step 4:

[0944] The server collects training data, nutrition data, and form data of top athletes and stores it in a database.

[0945] Step 5:

[0946] The device collects emotion data from the user's facial expressions and voice and sends it to the server. In this step, the emotion engine performs facial expression recognition and voice analysis to extract the user's emotion as numerical data.

[0947] Step 6:

[0948] The server receives the emotion data and stores it in a database.

[0949] Step 7:

[0950] The server preprocesses the accumulated data (user data and top athlete data) and generates a dataset for analysis.

[0951] Step 8:

[0952] The server uses a generative AI model to analyze the pre-processed data and generate optimal training methods, nutritional intake methods, and form correction points for the user.

[0953] Step 9:

[0954] The server dynamically adjusts the difficulty and intensity of the suggested content based on the emotional data, creating a flexible training plan that suits the user's psychological state.

[0955] Step 10:

[0956] The server transmits the generated training method, nutritional intake method, and form correction points to the user terminal.

[0957] Step 11:

[0958] The device displays the suggestions received from the server to the user, who then checks the suggestions and carries out the actual training and meal plan.

[0959] Step 12:

[0960] The user performs training and nutritional intake based on the suggestions, and then inputs the results and impressions into the terminal.

[0961] Step 13:

[0962] The terminal transmits the input feedback data to the server.

[0963] Step 14:

[0964] The server analyzes the received feedback and retrains the generative AI model to improve the accuracy of the suggestions. It also analyzes newly collected emotion data and incorporates it into the next suggestions.

[0965] Step 15:

[0966] The server receives advertising data from sporting goods manufacturers and nutritional food manufacturers and generates optimal advertisements to display on user terminals.

[0967] Step 16:

[0968] The device displays the advertisements and recommended product information received from the server to the user, who can then select the products they are interested in and proceed with the purchase.

[0969] Example 2

[0970] 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."

[0971] Conventional training support systems support users' training and nutritional management, but they are unable to make suggestions that take into account each individual's psychological state, making it difficult to achieve effective training and nutritional management. Furthermore, systems that dynamically update suggestions based on user feedback are also lacking. This results in insufficient support for users to achieve high performance.

[0972] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0973] In this invention, the server includes means for receiving training data, nutritional data, and physical information from a user, means for collecting and storing exercise data, nutritional data, and form data of top athletes, means for analyzing the stored data and using a generative AI model to generate an optimal training method, nutritional intake method, and form correction points for the user, means for transmitting the generated training method, nutritional intake method, and form correction points to a user terminal, means for collecting and analyzing emotional data from the user terminal, means for generating training method and nutritional intake method suggestions that reflect the emotional data, and means for analyzing feedback received from the user and updating the suggestions. This enables flexible suggestions that take the user's emotional data into consideration, and makes it possible to provide optimal training methods and nutritional intake methods that are dynamically updated.

[0974] "User" means an individual who wishes to use the System to improve their own training and nutritional management.

[0975] "Training data" refers to a record of the type, duration, intensity, etc. of exercise performed by the user.

[0976] "Nutrition data" refers to information such as the type and amount of food consumed by the user, calories, nutrients, etc.

[0977] "Physical information" refers to data that indicates the user's physical characteristics, such as weight, height, and body fat percentage.

[0978] A "top athlete" is a competitor who has demonstrated great skill and achievement in a particular sporting field.

[0979] "Athletic data" refers to information about training content and performance recorded by top athletes.

[0980] "Form data" refers to detailed information that records the physical movements of top athletes during exercise.

[0981] A "generative AI model" is an artificial intelligence used to generate optimal training and nutrition plans based on large amounts of data.

[0982] "Emotion data" refers to information about a user's psychological state that can be inferred from facial expressions, voice tone, text input, and the like.

[0983] A "user terminal" refers to a device such as a computer or smartphone used by a user.

[0984] "Feedback" refers to information that a user provides to the system regarding the results and impressions of their training and nutritional intake.

[0985] "Suggestions" refer to training methods, nutritional intake methods, and form correction points provided to users based on the results of analysis of the generative AI model and emotional data.

[0986] The present invention relates to a system that supports users in more effectively managing their training and nutrition, enabling them to perform at the level of a top athlete. A specific example of this system is described below.

[0987] The system consists of a server, a user device, an emotion engine, and a generative AI model. The server receives training data, nutritional data, and physical information from the user and stores this data in a database. The software used includes a database management system and a generative AI model. It also collects exercise data, nutritional data, and form data from top athletes and stores this in the database. The server analyzes the accumulated data and uses the generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user.

[0988] The user terminal has the function of inputting data from the user via an input interface and sending it to the server. This data includes the user's training history, dietary content, and physical information. The user terminal also has the function of receiving and displaying suggestions sent from the server. Furthermore, the user can input the results and impressions of their training and nutritional intake as feedback and send it to the server. It also has an interface for collecting emotional data. This emotion engine has the function of collecting and analyzing emotional data from the user's facial expressions, voice tone, text input, etc. Emotional data is used to understand the user's current psychological state and reflect it in training and nutrition plan suggestions.

[0989] As a specific use case, consider the case where a high school athlete inputs and sends their weight, height, dietary habits, and training history into their device. The server receives this data and analyzes it by comparing it with a database of top athletes. At the same time, the emotion engine analyzes the user's psychological state. As a result, the system generates an optimal training menu for the user (e.g., running and strength training five times a week), a nutrition plan (e.g., a high-protein, low-fat diet), and form corrections (e.g., improving arm swing), and sends these suggestions to the user's device. The user then trains and takes in nutrients according to these suggestions, and provides feedback on the results and emotional data to the server. The server analyzes the feedback and emotional data, retrains the generative AI model, and updates the suggestions.

[0990] A unique feature of this system is that it can propose flexible training and nutrition plans that reflect the user's emotional data, allowing users to find training and nutritional methods that are optimal for their own psychological state, thereby improving their sports performance.

[0991] Examples of prompts to be used in this system include, "Generate the optimal training menu and nutrition plan based on the user's training data, nutrition data, and physical information. Also, make suggestions for improvements taking the user's emotional data into consideration," "Output the results of an analysis of the user's training menu compared with data from top athletes," and "Update the suggestions based on the user's real-time feedback to provide a more accurate training menu."

[0992] In this way, the present invention allows users to obtain optimal training methods, nutritional intake methods, and form corrections based on scientific evidence, thereby enabling them to improve their competitive level. Furthermore, by using emotional data, flexible suggestions can be made based on the user's psychological state, which can lead to better results.

[0993] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0994] Step 1: Enter and submit data

[0995] The user inputs their weight, height, dietary habits, training history, etc. into the user terminal. This data is collected through an input interface installed on the user terminal. When the user presses the "send" button, the user terminal sends this data to the server.

[0996] Input: Weight, height, diet, training history

[0997] Output: Data sent from the user device to the server

[0998] Specific action: The user enters data into a smartphone application and presses the "Submit" button.

[0999] Step 2: Receiving and storing data

[1000] The server receives the data sent from the user terminal and stores the received data in a database.

[1001] Input: Data sent from the user's device

[1002] Output: User data stored in the database

[1003] What it does: The server listens on a specific port and automatically stores the received data in a MySQL database.

[1004] Step 3: Collecting and storing top athlete data

[1005] The server collects the exercise data, nutrition data, and form data of top athletes and stores them in a database.

[1006] Input: Top athletes' exercise data, nutrition data, and form data

[1007] Output: Top athlete data stored in a database

[1008] Specific operation: Automatically collect data from various data sources using APIs and store it in a database.

[1009] Step 4: Data analysis and proposal generation

[1010] The server compares the user data stored in the database with the data of top athletes and uses a generative AI model to generate optimal training methods, nutritional intake methods, and form corrections for the user. In this process, the generative AI model runs on frameworks such as TensorFlow.

[1011] Input: User data and top athlete data stored in the database

[1012] Output: Optimal training methods, nutritional intake methods, and form correction points

[1013] Specific operation: The generative AI model analyzes the data and outputs the results in JSON format, and the server generates suggestions based on this.

[1014] Step 5: Submit and view your proposal

[1015] The server sends the generated training methods, nutritional intake methods, and form correction suggestions to the user's device. The user's device receives the suggestions and displays them to the user. They are displayed in the form of a notification, allowing the user to check the details.

[1016] Input: Optimal training methods, nutritional intake methods, form correction points

[1017] Output: Proposal content notified to the user's device

[1018] Specific operation: The proposal is displayed in the form of a notification in the application on the user's device.

[1019] Step 6: Collect and analyze emotion data

[1020] The user terminal collects emotion data from facial expressions, voice tones, and text input. The emotion engine analyzes the emotion data and sends the results to the server.

[1021] Input: Facial expressions, voice tone, text input

[1022] Output: Emotion data analysis results sent to the server

[1023] How it works: The facial expression recognition software uses OpenCV to analyze the user's facial expressions in real time and sends the results to the server.

[1024] Step 7: Update suggestions taking into account sentiment data

[1025] The server reflects the emotional data obtained from the emotion engine and generates suggestions for training methods and nutritional intake methods.

[1026] Input: Emotion data analysis results

[1027] Output: Suggestions for training and nutritional intake methods that reflect emotional data

[1028] Specific operation: The generative AI model is run again based on the results of emotion data analysis to generate new suggestions.

[1029] Step 8: Send and analyze feedback

[1030] The user follows the suggested training menu and nutrition plan, inputs the results and impressions into the user's device, and sends them to the server. The server receives and analyzes the feedback, and based on the results, retrains the generative AI model and updates the suggestions.

[1031] Input: Training execution results, feedback

[1032] Output: Updated proposal

[1033] Specific operation: The user enters details of their training and diet into the application, and by pressing the "Feedback" button, the information is sent to the server. The server analyzes the feedback and reflects it in the generative AI model.

[1034] This will enable the system to dynamically provide optimal training and nutritional intake methods that take into account the user's emotional data, thereby supporting high sports performance.

[1035] (Application example 2)

[1036] 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."

[1037] While conventional training support systems can collect and analyze users' training and nutritional data, they have difficulty personalizing training and nutritional management by taking into account the user's psychological state and emotions. Furthermore, due to a lack of provision of personalized meal plans based on this data and collaboration with food delivery companies, it has been difficult for users to achieve consistent training and nutritional management.

[1038] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1039] In this invention, the server includes a means for receiving training data, nutritional data, and physical information from the user, a means for collecting and storing training data, nutritional data, and form data of top athletes, and a means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user. This makes it possible to generate optimal training methods and personalized meal plans based on the individual health and psychological state of the user, and to support their implementation.

[1040] The "means for receiving training data, nutritional data, and physical information from the user" refers to an interface that allows the user to input their own training history, dietary content, and physical information such as weight and height, and transmit this information in digital form to the server.

[1041] "Means for collecting and storing training data, nutritional data, and form data of top athletes" refers to a system for compiling and storing information on the training methods, nutritional intake patterns, and movement form of outstanding athletes in a database.

[1042] "Means of analyzing accumulated data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for each user" refers to technology that analyzes the vast amount of data accumulated on a server and utilizes artificial intelligence to generate training plans, nutritional intake plans, and movement improvement points that are customized for each individual user.

[1043] "Means for transmitting the generated training methods, nutritional intake methods, and form correction points to the user's terminal" refers to a communication technology that sends the suggestions and plans generated by the server to the user's terminal, such as a smartphone or PC, and displays them.

[1044] The "means for analyzing feedback received from users and updating the content of suggestions" refers to a system that collects the results and impressions of the user's training and diet, analyzes them, and updates the next suggestions to make them more accurate.

[1045] "Means for collecting and analyzing emotional data" refers to technology that reads the user's emotional state from their facial expressions and vocal tone, and analyzes that data to understand the user's psychological state.

[1046] "Means for generating personalized meal menus based on a user's training history, nutritional data, and emotional data, and sending orders to food delivery companies" refers to a system that plans individually optimized meal menus taking into account a user's past training, dietary history, and emotional state, and automatically places orders with a food delivery service.

[1047] The present invention provides a system that allows a user to perform training and nutritional management more effectively. Specific embodiments for carrying out the invention are described below.

[1048] 1. System Overview

[1049] The server has the function of receiving training data, nutritional data, and physical information from the user's device. This includes an interface for users to input their own data and communication technology for transmitting that data to the server. Users input data using devices such as smartphones or PCs.

[1050] 2. Data collection and storage

[1051] The server collects training data, nutrition data, and form data from top athletes and stores them in a database. Data on outstanding athletes is obtained from books, the internet, and specialist institutions, and then categorized and stored in the database. This data serves as the basis for optimal recommendations to users.

[1052] 3. Analysis using generative AI models

[1053] The server analyzes the accumulated data and uses a generative AI model to generate optimal training methods, nutritional intake methods, and form corrections for the user. The generated suggestions are based on customized and pre-programmed algorithms.

[1054] 4. Submit your proposal

[1055] The server then sends the generated training methods, nutritional intake methods, and form correction points to the user's device. The communication protocol uses an internet connection, allowing the user to act on this information and plan their next training and meal plans.

[1056] 5. Analyzing feedback and updating suggestions

[1057] The server analyzes the feedback received from the user and updates the suggestions. This feedback includes the results and thoughts of the user on their training and diet. Based on the feedback, the generative AI model retrains and improves the accuracy of the suggestions.

[1058] 6. Emotional Data Collection and Analysis

[1059] The server uses an emotion engine to collect and analyze emotional data from the user's facial expressions, voice tone, text input, etc. This allows the server to understand the user's psychological state and reflect this in training and nutrition plan suggestions.

[1060] 7. Generate personalized meal menus and order from food delivery providers

[1061] The server generates a personalized meal menu based on the user's training history, nutritional data, and emotional data, and automatically sends the generated menu to a food delivery company, allowing the user to receive the optimal meal at the right time.

[1062] Hardware and software used

[1063] Hardware:

[1064] Smartphone: A device equipped with a camera and microphone.

[1065] Server: A high-performance server for receiving, analyzing, and sending data.

[1066] software:

[1067] Python scripting: Used to process data, analyze, and operate generative AI models.

[1068] Emotion Recognition API: An external API for analyzing user emotion data.

[1069] Generative AI model API: Used to generate training methods and nutrition plans.

[1070] Database system: Used to store data (e.g. PostgreSQL).

[1071] Specific examples

[1072] High school athlete users enter their weight, height, dietary habits, and training history into a smartphone app and send it to a server. The server receives this data and analyzes it by comparing it with a database of top athletes. At the same time, it analyzes the user's psychological state using an emotion engine. As a result, it generates an optimal training menu for the user (running five times a week and strength training), a nutrition plan (high-protein, low-fat diet), and form correction points (improving arm swing), and sends these to the user's device. The user trains and takes in nutrients according to these suggestions, and then feeds the results and emotional data back to the server. The server analyzes the feedback and emotional data, retrains the generative AI model, and updates the suggestions.

[1073] Prompt Sentence Examples

[1074] "Recommend optimal training and nutrition plans based on the user's training history and nutrition data. Also consider the user's emotional state and include elements that help reduce stress."

[1075] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1076] Step 1:

[1077] Input: The user enters training data, nutrition data, and physical information into the smartphone device and presses the send button.

[1078] Processing: The terminal sends the entered data to the server.

[1079] Output: The server receives the user's training data, nutrition data, and physical information and stores them in a database.

[1080] Specific operation: The user enters information such as weight, height, dietary habits, and training history into the input form and presses the "Submit" button. The device converts the data into JSON format and sends an HTTP request to the server. The server receives this and stores it in a database.

[1081] Step 2:

[1082] Input: The server reads the accumulated training, nutrition, and form data of top athletes.

[1083] Processing: The server prepares the user data and top athlete data for comparison and analysis.

[1084] Output: The top athlete data and user data are ready and we move on to the analysis phase.

[1085] Specific operation: The server queries the necessary items from the database of top athletes and converts them into a format that can be integrated with user data.

[1086] Step 3:

[1087] Input: User data and top athlete data.

[1088] Processing: The server uses the generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user.

[1089] Output: Generates a personalized training plan, nutrition plan, and form corrections.

[1090] How it works: Enter a prompt into the generative AI model, such as, "Based on the user's training history and nutrition data, suggest the optimal training menu and nutrition plan. Include elements that will help reduce stress, taking into account the user's emotional state." The model then analyzes the data and generates the optimal suggestion.

[1091] Step 4:

[1092] Input: Training plan, nutrition plan, and form correction points generated by a generative AI model.

[1093] Processing: The server sends the generated proposal to the user terminal.

[1094] Output: Training plan, nutrition plan, and form correction points are displayed on the user's device.

[1095] Specific operation: The server sends the generated proposal content to the user's device as an HTTP response. The user's device displays the received data in a format that is easy for the user to view.

[1096] Step 5:

[1097] Input: User feedback.

[1098] Processing: The server receives the feedback and uses it for analysis.

[1099] Output: Feedback data parsed by the server.

[1100] Specific operation: The user inputs the results of their training and diet and their thoughts on the device, and presses the "Send Feedback" button. The device then sends the data to the server, which receives and analyzes it.

[1101] Step 6:

[1102] Input: User feedback and sentiment data.

[1103] Processing: The server analyzes the feedback data and sentiment data and updates the suggestions using the generative AI model.

[1104] Output: Updated training plan, nutrition plan.

[1105] How it works: The server analyzes the feedback and emotion data and retrains the generative AI model. The updated model generates new optimized training and nutrition plans.

[1106] Step 7:

[1107] Input: User emotion data.

[1108] Processing: The server analyzes the emotion data using the emotion engine.

[1109] Output: Data based on the user's emotional state.

[1110] Specific operation: The server analyzes the user's facial expressions and voice data and obtains emotion data using the emotion engine API. This emotion data is used as input data for the generative AI model.

[1111] Step 8:

[1112] Input: User's training history, nutritional data, and emotional data.

[1113] Processing: The server generates a personalized meal menu based on this data and sends the order to the food delivery company.

[1114] Output: A personalized meal menu and the order data generated based on it.

[1115] How it works: The server uses a generative AI model to analyze user data and generate an optimal meal menu, which is then automatically sent as an order to a food delivery service.

[1116] 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.

[1117] 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.

[1118] 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.

[1119] [Fourth embodiment]

[1120] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1121] 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.

[1122] 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).

[1123] 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.

[1124] 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.

[1125] 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).

[1126] 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.

[1127] 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.

[1128] 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.

[1129] 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.

[1130] 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.

[1131] 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.

[1132] 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."

[1133] The present invention relates to a system that enables users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, and form correction points. Specific examples of the present invention are described below.

[1134] 1. Server system overview:

[1135] The server has the function of collecting and storing training data, nutritional data, and form data of top athletes. This data is stored in a database and used for analysis. The server also has the function of receiving data entered by users (training data, nutritional data, physical information) and analyzing it using a generative AI model. Based on the analysis results, the generative AI model generates optimal training methods, nutritional intake methods, and form correction points for the user. The generated suggestions are then sent to the user's device.

[1136] 2. Device Features:

[1137] The user terminal has the function of inputting data from the user via an input interface and sending it to the server. This data includes the user's training history, dietary content, and physical information. The user terminal also has the function of receiving suggestions sent from the server and displaying them. Furthermore, the user can input the results and impressions of their training and nutritional intake as feedback and send it to the server.

[1138] 3. User Action:

[1139] The user first enters their physical information, training history, and dietary details into the user device. The device then sends this data to the server, which receives it and begins analysis. Using a generative AI model, the system generates training methods, nutritional intake methods, and form correction points suited to the user, and sends these suggestions to the user's device. The user then performs training and nutritional intake based on the suggestions, and enters the results and impressions into the device to send feedback to the server. The server then reanalyzes the data based on the received feedback and updates the suggestions.

[1140] 4. Example:

[1141] High school athlete users input their weight, height, dietary habits, and training history into their device and send it. The server receives this data and analyzes it by comparing it with a database of top athletes. As a result, it generates an optimal training menu for the user (e.g., running and strength training five times a week), a nutritional intake plan (e.g., a high-protein, low-fat diet), and form corrections (e.g., improving arm swing), and sends these to the user's device. The user follows these suggestions to train and consume nutritional information, and then provides feedback on the results to the server. By repeating this cycle, the system continuously supports the user's growth.

[1142] In this way, the present invention allows users to obtain scientifically based optimal training methods, nutritional intake methods, and form corrections, thereby improving their competitive level. Furthermore, as the generative AI model continuously learns based on feedback, the accuracy of its suggestions improves, allowing it to provide support that is even more tailored to the individual needs of the user.

[1143] The processing flow will be explained below.

[1144] Step 1:

[1145] The user inputs physical information such as weight, height, training history, dietary details, and activity data into the user terminal.

[1146] Step 2:

[1147] The terminal transmits the input data to the server.

[1148] Step 3:

[1149] The server receives the data sent by the user and stores it in a database.

[1150] Step 4:

[1151] The server collects training data, nutritional data, and form data of top athletes and stores it in a database.

[1152] Step 5:

[1153] The server performs preprocessing to analyze the accumulated data, for example, extracting form keyframes from video data and converting them into numerical data.

[1154] Step 6:

[1155] The server inputs the preprocessed data into a generative AI model, which learns the successful patterns of top athletes.

[1156] Step 7:

[1157] The server uses the received user data and a trained AI model to generate optimal training methods, nutritional intake methods, and form corrections for the user.

[1158] Step 8:

[1159] The server transmits the generated proposal content to the user terminal.

[1160] Step 9:

[1161] The terminal displays the suggestions received from the server to the user, who then checks the suggested training method, nutrition plan, and form correction points.

[1162] Step 10:

[1163] The user follows the suggestions to train and take in nutrients, and then enters the results and impressions into the device.

[1164] Step 11:

[1165] The terminal transmits the input feedback data to the server.

[1166] Step 12:

[1167] The server analyzes the received feedback and retrains the generative AI model to improve the accuracy of the suggestions.

[1168] Step 13:

[1169] The server receives advertising data from sporting goods manufacturers and nutritional food manufacturers and generates optimal advertisements to display on user terminals.

[1170] Step 14:

[1171] The device displays the advertisements and recommended product information received from the server to the user, who can then select the products they are interested in and proceed with the purchase.

[1172] Example 1

[1173] 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."

[1174] Conventional systems were not sufficient for users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, and form correction points. In particular, it was difficult to efficiently reflect user feedback and provide suggestions for continuous improvement. There was also a need to quickly and accurately transmit user-entered data to the server and improve the accuracy of analysis.

[1175] 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.

[1176] In this invention, the server includes a means for receiving training data, nutritional data, and physical information from the user, a means for collecting and storing training data, nutritional data, and form data of top athletes, and a means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user. This allows the user to obtain optimal training methods, nutritional intake methods, and form correction points based on scientific evidence in a timely manner. In addition, data entered through the user's terminal can be quickly sent to the server, allowing for continuous improvement in the accuracy of the analysis.

[1177] A "user" is an individual who aims to become a top athlete by using this system to improve their own training methods, nutritional intake methods, and form correction points.

[1178] "Training data" refers to a record of the type, frequency, intensity, duration, etc. of exercise a user is performing.

[1179] "Nutrition data" refers to information such as the user's daily diet, calorie intake, and nutrient ratios.

[1180] "Physical information" refers to basic data about the user's body, such as height, weight, and body fat percentage.

[1181] "Server" means a central data processing unit that collects, stores, and analyzes data received from users, and generates and transmits proposals.

[1182] The "generative AI model" is an artificial intelligence model that analyzes accumulated data and automatically generates optimal training methods, nutritional intake methods, and form correction points for each user.

[1183] "Training method" refers to the individual exercises or programs that a user performs, including the frequency of exercise per week and the type of exercise.

[1184] "Nutrition method" refers to the dietary content and nutrient intake balance that a user should have.

[1185] "Form correction points" refer to areas where the user can improve their body movements and posture during exercise.

[1186] "Feedback" refers to the results and impressions of the user when they carry out the suggested training and nutritional intake methods.

[1187] A "user terminal" is an electronic device that a user uses to input data and communicate with a server.

[1188] The present invention relates to a system that enables users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, and form correction points. Specific embodiments of the present invention are described below.

[1189] Server Configuration

[1190] The server is equipped with a high-performance processor (e.g., Intel Xeon), a large amount of memory (128 GB RAM), and high-speed storage (2 TB SSD). A database management system (e.g., MySQL) and a generative AI model (e.g., TensorFlow) are installed on the server. The server has the following main functions:

[1191] 1. Receive training data, nutrition data, and physical information from the user.

[1192] 2. Collect training data, nutritional data, and form data of top athletes and store it in a database.

[1193] 3. Analyze the received and accumulated data and use a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user.

[1194] 4. The generated proposal is sent to the user's device.

[1195] 5. Analyze the feedback received from users and update the suggestions.

[1196] Device configuration

[1197] The user device is a mobile information terminal such as a smartphone or tablet, equipped with an input interface. A dedicated mobile application (e.g., an app developed with React Native) is installed on the device, and has the following main functions:

[1198] 1. The user enters their physical information, training history, and dietary information.

[1199] 2. Send the entered data to the server.

[1200] 3. Receive and display the proposal sent from the server.

[1201] 4. The user inputs the results and impressions of their training and nutritional intake as feedback and sends it to the server.

[1202] User operations

[1203] First, the user enters their physical information (e.g., height, weight), training history (e.g., weekly exercise frequency, type of exercise), and dietary details into the user device. The entered data is sent to the server via the device. The server receives the data and stores it in a database. The data is then analyzed using a generative AI model to generate the optimal training method, nutritional intake method, and form correction points for the user. The generated suggestions are sent to the user's device and presented to the user. The user then performs training and nutritional intake based on the presented suggestions. The results and impressions are entered into the user device and fed back to the server. The server re-analyzes the feedback and updates the suggestions.

[1204] Specific examples

[1205] For example, a high school athlete enters their weight, height, diet, and training history into a form on a smartphone app. An example input might be "height 180 cm, weight 75 kg, breakfast: salad and yogurt, training: 30 minutes of running." When this information is sent to the server, it is saved in a database and analyzed using a generative AI model. As a result, recommendations are generated for the user, such as "strength training five times a week, high-protein, low-fat diet, form correction: arm swing," and sent to the user's device. The user then trains and takes in nutrients based on the recommendations, and as a result, provides feedback such as "I feel like my muscle strength has improved in a week," which is then sent to the server. Based on this feedback, the server performs further analysis to improve the accuracy of the recommendations.

[1206] Prompt Sentence Examples

[1207] "Generate a suitable workout schedule for a user who is 180cm tall, weighs 75kg, and trains four times a week."

[1208] The above is an embodiment of the present invention. This system allows users to obtain optimal training methods, nutritional intake methods, and form corrections based on scientific evidence. In addition, the generative AI model continuously learns based on user feedback, improving the accuracy of its suggestions.

[1209] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1210] Step 1:

[1211] User data entry and submission

[1212] The user uses the device to input their physical information, training history, and dietary details. Data input by the user may include, for example, "height 180 cm, weight 75 kg, diet: salad and yogurt for breakfast, 30 minutes of running for training." After completing the input, the device formats the user data and sends it to the server. The input at this stage is all the personal data the user provides to the device, and the output is the formatted user data and its transmission to the server.

[1213] Step 2:

[1214] Receiving and storing data

[1215] The server immediately receives the user data from the terminal. The received data is stored in a database system (e.g., MySQL) on the server. Specifically, the server stores the data in the database as "User ID 123, height 180 cm, weight 75 kg, diet: salad and yogurt for breakfast, 30 minutes of running for training." The input is the user data from the terminal, and the output is the data stored in the database on the server.

[1216] Step 3:

[1217] Data analysis

[1218] The server retrieves the saved user data from the database and passes it to a generative AI model (example of use: TensorFlow). The generative AI model performs analysis based on the user data and accumulated data on top athletes. As a result, it generates the optimal training method, nutritional intake method, and form correction points for the user. For example, analysis of the input user data may generate suggestions such as "strength training five times a week, a high-protein, low-fat diet, and form correction points: arm swing." The input is the user data retrieved from the database, and the output is the optimal suggestion from the generative AI model.

[1219] Step 4:

[1220] Submit your proposal

[1221] The server sends the suggestions output from the generative AI model to the user's device. For example, suggestions such as "strength training five times a week, high-protein, low-fat diet, and form corrections: arm swing" are sent to the user's device. The input is the generated suggestions, and the output is the data sent to the user's device.

[1222] Step 5:

[1223] User execution and feedback

[1224] The user checks the suggestions sent from the server and performs the training and diet based on them. The results and impressions of the training are input into the user's device. For example, the user may input their impressions after training, such as "I feel like my muscle strength has improved in a week," and send the feedback to the server via the device. The input is the user's results and impressions, and the output is the feedback data sent to the server.

[1225] Step 6:

[1226] Analyzing feedback and updating suggestions

[1227] The server receives feedback sent by the user and stores it in a database. Based on the stored feedback, the generative AI model is used again to analyze it and improve the accuracy of the suggestions. The updated suggestions are then sent back to the user's device. For example, as a result of analyzing the feedback "I feel like my muscle strength has improved," a new suggestion "Slightly increase the load of your strength training" is generated and sent to the user's device. The input is the feedback data, and the output is the updated suggestions.

[1228] keyword

[1229] Generative AI model, prompt sentence

[1230] (Application example 1)

[1231] 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."

[1232] Previous user training systems and factory robot motion optimization systems lacked a way to efficiently provide optimal training methods or correction points for robot motion. Furthermore, they lacked a system for quickly updating suggestions based on user feedback, making it difficult to provide support that met individual needs.

[1233] 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.

[1234] In this invention, the server includes means for receiving training data, nutritional data, and physical information from users, means for collecting and storing training data, nutritional data, and form data of top athletes, means for collecting and storing factory robot motion data, means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, form correction points, and robot motion correction points for users, means for transmitting the generated training methods, nutritional intake methods, form correction points, and robot motion correction points to a user terminal, and means for analyzing feedback received from users and updating the suggested content, thereby making it possible to provide optimal training methods and motion correction points based on individual needs.

[1235] "User" is the person providing the training data, nutritional data, and physical information or the operator of the equipment.

[1236] "Training data" refers to information that refers to the history and details of the exercises and practices that a user has performed.

[1237] "Nutrition data" refers to information about the dietary content and nutrients that a user has consumed.

[1238] "Physical information" refers to physical data such as the user's weight, height, and body fat percentage.

[1239] A "top athlete" is an athlete who performs at the highest level in their field.

[1240] "Form data" is data that includes details of posture and movement during exercise or movement.

[1241] "Factory robot" refers to automated machinery used in factories and manufacturing environments.

[1242] "Operation data" refers to the history and performance data of the operations performed by factory robots.

[1243] A "generative AI model" is an artificial intelligence algorithm that analyzes accumulated data and calculates optimal training methods and movement correction points.

[1244] "Feedback" refers to information provided by the user about the results and impressions of training and nutritional intake.

[1245] "Analysis" is the process of examining data in detail and extracting meaningful information.

[1246] "Suggested content" refers to training methods, nutritional intake methods, form correction points, or robot movement correction points that are shown to the user by the generative AI model.

[1247] This invention relates to a system that enables users aiming to become top athletes to obtain optimal training methods, nutritional intake methods, form correction points, or factory robot movement correction points. This system collects various data from users, analyzes it using a generative AI model, and provides appropriate suggestions to the users.

[1248] 1. System configuration:

[1249] server:

[1250] The server mainly collects, stores, and analyzes data, and transmits the results. Specifically, it runs a generative AI model using Python and TensorFlow, and stores the data in a PostgreSQL database. The MQTT protocol is used for data transmission and reception.

[1251] User device:

[1252] The user device receives training data, nutritional data, physical information, and feedback from the user via an input interface. This data is then sent to the server using the MQTT protocol. The server also displays the optimal training method, nutritional intake method, and form correction points sent from the server.

[1253] Factory robots:

[1254] Factory robots use sensors to collect operational data and send it to a server. They then execute the operational correction points sent from the server, collect operational data again, and send it to the server to optimize their operations.

[1255] 2. Data flow:

[1256] Data collection:

[1257] Users use the device's input interface to input data such as physical information, training history, and dietary details, while factory robots equipped with sensors collect movement data.

[1258] Data transmission:

[1259] The user terminal and the factory robot send the collected data to the server via the MQTT protocol.

[1260] Data Analysis:

[1261] The server uses Python and TensorFlow to analyze the received data and calculates optimal training methods, nutritional intake methods, form corrections, or robot movement corrections using a generative AI model. The analysis results are stored in a PostgreSQL database.

[1262] Generate and submit a proposal:

[1263] The optimization proposals generated by the server are sent to the user terminal and factory robot via the MQTT protocol.

[1264] 3. Example:

[1265] For example, when a high school athlete inputs and sends their weight, height, dietary habits, and training history to a device, this data is compared with that of top athletes and analyzed by the server. As a result, an optimal training menu and nutrition plan for the user is generated and sent to the user's device. Similarly, the operation data of a factory robot can be sent to the server, and optimal operation correction points can be received.

[1266] An example of a prompt would be, "Use a generative AI model to analyze the operation data of a factory robot and suggest optimized operation patterns and error correction points."

[1267] This allows users to efficiently obtain optimal training methods and movement corrections tailored to their individual needs.In addition, the generative AI model continuously learns based on user feedback and newly collected data, enabling it to improve the accuracy of its suggestions.

[1268] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1269] Step 1:

[1270] The user device uses an input interface to collect data from the user, such as physical information, training history, and dietary details. The input data includes the user's weight, height, exercise details, and dietary details. This data is formatted to be stored in a database and then sent to the server using the MQTT protocol.

[1271] Step 2:

[1272] The server receives data sent from the user's device, including physical information, training history, and dietary details. The server stores this data in a PostgreSQL database.

[1273] Step 3:

[1274] Factory robots use sensors to collect operational data, including the robot's movement patterns, speed, error rate, etc. This data is also sent to a server using the MQTT protocol.

[1275] Step 4:

[1276] The server receives operation data sent from the factory robots and stores it in a PostgreSQL database, allowing for centralized management of both user data and robot data.

[1277] Step 5:

[1278] The server uses Python and TensorFlow to analyze data stored in PostgreSQL. Specifically, it uses a generative AI model to generate optimal training methods, nutritional intake methods, form corrections, and factory robot operation corrections for each user. The analysis uses data from past top athletes and existing optimization algorithms.

[1279] Step 6:

[1280] The server transmits the generated training methods, nutritional intake methods, form correction points, and factory robot operation correction points to the user terminal and the factory robot again via the MQTT protocol.

[1281] Step 7:

[1282] The user terminal receives the suggestions sent from the server and displays them to the user, who then performs training and nutritional intake based on them.

[1283] Step 8:

[1284] The factory robot receives the operation correction points sent from the server and corrects and optimizes its operation. The robot collects the corrected operation data again and sends it to the server.

[1285] Step 9:

[1286] The results and impressions obtained by the user and the factory robot are entered as feedback into the input interface of the user terminal and the robot, and sent to the server. The server analyzes the received feedback and stores and updates it in the PostgreSQL database.

[1287] Step 10:

[1288] The server updates the generative AI model based on the received feedback and newly collected data, and performs re-analysis to improve the accuracy of the suggestions, thereby repeatedly providing optimal suggestions for the user and the robot, enabling continuous performance improvement.

[1289] 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.

[1290] The present invention relates to a system that supports a user in more effectively managing their training and nutrition, enabling them to perform at the level of a top athlete. Specific examples of the present invention are described below.

[1291] 1. Server system overview:

[1292] The server has the ability to receive training data, nutritional data, and physical information from users and store it in a database. The server also collects training data, nutritional data, and form data from top athletes and stores it in a database. The server then uses a generative AI model to analyze the accumulated data and generate optimal training menus, nutrition plans, and form correction suggestions for each user. It also has the ability to send suggestions to the user's device and update the suggestions based on feedback received from the user.

[1293] 2. Emotion engine feature additions:

[1294] The system also incorporates an emotion engine, which has the ability to collect and analyze emotional data from the user's facial expressions, voice tone, text input, etc. The emotional data is used to understand the user's current psychological state and reflect it in training and nutrition plan suggestions.

[1295] 3. Device Features:

[1296] The user terminal has the function of inputting data from the user via an input interface and sending it to the server. This data includes the user's training history, dietary content, and physical information. The user terminal also has the function of receiving suggestions sent from the server and displaying them. Furthermore, the user can input the results and impressions of their training and nutritional intake as feedback and send them to the server. It also has an interface for collecting emotional data.

[1297] 4. User Action:

[1298] The user first enters their physical information, training history, and dietary details into the user device. The device sends this data to the server, which receives it and begins analysis. A generative AI model is used to generate training methods, nutritional intake methods, and form correction points that are suitable for the user. An emotion engine is also used to collect and analyze the user's emotional data and reflect this in the suggestions. The generated suggestions are sent to the user device. The user then performs training and nutritional intake based on the suggestions, and enters the results and impressions into the device, sending feedback to the server. The server analyzes the received feedback and emotional data to improve the accuracy of the suggestions.

[1299] 5. Examples:

[1300] A high school athlete user inputs and sends their weight, height, dietary habits, and training history into their device. The server receives this data and analyzes it by comparing it with a database of top athletes. At the same time, an emotion engine analyzes the user's psychological state. As a result, an optimal training menu (five times a week of running and strength training), nutrition plan (high-protein, low-fat diet), and form correction points (improvement of arm swing) are generated and sent to the user's device. The user trains and takes in nutrients according to these suggestions, and then feeds the results and emotional data back to the server. The server analyzes the feedback and emotional data, retrains the generative AI model, and updates the suggestions.

[1301] In this way, the present invention allows users to obtain optimal training methods, nutritional intake methods, and form correction points based on scientific evidence, thereby enabling them to improve their competitive level. Furthermore, by using emotional data, flexible suggestions can be made based on the user's psychological state, which can lead to better results.

[1302] The processing flow will be explained below.

[1303] Step 1:

[1304] The user inputs their physical information (weight, height, etc.), training history, and dietary details into the user terminal.

[1305] Step 2:

[1306] The terminal transmits the input data to the server.

[1307] Step 3:

[1308] The server receives the data sent by the user and stores it in a database.

[1309] Step 4:

[1310] The server collects training data, nutrition data, and form data of top athletes and stores it in a database.

[1311] Step 5:

[1312] The device collects emotion data from the user's facial expressions and voice and sends it to the server. In this step, the emotion engine performs facial expression recognition and voice analysis to extract the user's emotion as numerical data.

[1313] Step 6:

[1314] The server receives the emotion data and stores it in a database.

[1315] Step 7:

[1316] The server preprocesses the accumulated data (user data and top athlete data) and generates a dataset for analysis.

[1317] Step 8:

[1318] The server uses a generative AI model to analyze the pre-processed data and generate optimal training methods, nutritional intake methods, and form correction points for the user.

[1319] Step 9:

[1320] The server dynamically adjusts the difficulty and intensity of the suggested content based on the emotional data, creating a flexible training plan that suits the user's psychological state.

[1321] Step 10:

[1322] The server transmits the generated training method, nutritional intake method, and form correction points to the user terminal.

[1323] Step 11:

[1324] The device displays the suggestions received from the server to the user, who then checks the suggestions and carries out the actual training and meal plan.

[1325] Step 12:

[1326] The user performs training and nutritional intake based on the suggestions, and then inputs the results and impressions into the terminal.

[1327] Step 13:

[1328] The terminal transmits the input feedback data to the server.

[1329] Step 14:

[1330] The server analyzes the received feedback and retrains the generative AI model to improve the accuracy of the suggestions. It also analyzes newly collected emotion data and incorporates it into the next suggestions.

[1331] Step 15:

[1332] The server receives advertising data from sporting goods manufacturers and nutritional food manufacturers and generates optimal advertisements to display on user terminals.

[1333] Step 16:

[1334] The device displays the advertisements and recommended product information received from the server to the user, who can then select the products they are interested in and proceed with the purchase.

[1335] Example 2

[1336] 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."

[1337] Conventional training support systems support users' training and nutritional management, but they are unable to make suggestions that take into account each individual's psychological state, making it difficult to achieve effective training and nutritional management. Furthermore, systems that dynamically update suggestions based on user feedback are also lacking. This results in insufficient support for users to achieve high performance.

[1338] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1339] In this invention, the server includes means for receiving training data, nutritional data, and physical information from a user, means for collecting and storing exercise data, nutritional data, and form data of top athletes, means for analyzing the stored data and using a generative AI model to generate an optimal training method, nutritional intake method, and form correction points for the user, means for transmitting the generated training method, nutritional intake method, and form correction points to a user terminal, means for collecting and analyzing emotional data from the user terminal, means for generating training method and nutritional intake method suggestions that reflect the emotional data, and means for analyzing feedback received from the user and updating the suggestions. This enables flexible suggestions that take the user's emotional data into consideration, and makes it possible to provide optimal training methods and nutritional intake methods that are dynamically updated.

[1340] "User" means an individual who wishes to use the System to improve their own training and nutritional management.

[1341] "Training data" refers to a record of the type, duration, intensity, etc. of exercise performed by the user.

[1342] "Nutrition data" refers to information such as the type and amount of food consumed by the user, calories, nutrients, etc.

[1343] "Physical information" refers to data that indicates the user's physical characteristics, such as weight, height, and body fat percentage.

[1344] A "top athlete" is a competitor who has demonstrated great skill and achievement in a particular sporting field.

[1345] "Athletic data" refers to information about training content and performance recorded by top athletes.

[1346] "Form data" refers to detailed information that records the physical movements of top athletes during exercise.

[1347] A "generative AI model" is an artificial intelligence used to generate optimal training and nutrition plans based on large amounts of data.

[1348] "Emotion data" refers to information about a user's psychological state that can be inferred from facial expressions, voice tone, text input, and the like.

[1349] A "user terminal" refers to a device such as a computer or smartphone used by a user.

[1350] "Feedback" refers to information that a user provides to the system regarding the results and impressions of their training and nutritional intake.

[1351] "Suggestions" refer to training methods, nutritional intake methods, and form correction points provided to users based on the results of analysis of the generative AI model and emotional data.

[1352] The present invention relates to a system that supports users in more effectively managing their training and nutrition, enabling them to perform at the level of a top athlete. A specific example of this system is described below.

[1353] The system consists of a server, a user device, an emotion engine, and a generative AI model. The server receives training data, nutritional data, and physical information from the user and stores this data in a database. The software used includes a database management system and a generative AI model. It also collects exercise data, nutritional data, and form data from top athletes and stores this in the database. The server analyzes the accumulated data and uses the generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user.

[1354] The user terminal has the function of inputting data from the user via an input interface and sending it to the server. This data includes the user's training history, dietary content, and physical information. The user terminal also has the function of receiving and displaying suggestions sent from the server. Furthermore, the user can input the results and impressions of their training and nutritional intake as feedback and send it to the server. It also has an interface for collecting emotional data. This emotion engine has the function of collecting and analyzing emotional data from the user's facial expressions, voice tone, text input, etc. Emotional data is used to understand the user's current psychological state and reflect it in training and nutrition plan suggestions.

[1355] As a specific use case, consider the case where a high school athlete inputs and sends their weight, height, dietary habits, and training history into their device. The server receives this data and analyzes it by comparing it with a database of top athletes. At the same time, the emotion engine analyzes the user's psychological state. As a result, the system generates an optimal training menu for the user (e.g., running and strength training five times a week), a nutrition plan (e.g., a high-protein, low-fat diet), and form corrections (e.g., improving arm swing), and sends these suggestions to the user's device. The user then trains and takes in nutrients according to these suggestions, and provides feedback on the results and emotional data to the server. The server analyzes the feedback and emotional data, retrains the generative AI model, and updates the suggestions.

[1356] A unique feature of this system is that it can propose flexible training and nutrition plans that reflect the user's emotional data, allowing users to find training and nutritional methods that are optimal for their own psychological state, thereby improving their sports performance.

[1357] Examples of prompts to be used in this system include, "Generate the optimal training menu and nutrition plan based on the user's training data, nutrition data, and physical information. Also, make suggestions for improvements taking the user's emotional data into consideration," "Output the results of an analysis of the user's training menu compared with data from top athletes," and "Update the suggestions based on the user's real-time feedback to provide a more accurate training menu."

[1358] In this way, the present invention allows users to obtain optimal training methods, nutritional intake methods, and form corrections based on scientific evidence, thereby enabling them to improve their competitive level. Furthermore, by using emotional data, flexible suggestions can be made based on the user's psychological state, which can lead to better results.

[1359] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1360] Step 1: Enter and submit data

[1361] The user inputs their weight, height, dietary habits, training history, etc. into the user terminal. This data is collected through an input interface installed on the user terminal. When the user presses the "send" button, the user terminal sends this data to the server.

[1362] Input: Weight, height, diet, training history

[1363] Output: Data sent from the user device to the server

[1364] Specific action: The user enters data into a smartphone application and presses the "Submit" button.

[1365] Step 2: Receiving and storing data

[1366] The server receives the data sent from the user terminal and stores the received data in a database.

[1367] Input: Data sent from the user's device

[1368] Output: User data stored in the database

[1369] What it does: The server listens on a specific port and automatically stores the received data in a MySQL database.

[1370] Step 3: Collecting and storing top athlete data

[1371] The server collects the exercise data, nutrition data, and form data of top athletes and stores them in a database.

[1372] Input: Top athletes' exercise data, nutrition data, and form data

[1373] Output: Top athlete data stored in a database

[1374] Specific operation: Automatically collect data from various data sources using APIs and store it in a database.

[1375] Step 4: Data analysis and proposal generation

[1376] The server compares the user data stored in the database with the data of top athletes and uses a generative AI model to generate optimal training methods, nutritional intake methods, and form corrections for the user. In this process, the generative AI model runs on frameworks such as TensorFlow.

[1377] Input: User data and top athlete data stored in the database

[1378] Output: Optimal training methods, nutritional intake methods, and form correction points

[1379] Specific operation: The generative AI model analyzes the data and outputs the results in JSON format, and the server generates suggestions based on this.

[1380] Step 5: Submit and view your proposal

[1381] The server sends the generated training methods, nutritional intake methods, and form correction suggestions to the user's device. The user's device receives the suggestions and displays them to the user. They are displayed in the form of a notification, allowing the user to check the details.

[1382] Input: Optimal training methods, nutritional intake methods, form correction points

[1383] Output: Proposal content notified to the user's device

[1384] Specific operation: The proposal is displayed in the form of a notification in the application on the user's device.

[1385] Step 6: Collect and analyze emotion data

[1386] The user terminal collects emotion data from facial expressions, voice tones, and text input. The emotion engine analyzes the emotion data and sends the results to the server.

[1387] Input: Facial expressions, voice tone, text input

[1388] Output: Emotion data analysis results sent to the server

[1389] How it works: The facial expression recognition software uses OpenCV to analyze the user's facial expressions in real time and sends the results to the server.

[1390] Step 7: Update suggestions taking into account sentiment data

[1391] The server reflects the emotional data obtained from the emotion engine and generates suggestions for training methods and nutritional intake methods.

[1392] Input: Emotion data analysis results

[1393] Output: Suggestions for training and nutritional intake methods that reflect emotional data

[1394] Specific operation: The generative AI model is run again based on the results of emotion data analysis to generate new suggestions.

[1395] Step 8: Send and analyze feedback

[1396] The user follows the suggested training menu and nutrition plan, inputs the results and impressions into the user's device, and sends them to the server. The server receives and analyzes the feedback, and based on the results, retrains the generative AI model and updates the suggestions.

[1397] Input: Training execution results, feedback

[1398] Output: Updated proposal

[1399] Specific operation: The user enters details of their training and diet into the application, and by pressing the "Feedback" button, the information is sent to the server. The server analyzes the feedback and reflects it in the generative AI model.

[1400] This will enable the system to dynamically provide optimal training and nutritional intake methods that take into account the user's emotional data, thereby supporting high sports performance.

[1401] (Application example 2)

[1402] 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."

[1403] While conventional training support systems can collect and analyze users' training and nutritional data, they have difficulty personalizing training and nutritional management by taking into account the user's psychological state and emotions. Furthermore, due to a lack of provision of personalized meal plans based on this data and collaboration with food delivery companies, it has been difficult for users to achieve consistent training and nutritional management.

[1404] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1405] In this invention, the server includes a means for receiving training data, nutritional data, and physical information from the user, a means for collecting and storing training data, nutritional data, and form data of top athletes, and a means for analyzing the stored data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user. This makes it possible to generate optimal training methods and personalized meal plans based on the individual health and psychological state of the user, and to support their implementation.

[1406] The "means for receiving training data, nutritional data, and physical information from the user" refers to an interface that allows the user to input their own training history, dietary content, and physical information such as weight and height, and transmit this information in digital form to the server.

[1407] "Means for collecting and storing training data, nutritional data, and form data of top athletes" refers to a system for compiling and storing information on the training methods, nutritional intake patterns, and movement form of outstanding athletes in a database.

[1408] "Means of analyzing accumulated data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for each user" refers to technology that analyzes the vast amount of data accumulated on a server and utilizes artificial intelligence to generate training plans, nutritional intake plans, and movement improvement points that are customized for each individual user.

[1409] "Means for transmitting the generated training methods, nutritional intake methods, and form correction points to the user's terminal" refers to a communication technology that sends the suggestions and plans generated by the server to the user's terminal, such as a smartphone or PC, and displays them.

[1410] The "means for analyzing feedback received from users and updating the content of suggestions" refers to a system that collects the results and impressions of the user's training and diet, analyzes them, and updates the next suggestions to make them more accurate.

[1411] "Means for collecting and analyzing emotional data" refers to technology that reads the user's emotional state from their facial expressions and vocal tone, and analyzes that data to understand the user's psychological state.

[1412] "Means for generating personalized meal menus based on a user's training history, nutritional data, and emotional data, and sending orders to food delivery companies" refers to a system that plans individually optimized meal menus taking into account a user's past training, dietary history, and emotional state, and automatically places orders with a food delivery service.

[1413] The present invention provides a system that allows a user to perform training and nutritional management more effectively. Specific embodiments for carrying out the invention are described below.

[1414] 1. System Overview

[1415] The server has the function of receiving training data, nutritional data, and physical information from the user's device. This includes an interface for users to input their own data and communication technology for transmitting that data to the server. Users input data using devices such as smartphones or PCs.

[1416] 2. Data collection and storage

[1417] The server collects training data, nutrition data, and form data from top athletes and stores them in a database. Data on outstanding athletes is obtained from books, the internet, and specialist institutions, and then categorized and stored in the database. This data serves as the basis for optimal recommendations to users.

[1418] 3. Analysis using generative AI models

[1419] The server analyzes the accumulated data and uses a generative AI model to generate optimal training methods, nutritional intake methods, and form corrections for the user. The generated suggestions are based on customized and pre-programmed algorithms.

[1420] 4. Submit your proposal

[1421] The server then sends the generated training methods, nutritional intake methods, and form correction points to the user's device. The communication protocol uses an internet connection, allowing the user to act on this information and plan their next training and meal plans.

[1422] 5. Analyzing feedback and updating suggestions

[1423] The server analyzes the feedback received from the user and updates the suggestions. This feedback includes the results and thoughts of the user on their training and diet. Based on the feedback, the generative AI model retrains and improves the accuracy of the suggestions.

[1424] 6. Emotional Data Collection and Analysis

[1425] The server uses an emotion engine to collect and analyze emotional data from the user's facial expressions, voice tone, text input, etc. This allows the server to understand the user's psychological state and reflect this in training and nutrition plan suggestions.

[1426] 7. Generate personalized meal menus and order from food delivery providers

[1427] The server generates a personalized meal menu based on the user's training history, nutritional data, and emotional data, and automatically sends the generated menu to a food delivery company, allowing the user to receive the optimal meal at the right time.

[1428] Hardware and software used

[1429] Hardware:

[1430] Smartphone: A device equipped with a camera and microphone.

[1431] Server: A high-performance server for receiving, analyzing, and sending data.

[1432] software:

[1433] Python scripting: Used to process data, analyze, and operate generative AI models.

[1434] Emotion Recognition API: An external API for analyzing user emotion data.

[1435] Generative AI model API: Used to generate training methods and nutrition plans.

[1436] Database system: Used to store data (e.g. PostgreSQL).

[1437] Specific examples

[1438] High school athlete users enter their weight, height, dietary habits, and training history into a smartphone app and send it to a server. The server receives this data and analyzes it by comparing it with a database of top athletes. At the same time, it analyzes the user's psychological state using an emotion engine. As a result, it generates an optimal training menu for the user (running five times a week and strength training), a nutrition plan (high-protein, low-fat diet), and form correction points (improving arm swing), and sends these to the user's device. The user trains and takes in nutrients according to these suggestions, and then feeds the results and emotional data back to the server. The server analyzes the feedback and emotional data, retrains the generative AI model, and updates the suggestions.

[1439] Prompt Sentence Examples

[1440] "Recommend optimal training and nutrition plans based on the user's training history and nutrition data. Also consider the user's emotional state and include elements that help reduce stress."

[1441] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1442] Step 1:

[1443] Input: The user enters training data, nutrition data, and physical information into the smartphone device and presses the send button.

[1444] Processing: The terminal sends the entered data to the server.

[1445] Output: The server receives the user's training data, nutrition data, and physical information and stores them in a database.

[1446] Specific operation: The user enters information such as weight, height, dietary habits, and training history into the input form and presses the "Submit" button. The device converts the data into JSON format and sends an HTTP request to the server. The server receives this and stores it in a database.

[1447] Step 2:

[1448] Input: The server reads the accumulated training, nutrition, and form data of top athletes.

[1449] Processing: The server prepares the user data and top athlete data for comparison and analysis.

[1450] Output: The top athlete data and user data are ready and we move on to the analysis phase.

[1451] Specific operation: The server queries the necessary items from the database of top athletes and converts them into a format that can be integrated with user data.

[1452] Step 3:

[1453] Input: User data and top athlete data.

[1454] Processing: The server uses the generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for the user.

[1455] Output: Generates a personalized training plan, nutrition plan, and form corrections.

[1456] How it works: Enter a prompt into the generative AI model, such as, "Based on the user's training history and nutrition data, suggest the optimal training menu and nutrition plan. Include elements that will help reduce stress, taking into account the user's emotional state." The model then analyzes the data and generates the optimal suggestion.

[1457] Step 4:

[1458] Input: Training plan, nutrition plan, and form correction points generated by a generative AI model.

[1459] Processing: The server sends the generated proposal to the user terminal.

[1460] Output: Training plan, nutrition plan, and form correction points are displayed on the user's device.

[1461] Specific operation: The server sends the generated proposal content to the user's device as an HTTP response. The user's device displays the received data in a format that is easy for the user to view.

[1462] Step 5:

[1463] Input: User feedback.

[1464] Processing: The server receives the feedback and uses it for analysis.

[1465] Output: Feedback data parsed by the server.

[1466] Specific operation: The user inputs the results of their training and diet and their thoughts on the device, and presses the "Send Feedback" button. The device then sends the data to the server, which receives and analyzes it.

[1467] Step 6:

[1468] Input: User feedback and sentiment data.

[1469] Processing: The server analyzes the feedback data and sentiment data and updates the suggestions using the generative AI model.

[1470] Output: Updated training plan, nutrition plan.

[1471] How it works: The server analyzes the feedback and emotion data and retrains the generative AI model. The updated model generates new optimized training and nutrition plans.

[1472] Step 7:

[1473] Input: User emotion data.

[1474] Processing: The server analyzes the emotion data using the emotion engine.

[1475] Output: Data based on the user's emotional state.

[1476] Specific operation: The server analyzes the user's facial expressions and voice data and obtains emotion data using the emotion engine API. This emotion data is used as input data for the generative AI model.

[1477] Step 8:

[1478] Input: User's training history, nutritional data, and emotional data.

[1479] Processing: The server generates a personalized meal menu based on this data and sends the order to the food delivery company.

[1480] Output: A personalized meal menu and the order data generated based on it.

[1481] How it works: The server uses a generative AI model to analyze user data and generate an optimal meal menu, which is then automatically sent as an order to a food delivery service.

[1482] 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.

[1483] 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.

[1484] 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.

[1485] 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.

[1486] 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.

[1487] 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.

[1488] 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).

[1489] 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.

[1490] 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."

[1491] 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.

[1492] 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).

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] 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.

[1499] 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.

[1500] 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.

[1501] 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.

[1502] 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.

[1503] The following is further disclosed regarding the above embodiment.

[1504] (Claim 1)

[1505] means for receiving training data, nutritional data, and physical information from a user;

[1506] A means to collect and store training data, nutrition data, and form data of top athletes,

[1507] A means for analyzing the accumulated data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for users;

[1508] a means for transmitting the generated training method, nutritional intake method, and form correction points to a user terminal;

[1509] The system includes a means for analyzing feedback received from users and updating the recommendations.

[1510] (Claim 2)

[1511] 10. The system of claim 1, wherein data input from a user terminal is used as a means for receiving training data, nutrition data, and physical information from the user.

[1512] (Claim 3)

[1513] 10. The system according to claim 1, further comprising means for receiving advertising data from sporting goods manufacturers and nutritional food manufacturers and displaying the same on the user terminal.

[1514] "Example 1"

[1515] (Claim 1)

[1516] means for receiving training data, nutritional data, and physical information from a user;

[1517] A means to collect and store training data, nutrition data, and form data of top athletes,

[1518] A means for analyzing the accumulated data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for users;

[1519] a means for transmitting the generated training method, nutritional intake method, and form correction points to a user terminal;

[1520] a means for analyzing feedback received from users and updating the suggestions;

[1521] A system including means for receiving data entered into a user terminal and transmitting the data to a server.

[1522] (Claim 2)

[1523] 2. The system according to claim 1, further comprising means for receiving data input from a user terminal, transmitting the data to a server, and storing the data therein.

[1524] (Claim 3)

[1525] 10. The system of claim 1, further comprising means for analyzing feedback using a generative AI model based on the suggestions sent to the user terminal to improve the accuracy of the suggestions.

[1526] "Application Example 1"

[1527] (Claim 1)

[1528] means for receiving training data, nutritional data, and physical information from a user;

[1529] A means to collect and store training data, nutrition data, and form data of top athletes,

[1530] A means for collecting and storing operation data of the factory robot;

[1531] A means for analyzing the accumulated data and using a generative AI model to generate optimal training methods, nutritional intake methods, form correction points, and robot movement correction points for the user;

[1532] a means for transmitting the generated training method, nutritional intake method, form correction points, and robot movement correction points to a user terminal;

[1533] The system includes a means for analyzing feedback received from users and updating the recommendations.

[1534] (Claim 2)

[1535] 10. The system of claim 1, wherein data input from a user terminal is used as a means for receiving training data, nutrition data, and physical information from the user.

[1536] (Claim 3)

[1537] 2. The system according to claim 1, wherein data input from a factory machine is used as a means for receiving operation data of the factory robot.

[1538] "Example 2: Combining Emotion Engines"

[1539] (Claim 1)

[1540] means for receiving training data, nutritional data, and physical information from a user;

[1541] A means of collecting and storing exercise data, nutritional data, and form data of top athletes,

[1542] A means for analyzing the accumulated data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for users;

[1543] a means for transmitting the generated training method, nutritional intake method, and form correction points to a user terminal;

[1544] A means for collecting and analyzing emotion data from a user terminal;

[1545] A means for generating suggestions for training methods and nutritional intake methods that reflect the emotion data;

[1546] The system includes a means for analyzing feedback received from users and updating the recommendations.

[1547] (Claim 2)

[1548] 10. The system of claim 1, wherein data input from a user terminal is used as a means for receiving training data, nutrition data, and physical information from the user.

[1549] (Claim 3)

[1550] 10. The system according to claim 1, further comprising means for receiving advertising data from sporting goods manufacturers and nutritional food manufacturers and displaying the same on the user terminal.

[1551] "Application example 2 when combining emotion engines"

[1552] (Claim 1)

[1553] means for receiving training data, nutritional data, and physical information from a user;

[1554] A means to collect and store training data, nutrition data, and form data of top athletes,

[1555] A means for analyzing the accumulated data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for users;

[1556] a means for transmitting the generated training method, nutritional intake method, and form correction points to a user terminal;

[1557] a means for analyzing feedback received from users and updating the suggestions;

[1558] a means for collecting and analyzing emotion data;

[1559] The system includes a means for generating a personalized meal menu based on a user's training history, nutritional data, and emotional data, and sending an order to a food delivery company.

[1560] (Claim 2)

[1561] 10. The system of claim 1, wherein data input from a user terminal is used as a means for receiving training data, nutrition data, and physical information from the user.

[1562] (Claim 3)

[1563] 10. The system according to claim 1, further comprising means for receiving advertising data from sporting goods manufacturers and nutritional food manufacturers and displaying the same on the user terminal. [Explanation of symbols]

[1564] 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. means for receiving training data, nutritional data, and physical information from a user; A means to collect and store training data, nutrition data, and form data of top athletes, A means for analyzing the accumulated data and using a generative AI model to generate optimal training methods, nutritional intake methods, and form correction points for users; a means for transmitting the generated training method, nutritional intake method, and form correction points to a user terminal; The system includes a means for analyzing feedback received from users and updating the recommendations.

2. 2. The system according to claim 1, wherein data input from a user terminal is used as a means for receiving training data, nutritional data, and physical information from the user.

3. The system according to claim 1, further comprising means for receiving advertising data from sporting goods manufacturers and nutritional food manufacturers and displaying the advertising data on the user terminal.

Images