System

Abstract

A system is provided.SOLUTION: A system comprising: means for allowing a user to input a training goal and personal body information; means for generating, by a server, a training menu based on the input training goal and personal body information; means for providing the generated training menu to a terminal of the user; means for allowing the user to input a result of the training and a self-score after the user performs training according to the training menu; and means for generating feedback and advice for next training based on the input result and self-score and providing the feedback and advice to the terminal of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, the rise in health consciousness has led to an increase in the number of people using training gyms, but many people are troubled by not knowing how to conduct effective training. Traditional methods require using an instructor or obtaining information online, which takes time and effort. In addition, the cost of instructors who create individual training menus is high. This situation presents the challenge of making it difficult to easily create an efficient training plan tailored to each individual's goals. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides a system including: means for having a user input training goals and personal physical information; means for a server to generate a training menu based on the input training goals and personal physical information; means for providing the generated training menu to the user's terminal; means for having the user input the results of the training and a self-evaluation after training according to the training menu; and means for generating feedback and advice for the next training session based on the input results and self-evaluation and providing the feedback and advice to the user's terminal. This allows the user to easily receive the training menu that is best suited to them and to train efficiently.

[0006] "User" refers to a person who receives the training menu, performs it, and inputs the results.

[0007] "Training Goal" means a specific health or fitness objective that a user wishes to achieve (e.g., building muscle, losing weight, etc.).

[0008] "Physical information" refers to physical data such as the user's height, weight, age, and gender.

[0009] "Lifestyle" refers to information such as a user's daily eating habits, sleep time, and activity level.

[0010] "Server" refers to a central system that receives information sent by users, generates training menus, and sends them to terminals.

[0011] "Generative AI" refers to an artificial intelligence engine that generates optimal training menus based on user information and provides feedback.

[0012] "Training menu" refers to the exercise program (e.g., number of exercises, number of sets, weight, etc.) provided by the generating AI based on the user's information.

[0013] "Terminal" refers to a device (e.g., smartphone, PC, etc.) through which a user inputs information and receives training menus and feedback.

[0014] "Self-rating" refers to the act of a user inputting a subjective evaluation of the training they have performed.

[0015] "Feedback" refers to advice and improvements that the generative AI provides based on the user's training results and self-assessment. [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] In this embodiment, a personal trainer system that utilizes a generation AI to provide an effective training menu tailored to each individual's goals will be described. The following describes the operation flow of this system and the specific processing at each step.

[0038] 1. Collection of User Information

[0039] User Behavior

[0040] First, a user accesses the AI ​​personal trainer application using their own device (such as a smartphone or PC). Next, the user enters their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and frequency of gym visits (how many times per week) into the application. The user then sets their training goals (e.g., lose weight, gain muscle, improve physical strength).

[0041] Terminal handling

[0042] The terminal collects the information entered by the user and transmits the data to the server.

[0043] 2. Creation of training menu

[0044] Server Processing

[0045] The server receives the user's data and sends it to the generative AI engine. The generative AI engine generates an optimal training menu based on the user's information and goals. For example, if the user's goal is to "lose weight," the generative AI will provide a menu that takes into account the balance of aerobic exercise (running and cycling) and strength training (squats and dumbbell exercises, etc.). The generated training menu is sent from the server to the user's device.

[0046] 3. Display and execute the training menu

[0047] Terminal handling

[0048] The terminal displays the training menu sent from the server to the user. The user starts training and performs the training according to the details in the menu (e.g., running time, number of crunches, weight of dumbbells, etc.).

[0049] 4. Record your training and self-assess

[0050] User Behavior

[0051] After the workout, the user enters details of the workout (e.g., 50 squats using 5kg dumbbells) and their own assessment (e.g., subjective assessment of whether the workout was difficult) into the device.

[0052] Terminal handling

[0053] The device collects the training details and self-assessment entered by the user and sends the data to a server.

[0054] 5. Feedback and training advice for your next workout

[0055] Server Processing

[0056] The server sends the collected data to the generation AI, which generates feedback based on past training results and self-assessment, and provides advice for the next training. For example, if the user's self-assessment result indicates that they have done too many squats and are putting strain on their knees, the system will suggest knee-friendly training for the next training session. This feedback and advice is sent from the server to the user's device.

[0057] Terminal handling

[0058] The terminal displays the feedback and advice received from the server to the user.

[0059] Specific examples

[0060] User A (Goal: Muscle building)

[0061] Step 1

[0062] User A accesses the app and enters his / her height (180 cm), weight (70 kg), ability to go to the gym three times a week, and goal of "gaining muscle." The device then sends this data to the server.

[0063] Step 2

[0064] The server receives the data and passes it to the generation AI. The generation AI generates a training menu for User A three times a week. For example, it might provide a menu such as "Squat 60kg x 3 sets, Bench press 50kg x 3 sets, Deadlift 80kg x 3 sets." The training menu is sent to the device.

[0065] Step 3

[0066] The device displays the training menu to User A. User A then performs training at the gym.

[0067] Step 4

[0068] User A enters the details of the training he or she performed and his or her own rating. For example, he or she might enter "Squats 60kg x 3 sets, self-rating 4 / 5." The device then sends the data to the server.

[0069] Step 5

[0070] The server receives the data and passes it to the generation AI. The generation AI analyzes the data and generates feedback such as "Next time, increase the number of squat sets to 4." The feedback is sent to the device and displayed to User A.

[0071] In this way, the present invention is a system that enables a user to easily receive a training menu that is best suited to the user and to train efficiently and effectively.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] The user accesses the generated AI personal trainer application using a device (such as a smartphone or PC). The user inputs their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and frequency of gym visits (how many times per week). The user then sets their own training goals (e.g., lose weight, gain muscle, improve physical strength).

[0075] Step 2:

[0076] The terminal collects the information entered by the user and sends the data to the server.

[0077] Step 3:

[0078] The server receives the user information sent from the device and passes the received information to the generation AI engine.

[0079] Step 4:

[0080] The generative AI engine generates the optimal training menu for each individual user based on their information and training goals. For example, if your goal is to lose weight, it will generate a menu that balances cardio and strength training.

[0081] Step 5:

[0082] The server transmits the generated training menu to the terminal.

[0083] Step 6:

[0084] The device displays a training menu to the user, who then checks the menu and follows it to train at the gym or at home.

[0085] Step 7:

[0086] After the user completes the training, they enter details of each exercise (e.g., 30 minutes of running, 5 km run) and their own assessment into the device.

[0087] Step 8:

[0088] The terminal transmits the detailed training data and self-evaluation results input by the user to the server.

[0089] Step 9:

[0090] The server passes the detailed training data and self-assessment results received from the device to the generation AI engine. The generation AI analyzes the past training history and self-assessment results and generates feedback and advice for the next training session. For example, if the user's knees are under strain, it will suggest knee-friendly training for the next session.

[0091] Step 10:

[0092] A server is generated to send feedback and advice to the terminal.

[0093] Step 11:

[0094] The device displays the feedback and advice received from the server to the user, who can then review the displayed feedback and use it for their next training session.

[0095] Example 1

[0096] 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."

[0097] Conventional training menus often provide uniform programs, which have the problem of not being able to provide an optimal menu tailored to each user's physical information or specific goals. Furthermore, there is an insufficient mechanism for users to receive feedback after training and use that feedback to improve their next training. Furthermore, the time and effort required for users to self-evaluate their training results can discourage users from continuing to train.

[0098] 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.

[0099] In this invention, the server includes: means for having a user input training goals and physical information; means for transmitting the input training goals and physical information to the server via a terminal; means for generating a training menu using a generative AI model based on the input training goals and physical information via the server; means for providing the generated training menu to the user's terminal; means for having the user input the training results and self-assessment after training according to the training menu; means for transmitting the input results and self-assessment via the terminal to the server; and means for generating feedback and advice for the next training session using the generative AI model based on the input results and self-assessment and providing the feedback and advice to the user's terminal. This makes it possible to provide a training menu optimized for the user's individual physical information and goals, and to continuously provide appropriate feedback and advice according to the training results.

[0100] "User" refers to a user who uses the Generative AI Personal Trainer System.

[0101] A "training goal" is a specific exercise objective that a user wants to achieve, such as losing weight, gaining muscle, or improving physical strength.

[0102] "Physical information" refers to basic physical data such as a user's weight, height, age, and gender.

[0103] A "terminal" is a device used by a user to access the system and input information, including a smartphone or PC.

[0104] "Server" refers to the central management system that receives user input data, generates optimal training menus using generative AI models, and provides feedback and advice.

[0105] A "generative AI model" is an artificial intelligence model that automatically generates training menus and feedback based on user information, and refers to one that utilizes natural language processing technology, for example.

[0106] A "training menu" refers to a specific exercise plan proposed by the generative AI model based on the user's training goals and physical information.

[0107] "Training results" is a detailed record of the training the user actually performed, including the number of exercises, number of sets, weight used, etc.

[0108] "Self-rating" is when a user inputs a personal evaluation of the training content after completing the training, and includes subjective impressions and comments about the state of the body.

[0109] "Feedback" refers to the general term for improvements and advice provided by the generative AI model for the next training session based on the training results and self-assessment entered by the user.

[0110] "Advice" refers to specific training method suggestions and points of caution provided to users by the generative AI model.

[0111] In this embodiment, we will explain a personal trainer system that utilizes a generative AI model to provide an effective training menu tailored to each individual's training goals. First, the system collects data from the user, such as physical information and training goals, and generates an optimal menu based on the generative AI model. After the training, the system then provides feedback and advice for the next training session.

[0112] Collection of User Information

[0113] User Behavior

[0114] Users access the generated AI personal trainer application using their own devices. Specific hardware examples include smartphones and PCs, and software examples include dedicated applications that can be accessed via a browser.

[0115] The user enters the following information within the application:

[0116] Physical information (e.g., weight, height, age, gender)

[0117] Lifestyle habits (e.g., eating habits, sleep duration)

[0118] How often you can go to the gym (e.g., how many times a week)

[0119] Training goals (e.g., lose weight, gain muscle, improve strength)

[0120] Training menu generation

[0121] Terminal handling

[0122] The device sends the collected user information to the server, using a secure communication protocol such as HTTPS.

[0123] Server Processing

[0124] The server runs the received data on a cloud infrastructure (e.g., AWS (registered trademark), Google (registered trademark) Cloud Platform) because it requires high-performance computing resources. The server then sends the data to a generative AI model (e.g., OpenAI (registered trademark)'s GPT-3 (registered trademark)), which generates an optimal training menu based on the input information. The generated training menu is then sent from the server to the user's device.

[0125] Displaying and executing training menus

[0126] Terminal handling

[0127] The device displays the received training menu to the user, who then performs the training according to the menu. Training items include running time, number of crunches, weight of dumbbells, etc.

[0128] Record and self-assess your training

[0129] User Behavior

[0130] After the training, the user inputs the details of the training (e.g., 50 squats using 5kg dumbbells) and their own assessment (e.g., how difficult the training was) into the terminal.

[0131] Terminal handling

[0132] The terminal collects the user's input and sends the data back to the server.

[0133] Feedback and advice for your next training session

[0134] Server Processing

[0135] The server sends the collected training data and self-assessment to the generative AI model, which then generates feedback and advice for the next training session. For example, if the user's knees are under strain, the model will suggest training that is gentler on the knees. The generated feedback and advice are then sent from the server to the user's device.

[0136] Terminal handling

[0137] The terminal displays feedback and advice to the user.

[0138] Specific examples

[0139] User A (Goal: Muscle building)

[0140] 1. User A accesses the app and enters his / her information: height 180 cm, weight 70 kg, ability to go to the gym three times a week, and goal of "gaining muscle."

[0141] 2. The device sends this data to the server.

[0142] 3. The server receives the data and passes it to the generation AI, which then generates a menu such as "Squat 60kg x 3 sets, Bench press 50kg x 3 sets, Deadlift 80kg x 3 sets."

[0143] 4. The training menu is sent to the device and displayed on User A. User A then performs the training at the gym.

[0144] 5. User A enters the details of the training he or she performed and his or her own evaluation. For example, he or she enters "Squats 60kg x 3 sets, self-evaluation 4 / 5." The device sends the input data to the server.

[0145] 6. The server receives the data and passes it to the generation AI. The generation AI analyzes the data and generates feedback such as "Next time, increase the number of squat sets to 4." This feedback is sent to the device and displayed to User A.

[0146] Prompt Sentence Examples

[0147] "User A is 180cm tall, weighs 70kg, can go to the gym three times a week, and wants to build muscle. Please create an optimal training menu based on this information."

[0148] or

[0149] "Generate a training menu based on the following user information: height 180cm, weight 70kg, gym visits 3 times a week, goal is to build muscle."

[0150] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0151] Step 1:

[0152] Entering user information

[0153] User Behavior

[0154] Users access the AI-generated personal trainer application using their own devices (smartphones or PCs). Within the application, users input their physical information (weight, height, age, gender), lifestyle habits (eating habits, sleep time, etc.), frequency of gym visits (how many times a week they can go), and training goals (lose weight, gain muscle, improve physical strength).

[0155] Terminal handling

[0156] The terminal stores the input user information in a database format and transmits it to the server as structured data.

[0157] Input: User's physical information, lifestyle habits, gym visit frequency, and training goals.

[0158] Output: Structured data to send to the server.

[0159] Step 2:

[0160] Training menu generation

[0161] Server Processing

[0162] The server sends data to a generative AI model based on the received user information. The generative AI model (e.g., GPT-3) generates an optimal training menu based on the user's physical information and goals. For example, if the user's goal is to "lose weight," the generative AI model will provide a menu that takes into account the balance of aerobic exercise and strength training.

[0163] Input: Structured user information.

[0164] Output: A training menu optimized for the user.

[0165] Server Processing

[0166] The generated training menu is sent from the server to the user's terminal.

[0167] Step 3:

[0168] Displaying and executing training menus

[0169] Terminal handling

[0170] The terminal displays the training menu received from the server to the user. The user follows the displayed menu and performs training based on details of, for example, running or strength training (running time, number of crunches, weight of dumbbells).

[0171] Input: Training menu from the server.

[0172] Output: Display of training menu, notification to user.

[0173] Step 4:

[0174] Record and self-assess your training

[0175] User Behavior

[0176] After the training, the user inputs details of the training into the device, such as 50 squats using 5kg dumbbells, and also inputs a self-evaluation of the difficulty of the training.

[0177] Terminal handling

[0178] The device collects these training results and self-assessment and sends them to the server.

[0179] Input: Training details from user, self-assessment.

[0180] Output: Training data to send to the server.

[0181] Step 5:

[0182] Generate feedback and next training advice

[0183] Server Processing

[0184] The server then sends the received training data and self-evaluation back to the generative AI model, which then generates feedback and advice for the next training session. For example, if the user feels strain on their knees, the generative AI model will suggest knee-friendly training for the next session.

[0185] Input: Collected training results and self-assessment.

[0186] Output: Feedback and next training advice.

[0187] Server Processing

[0188] The generated feedback and advice are sent from the server to the user's terminal.

[0189] Step 6:

[0190] View feedback and advice

[0191] Terminal handling

[0192] The device receives feedback and advice from the server and displays it to the user, giving them specific instructions for their next workout.

[0193] Input: Feedback and advice from the server.

[0194] Output: Displaying feedback and advice to the user.

[0195] (Application example 1)

[0196] 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."

[0197] Conventional training menu provision systems lack the functionality to generate optimal training plans based on an individual's specific goals and physical information, making it difficult to maximize effectiveness. In particular, they lacked a mechanism to dynamically adjust the next training menu and provide feedback based on an individual's training results and self-evaluation.

[0198] 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.

[0199] In this invention, the server includes: means for having the user input training goals and personal physical information; means for generating a training menu based on the input training goals and personal physical information; means for providing the generated training menu to the user's terminal; means for having the user input the training results and self-assessment after training according to the training menu; means for generating feedback and advice for the next training session based on the input results and self-assessment and providing the feedback and advice to the user's terminal; and means for using a generative AI model to generate the feedback and advice. This allows for the provision of an optimal training menu based on the user's individual goals and condition, and dynamic feedback and advice, enabling highly effective training.

[0200] "User" refers to an individual who receives the training menu in the invention.

[0201] "Training goal" refers to a specific fitness goal that a user wishes to achieve, such as losing weight, building muscle, or improving strength.

[0202] "Physical information" refers to physical data such as a user's height, weight, age, and gender.

[0203] "Server" refers to a central control device that receives and processes information sent by users, generates training menus based on the information, and provides feedback.

[0204] "Generative AI model" refers to artificial intelligence technology that generates optimal training menus and feedback based on user information.

[0205] "User's terminal" refers to a device used by the user for input and display, such as a smartphone, PC, or tablet.

[0206] A "training menu" refers to a specific exercise or plan that a user should perform, including, for example, the type of exercise, number of repetitions, number of sets, weight, etc.

[0207] "Training Results" refers to details of the training a user actually performed, including, for example, the number of sets performed and the weight used.

[0208] "Self-rating" refers to a subjective evaluation made by the user after completing a workout, including, for example, the difficulty of the workout and the level of fatigue.

[0209] "Feedback" refers to improvements and advice for the next training session based on the training results and self-assessment entered by the user.

[0210] An embodiment of the present invention will be described.

[0211] Overall system overview

[0212] The system works by combining the user's device, a server, and a generative AI model.

[0213] Collection of User Information

[0214] First, a user accesses the application using a device such as a smartphone or tablet. The application provides a user input form and asks the user to enter the following information:

[0215] Height, weight, age, gender (physical information)

[0216] Eating habits, sleep time, etc. (lifestyle)

[0217] How often can you go to the gym per week?

[0218] Training goals (e.g., lose weight, gain muscle, improve strength)

[0219] Training menu generation

[0220] The device sends the input information to the server. The server receives this data and generates an optimal training menu based on a generative AI model. The generative AI model uses, for example, ChatGPT (registered trademark) or GPT-4 (registered trademark). The generated training menu is provided to the user's device. The menu includes the type of exercise, number of repetitions, number of sets, weight, etc.

[0221] Displaying and executing training menus

[0222] The terminal displays the training menu sent from the server to the user, who then trains at the gym according to the training menu.

[0223] Record and self-assess your training

[0224] After the training, the user inputs details of the training (e.g., 50 squats using 5 kg dumbbells) and their own evaluation (e.g., subjective evaluation of whether the training was hard or not) into the device. The device then sends this data back to the server.

[0225] Feedback and advice for your next training session

[0226] The server sends the collected data to the generative AI model, which generates feedback and advice for the next training session based on past training results and self-evaluation. The advice includes specific areas for improvement, such as "Next time, increase the number of squat sets to four." The feedback and advice are sent to the user's device and displayed to the user.

[0227] Specific examples

[0228] User A launches the app and enters the following information:

[0229] Height: 180cm

[0230] Weight: 75kg

[0231] Age: 30

[0232] Gender: Male

[0233] How often can you go to the gym per week: 4 times

[0234] Training goal: Gain muscle

[0235] This information is sent to the server, and the generative AI model creates a training menu of "60kg squats x 3 sets, 50kg bench press x 3 sets, 80kg deadlift x 3 sets." User A executes this menu and inputs the results as "60kg squats x 3 sets, self-rating 4 / 5." Based on these results, the server returns feedback such as "Increase the number of squat sets to 4 next time."

[0236] Prompt Sentence Examples

[0237] An example of a prompt to input to a generative AI model is as follows:

[0238] User Information:

[0239] Height: 180cm

[0240] Weight: 75kg

[0241] Age: 30

[0242] Gender: Male

[0243] How often can you go to the gym per week: 4 times

[0244] Training goal: Gain muscle

[0245] Based on this, generate the following training menu:

[0246] Amount and type of aerobic exercise

[0247] Strength training type, number of sets, and weight

[0248] As described above, by implementing the present invention, it becomes possible to provide an optimized training menu to the user and provide feedback thereto.

[0249] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0250] Step 1:

[0251] Users access the application using a device such as a smartphone or tablet. They enter their height, weight, age, gender, eating habits, sleep time, frequency of gym visits, and training goals in the form displayed on the device. The entered data is then sent from the device to the server.

[0252] Input: height, weight, age, gender, eating habits, sleep time, frequency of gym visits, training goals

[0253] Output: User information sent to the server

[0254] Step 2:

[0255] The server analyzes the received user information and generates an optimal training menu based on the generative AI model. Specifically, it determines the type of exercise, number of sets, repetitions, weight, etc. based on the user's physical information and training goals. The generated training menu is sent from the server to the device.

[0256] Input: User information

[0257] Data processing: Generative AI model generates training menu

[0258] Output: Generated training menu

[0259] Step 3:

[0260] The terminal displays the generated training menu to the user, who then goes to the gym and performs the training according to the displayed menu.

[0261] Input: Generated training menu

[0262] Output: Training menu displayed to the user

[0263] Step 4:

[0264] After completing a workout, the user inputs details of the workout into the device, such as the number of sets, weight, number of repetitions, and self-evaluation for each exercise. The input data is then sent from the device to the server.

[0265] Input: Training results (number of sets, weight, number of repetitions, self-evaluation)

[0266] Output: Training run results sent to the server

[0267] Step 5:

[0268] The server uses the generative AI model to generate feedback and training advice for the next time based on the received training results and self-evaluation. This includes specific advice such as "Increase the number of sets for your next squat to four." The generated feedback and advice are sent from the server to the device.

[0269] Input: Training execution results, self-evaluation

[0270] Data Transformation: Generative AI Models Generate Feedback and Advice

[0271] Output: Generated feedback and advice

[0272] Step 6:

[0273] The terminal displays the feedback and next training advice sent from the server to the user, who can then plan his next training session.

[0274] Input: Generated feedback and advice

[0275] Output: Feedback and advice displayed to the user

[0276] 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.

[0277] As an embodiment of the present invention, a personal trainer system that combines a generative AI and an emotion engine will be described. This system generates an individually optimized training menu based on user input information, and also recognizes the user's emotional state and reflects this in feedback and advice. The following describes in detail the operation flow of this system and its specific processing.

[0278] 1. Collection of User Information

[0279] User Behavior

[0280] First, a user accesses the AI ​​personal trainer application using their own device (such as a smartphone or PC). Next, the user enters their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and frequency of gym visits (how many times per week) into the application. The user also sets their training goals (e.g., to lose weight, gain muscle, or improve physical strength).

[0281] Terminal handling

[0282] The terminal collects the information entered by the user and transmits the data to the server.

[0283] 2. Creation of training menu

[0284] Server Processing

[0285] The server receives the user's data and sends it to the generative AI engine. The generative AI engine generates an optimal training menu based on the user's information and goals. For example, if the user's goal is to "lose weight," the generative AI will provide a menu that takes into account the balance of aerobic exercise (running and cycling) and strength training (squats and dumbbell exercises, etc.). The generated training menu is sent from the server to the user's device.

[0286] 3. Display and execute the training menu

[0287] Terminal handling

[0288] The terminal displays the training menu sent from the server to the user. The user starts training and performs the training according to the details in the menu (e.g., running time, number of crunches, weight of dumbbells, etc.).

[0289] 4. Record your training and self-assess

[0290] User Behavior

[0291] After the workout, the user enters details of the workout (e.g., 50 squats using 5kg dumbbells) and their own assessment (e.g., subjective assessment of whether the workout was difficult) into the device.

[0292] Terminal handling

[0293] The device collects the training details and self-assessment entered by the user and sends the data to a server.

[0294] 5. Emotional Recognition

[0295] User Behavior

[0296] While the user is performing the training and after the training, the device collects the user's facial expression, voice, and text data.

[0297] Terminal handling

[0298] The device's built-in emotion engine analyzes the user's emotional state based on the collected data, recognizing, for example, whether the user is tired, motivated, or stressed.

[0299] 6. Feedback and advice for your next training session

[0300] Server Processing

[0301] The server sends the collected training data, self-evaluation results, and emotion analysis results from the emotion engine to the generation AI. The generation AI generates feedback based on the user's past training history and emotional state, and provides advice for the next training session. For example, if the user felt stressed during training, it will suggest more relaxing exercises for the next session.

[0302] Server Processing

[0303] Send generated feedback and advice to the device.

[0304] Terminal handling

[0305] The device receives feedback and advice from the server and displays it to the user, who can then review the feedback and use it to improve their next training session.

[0306] Specific examples

[0307] User B (Goal: Weight loss)

[0308] Step 1

[0309] User B accesses the app and enters information such as his height of 165 cm, his weight of 80 kg, the ability to go to the gym four times a week, and his goal of "losing weight." The device then sends this data to the server.

[0310] Step 2

[0311] The server receives the data and passes it to the generation AI. The generation AI generates a training menu for User B four times a week. For example, it may provide a menu such as "30 minutes of running, 20 squats, and 10 burpee jumps." The training menu is sent to the device.

[0312] Step 3

[0313] The device displays the training menu to User B. User B then performs the training at the gym.

[0314] Step 4

[0315] User B enters details of the workout he or she performed. For example, he or she might enter "30 minutes of running, 5km run, self-rating 5 / 5." The emotion engine analyzes User B's facial expressions and voice and recognizes the emotion "motivated" based on the microexpression. The data is sent from the device to the server.

[0316] Step 5

[0317] The server receives the data and passes it to the generation AI. The generation AI analyzes the data and generates advice for the next training menu. For example, "Extend your running time to 40 minutes next time." The feedback is sent to User B's device and displayed.

[0318] In this way, the generative AI personal trainer system using the emotion engine can provide an individually optimized training menu taking into account the user's emotional state, maximizing efficiency and effectiveness.

[0319] The processing flow will be explained below.

[0320] Step 1:

[0321] A user accesses the generated AI personal trainer application using a device (such as a smartphone or PC). The user inputs their physical information (e.g., weight, height, age, gender) and lifestyle habits (e.g., eating habits, sleep time), as well as the frequency of gym visits (e.g., how many times per week they can go). In addition, the user sets training goals (e.g., to lose weight, gain muscle, improve physical strength).

[0322] Step 2:

[0323] The terminal collects the information entered by the user and transmits the data to the server.

[0324] Step 3:

[0325] The server receives the user information sent from the device and passes the received information to the generation AI engine.

[0326] Step 4:

[0327] The generative AI engine generates the optimal training menu for each individual user based on their information and training goals. For example, if your goal is to lose weight, it will generate a menu that balances cardio and strength training.

[0328] Step 5:

[0329] The server transmits the generated training menu to the terminal.

[0330] Step 6:

[0331] The device displays the training menu sent from the server to the user, who then checks the training menu and follows it to train at the gym or at home.

[0332] Step 7:

[0333] After the user completes the training, they enter details of each exercise (e.g., 30 minutes of running, 5 km run) and their own assessment (e.g., subjective assessment of whether the training was hard) into the device.

[0334] Step 8:

[0335] The terminal transmits the detailed training data and self-evaluation results input by the user to the server.

[0336] Step 9:

[0337] While the user is training and afterward, the device collects facial, voice, and text data from the user. The device's built-in emotion engine analyzes the user's emotional state based on the collected data. For example, it can recognize emotions such as tiredness, motivation, and stress.

[0338] Step 10:

[0339] The server receives detailed training data, self-assessment results, and emotion analysis results from the emotion engine from the device, and passes them to the generative AI engine. The generative AI generates feedback based on the user's past training history and emotional state, and provides advice for the next training session. For example, if the user felt stressed during training, it will suggest more relaxing exercises for the next session.

[0340] Step 11:

[0341] The server sends the generated feedback and advice to the device.

[0342] Step 12:

[0343] The device displays the feedback and advice received from the server to the user, who can then review the feedback and use it to improve their next training session.

[0344] Example 2

[0345] 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."

[0346] Conventional personal trainer systems provide training menus based on a user's physical information and training goals, but they are unable to take into account the user's emotional state or performance during training, resulting in insufficient individual optimization. As a result, users often find it difficult to continue training and maintain motivation. The present invention aims to solve this problem by providing feedback and training advice that takes into account the user's emotional state.

[0347] 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.

[0348] In this invention, the server includes: means for having the user input training goals and personal physical information; means for transmitting the input physical information, lifestyle habits, and training frequency to the server via a terminal; means for generating a training menu based on the input training goals and personal physical information via the server; means for providing the generated training menu to the user's terminal; means for having the user input training results and self-evaluation after training according to the training menu; means for collecting facial expressions, voice, and text data of the user during and after the training and recognizing emotions via the terminal; and means for generating feedback and advice for the next training session based on the input results, self-evaluation, and emotional data via the server and providing the feedback and advice to the user's terminal. This makes it possible to provide feedback that takes the user's emotional state into account and individually optimized training advice.

[0349] "User" refers to an individual who uses the generative AI personal trainer system to generate a training menu and receive feedback.

[0350] A "training goal" is a physical goal that a user wants to achieve, examples of which include "lose weight" or "gain muscle."

[0351] "Physical information" refers to basic personal data such as a user's height, weight, age, and gender.

[0352] "Lifestyle habits" refers to information such as the user's eating habits and sleeping hours in their daily lives.

[0353] "Training frequency" refers to the number of times or frequency with which a user trains, and examples include "how many times per week they train."

[0354] A "terminal" is a device used by a user to input data and receive training menus and feedback, and examples include smartphones and PCs.

[0355] "Server" refers to the computer at the core of the system that receives data sent by users and uses generation AI to generate training menus and provide feedback.

[0356] A "generative AI engine" refers to an artificial intelligence model that generates optimal training menus based on user input information and training goals.

[0357] "Self-rating" refers to data that allows users to subjectively evaluate their own performance and impressions after training.

[0358] "Emotional data" refers to information about a user's emotional state analyzed from facial expressions, voice, text data, and the like.

[0359] "Feedback" refers to the advice and evaluation provided by the generative AI engine based on the results of the training the user has performed.

[0360] "Training menu" refers to the specific training content generated by the AI ​​engine based on the user's goals, and includes the number of exercises, number of sets, weight, etc.

[0361] An "emotion engine" is software built into the device that analyzes the user's emotional state based on collected data.

[0362] "Feedback and advice" refers to providing specific instructions and improvements for the next workout based on the user's workout results and emotional state.

[0363] "Training results" refers to detailed data when a user performs training, including, for example, the number of squats and the weight used.

[0364] This invention provides a personal trainer system that combines generative AI and an emotion engine to provide feedback and individually optimized training advice that takes into account the user's emotional state. This system is implemented in the following specific steps.

[0365] First, the user accesses the AI ​​personal trainer application from their own device (such as a smartphone or PC). The user enters their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and training frequency (how many times per week) into the application. The user then sets training goals, such as "lose weight" or "gain muscle."

[0366] The device collects the information entered by the user and sends the data to a server in an appropriate format, such as JSON. The server receives this data and passes it to a generative AI engine, which then generates an optimal training menu based on the user's information and goals. The generative AI engine can then use cloud-based services or dedicated AI models for this processing.

[0367] The generated training menu is sent from the server to the user's device. The device displays the training menu received from the server to the user, and the user performs the training according to the displayed menu. After the training, the user enters details of the training they performed (e.g., 50 squats using 5kg dumbbells) and their self-evaluation (difficulty and satisfaction of the training) into the device.

[0368] The device also collects the user's facial expressions, voice, and text data during and after the user's training. The collected data is analyzed by the device's built-in emotion engine to recognize the user's emotional state (e.g., fatigue, motivation, stress, etc.). This emotion data is also sent to the server.

[0369] The server receives the training results, self-evaluation, and emotional data, and passes them to the generative AI engine to generate feedback and advice for the next training session. For example, if the user felt stressed during training, the server will suggest more relaxing exercises for the next session. This feedback and advice is sent from the server to the user's device and displayed to the user.

[0370] Specific examples

[0371] User B accesses a personal trainer application and enters their height (165 cm), weight (80 kg), ability to go to the gym four times a week, and goal of "losing weight." The device sends this data to the server. The server receives the data and passes it to the generation AI. The generation AI generates a training menu for User B four times a week. For example, it may provide a menu such as "30 minutes of running, 20 squats, and 10 burpee jumps." The training menu is sent to the device, which displays it to User B. User B trains at the gym and then enters "30 minutes of running, 5 km run, self-rating 5 / 5." The emotion engine analyzes User B's facial expressions and voice and recognizes the emotion "motivated." This data is sent from the device to the server, which passes it to the generation AI. The generation AI analyzes the data and generates advice such as "extend your running time to 40 minutes next time." This feedback is sent to the device and displayed to User B.

[0372] Prompt Sentence Examples

[0373] Below are some examples of prompts that could be passed to the generation AI when the user uses the application.

[0374] "Generate a weekly training plan for weight loss based on user data. The data is as follows: height 170cm, weight 70kg, able to train 3 times a week."

[0375] The system provides more personalized training menus and feedback that take into account the user's emotional state, maximizing the effectiveness of training.

[0376] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0377] Step 1:

[0378] The user enters information

[0379] User Behavior

[0380] Users access the AI ​​personal trainer application from their own devices and input their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and training frequency. Users also set training goals (e.g., losing weight, gaining muscle).

[0381] input

[0382] Physical information, lifestyle, training frequency, training goals

[0383] output

[0384] Temporarily save the input data as a JSON format file

[0385] Step 2:

[0386] The device sends the input information to the server

[0387] Terminal handling

[0388] The device collects the information entered by the user and sends it to the server in an appropriate format, such as JSON, including the user's height, weight, age, gender, lifestyle, training frequency, and training goals.

[0389] input

[0390] User's physical information, lifestyle habits, training frequency, and training goals stored on the device

[0391] output

[0392] JSON format data sent to the server

[0393] Step 3:

[0394] The server receives the data and passes it to the generative AI engine

[0395] Server Processing

[0396] The server receives user information sent from the device and passes this data to the generation AI engine.

[0397] input

[0398] JSON format data sent from the device

[0399] output

[0400] User information passed to the generation AI engine

[0401] Step 4:

[0402] Generative AI engine generates training menus

[0403] Generative AI engine processing

[0404] The generative AI engine generates an optimal training menu based on the received user information and training goals, and also takes into account past data and training data of similar users.

[0405] input

[0406] User information, training goals, generative AI model

[0407] output

[0408] Generated training menu

[0409] Step 5:

[0410] Send the training menu to the device and provide it to the user

[0411] Server Processing

[0412] The server sends the training menu received from the AI ​​generation engine to the user's device, which then displays it to the user.

[0413] input

[0414] Generated training menu

[0415] output

[0416] Training menu displayed on the user's device

[0417] Step 6:

[0418] The user performs the training and enters the results

[0419] User Behavior

[0420] The user follows the training menu displayed on the device and performs the training. After the training, the user enters the details of the training and their own evaluation into the device.

[0421] input

[0422] Training results, self-assessment

[0423] output

[0424] Input training results and self-assessment data

[0425] Step 7:

[0426] The device sends the training results and self-evaluation to the server.

[0427] Terminal handling

[0428] The terminal collects the training results and self-assessment entered by the user and transmits them to the server.

[0429] input

[0430] User-entered training results and self-assessment data

[0431] output

[0432] Training results and self-assessment data sent to the server

[0433] Step 8:

[0434] The device collects and analyzes emotional data

[0435] Terminal handling

[0436] The device collects the user's facial expressions, voice, and text data during and after training, which is then analyzed by the device's built-in emotion engine to determine the user's emotional state.

[0437] input

[0438] User facial expressions, voice, and text data

[0439] output

[0440] Analyzed emotion data

[0441] Step 9:

[0442] Send emotion data to the server

[0443] Terminal handling

[0444] The device transmits the analyzed emotion data to the server.

[0445] input

[0446] Analyzed emotion data

[0447] output

[0448] Emotion data sent to the server

[0449] Step 10:

[0450] The server generates feedback and advice for the next training session

[0451] Server Processing

[0452] The server instructs the AI ​​engine to analyze the training results, self-assessment, and emotional data, and generates feedback and advice for the next training session.

[0453] input

[0454] Training results, self-rating, emotion data, generative AI model

[0455] output

[0456] Generated feedback and next training advice

[0457] Step 11:

[0458] Send feedback and advice to the device and provide it to the user

[0459] Server Processing

[0460] The server sends the generated feedback and next training advice to the user's terminal, which displays it to the user.

[0461] input

[0462] Generated feedback and next training advice

[0463] output

[0464] Feedback displayed on the user's device and advice for the next training session

[0465] (Application example 2)

[0466] 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."

[0467] Conventional personal trainer systems typically generate training menus and feedback based on the user's physical data and training results. However, they do not take the user's emotional state into consideration, making it difficult to maximize the effectiveness of training. In particular, in the field of food delivery, users' moods and emotions have a significant impact on their appetite and choices, so there is a demand for suggestions based on emotions. Therefore, realizing a system that incorporates emotional data has been a challenge.

[0468] 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.

[0469] In this invention, the server includes: means for having the user input training goals and personal physical information; means for generating a training menu based on the input training goals and personal physical information; means for providing the generated training menu to the user's terminal; means for having the user input training results and self-evaluation after training according to the training menu; means for generating feedback and advice for the next training session based on the input results and self-evaluation and providing the feedback and advice to the user's terminal; and means for incorporating an emotion engine that analyzes the user's emotional state and adjusting the training menu and feedback based on the emotional state, thereby making it possible to propose optimal training and meal menus according to the user's emotional state.

[0470] "User" refers to an individual who uses the system.

[0471] "Training goal" refers to a specific goal in exercise that a user wants to achieve.

[0472] "Personal physical information" refers to data about a user's body, such as weight, height, age, and gender.

[0473] The term "server" refers to a central processing unit that processes information input by a user, generates a training menu and feedback, and transmits the menu and feedback to a user terminal.

[0474] A "training menu" refers to a training plan or plan that is generated based on the user's goals.

[0475] "User's device" refers to a device used by a user to access the system and input or provide information, such as a smartphone or tablet.

[0476] The "generated training menu" refers to an exercise program created by the server based on the user's input data.

[0477] "Training results" refers to the content and results of the training that the user actually undertook.

[0478] "Self-assessment" refers to a user's self-evaluation of the training they have completed.

[0479] "Feedback" refers to advice and areas for improvement generated based on training results and self-assessment.

[0480] "Emotional state" refers to a user's current mood or emotions.

[0481] An "emotion engine" refers to a system that analyzes a user's facial expressions and voice data to recognize the user's emotional state.

[0482] "Means for adjusting training menus and feedback" refers to means for optimizing exercise programs and advice by reflecting the user's emotional state.

[0483] This invention is a system that generates an optimal training menu based on a user's training goals and personal physical information, and further analyzes the user's emotional state to adjust feedback and advice. This system can be applied to the food delivery field to provide an optimal meal menu according to the user's emotional state.

[0484] System Program Overview

[0485] 1. Collection of User Information

[0486] Users use a smartphone app to input information such as their training goals, personal physical information, food preferences, allergy information, and meal timings.

[0487] The terminal transmits this information to the server.

[0488] 2. Recognizing emotional states

[0489] When a user accesses the app, the smartphone's camera and microphone are used to collect facial expressions and voice, and the emotion engine analyzes the user's current emotional state.

[0490] Images collected by the camera are processed using the OpenCV library and input into an emotion recognition model (using TENSORFLOW®).

[0491] The audio data collected by the microphone is converted from audio to text using the SpeechRecognition library, and emotions are recognized based on the text data.

[0492] 3. Creation of training and meal menus

[0493] The server sends the user's input information and data from the emotion engine to the generation AI engine, and generates training and meal menus.

[0494] For example, if the user feels "tired," a menu of relaxing meals (soup, salad, herbal tea, etc.) will be generated.

[0495] 4. Providing Feedback

[0496] After the user completes a workout or meal, they enter their results and self-evaluation into the app.

[0497] The terminal collects this data and sends it to the server.

[0498] The server then refers back to the analysis results of the emotion engine and uses generative AI to generate feedback and advice for the next workout or meal.

[0499] Hardware and Software Use Cases

[0500] Smartphones: Used by users to input information and recognize emotional states.

[0501] Server: Processes user information, generates training menus and meal menus, and generates feedback.

[0502] Software: OpenCV (for image processing), TensorFlow (for emotion recognition models), SpeechRecognition (for voice recognition).

[0503] Specific examples

[0504] When User A opens the app, takes a picture of their face with the camera and says "I'm tired," the app suggests "soup" and "herbal tea." After User A confirms this, they place their order and enter their impressions after eating and drinking as feedback. An example of a prompt sentence using the generative AI model is as follows:

[0505] Prompt Sentence Examples

[0506] "I'm feeling unmotivated. Please suggest some relaxing meals. User information is as follows: I like Japanese food, I have no allergies, and I always eat at 12:00 and 18:00."

[0507] In this way, the present invention can provide optimal training and meal menus based on the user's emotional state, thereby improving the user's health maintenance and meal satisfaction.

[0508] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0509] Step 1:

[0510] The user launches the smartphone app and inputs their training goals, personal physical information, food preferences, allergy information, meal timing, etc. Based on this, the device organizes this data and sends it to the server. The input data includes specific training goals (e.g., losing weight) and physical data (e.g., height, weight, age, gender).

[0511] Input: Training goals, personal physical information, food preferences, allergy information, meal timing

[0512] Output: Structured user data

[0513] Step 2:

[0514] The server processes the received user data and generates a training menu using a generative AI engine based on the user's training goals and personal physical information. The generated training menu is optimized for the user's goals.

[0515] Input: Structured user data

[0516] Output: Training menu

[0517] Step 3:

[0518] The server sends the generated training menu to the user's terminal, which displays it to the user. The user checks the training menu and performs the training.

[0519] Input: Generated training menu

[0520] Output: Training menu displayed to the user

[0521] Step 4:

[0522] After completing the training, the user enters the results of the training and their self-evaluation into the smartphone app. The device collects this data and sends it to the server.

[0523] Input: Training results and self-assessment

[0524] Output: Structured training data and self-scoring data

[0525] Step 5:

[0526] The device captures the user's facial expressions with a camera and collects audio with a microphone. It then uses an emotion engine to analyze this data and recognize the user's emotional state. Specifically, it analyzes facial expressions using the image processing library OpenCV and determines emotions using an emotion recognition model using TensorFlow. It also converts audio into text using the speech recognition library SpeechRecognition and determines emotions.

[0527] Input: facial expression image data, voice data

[0528] Output: Perceived emotional state

[0529] Step 6:

[0530] The server inputs the collected training data, self-assessment data, and emotional state data into a generative AI engine to generate the next training menu and feedback. For example, if the server determines that the user is feeling tired, it will suggest relaxing exercises.

[0531] Input: training data, self-rating data, emotional state data

[0532] Output: Next training menu and feedback

[0533] Step 7:

[0534] The server sends the generated next training menu and feedback to the user's terminal, which displays it to the user. The user can then check the feedback and use it in their next training session.

[0535] Input: Next training menu and feedback

[0536] Output: The next training menu displayed to the user and feedback

[0537] 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.

[0538] 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 (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.

[0539] 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.

[0540] [Second embodiment]

[0541] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0542] 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.

[0543] 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).

[0544] 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.

[0545] 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.

[0546] 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).

[0547] 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. 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.

[0548] 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.

[0549] 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.

[0550] 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.

[0551] 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.

[0552] 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."

[0553] In this embodiment, a personal trainer system that utilizes a generation AI to provide an effective training menu tailored to each individual's goals will be described. The following describes the operation flow of this system and the specific processing at each step.

[0554] 1. Collection of User Information

[0555] User Behavior

[0556] First, a user accesses the AI ​​personal trainer application using their own device (such as a smartphone or PC). Next, the user enters their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and frequency of gym visits (how many times per week) into the application. The user then sets their training goals (e.g., lose weight, gain muscle, improve physical strength).

[0557] Terminal handling

[0558] The terminal collects the information entered by the user and transmits the data to the server.

[0559] 2. Creation of training menu

[0560] Server Processing

[0561] The server receives the user's data and sends it to the generative AI engine. The generative AI engine generates an optimal training menu based on the user's information and goals. For example, if the user's goal is to "lose weight," the generative AI will provide a menu that takes into account the balance of aerobic exercise (running and cycling) and strength training (squats and dumbbell exercises, etc.). The generated training menu is sent from the server to the user's device.

[0562] 3. Display and execute the training menu

[0563] Terminal handling

[0564] The terminal displays the training menu sent from the server to the user. The user starts training and performs the training according to the details in the menu (e.g., running time, number of crunches, weight of dumbbells, etc.).

[0565] 4. Record your training and self-assess

[0566] User Behavior

[0567] After the workout, the user enters details of the workout (e.g., 50 squats using 5kg dumbbells) and their own assessment (e.g., subjective assessment of whether the workout was difficult) into the device.

[0568] Terminal handling

[0569] The device collects the training details and self-assessment entered by the user and sends the data to a server.

[0570] 5. Feedback and training advice for your next workout

[0571] Server Processing

[0572] The server sends the collected data to the generation AI, which generates feedback based on past training results and self-assessment, and provides advice for the next training. For example, if the user's self-assessment result indicates that they have done too many squats and are putting strain on their knees, the system will suggest knee-friendly training for the next training session. This feedback and advice is sent from the server to the user's device.

[0573] Terminal handling

[0574] The terminal displays the feedback and advice received from the server to the user.

[0575] Specific examples

[0576] User A (Goal: Muscle building)

[0577] Step 1

[0578] User A accesses the app and enters his / her height (180 cm), weight (70 kg), ability to go to the gym three times a week, and goal of "gaining muscle." The device then sends this data to the server.

[0579] Step 2

[0580] The server receives the data and passes it to the generation AI. The generation AI generates a training menu for User A three times a week. For example, it might provide a menu such as "Squat 60kg x 3 sets, Bench press 50kg x 3 sets, Deadlift 80kg x 3 sets." The training menu is sent to the device.

[0581] Step 3

[0582] The device displays the training menu to User A. User A then performs training at the gym.

[0583] Step 4

[0584] User A enters the details of the training he or she performed and his or her own rating. For example, he or she might enter "Squats 60kg x 3 sets, self-rating 4 / 5." The device then sends the data to the server.

[0585] Step 5

[0586] The server receives the data and passes it to the generation AI. The generation AI analyzes the data and generates feedback such as "Next time, increase the number of squat sets to 4." The feedback is sent to the device and displayed to User A.

[0587] In this way, the present invention is a system that enables a user to easily receive a training menu that is best suited to the user and to train efficiently and effectively.

[0588] The processing flow will be explained below.

[0589] Step 1:

[0590] The user accesses the generated AI personal trainer application using a device (such as a smartphone or PC). The user inputs their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and frequency of gym visits (how many times per week). The user then sets their own training goals (e.g., lose weight, gain muscle, improve physical strength).

[0591] Step 2:

[0592] The terminal collects the information entered by the user and sends the data to the server.

[0593] Step 3:

[0594] The server receives the user information sent from the device and passes the received information to the generation AI engine.

[0595] Step 4:

[0596] The generative AI engine generates the optimal training menu for each individual user based on their information and training goals. For example, if your goal is to lose weight, it will generate a menu that balances cardio and strength training.

[0597] Step 5:

[0598] The server transmits the generated training menu to the terminal.

[0599] Step 6:

[0600] The device displays a training menu to the user, who then checks the menu and follows it to train at the gym or at home.

[0601] Step 7:

[0602] After the user completes the training, they enter details of each exercise (e.g., 30 minutes of running, 5 km run) and their own assessment into the device.

[0603] Step 8:

[0604] The terminal transmits the detailed training data and self-evaluation results input by the user to the server.

[0605] Step 9:

[0606] The server passes the detailed training data and self-assessment results received from the device to the generation AI engine. The generation AI analyzes the past training history and self-assessment results and generates feedback and advice for the next training session. For example, if the user's knees are under strain, it will suggest knee-friendly training for the next session.

[0607] Step 10:

[0608] A server is generated to send feedback and advice to the terminal.

[0609] Step 11:

[0610] The device displays the feedback and advice received from the server to the user, who can then review the displayed feedback and use it for their next training session.

[0611] Example 1

[0612] 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."

[0613] Conventional training menus often provide uniform programs, which have the problem of not being able to provide an optimal menu tailored to each user's physical information or specific goals. Furthermore, there is an insufficient mechanism for users to receive feedback after training and use that feedback to improve their next training. Furthermore, the time and effort required for users to self-evaluate their training results can discourage users from continuing to train.

[0614] 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.

[0615] In this invention, the server includes: means for having a user input training goals and physical information; means for transmitting the input training goals and physical information to the server via a terminal; means for generating a training menu using a generative AI model based on the input training goals and physical information via the server; means for providing the generated training menu to the user's terminal; means for having the user input the training results and self-assessment after training according to the training menu; means for transmitting the input results and self-assessment via the terminal to the server; and means for generating feedback and advice for the next training session using the generative AI model based on the input results and self-assessment and providing the feedback and advice to the user's terminal. This makes it possible to provide a training menu optimized for the user's individual physical information and goals, and to continuously provide appropriate feedback and advice according to the training results.

[0616] "User" refers to a user who uses the Generative AI Personal Trainer System.

[0617] A "training goal" is a specific exercise objective that a user wants to achieve, such as losing weight, gaining muscle, or improving physical strength.

[0618] "Physical information" refers to basic physical data such as a user's weight, height, age, and gender.

[0619] A "terminal" is a device used by a user to access the system and input information, including a smartphone or PC.

[0620] "Server" refers to the central management system that receives user input data, generates optimal training menus using generative AI models, and provides feedback and advice.

[0621] A "generative AI model" is an artificial intelligence model that automatically generates training menus and feedback based on user information, and refers to one that utilizes natural language processing technology, for example.

[0622] A "training menu" refers to a specific exercise plan proposed by the generative AI model based on the user's training goals and physical information.

[0623] "Training results" is a detailed record of the training the user actually performed, including the number of exercises, number of sets, weight used, etc.

[0624] "Self-rating" is when a user inputs a personal evaluation of the training content after completing the training, and includes subjective impressions and comments about the state of the body.

[0625] "Feedback" refers to the general term for improvements and advice provided by the generative AI model for the next training session based on the training results and self-assessment entered by the user.

[0626] "Advice" refers to specific training method suggestions and points of caution provided to users by the generative AI model.

[0627] In this embodiment, we will explain a personal trainer system that utilizes a generative AI model to provide an effective training menu tailored to each individual's training goals. First, the system collects data from the user, such as physical information and training goals, and generates an optimal menu based on the generative AI model. After the training, the system then provides feedback and advice for the next training session.

[0628] Collection of User Information

[0629] User Behavior

[0630] Users access the generated AI personal trainer application using their own devices. Specific hardware examples include smartphones and PCs, and software examples include dedicated applications that can be accessed via a browser.

[0631] The user enters the following information within the application:

[0632] Physical information (e.g., weight, height, age, gender)

[0633] Lifestyle habits (e.g., eating habits, sleep duration)

[0634] How often you can go to the gym (e.g., how many times a week)

[0635] Training goals (e.g., lose weight, gain muscle, improve strength)

[0636] Training menu generation

[0637] Terminal handling

[0638] The device sends the collected user information to the server, using a secure communication protocol such as HTTPS.

[0639] Server Processing

[0640] The server runs the received data on a cloud infrastructure (e.g., AWS, Google Cloud Platform) because it requires high-performance computing resources. The server then sends the data to a generative AI model (e.g., OpenAI's GPT-3), which generates an optimal training menu based on the input information. The generated training menu is then sent from the server to the user's device.

[0641] Displaying and executing training menus

[0642] Terminal handling

[0643] The device displays the received training menu to the user, who then performs the training according to the menu. Training items include running time, number of crunches, weight of dumbbells, etc.

[0644] Record and self-assess your training

[0645] User Behavior

[0646] After the training, the user inputs the details of the training (e.g., 50 squats using 5kg dumbbells) and their own assessment (e.g., how difficult the training was) into the terminal.

[0647] Terminal handling

[0648] The terminal collects the user's input and sends the data back to the server.

[0649] Feedback and advice for your next training session

[0650] Server Processing

[0651] The server sends the collected training data and self-assessment to the generative AI model, which then generates feedback and advice for the next training session. For example, if the user's knees are under strain, the model will suggest training that is gentler on the knees. The generated feedback and advice are then sent from the server to the user's device.

[0652] Terminal handling

[0653] The terminal displays feedback and advice to the user.

[0654] Specific examples

[0655] User A (Goal: Muscle building)

[0656] 1. User A accesses the app and enters his / her information: height 180 cm, weight 70 kg, ability to go to the gym three times a week, and goal of "gaining muscle."

[0657] 2. The device sends this data to the server.

[0658] 3. The server receives the data and passes it to the generation AI, which then generates a menu such as "Squat 60kg x 3 sets, Bench press 50kg x 3 sets, Deadlift 80kg x 3 sets."

[0659] 4. The training menu is sent to the device and displayed on User A. User A then performs the training at the gym.

[0660] 5. User A enters the details of the training he or she performed and his or her own evaluation. For example, he or she enters "Squats 60kg x 3 sets, self-evaluation 4 / 5." The device sends the input data to the server.

[0661] 6. The server receives the data and passes it to the generation AI. The generation AI analyzes the data and generates feedback such as "Next time, increase the number of squat sets to 4." This feedback is sent to the device and displayed to User A.

[0662] Prompt Sentence Examples

[0663] "User A is 180cm tall, weighs 70kg, can go to the gym three times a week, and wants to build muscle. Please create an optimal training menu based on this information."

[0664] or

[0665] "Generate a training menu based on the following user information: height 180cm, weight 70kg, gym visits 3 times a week, goal is to build muscle."

[0666] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0667] Step 1:

[0668] Entering user information

[0669] User Behavior

[0670] Users access the AI-generated personal trainer application using their own devices (smartphones or PCs). Within the application, users input their physical information (weight, height, age, gender), lifestyle habits (eating habits, sleep time, etc.), frequency of gym visits (how many times a week they can go), and training goals (lose weight, gain muscle, improve physical strength).

[0671] Terminal handling

[0672] The terminal stores the input user information in a database format and transmits it to the server as structured data.

[0673] Input: User's physical information, lifestyle habits, gym visit frequency, and training goals.

[0674] Output: Structured data to send to the server.

[0675] Step 2:

[0676] Training menu generation

[0677] Server Processing

[0678] The server sends data to a generative AI model based on the received user information. The generative AI model (e.g., GPT-3) generates an optimal training menu based on the user's physical information and goals. For example, if the user's goal is to "lose weight," the generative AI model will provide a menu that takes into account the balance of aerobic exercise and strength training.

[0679] Input: Structured user information.

[0680] Output: A training menu optimized for the user.

[0681] Server Processing

[0682] The generated training menu is sent from the server to the user's terminal.

[0683] Step 3:

[0684] Displaying and executing training menus

[0685] Terminal handling

[0686] The terminal displays the training menu received from the server to the user. The user follows the displayed menu and performs training based on details of, for example, running or strength training (running time, number of crunches, weight of dumbbells).

[0687] Input: Training menu from the server.

[0688] Output: Display of training menu, notification to user.

[0689] Step 4:

[0690] Record and self-assess your training

[0691] User Behavior

[0692] After the training, the user inputs details of the training into the device, such as 50 squats using 5kg dumbbells, and also inputs a self-evaluation of the difficulty of the training.

[0693] Terminal handling

[0694] The device collects these training results and self-assessment and sends them to the server.

[0695] Input: Training details from user, self-assessment.

[0696] Output: Training data to send to the server.

[0697] Step 5:

[0698] Generate feedback and next training advice

[0699] Server Processing

[0700] The server then sends the received training data and self-evaluation back to the generative AI model, which then generates feedback and advice for the next training session. For example, if the user feels strain on their knees, the generative AI model will suggest knee-friendly training for the next session.

[0701] Input: Collected training results and self-assessment.

[0702] Output: Feedback and next training advice.

[0703] Server Processing

[0704] The generated feedback and advice are sent from the server to the user's terminal.

[0705] Step 6:

[0706] View feedback and advice

[0707] Terminal handling

[0708] The device receives feedback and advice from the server and displays it to the user, giving them specific instructions for their next workout.

[0709] Input: Feedback and advice from the server.

[0710] Output: Displaying feedback and advice to the user.

[0711] (Application example 1)

[0712] 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."

[0713] Conventional training menu provision systems lack the functionality to generate optimal training plans based on an individual's specific goals and physical information, making it difficult to maximize effectiveness. In particular, they lacked a mechanism to dynamically adjust the next training menu and provide feedback based on an individual's training results and self-evaluation.

[0714] 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.

[0715] In this invention, the server includes: means for having the user input training goals and personal physical information; means for generating a training menu based on the input training goals and personal physical information; means for providing the generated training menu to the user's terminal; means for having the user input the training results and self-assessment after training according to the training menu; means for generating feedback and advice for the next training session based on the input results and self-assessment and providing the feedback and advice to the user's terminal; and means for using a generative AI model to generate the feedback and advice. This allows for the provision of an optimal training menu based on the user's individual goals and condition, and dynamic feedback and advice, enabling highly effective training.

[0716] "User" refers to an individual who receives the training menu in the invention.

[0717] "Training goal" refers to a specific fitness goal that a user wishes to achieve, such as losing weight, building muscle, or improving strength.

[0718] "Physical information" refers to physical data such as a user's height, weight, age, and gender.

[0719] "Server" refers to a central control device that receives and processes information sent by users, generates training menus based on the information, and provides feedback.

[0720] "Generative AI model" refers to artificial intelligence technology that generates optimal training menus and feedback based on user information.

[0721] "User's terminal" refers to a device used by the user for input and display, such as a smartphone, PC, or tablet.

[0722] A "training menu" refers to a specific exercise or plan that a user should perform, including, for example, the type of exercise, number of repetitions, number of sets, weight, etc.

[0723] "Training Results" refers to details of the training a user actually performed, including, for example, the number of sets performed and the weight used.

[0724] "Self-rating" refers to a subjective evaluation made by the user after completing a workout, including, for example, the difficulty of the workout and the level of fatigue.

[0725] "Feedback" refers to improvements and advice for the next training session based on the training results and self-assessment entered by the user.

[0726] An embodiment of the present invention will be described.

[0727] Overall system overview

[0728] The system works by combining the user's device, a server, and a generative AI model.

[0729] Collection of User Information

[0730] First, a user accesses the application using a device such as a smartphone or tablet. The application provides a user input form and asks the user to enter the following information:

[0731] Height, weight, age, gender (physical information)

[0732] Eating habits, sleep time, etc. (lifestyle)

[0733] How often can you go to the gym per week?

[0734] Training goals (e.g., lose weight, gain muscle, improve strength)

[0735] Training menu generation

[0736] The device sends the input information to the server. The server receives this data and generates an optimal training menu based on a generative AI model. The generative AI model uses, for example, ChatGPT or GPT-4. The generated training menu is then provided to the user's device. The menu includes the type of exercise, number of repetitions, number of sets, weight, etc.

[0737] Displaying and executing training menus

[0738] The terminal displays the training menu sent from the server to the user, who then trains at the gym according to the training menu.

[0739] Record and self-assess your training

[0740] After the training, the user inputs details of the training (e.g., 50 squats using 5 kg dumbbells) and their own evaluation (e.g., subjective evaluation of whether the training was hard or not) into the device. The device then sends this data back to the server.

[0741] Feedback and advice for your next training session

[0742] The server sends the collected data to the generative AI model, which generates feedback and advice for the next training session based on past training results and self-evaluation. The advice includes specific areas for improvement, such as "Next time, increase the number of squat sets to four." The feedback and advice are sent to the user's device and displayed to the user.

[0743] Specific examples

[0744] User A launches the app and enters the following information:

[0745] Height: 180cm

[0746] Weight: 75kg

[0747] Age: 30

[0748] Gender: Male

[0749] How often can you go to the gym per week: 4 times

[0750] Training goal: Gain muscle

[0751] This information is sent to the server, and the generative AI model creates a training menu of "60kg squats x 3 sets, 50kg bench press x 3 sets, 80kg deadlift x 3 sets." User A executes this menu and inputs the results as "60kg squats x 3 sets, self-rating 4 / 5." Based on these results, the server returns feedback such as "Increase the number of squat sets to 4 next time."

[0752] Prompt Sentence Examples

[0753] An example of a prompt to input to a generative AI model is as follows:

[0754] User Information:

[0755] Height: 180cm

[0756] Weight: 75kg

[0757] Age: 30

[0758] Gender: Male

[0759] How often can you go to the gym per week: 4 times

[0760] Training goal: Gain muscle

[0761] Based on this, generate the following training menu:

[0762] Amount and type of aerobic exercise

[0763] Strength training type, number of sets, and weight

[0764] As described above, by implementing the present invention, it becomes possible to provide an optimized training menu to the user and provide feedback thereto.

[0765] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0766] Step 1:

[0767] Users access the application using a device such as a smartphone or tablet. They enter their height, weight, age, gender, eating habits, sleep time, frequency of gym visits, and training goals in the form displayed on the device. The entered data is then sent from the device to the server.

[0768] Input: height, weight, age, gender, eating habits, sleep time, frequency of gym visits, training goals

[0769] Output: User information sent to the server

[0770] Step 2:

[0771] The server analyzes the received user information and generates an optimal training menu based on the generative AI model. Specifically, it determines the type of exercise, number of sets, repetitions, weight, etc. based on the user's physical information and training goals. The generated training menu is sent from the server to the device.

[0772] Input: User information

[0773] Data processing: Generative AI model generates training menu

[0774] Output: Generated training menu

[0775] Step 3:

[0776] The terminal displays the generated training menu to the user, who then goes to the gym and performs the training according to the displayed menu.

[0777] Input: Generated training menu

[0778] Output: Training menu displayed to the user

[0779] Step 4:

[0780] After completing a workout, the user inputs details of the workout into the device, such as the number of sets, weight, number of repetitions, and self-evaluation for each exercise. The input data is then sent from the device to the server.

[0781] Input: Training results (number of sets, weight, number of repetitions, self-evaluation)

[0782] Output: Training run results sent to the server

[0783] Step 5:

[0784] The server uses the generative AI model to generate feedback and training advice for the next time based on the received training results and self-evaluation. This includes specific advice such as "Increase the number of sets for your next squat to four." The generated feedback and advice are sent from the server to the device.

[0785] Input: Training execution results, self-evaluation

[0786] Data Transformation: Generative AI Models Generate Feedback and Advice

[0787] Output: Generated feedback and advice

[0788] Step 6:

[0789] The terminal displays the feedback and next training advice sent from the server to the user, who can then plan his next training session.

[0790] Input: Generated feedback and advice

[0791] Output: Feedback and advice displayed to the user

[0792] 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.

[0793] As an embodiment of the present invention, a personal trainer system that combines a generative AI and an emotion engine will be described. This system generates an individually optimized training menu based on user input information, and also recognizes the user's emotional state and reflects this in feedback and advice. The following describes in detail the operation flow of this system and its specific processing.

[0794] 1. Collection of User Information

[0795] User Behavior

[0796] First, a user accesses the AI ​​personal trainer application using their own device (such as a smartphone or PC). Next, the user enters their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and frequency of gym visits (how many times per week) into the application. The user also sets their training goals (e.g., to lose weight, gain muscle, or improve physical strength).

[0797] Terminal handling

[0798] The terminal collects the information entered by the user and transmits the data to the server.

[0799] 2. Creation of training menu

[0800] Server Processing

[0801] The server receives the user's data and sends it to the generative AI engine. The generative AI engine generates an optimal training menu based on the user's information and goals. For example, if the user's goal is to "lose weight," the generative AI will provide a menu that takes into account the balance of aerobic exercise (running and cycling) and strength training (squats and dumbbell exercises, etc.). The generated training menu is sent from the server to the user's device.

[0802] 3. Display and execute the training menu

[0803] Terminal handling

[0804] The terminal displays the training menu sent from the server to the user. The user starts training and performs the training according to the details in the menu (e.g., running time, number of crunches, weight of dumbbells, etc.).

[0805] 4. Record your training and self-assess

[0806] User Behavior

[0807] After the workout, the user enters details of the workout (e.g., 50 squats using 5kg dumbbells) and their own assessment (e.g., subjective assessment of whether the workout was difficult) into the device.

[0808] Terminal handling

[0809] The device collects the training details and self-assessment entered by the user and sends the data to a server.

[0810] 5. Emotional Recognition

[0811] User Behavior

[0812] While the user is performing the training and after the training, the device collects the user's facial expression, voice, and text data.

[0813] Terminal handling

[0814] The device's built-in emotion engine analyzes the user's emotional state based on the collected data, recognizing, for example, whether the user is tired, motivated, or stressed.

[0815] 6. Feedback and advice for your next training session

[0816] Server Processing

[0817] The server sends the collected training data, self-evaluation results, and emotion analysis results from the emotion engine to the generation AI. The generation AI generates feedback based on the user's past training history and emotional state, and provides advice for the next training session. For example, if the user felt stressed during training, it will suggest more relaxing exercises for the next session.

[0818] Server Processing

[0819] Send generated feedback and advice to the device.

[0820] Terminal handling

[0821] The device receives feedback and advice from the server and displays it to the user, who can then review the feedback and use it to improve their next training session.

[0822] Specific examples

[0823] User B (Goal: Weight loss)

[0824] Step 1

[0825] User B accesses the app and enters information such as his height of 165 cm, his weight of 80 kg, the ability to go to the gym four times a week, and his goal of "losing weight." The device then sends this data to the server.

[0826] Step 2

[0827] The server receives the data and passes it to the generation AI. The generation AI generates a training menu for User B four times a week. For example, it may provide a menu such as "30 minutes of running, 20 squats, and 10 burpee jumps." The training menu is sent to the device.

[0828] Step 3

[0829] The device displays the training menu to User B. User B then performs the training at the gym.

[0830] Step 4

[0831] User B enters details of the workout he or she performed. For example, he or she might enter "30 minutes of running, 5km run, self-rating 5 / 5." The emotion engine analyzes User B's facial expressions and voice and recognizes the emotion "motivated" based on the microexpression. The data is sent from the device to the server.

[0832] Step 5

[0833] The server receives the data and passes it to the generation AI. The generation AI analyzes the data and generates advice for the next training menu. For example, "Extend your running time to 40 minutes next time." The feedback is sent to User B's device and displayed.

[0834] In this way, the generative AI personal trainer system using the emotion engine can provide an individually optimized training menu taking into account the user's emotional state, maximizing efficiency and effectiveness.

[0835] The processing flow will be explained below.

[0836] Step 1:

[0837] A user accesses the generated AI personal trainer application using a device (such as a smartphone or PC). The user inputs their physical information (e.g., weight, height, age, gender) and lifestyle habits (e.g., eating habits, sleep time), as well as the frequency of gym visits (e.g., how many times per week they can go). In addition, the user sets training goals (e.g., to lose weight, gain muscle, improve physical strength).

[0838] Step 2:

[0839] The terminal collects the information entered by the user and transmits the data to the server.

[0840] Step 3:

[0841] The server receives the user information sent from the device and passes the received information to the generation AI engine.

[0842] Step 4:

[0843] The generative AI engine generates the optimal training menu for each individual user based on their information and training goals. For example, if your goal is to lose weight, it will generate a menu that balances cardio and strength training.

[0844] Step 5:

[0845] The server transmits the generated training menu to the terminal.

[0846] Step 6:

[0847] The device displays the training menu sent from the server to the user, who then checks the training menu and follows it to train at the gym or at home.

[0848] Step 7:

[0849] After the user completes the training, they enter details of each exercise (e.g., 30 minutes of running, 5 km run) and their own assessment (e.g., subjective assessment of whether the training was hard) into the device.

[0850] Step 8:

[0851] The terminal transmits the detailed training data and self-evaluation results input by the user to the server.

[0852] Step 9:

[0853] While the user is training and afterward, the device collects facial, voice, and text data from the user. The device's built-in emotion engine analyzes the user's emotional state based on the collected data. For example, it can recognize emotions such as tiredness, motivation, and stress.

[0854] Step 10:

[0855] The server receives detailed training data, self-assessment results, and emotion analysis results from the emotion engine from the device, and passes them to the generative AI engine. The generative AI generates feedback based on the user's past training history and emotional state, and provides advice for the next training session. For example, if the user felt stressed during training, it will suggest more relaxing exercises for the next session.

[0856] Step 11:

[0857] The server sends the generated feedback and advice to the device.

[0858] Step 12:

[0859] The device displays the feedback and advice received from the server to the user, who can then review the feedback and use it to improve their next training session.

[0860] Example 2

[0861] 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."

[0862] Conventional personal trainer systems provide training menus based on a user's physical information and training goals, but they are unable to take into account the user's emotional state or performance during training, resulting in insufficient individual optimization. As a result, users often find it difficult to continue training and maintain motivation. The present invention aims to solve this problem by providing feedback and training advice that takes into account the user's emotional state.

[0863] 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.

[0864] In this invention, the server includes: means for having the user input training goals and personal physical information; means for transmitting the input physical information, lifestyle habits, and training frequency to the server via a terminal; means for generating a training menu based on the input training goals and personal physical information via the server; means for providing the generated training menu to the user's terminal; means for having the user input training results and self-evaluation after training according to the training menu; means for collecting facial expressions, voice, and text data of the user during and after the training and recognizing emotions via the terminal; and means for generating feedback and advice for the next training session based on the input results, self-evaluation, and emotional data via the server and providing the feedback and advice to the user's terminal. This makes it possible to provide feedback that takes the user's emotional state into account and individually optimized training advice.

[0865] "User" refers to an individual who uses the generative AI personal trainer system to generate a training menu and receive feedback.

[0866] A "training goal" is a physical goal that a user wants to achieve, examples of which include "lose weight" or "gain muscle."

[0867] "Physical information" refers to basic personal data such as a user's height, weight, age, and gender.

[0868] "Lifestyle habits" refers to information such as the user's eating habits and sleeping hours in their daily lives.

[0869] "Training frequency" refers to the number of times or frequency with which a user trains, and examples include "how many times per week they train."

[0870] A "terminal" is a device used by a user to input data and receive training menus and feedback, and examples include smartphones and PCs.

[0871] "Server" refers to the computer at the core of the system that receives data sent by users and uses generation AI to generate training menus and provide feedback.

[0872] A "generative AI engine" refers to an artificial intelligence model that generates optimal training menus based on user input information and training goals.

[0873] "Self-rating" refers to data that allows users to subjectively evaluate their own performance and impressions after training.

[0874] "Emotional data" refers to information about a user's emotional state analyzed from facial expressions, voice, text data, and the like.

[0875] "Feedback" refers to the advice and evaluation provided by the generative AI engine based on the results of the training the user has performed.

[0876] "Training menu" refers to the specific training content generated by the AI ​​engine based on the user's goals, and includes the number of exercises, number of sets, weight, etc.

[0877] An "emotion engine" is software built into the device that analyzes the user's emotional state based on collected data.

[0878] "Feedback and advice" refers to providing specific instructions and improvements for the next workout based on the user's workout results and emotional state.

[0879] "Training results" refers to detailed data when a user performs training, including, for example, the number of squats and the weight used.

[0880] This invention provides a personal trainer system that combines generative AI and an emotion engine to provide feedback and individually optimized training advice that takes into account the user's emotional state. This system is implemented in the following specific steps.

[0881] First, the user accesses the AI ​​personal trainer application from their own device (such as a smartphone or PC). The user enters their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and training frequency (how many times per week) into the application. The user then sets training goals, such as "lose weight" or "gain muscle."

[0882] The device collects the information entered by the user and sends the data to a server in an appropriate format, such as JSON. The server receives this data and passes it to a generative AI engine, which then generates an optimal training menu based on the user's information and goals. The generative AI engine can then use cloud-based services or dedicated AI models for this processing.

[0883] The generated training menu is sent from the server to the user's device. The device displays the training menu received from the server to the user, and the user performs the training according to the displayed menu. After the training, the user enters details of the training they performed (e.g., 50 squats using 5kg dumbbells) and their self-evaluation (difficulty and satisfaction of the training) into the device.

[0884] The device also collects the user's facial expressions, voice, and text data during and after the user's training. The collected data is analyzed by the device's built-in emotion engine to recognize the user's emotional state (e.g., fatigue, motivation, stress, etc.). This emotion data is also sent to the server.

[0885] The server receives the training results, self-evaluation, and emotional data, and passes them to the generative AI engine to generate feedback and advice for the next training session. For example, if the user felt stressed during training, the server will suggest more relaxing exercises for the next session. This feedback and advice is sent from the server to the user's device and displayed to the user.

[0886] Specific examples

[0887] User B accesses a personal trainer application and enters their height (165 cm), weight (80 kg), ability to go to the gym four times a week, and goal of "losing weight." The device sends this data to the server. The server receives the data and passes it to the generation AI. The generation AI generates a training menu for User B four times a week. For example, it may provide a menu such as "30 minutes of running, 20 squats, and 10 burpee jumps." The training menu is sent to the device, which displays it to User B. User B trains at the gym and then enters "30 minutes of running, 5 km run, self-rating 5 / 5." The emotion engine analyzes User B's facial expressions and voice and recognizes the emotion "motivated." This data is sent from the device to the server, which passes it to the generation AI. The generation AI analyzes the data and generates advice such as "extend your running time to 40 minutes next time." This feedback is sent to the device and displayed to User B.

[0888] Prompt Sentence Examples

[0889] Below are some examples of prompts that could be passed to the generation AI when the user uses the application.

[0890] "Generate a weekly training plan for weight loss based on user data. The data is as follows: height 170cm, weight 70kg, able to train 3 times a week."

[0891] The system provides more personalized training menus and feedback that take into account the user's emotional state, maximizing the effectiveness of training.

[0892] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0893] Step 1:

[0894] The user enters information

[0895] User Behavior

[0896] Users access the AI ​​personal trainer application from their own devices and input their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and training frequency. Users also set training goals (e.g., losing weight, gaining muscle).

[0897] input

[0898] Physical information, lifestyle, training frequency, training goals

[0899] output

[0900] Temporarily save the input data as a JSON format file

[0901] Step 2:

[0902] The device sends the input information to the server

[0903] Terminal handling

[0904] The device collects the information entered by the user and sends it to the server in an appropriate format, such as JSON, including the user's height, weight, age, gender, lifestyle, training frequency, and training goals.

[0905] input

[0906] User's physical information, lifestyle habits, training frequency, and training goals stored on the device

[0907] output

[0908] JSON format data sent to the server

[0909] Step 3:

[0910] The server receives the data and passes it to the generative AI engine

[0911] Server Processing

[0912] The server receives user information sent from the device and passes this data to the generation AI engine.

[0913] input

[0914] JSON format data sent from the device

[0915] output

[0916] User information passed to the generation AI engine

[0917] Step 4:

[0918] Generative AI engine generates training menus

[0919] Generative AI engine processing

[0920] The generative AI engine generates an optimal training menu based on the received user information and training goals, and also takes into account past data and training data of similar users.

[0921] input

[0922] User information, training goals, generative AI model

[0923] output

[0924] Generated training menu

[0925] Step 5:

[0926] Send the training menu to the device and provide it to the user

[0927] Server Processing

[0928] The server sends the training menu received from the AI ​​generation engine to the user's device, which then displays it to the user.

[0929] input

[0930] Generated training menu

[0931] output

[0932] Training menu displayed on the user's device

[0933] Step 6:

[0934] The user performs the training and enters the results

[0935] User Behavior

[0936] The user follows the training menu displayed on the device and performs the training. After the training, the user enters the details of the training and their own evaluation into the device.

[0937] input

[0938] Training results, self-assessment

[0939] output

[0940] Input training results and self-assessment data

[0941] Step 7:

[0942] The device sends the training results and self-evaluation to the server.

[0943] Terminal handling

[0944] The terminal collects the training results and self-assessment entered by the user and transmits them to the server.

[0945] input

[0946] User-entered training results and self-assessment data

[0947] output

[0948] Training results and self-assessment data sent to the server

[0949] Step 8:

[0950] The device collects and analyzes emotional data

[0951] Terminal handling

[0952] The device collects the user's facial expressions, voice, and text data during and after training, which is then analyzed by the device's built-in emotion engine to determine the user's emotional state.

[0953] input

[0954] User facial expressions, voice, and text data

[0955] output

[0956] Analyzed emotion data

[0957] Step 9:

[0958] Send emotion data to the server

[0959] Terminal handling

[0960] The device transmits the analyzed emotion data to the server.

[0961] input

[0962] Analyzed emotion data

[0963] output

[0964] Emotion data sent to the server

[0965] Step 10:

[0966] The server generates feedback and advice for the next training session

[0967] Server Processing

[0968] The server instructs the AI ​​engine to analyze the training results, self-assessment, and emotional data, and generates feedback and advice for the next training session.

[0969] input

[0970] Training results, self-rating, emotion data, generative AI model

[0971] output

[0972] Generated feedback and next training advice

[0973] Step 11:

[0974] Send feedback and advice to the device and provide it to the user

[0975] Server Processing

[0976] The server sends the generated feedback and next training advice to the user's terminal, which displays it to the user.

[0977] input

[0978] Generated feedback and next training advice

[0979] output

[0980] Feedback displayed on the user's device and advice for the next training session

[0981] (Application example 2)

[0982] 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."

[0983] Conventional personal trainer systems typically generate training menus and feedback based on the user's physical data and training results. However, they do not take the user's emotional state into consideration, making it difficult to maximize the effectiveness of training. In particular, in the field of food delivery, users' moods and emotions have a significant impact on their appetite and choices, so there is a demand for suggestions based on emotions. Therefore, realizing a system that incorporates emotional data has been a challenge.

[0984] 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.

[0985] In this invention, the server includes: means for having the user input training goals and personal physical information; means for generating a training menu based on the input training goals and personal physical information; means for providing the generated training menu to the user's terminal; means for having the user input training results and self-evaluation after training according to the training menu; means for generating feedback and advice for the next training session based on the input results and self-evaluation and providing the feedback and advice to the user's terminal; and means for incorporating an emotion engine that analyzes the user's emotional state and adjusting the training menu and feedback based on the emotional state, thereby making it possible to propose optimal training and meal menus according to the user's emotional state.

[0986] "User" refers to an individual who uses the system.

[0987] "Training goal" refers to a specific goal in exercise that a user wants to achieve.

[0988] "Personal physical information" refers to data about a user's body, such as weight, height, age, and gender.

[0989] The term "server" refers to a central processing unit that processes information input by a user, generates a training menu and feedback, and transmits the menu and feedback to a user terminal.

[0990] A "training menu" refers to a training plan or plan that is generated based on the user's goals.

[0991] "User's device" refers to a device used by a user to access the system and input or provide information, such as a smartphone or tablet.

[0992] The "generated training menu" refers to an exercise program created by the server based on the user's input data.

[0993] "Training results" refers to the content and results of the training that the user actually undertook.

[0994] "Self-assessment" refers to a user's self-evaluation of the training they have completed.

[0995] "Feedback" refers to advice and areas for improvement generated based on training results and self-assessment.

[0996] "Emotional state" refers to a user's current mood or emotions.

[0997] An "emotion engine" refers to a system that analyzes a user's facial expressions and voice data to recognize the user's emotional state.

[0998] "Means for adjusting training menus and feedback" refers to means for optimizing exercise programs and advice by reflecting the user's emotional state.

[0999] This invention is a system that generates an optimal training menu based on a user's training goals and personal physical information, and further analyzes the user's emotional state to adjust feedback and advice. This system can be applied to the food delivery field to provide an optimal meal menu according to the user's emotional state.

[1000] System Program Overview

[1001] 1. Collection of User Information

[1002] Users use a smartphone app to input information such as their training goals, personal physical information, food preferences, allergy information, and meal timings.

[1003] The terminal transmits this information to the server.

[1004] 2. Recognizing emotional states

[1005] When a user accesses the app, the smartphone's camera and microphone are used to collect facial expressions and voice, and the emotion engine analyzes the user's current emotional state.

[1006] Images collected by the camera are processed using the OpenCV library and input into an emotion recognition model (using TensorFlow).

[1007] The audio data collected by the microphone is converted from audio to text using the SpeechRecognition library, and emotions are recognized based on the text data.

[1008] 3. Creation of training and meal menus

[1009] The server sends the user's input information and data from the emotion engine to the generation AI engine, and generates training and meal menus.

[1010] For example, if the user feels "tired," a menu of relaxing meals (soup, salad, herbal tea, etc.) will be generated.

[1011] 4. Providing Feedback

[1012] After the user completes a workout or meal, they enter their results and self-evaluation into the app.

[1013] The terminal collects this data and sends it to the server.

[1014] The server then refers back to the analysis results of the emotion engine and uses generative AI to generate feedback and advice for the next workout or meal.

[1015] Hardware and Software Use Cases

[1016] Smartphones: Used by users to input information and recognize emotional states.

[1017] Server: Processes user information, generates training menus and meal menus, and generates feedback.

[1018] Software: OpenCV (for image processing), TensorFlow (for emotion recognition models), SpeechRecognition (for voice recognition).

[1019] Specific examples

[1020] When User A opens the app, takes a picture of their face with the camera and says "I'm tired," the app suggests "soup" and "herbal tea." After User A confirms this, they place their order and enter their impressions after eating and drinking as feedback. An example of a prompt sentence using the generative AI model is as follows:

[1021] Prompt Sentence Examples

[1022] "I'm feeling unmotivated. Please suggest some relaxing meals. User information is as follows: I like Japanese food, I have no allergies, and I always eat at 12:00 and 18:00."

[1023] In this way, the present invention can provide optimal training and meal menus based on the user's emotional state, thereby improving the user's health maintenance and meal satisfaction.

[1024] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1025] Step 1:

[1026] The user launches the smartphone app and inputs their training goals, personal physical information, food preferences, allergy information, meal timing, etc. Based on this, the device organizes this data and sends it to the server. The input data includes specific training goals (e.g., losing weight) and physical data (e.g., height, weight, age, gender).

[1027] Input: Training goals, personal physical information, food preferences, allergy information, meal timing

[1028] Output: Structured user data

[1029] Step 2:

[1030] The server processes the received user data and generates a training menu using a generative AI engine based on the user's training goals and personal physical information. The generated training menu is optimized for the user's goals.

[1031] Input: Structured user data

[1032] Output: Training menu

[1033] Step 3:

[1034] The server sends the generated training menu to the user's terminal, which displays it to the user. The user checks the training menu and performs the training.

[1035] Input: Generated training menu

[1036] Output: Training menu displayed to the user

[1037] Step 4:

[1038] After completing the training, the user enters the results of the training and their self-evaluation into the smartphone app. The device collects this data and sends it to the server.

[1039] Input: Training results and self-assessment

[1040] Output: Structured training data and self-scoring data

[1041] Step 5:

[1042] The device captures the user's facial expressions with a camera and collects audio with a microphone. It then uses an emotion engine to analyze this data and recognize the user's emotional state. Specifically, it analyzes facial expressions using the image processing library OpenCV and determines emotions using an emotion recognition model using TensorFlow. It also converts audio into text using the speech recognition library SpeechRecognition and determines emotions.

[1043] Input: facial expression image data, voice data

[1044] Output: Perceived emotional state

[1045] Step 6:

[1046] The server inputs the collected training data, self-assessment data, and emotional state data into a generative AI engine to generate the next training menu and feedback. For example, if the server determines that the user is feeling tired, it will suggest relaxing exercises.

[1047] Input: training data, self-rating data, emotional state data

[1048] Output: Next training menu and feedback

[1049] Step 7:

[1050] The server sends the generated next training menu and feedback to the user's terminal, which displays it to the user. The user can then check the feedback and use it in their next training session.

[1051] Input: Next training menu and feedback

[1052] Output: The next training menu displayed to the user and feedback

[1053] 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.

[1054] 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.

[1055] 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.

[1056] [Third embodiment]

[1057] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1058] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1059] 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).

[1060] 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.

[1061] 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.

[1062] 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).

[1063] 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. 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.

[1064] 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.

[1065] 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.

[1066] 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.

[1067] 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.

[1068] 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."

[1069] In this embodiment, a personal trainer system that utilizes a generation AI to provide an effective training menu tailored to each individual's goals will be described. The following describes the operation flow of this system and the specific processing at each step.

[1070] 1. Collection of User Information

[1071] User Behavior

[1072] First, a user accesses the AI ​​personal trainer application using their own device (such as a smartphone or PC). Next, the user enters their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and frequency of gym visits (how many times per week) into the application. The user then sets their training goals (e.g., lose weight, gain muscle, improve physical strength).

[1073] Terminal handling

[1074] The terminal collects the information entered by the user and transmits the data to the server.

[1075] 2. Creation of training menu

[1076] Server Processing

[1077] The server receives the user's data and sends it to the generative AI engine. The generative AI engine generates an optimal training menu based on the user's information and goals. For example, if the user's goal is to "lose weight," the generative AI will provide a menu that takes into account the balance of aerobic exercise (running and cycling) and strength training (squats and dumbbell exercises, etc.). The generated training menu is sent from the server to the user's device.

[1078] 3. Display and execute the training menu

[1079] Terminal handling

[1080] The terminal displays the training menu sent from the server to the user. The user starts training and performs the training according to the details in the menu (e.g., running time, number of crunches, weight of dumbbells, etc.).

[1081] 4. Record your training and self-assess

[1082] User Behavior

[1083] After the workout, the user enters details of the workout (e.g., 50 squats using 5kg dumbbells) and their own assessment (e.g., subjective assessment of whether the workout was difficult) into the device.

[1084] Terminal handling

[1085] The device collects the training details and self-assessment entered by the user and sends the data to a server.

[1086] 5. Feedback and training advice for your next workout

[1087] Server Processing

[1088] The server sends the collected data to the generation AI, which generates feedback based on past training results and self-assessment, and provides advice for the next training. For example, if the user's self-assessment result indicates that they have done too many squats and are putting strain on their knees, the system will suggest knee-friendly training for the next training session. This feedback and advice is sent from the server to the user's device.

[1089] Terminal handling

[1090] The terminal displays the feedback and advice received from the server to the user.

[1091] Specific examples

[1092] User A (Goal: Muscle building)

[1093] Step 1

[1094] User A accesses the app and enters his / her height (180 cm), weight (70 kg), ability to go to the gym three times a week, and goal of "gaining muscle." The device then sends this data to the server.

[1095] Step 2

[1096] The server receives the data and passes it to the generation AI. The generation AI generates a training menu for User A three times a week. For example, it might provide a menu such as "Squat 60kg x 3 sets, Bench press 50kg x 3 sets, Deadlift 80kg x 3 sets." The training menu is sent to the device.

[1097] Step 3

[1098] The device displays the training menu to User A. User A then performs training at the gym.

[1099] Step 4

[1100] User A enters the details of the training he or she performed and his or her own rating. For example, he or she might enter "Squats 60kg x 3 sets, self-rating 4 / 5." The device then sends the data to the server.

[1101] Step 5

[1102] The server receives the data and passes it to the generation AI. The generation AI analyzes the data and generates feedback such as "Next time, increase the number of squat sets to 4." The feedback is sent to the device and displayed to User A.

[1103] In this way, the present invention is a system that enables a user to easily receive a training menu that is best suited to the user and to train efficiently and effectively.

[1104] The processing flow will be explained below.

[1105] Step 1:

[1106] The user accesses the generated AI personal trainer application using a device (such as a smartphone or PC). The user inputs their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and frequency of gym visits (how many times per week). The user then sets their own training goals (e.g., lose weight, gain muscle, improve physical strength).

[1107] Step 2:

[1108] The terminal collects the information entered by the user and sends the data to the server.

[1109] Step 3:

[1110] The server receives the user information sent from the device and passes the received information to the generation AI engine.

[1111] Step 4:

[1112] The generative AI engine generates the optimal training menu for each individual user based on their information and training goals. For example, if your goal is to lose weight, it will generate a menu that balances cardio and strength training.

[1113] Step 5:

[1114] The server transmits the generated training menu to the terminal.

[1115] Step 6:

[1116] The device displays a training menu to the user, who then checks the menu and follows it to train at the gym or at home.

[1117] Step 7:

[1118] After the user completes the training, they enter details of each exercise (e.g., 30 minutes of running, 5 km run) and their own assessment into the device.

[1119] Step 8:

[1120] The terminal transmits the detailed training data and self-evaluation results input by the user to the server.

[1121] Step 9:

[1122] The server passes the detailed training data and self-assessment results received from the device to the generation AI engine. The generation AI analyzes the past training history and self-assessment results and generates feedback and advice for the next training session. For example, if the user's knees are under strain, it will suggest knee-friendly training for the next session.

[1123] Step 10:

[1124] A server is generated to send feedback and advice to the terminal.

[1125] Step 11:

[1126] The device displays the feedback and advice received from the server to the user, who can then review the displayed feedback and use it for their next training session.

[1127] Example 1

[1128] 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."

[1129] Conventional training menus often provide uniform programs, which have the problem of not being able to provide an optimal menu tailored to each user's physical information or specific goals. Furthermore, there is an insufficient mechanism for users to receive feedback after training and use that feedback to improve their next training. Furthermore, the time and effort required for users to self-evaluate their training results can discourage users from continuing to train.

[1130] 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.

[1131] In this invention, the server includes: means for having a user input training goals and physical information; means for transmitting the input training goals and physical information to the server via a terminal; means for generating a training menu using a generative AI model based on the input training goals and physical information via the server; means for providing the generated training menu to the user's terminal; means for having the user input the training results and self-assessment after training according to the training menu; means for transmitting the input results and self-assessment via the terminal to the server; and means for generating feedback and advice for the next training session using the generative AI model based on the input results and self-assessment and providing the feedback and advice to the user's terminal. This makes it possible to provide a training menu optimized for the user's individual physical information and goals, and to continuously provide appropriate feedback and advice according to the training results.

[1132] "User" refers to a user who uses the Generative AI Personal Trainer System.

[1133] A "training goal" is a specific exercise objective that a user wants to achieve, such as losing weight, gaining muscle, or improving physical strength.

[1134] "Physical information" refers to basic physical data such as a user's weight, height, age, and gender.

[1135] A "terminal" is a device used by a user to access the system and input information, including a smartphone or PC.

[1136] "Server" refers to the central management system that receives user input data, generates optimal training menus using generative AI models, and provides feedback and advice.

[1137] A "generative AI model" is an artificial intelligence model that automatically generates training menus and feedback based on user information, and refers to one that utilizes natural language processing technology, for example.

[1138] A "training menu" refers to a specific exercise plan proposed by the generative AI model based on the user's training goals and physical information.

[1139] "Training results" is a detailed record of the training the user actually performed, including the number of exercises, number of sets, weight used, etc.

[1140] "Self-rating" is when a user inputs a personal evaluation of the training content after completing the training, and includes subjective impressions and comments about the state of the body.

[1141] "Feedback" refers to the general term for improvements and advice provided by the generative AI model for the next training session based on the training results and self-assessment entered by the user.

[1142] "Advice" refers to specific training method suggestions and points of caution provided to users by the generative AI model.

[1143] In this embodiment, we will explain a personal trainer system that utilizes a generative AI model to provide an effective training menu tailored to each individual's training goals. First, the system collects data from the user, such as physical information and training goals, and generates an optimal menu based on the generative AI model. After the training, the system then provides feedback and advice for the next training session.

[1144] Collection of User Information

[1145] User Behavior

[1146] Users access the generated AI personal trainer application using their own devices. Specific hardware examples include smartphones and PCs, and software examples include dedicated applications that can be accessed via a browser.

[1147] The user enters the following information within the application:

[1148] Physical information (e.g., weight, height, age, gender)

[1149] Lifestyle habits (e.g., eating habits, sleep duration)

[1150] How often you can go to the gym (e.g., how many times a week)

[1151] Training goals (e.g., lose weight, gain muscle, improve strength)

[1152] Training menu generation

[1153] Terminal handling

[1154] The device sends the collected user information to the server, using a secure communication protocol such as HTTPS.

[1155] Server Processing

[1156] The server runs the received data on a cloud infrastructure (e.g., AWS, Google Cloud Platform) because it requires high-performance computing resources. The server then sends the data to a generative AI model (e.g., OpenAI's GPT-3), which generates an optimal training menu based on the input information. The generated training menu is then sent from the server to the user's device.

[1157] Displaying and executing training menus

[1158] Terminal handling

[1159] The device displays the received training menu to the user, who then performs the training according to the menu. Training items include running time, number of crunches, weight of dumbbells, etc.

[1160] Record and self-assess your training

[1161] User Behavior

[1162] After the training, the user inputs the details of the training (e.g., 50 squats using 5kg dumbbells) and their own assessment (e.g., how difficult the training was) into the terminal.

[1163] Terminal handling

[1164] The terminal collects the user's input and sends the data back to the server.

[1165] Feedback and advice for your next training session

[1166] Server Processing

[1167] The server sends the collected training data and self-assessment to the generative AI model, which then generates feedback and advice for the next training session. For example, if the user's knees are under strain, the model will suggest training that is gentler on the knees. The generated feedback and advice are then sent from the server to the user's device.

[1168] Terminal handling

[1169] The terminal displays feedback and advice to the user.

[1170] Specific examples

[1171] User A (Goal: Muscle building)

[1172] 1. User A accesses the app and enters his / her information: height 180 cm, weight 70 kg, ability to go to the gym three times a week, and goal of "gaining muscle."

[1173] 2. The device sends this data to the server.

[1174] 3. The server receives the data and passes it to the generation AI, which then generates a menu such as "Squat 60kg x 3 sets, Bench press 50kg x 3 sets, Deadlift 80kg x 3 sets."

[1175] 4. The training menu is sent to the device and displayed on User A. User A then performs the training at the gym.

[1176] 5. User A enters the details of the training he or she performed and his or her own evaluation. For example, he or she enters "Squats 60kg x 3 sets, self-evaluation 4 / 5." The device sends the input data to the server.

[1177] 6. The server receives the data and passes it to the generation AI. The generation AI analyzes the data and generates feedback such as "Next time, increase the number of squat sets to 4." This feedback is sent to the device and displayed to User A.

[1178] Prompt Sentence Examples

[1179] "User A is 180cm tall, weighs 70kg, can go to the gym three times a week, and wants to build muscle. Please create an optimal training menu based on this information."

[1180] or

[1181] "Generate a training menu based on the following user information: height 180cm, weight 70kg, gym visits 3 times a week, goal is to build muscle."

[1182] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1183] Step 1:

[1184] Entering user information

[1185] User Behavior

[1186] Users access the AI-generated personal trainer application using their own devices (smartphones or PCs). Within the application, users input their physical information (weight, height, age, gender), lifestyle habits (eating habits, sleep time, etc.), frequency of gym visits (how many times a week they can go), and training goals (lose weight, gain muscle, improve physical strength).

[1187] Terminal handling

[1188] The terminal stores the input user information in a database format and transmits it to the server as structured data.

[1189] Input: User's physical information, lifestyle habits, gym visit frequency, and training goals.

[1190] Output: Structured data to send to the server.

[1191] Step 2:

[1192] Training menu generation

[1193] Server Processing

[1194] The server sends data to a generative AI model based on the received user information. The generative AI model (e.g., GPT-3) generates an optimal training menu based on the user's physical information and goals. For example, if the user's goal is to "lose weight," the generative AI model will provide a menu that takes into account the balance of aerobic exercise and strength training.

[1195] Input: Structured user information.

[1196] Output: A training menu optimized for the user.

[1197] Server Processing

[1198] The generated training menu is sent from the server to the user's terminal.

[1199] Step 3:

[1200] Displaying and executing training menus

[1201] Terminal handling

[1202] The terminal displays the training menu received from the server to the user. The user follows the displayed menu and performs training based on details of, for example, running or strength training (running time, number of crunches, weight of dumbbells).

[1203] Input: Training menu from the server.

[1204] Output: Display of training menu, notification to user.

[1205] Step 4:

[1206] Record and self-assess your training

[1207] User Behavior

[1208] After the training, the user inputs details of the training into the device, such as 50 squats using 5kg dumbbells, and also inputs a self-evaluation of the difficulty of the training.

[1209] Terminal handling

[1210] The device collects these training results and self-assessment and sends them to the server.

[1211] Input: Training details from user, self-assessment.

[1212] Output: Training data to send to the server.

[1213] Step 5:

[1214] Generate feedback and next training advice

[1215] Server Processing

[1216] The server then sends the received training data and self-evaluation back to the generative AI model, which then generates feedback and advice for the next training session. For example, if the user feels strain on their knees, the generative AI model will suggest knee-friendly training for the next session.

[1217] Input: Collected training results and self-assessment.

[1218] Output: Feedback and next training advice.

[1219] Server Processing

[1220] The generated feedback and advice are sent from the server to the user's terminal.

[1221] Step 6:

[1222] View feedback and advice

[1223] Terminal handling

[1224] The device receives feedback and advice from the server and displays it to the user, giving them specific instructions for their next workout.

[1225] Input: Feedback and advice from the server.

[1226] Output: Displaying feedback and advice to the user.

[1227] (Application example 1)

[1228] 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."

[1229] Conventional training menu provision systems lack the functionality to generate optimal training plans based on an individual's specific goals and physical information, making it difficult to maximize effectiveness. In particular, they lacked a mechanism to dynamically adjust the next training menu and provide feedback based on an individual's training results and self-evaluation.

[1230] 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.

[1231] In this invention, the server includes: means for having the user input training goals and personal physical information; means for generating a training menu based on the input training goals and personal physical information; means for providing the generated training menu to the user's terminal; means for having the user input the training results and self-assessment after training according to the training menu; means for generating feedback and advice for the next training session based on the input results and self-assessment and providing the feedback and advice to the user's terminal; and means for using a generative AI model to generate the feedback and advice. This allows for the provision of an optimal training menu based on the user's individual goals and condition, and dynamic feedback and advice, enabling highly effective training.

[1232] "User" refers to an individual who receives the training menu in the invention.

[1233] "Training goal" refers to a specific fitness goal that a user wishes to achieve, such as losing weight, building muscle, or improving strength.

[1234] "Physical information" refers to physical data such as a user's height, weight, age, and gender.

[1235] "Server" refers to a central control device that receives and processes information sent by users, generates training menus based on the information, and provides feedback.

[1236] "Generative AI model" refers to artificial intelligence technology that generates optimal training menus and feedback based on user information.

[1237] "User's terminal" refers to a device used by the user for input and display, such as a smartphone, PC, or tablet.

[1238] A "training menu" refers to a specific exercise or plan that a user should perform, including, for example, the type of exercise, number of repetitions, number of sets, weight, etc.

[1239] "Training Results" refers to details of the training a user actually performed, including, for example, the number of sets performed and the weight used.

[1240] "Self-rating" refers to a subjective evaluation made by the user after completing a workout, including, for example, the difficulty of the workout and the level of fatigue.

[1241] "Feedback" refers to improvements and advice for the next training session based on the training results and self-assessment entered by the user.

[1242] An embodiment of the present invention will be described.

[1243] Overall system overview

[1244] The system works by combining the user's device, a server, and a generative AI model.

[1245] Collection of User Information

[1246] First, a user accesses the application using a device such as a smartphone or tablet. The application provides a user input form and asks the user to enter the following information:

[1247] Height, weight, age, gender (physical information)

[1248] Eating habits, sleep time, etc. (lifestyle)

[1249] How often can you go to the gym per week?

[1250] Training goals (e.g., lose weight, gain muscle, improve strength)

[1251] Training menu generation

[1252] The device sends the input information to the server. The server receives this data and generates an optimal training menu based on a generative AI model. The generative AI model uses, for example, ChatGPT or GPT-4. The generated training menu is then provided to the user's device. The menu includes the type of exercise, number of repetitions, number of sets, weight, etc.

[1253] Displaying and executing training menus

[1254] The terminal displays the training menu sent from the server to the user, who then trains at the gym according to the training menu.

[1255] Record and self-assess your training

[1256] After the training, the user inputs details of the training (e.g., 50 squats using 5 kg dumbbells) and their own evaluation (e.g., subjective evaluation of whether the training was hard or not) into the device. The device then sends this data back to the server.

[1257] Feedback and advice for your next training session

[1258] The server sends the collected data to the generative AI model, which generates feedback and advice for the next training session based on past training results and self-evaluation. The advice includes specific areas for improvement, such as "Next time, increase the number of squat sets to four." The feedback and advice are sent to the user's device and displayed to the user.

[1259] Specific examples

[1260] User A launches the app and enters the following information:

[1261] Height: 180cm

[1262] Weight: 75kg

[1263] Age: 30

[1264] Gender: Male

[1265] How often can you go to the gym per week: 4 times

[1266] Training goal: Gain muscle

[1267] This information is sent to the server, and the generative AI model creates a training menu of "60kg squats x 3 sets, 50kg bench press x 3 sets, 80kg deadlift x 3 sets." User A executes this menu and inputs the results as "60kg squats x 3 sets, self-rating 4 / 5." Based on these results, the server returns feedback such as "Increase the number of squat sets to 4 next time."

[1268] Prompt Sentence Examples

[1269] An example of a prompt to input to a generative AI model is as follows:

[1270] User Information:

[1271] Height: 180cm

[1272] Weight: 75kg

[1273] Age: 30

[1274] Gender: Male

[1275] How often can you go to the gym per week: 4 times

[1276] Training goal: Gain muscle

[1277] Based on this, generate the following training menu:

[1278] Amount and type of aerobic exercise

[1279] Strength training type, number of sets, and weight

[1280] As described above, by implementing the present invention, it becomes possible to provide an optimized training menu to the user and provide feedback thereto.

[1281] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1282] Step 1:

[1283] Users access the application using a device such as a smartphone or tablet. They enter their height, weight, age, gender, eating habits, sleep time, frequency of gym visits, and training goals in the form displayed on the device. The entered data is then sent from the device to the server.

[1284] Input: height, weight, age, gender, eating habits, sleep time, frequency of gym visits, training goals

[1285] Output: User information sent to the server

[1286] Step 2:

[1287] The server analyzes the received user information and generates an optimal training menu based on the generative AI model. Specifically, it determines the type of exercise, number of sets, repetitions, weight, etc. based on the user's physical information and training goals. The generated training menu is sent from the server to the device.

[1288] Input: User information

[1289] Data processing: Generative AI model generates training menu

[1290] Output: Generated training menu

[1291] Step 3:

[1292] The terminal displays the generated training menu to the user, who then goes to the gym and performs the training according to the displayed menu.

[1293] Input: Generated training menu

[1294] Output: Training menu displayed to the user

[1295] Step 4:

[1296] After completing a workout, the user inputs details of the workout into the device, such as the number of sets, weight, number of repetitions, and self-evaluation for each exercise. The input data is then sent from the device to the server.

[1297] Input: Training results (number of sets, weight, number of repetitions, self-evaluation)

[1298] Output: Training run results sent to the server

[1299] Step 5:

[1300] The server uses the generative AI model to generate feedback and training advice for the next time based on the received training results and self-evaluation. This includes specific advice such as "Increase the number of sets for your next squat to four." The generated feedback and advice are sent from the server to the device.

[1301] Input: Training execution results, self-evaluation

[1302] Data Transformation: Generative AI Models Generate Feedback and Advice

[1303] Output: Generated feedback and advice

[1304] Step 6:

[1305] The terminal displays the feedback and next training advice sent from the server to the user, who can then plan his next training session.

[1306] Input: Generated feedback and advice

[1307] Output: Feedback and advice displayed to the user

[1308] 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.

[1309] As an embodiment of the present invention, a personal trainer system that combines a generative AI and an emotion engine will be described. This system generates an individually optimized training menu based on user input information, and also recognizes the user's emotional state and reflects this in feedback and advice. The following describes in detail the operation flow of this system and its specific processing.

[1310] 1. Collection of User Information

[1311] User Behavior

[1312] First, a user accesses the AI ​​personal trainer application using their own device (such as a smartphone or PC). Next, the user enters their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and frequency of gym visits (how many times per week) into the application. The user also sets their training goals (e.g., to lose weight, gain muscle, or improve physical strength).

[1313] Terminal handling

[1314] The terminal collects the information entered by the user and transmits the data to the server.

[1315] 2. Creation of training menu

[1316] Server Processing

[1317] The server receives the user's data and sends it to the generative AI engine. The generative AI engine generates an optimal training menu based on the user's information and goals. For example, if the user's goal is to "lose weight," the generative AI will provide a menu that takes into account the balance of aerobic exercise (running and cycling) and strength training (squats and dumbbell exercises, etc.). The generated training menu is sent from the server to the user's device.

[1318] 3. Display and execute the training menu

[1319] Terminal handling

[1320] The terminal displays the training menu sent from the server to the user. The user starts training and performs the training according to the details in the menu (e.g., running time, number of crunches, weight of dumbbells, etc.).

[1321] 4. Record your training and self-assess

[1322] User Behavior

[1323] After the workout, the user enters details of the workout (e.g., 50 squats using 5kg dumbbells) and their own assessment (e.g., subjective assessment of whether the workout was difficult) into the device.

[1324] Terminal handling

[1325] The device collects the training details and self-assessment entered by the user and sends the data to a server.

[1326] 5. Emotional Recognition

[1327] User Behavior

[1328] While the user is performing the training and after the training, the device collects the user's facial expression, voice, and text data.

[1329] Terminal handling

[1330] The device's built-in emotion engine analyzes the user's emotional state based on the collected data, recognizing, for example, whether the user is tired, motivated, or stressed.

[1331] 6. Feedback and advice for your next training session

[1332] Server Processing

[1333] The server sends the collected training data, self-evaluation results, and emotion analysis results from the emotion engine to the generation AI. The generation AI generates feedback based on the user's past training history and emotional state, and provides advice for the next training session. For example, if the user felt stressed during training, it will suggest more relaxing exercises for the next session.

[1334] Server Processing

[1335] Send generated feedback and advice to the device.

[1336] Terminal handling

[1337] The device receives feedback and advice from the server and displays it to the user, who can then review the feedback and use it to improve their next training session.

[1338] Specific examples

[1339] User B (Goal: Weight loss)

[1340] Step 1

[1341] User B accesses the app and enters information such as his height of 165 cm, his weight of 80 kg, the ability to go to the gym four times a week, and his goal of "losing weight." The device then sends this data to the server.

[1342] Step 2

[1343] The server receives the data and passes it to the generation AI. The generation AI generates a training menu for User B four times a week. For example, it may provide a menu such as "30 minutes of running, 20 squats, and 10 burpee jumps." The training menu is sent to the device.

[1344] Step 3

[1345] The device displays the training menu to User B. User B then performs the training at the gym.

[1346] Step 4

[1347] User B enters details of the workout he or she performed. For example, he or she might enter "30 minutes of running, 5km run, self-rating 5 / 5." The emotion engine analyzes User B's facial expressions and voice and recognizes the emotion "motivated" based on the microexpression. The data is sent from the device to the server.

[1348] Step 5

[1349] The server receives the data and passes it to the generation AI. The generation AI analyzes the data and generates advice for the next training menu. For example, "Extend your running time to 40 minutes next time." The feedback is sent to User B's device and displayed.

[1350] In this way, the generative AI personal trainer system using the emotion engine can provide an individually optimized training menu taking into account the user's emotional state, maximizing efficiency and effectiveness.

[1351] The processing flow will be explained below.

[1352] Step 1:

[1353] A user accesses the generated AI personal trainer application using a device (such as a smartphone or PC). The user inputs their physical information (e.g., weight, height, age, gender) and lifestyle habits (e.g., eating habits, sleep time), as well as the frequency of gym visits (e.g., how many times per week they can go). In addition, the user sets training goals (e.g., to lose weight, gain muscle, improve physical strength).

[1354] Step 2:

[1355] The terminal collects the information entered by the user and transmits the data to the server.

[1356] Step 3:

[1357] The server receives the user information sent from the device and passes the received information to the generation AI engine.

[1358] Step 4:

[1359] The generative AI engine generates the optimal training menu for each individual user based on their information and training goals. For example, if your goal is to lose weight, it will generate a menu that balances cardio and strength training.

[1360] Step 5:

[1361] The server transmits the generated training menu to the terminal.

[1362] Step 6:

[1363] The device displays the training menu sent from the server to the user, who then checks the training menu and follows it to train at the gym or at home.

[1364] Step 7:

[1365] After the user completes the training, they enter details of each exercise (e.g., 30 minutes of running, 5 km run) and their own assessment (e.g., subjective assessment of whether the training was hard) into the device.

[1366] Step 8:

[1367] The terminal transmits the detailed training data and self-evaluation results input by the user to the server.

[1368] Step 9:

[1369] While the user is training and afterward, the device collects facial, voice, and text data from the user. The device's built-in emotion engine analyzes the user's emotional state based on the collected data. For example, it can recognize emotions such as tiredness, motivation, and stress.

[1370] Step 10:

[1371] The server receives detailed training data, self-assessment results, and emotion analysis results from the emotion engine from the device, and passes them to the generative AI engine. The generative AI generates feedback based on the user's past training history and emotional state, and provides advice for the next training session. For example, if the user felt stressed during training, it will suggest more relaxing exercises for the next session.

[1372] Step 11:

[1373] The server sends the generated feedback and advice to the device.

[1374] Step 12:

[1375] The device displays the feedback and advice received from the server to the user, who can then review the feedback and use it to improve their next training session.

[1376] Example 2

[1377] 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."

[1378] Conventional personal trainer systems provide training menus based on a user's physical information and training goals, but they are unable to take into account the user's emotional state or performance during training, resulting in insufficient individual optimization. As a result, users often find it difficult to continue training and maintain motivation. The present invention aims to solve this problem by providing feedback and training advice that takes into account the user's emotional state.

[1379] 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.

[1380] In this invention, the server includes: means for having the user input training goals and personal physical information; means for transmitting the input physical information, lifestyle habits, and training frequency to the server via a terminal; means for generating a training menu based on the input training goals and personal physical information via the server; means for providing the generated training menu to the user's terminal; means for having the user input training results and self-evaluation after training according to the training menu; means for collecting facial expressions, voice, and text data of the user during and after the training and recognizing emotions via the terminal; and means for generating feedback and advice for the next training session based on the input results, self-evaluation, and emotional data via the server and providing the feedback and advice to the user's terminal. This makes it possible to provide feedback that takes the user's emotional state into account and individually optimized training advice.

[1381] "User" refers to an individual who uses the generative AI personal trainer system to generate a training menu and receive feedback.

[1382] A "training goal" is a physical goal that a user wants to achieve, examples of which include "lose weight" or "gain muscle."

[1383] "Physical information" refers to basic personal data such as a user's height, weight, age, and gender.

[1384] "Lifestyle habits" refers to information such as the user's eating habits and sleeping hours in their daily lives.

[1385] "Training frequency" refers to the number of times or frequency with which a user trains, and examples include "how many times per week they train."

[1386] A "terminal" is a device used by a user to input data and receive training menus and feedback, and examples include smartphones and PCs.

[1387] "Server" refers to the computer at the core of the system that receives data sent by users and uses generation AI to generate training menus and provide feedback.

[1388] A "generative AI engine" refers to an artificial intelligence model that generates optimal training menus based on user input information and training goals.

[1389] "Self-rating" refers to data that allows users to subjectively evaluate their own performance and impressions after training.

[1390] "Emotional data" refers to information about a user's emotional state analyzed from facial expressions, voice, text data, and the like.

[1391] "Feedback" refers to the advice and evaluation provided by the generative AI engine based on the results of the training the user has performed.

[1392] "Training menu" refers to the specific training content generated by the AI ​​engine based on the user's goals, and includes the number of exercises, number of sets, weight, etc.

[1393] An "emotion engine" is software built into the device that analyzes the user's emotional state based on collected data.

[1394] "Feedback and advice" refers to providing specific instructions and improvements for the next workout based on the user's workout results and emotional state.

[1395] "Training results" refers to detailed data when a user performs training, including, for example, the number of squats and the weight used.

[1396] This invention provides a personal trainer system that combines generative AI and an emotion engine to provide feedback and individually optimized training advice that takes into account the user's emotional state. This system is implemented in the following specific steps.

[1397] First, the user accesses the AI ​​personal trainer application from their own device (such as a smartphone or PC). The user enters their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and training frequency (how many times per week) into the application. The user then sets training goals, such as "lose weight" or "gain muscle."

[1398] The device collects the information entered by the user and sends the data to a server in an appropriate format, such as JSON. The server receives this data and passes it to a generative AI engine, which then generates an optimal training menu based on the user's information and goals. The generative AI engine can then use cloud-based services or dedicated AI models for this processing.

[1399] The generated training menu is sent from the server to the user's device. The device displays the training menu received from the server to the user, and the user performs the training according to the displayed menu. After the training, the user enters details of the training they performed (e.g., 50 squats using 5kg dumbbells) and their self-evaluation (difficulty and satisfaction of the training) into the device.

[1400] The device also collects the user's facial expressions, voice, and text data during and after the user's training. The collected data is analyzed by the device's built-in emotion engine to recognize the user's emotional state (e.g., fatigue, motivation, stress, etc.). This emotion data is also sent to the server.

[1401] The server receives the training results, self-evaluation, and emotional data, and passes them to the generative AI engine to generate feedback and advice for the next training session. For example, if the user felt stressed during training, the server will suggest more relaxing exercises for the next session. This feedback and advice is sent from the server to the user's device and displayed to the user.

[1402] Specific examples

[1403] User B accesses a personal trainer application and enters their height (165 cm), weight (80 kg), ability to go to the gym four times a week, and goal of "losing weight." The device sends this data to the server. The server receives the data and passes it to the generation AI. The generation AI generates a training menu for User B four times a week. For example, it may provide a menu such as "30 minutes of running, 20 squats, and 10 burpee jumps." The training menu is sent to the device, which displays it to User B. User B trains at the gym and then enters "30 minutes of running, 5 km run, self-rating 5 / 5." The emotion engine analyzes User B's facial expressions and voice and recognizes the emotion "motivated." This data is sent from the device to the server, which passes it to the generation AI. The generation AI analyzes the data and generates advice such as "extend your running time to 40 minutes next time." This feedback is sent to the device and displayed to User B.

[1404] Prompt Sentence Examples

[1405] Below are some examples of prompts that could be passed to the generation AI when the user uses the application.

[1406] "Generate a weekly training plan for weight loss based on user data. The data is as follows: height 170cm, weight 70kg, able to train 3 times a week."

[1407] The system provides more personalized training menus and feedback that take into account the user's emotional state, maximizing the effectiveness of training.

[1408] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1409] Step 1:

[1410] The user enters information

[1411] User Behavior

[1412] Users access the AI ​​personal trainer application from their own devices and input their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and training frequency. Users also set training goals (e.g., losing weight, gaining muscle).

[1413] input

[1414] Physical information, lifestyle, training frequency, training goals

[1415] output

[1416] Temporarily save the input data as a JSON format file

[1417] Step 2:

[1418] The device sends the input information to the server

[1419] Terminal handling

[1420] The device collects the information entered by the user and sends it to the server in an appropriate format, such as JSON, including the user's height, weight, age, gender, lifestyle, training frequency, and training goals.

[1421] input

[1422] User's physical information, lifestyle habits, training frequency, and training goals stored on the device

[1423] output

[1424] JSON format data sent to the server

[1425] Step 3:

[1426] The server receives the data and passes it to the generative AI engine

[1427] Server Processing

[1428] The server receives user information sent from the device and passes this data to the generation AI engine.

[1429] input

[1430] JSON format data sent from the device

[1431] output

[1432] User information passed to the generation AI engine

[1433] Step 4:

[1434] Generative AI engine generates training menus

[1435] Generative AI engine processing

[1436] The generative AI engine generates an optimal training menu based on the received user information and training goals, and also takes into account past data and training data of similar users.

[1437] input

[1438] User information, training goals, generative AI model

[1439] output

[1440] Generated training menu

[1441] Step 5:

[1442] Send the training menu to the device and provide it to the user

[1443] Server Processing

[1444] The server sends the training menu received from the AI ​​generation engine to the user's device, which then displays it to the user.

[1445] input

[1446] Generated training menu

[1447] output

[1448] Training menu displayed on the user's device

[1449] Step 6:

[1450] The user performs the training and enters the results

[1451] User Behavior

[1452] The user follows the training menu displayed on the device and performs the training. After the training, the user enters the details of the training and their own evaluation into the device.

[1453] input

[1454] Training results, self-assessment

[1455] output

[1456] Input training results and self-assessment data

[1457] Step 7:

[1458] The device sends the training results and self-evaluation to the server.

[1459] Terminal handling

[1460] The terminal collects the training results and self-assessment entered by the user and transmits them to the server.

[1461] input

[1462] User-entered training results and self-assessment data

[1463] output

[1464] Training results and self-assessment data sent to the server

[1465] Step 8:

[1466] The device collects and analyzes emotional data

[1467] Terminal handling

[1468] The device collects the user's facial expressions, voice, and text data during and after training, which is then analyzed by the device's built-in emotion engine to determine the user's emotional state.

[1469] input

[1470] User facial expressions, voice, and text data

[1471] output

[1472] Analyzed emotion data

[1473] Step 9:

[1474] Send emotion data to the server

[1475] Terminal handling

[1476] The device transmits the analyzed emotion data to the server.

[1477] input

[1478] Analyzed emotion data

[1479] output

[1480] Emotion data sent to the server

[1481] Step 10:

[1482] The server generates feedback and advice for the next training session

[1483] Server Processing

[1484] The server instructs the AI ​​engine to analyze the training results, self-assessment, and emotional data, and generates feedback and advice for the next training session.

[1485] input

[1486] Training results, self-rating, emotion data, generative AI model

[1487] output

[1488] Generated feedback and next training advice

[1489] Step 11:

[1490] Send feedback and advice to the device and provide it to the user

[1491] Server Processing

[1492] The server sends the generated feedback and next training advice to the user's terminal, which displays it to the user.

[1493] input

[1494] Generated feedback and next training advice

[1495] output

[1496] Feedback displayed on the user's device and advice for the next training session

[1497] (Application example 2)

[1498] 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."

[1499] Conventional personal trainer systems typically generate training menus and feedback based on the user's physical data and training results. However, they do not take the user's emotional state into consideration, making it difficult to maximize the effectiveness of training. In particular, in the field of food delivery, users' moods and emotions have a significant impact on their appetite and choices, so there is a demand for suggestions based on emotions. Therefore, realizing a system that incorporates emotional data has been a challenge.

[1500] 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.

[1501] In this invention, the server includes: means for having the user input training goals and personal physical information; means for generating a training menu based on the input training goals and personal physical information; means for providing the generated training menu to the user's terminal; means for having the user input training results and self-evaluation after training according to the training menu; means for generating feedback and advice for the next training session based on the input results and self-evaluation and providing the feedback and advice to the user's terminal; and means for incorporating an emotion engine that analyzes the user's emotional state and adjusting the training menu and feedback based on the emotional state, thereby making it possible to propose optimal training and meal menus according to the user's emotional state.

[1502] "User" refers to an individual who uses the system.

[1503] "Training goal" refers to a specific goal in exercise that a user wants to achieve.

[1504] "Personal physical information" refers to data about a user's body, such as weight, height, age, and gender.

[1505] The term "server" refers to a central processing unit that processes information input by a user, generates a training menu and feedback, and transmits the menu and feedback to a user terminal.

[1506] A "training menu" refers to a training plan or plan that is generated based on the user's goals.

[1507] "User's device" refers to a device used by a user to access the system and input or provide information, such as a smartphone or tablet.

[1508] The "generated training menu" refers to an exercise program created by the server based on the user's input data.

[1509] "Training results" refers to the content and results of the training that the user actually undertook.

[1510] "Self-assessment" refers to a user's self-evaluation of the training they have completed.

[1511] "Feedback" refers to advice and areas for improvement generated based on training results and self-assessment.

[1512] "Emotional state" refers to a user's current mood or emotions.

[1513] An "emotion engine" refers to a system that analyzes a user's facial expressions and voice data to recognize the user's emotional state.

[1514] "Means for adjusting training menus and feedback" refers to means for optimizing exercise programs and advice by reflecting the user's emotional state.

[1515] This invention is a system that generates an optimal training menu based on a user's training goals and personal physical information, and further analyzes the user's emotional state to adjust feedback and advice. This system can be applied to the food delivery field to provide an optimal meal menu according to the user's emotional state.

[1516] System Program Overview

[1517] 1. Collection of User Information

[1518] Users use a smartphone app to input information such as their training goals, personal physical information, food preferences, allergy information, and meal timings.

[1519] The terminal transmits this information to the server.

[1520] 2. Recognizing emotional states

[1521] When a user accesses the app, the smartphone's camera and microphone are used to collect facial expressions and voice, and the emotion engine analyzes the user's current emotional state.

[1522] Images collected by the camera are processed using the OpenCV library and input into an emotion recognition model (using TensorFlow).

[1523] The audio data collected by the microphone is converted from audio to text using the SpeechRecognition library, and emotions are recognized based on the text data.

[1524] 3. Creation of training and meal menus

[1525] The server sends the user's input information and data from the emotion engine to the generation AI engine, and generates training and meal menus.

[1526] For example, if the user feels "tired," a menu of relaxing meals (soup, salad, herbal tea, etc.) will be generated.

[1527] 4. Providing Feedback

[1528] After the user completes a workout or meal, they enter their results and self-evaluation into the app.

[1529] The terminal collects this data and sends it to the server.

[1530] The server then refers back to the analysis results of the emotion engine and uses generative AI to generate feedback and advice for the next workout or meal.

[1531] Hardware and Software Use Cases

[1532] Smartphones: Used by users to input information and recognize emotional states.

[1533] Server: Processes user information, generates training menus and meal menus, and generates feedback.

[1534] Software: OpenCV (for image processing), TensorFlow (for emotion recognition models), SpeechRecognition (for voice recognition).

[1535] Specific examples

[1536] When User A opens the app, takes a picture of their face with the camera and says "I'm tired," the app suggests "soup" and "herbal tea." After User A confirms this, they place their order and enter their impressions after eating and drinking as feedback. An example of a prompt sentence using the generative AI model is as follows:

[1537] Prompt Sentence Examples

[1538] "I'm feeling unmotivated. Please suggest some relaxing meals. User information is as follows: I like Japanese food, I have no allergies, and I always eat at 12:00 and 18:00."

[1539] In this way, the present invention can provide optimal training and meal menus based on the user's emotional state, thereby improving the user's health maintenance and meal satisfaction.

[1540] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1541] Step 1:

[1542] The user launches the smartphone app and inputs their training goals, personal physical information, food preferences, allergy information, meal timing, etc. Based on this, the device organizes this data and sends it to the server. The input data includes specific training goals (e.g., losing weight) and physical data (e.g., height, weight, age, gender).

[1543] Input: Training goals, personal physical information, food preferences, allergy information, meal timing

[1544] Output: Structured user data

[1545] Step 2:

[1546] The server processes the received user data and generates a training menu using a generative AI engine based on the user's training goals and personal physical information. The generated training menu is optimized for the user's goals.

[1547] Input: Structured user data

[1548] Output: Training menu

[1549] Step 3:

[1550] The server sends the generated training menu to the user's terminal, which displays it to the user. The user checks the training menu and performs the training.

[1551] Input: Generated training menu

[1552] Output: Training menu displayed to the user

[1553] Step 4:

[1554] After completing the training, the user enters the results of the training and their self-evaluation into the smartphone app. The device collects this data and sends it to the server.

[1555] Input: Training results and self-assessment

[1556] Output: Structured training data and self-scoring data

[1557] Step 5:

[1558] The device captures the user's facial expressions with a camera and collects audio with a microphone. It then uses an emotion engine to analyze this data and recognize the user's emotional state. Specifically, it analyzes facial expressions using the image processing library OpenCV and determines emotions using an emotion recognition model using TensorFlow. It also converts audio into text using the speech recognition library SpeechRecognition and determines emotions.

[1559] Input: facial expression image data, voice data

[1560] Output: Perceived emotional state

[1561] Step 6:

[1562] The server inputs the collected training data, self-assessment data, and emotional state data into a generative AI engine to generate the next training menu and feedback. For example, if the server determines that the user is feeling tired, it will suggest relaxing exercises.

[1563] Input: training data, self-rating data, emotional state data

[1564] Output: Next training menu and feedback

[1565] Step 7:

[1566] The server sends the generated next training menu and feedback to the user's terminal, which displays it to the user. The user can then check the feedback and use it in their next training session.

[1567] Input: Next training menu and feedback

[1568] Output: The next training menu displayed to the user and feedback

[1569] 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.

[1570] 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.

[1571] 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.

[1572] [Fourth embodiment]

[1573] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1574] 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.

[1575] 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).

[1576] 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.

[1577] 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.

[1578] 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).

[1579] 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. 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.

[1580] 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.

[1581] 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.

[1582] 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.

[1583] 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.

[1584] 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.

[1585] 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."

[1586] In this embodiment, a personal trainer system that utilizes a generation AI to provide an effective training menu tailored to each individual's goals will be described. The following describes the operation flow of this system and the specific processing at each step.

[1587] 1. Collection of User Information

[1588] User Behavior

[1589] First, a user accesses the AI ​​personal trainer application using their own device (such as a smartphone or PC). Next, the user enters their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and frequency of gym visits (how many times per week) into the application. The user then sets their training goals (e.g., lose weight, gain muscle, improve physical strength).

[1590] Terminal handling

[1591] The terminal collects the information entered by the user and transmits the data to the server.

[1592] 2. Creation of training menu

[1593] Server Processing

[1594] The server receives the user's data and sends it to the generative AI engine. The generative AI engine generates an optimal training menu based on the user's information and goals. For example, if the user's goal is to "lose weight," the generative AI will provide a menu that takes into account the balance of aerobic exercise (running and cycling) and strength training (squats and dumbbell exercises, etc.). The generated training menu is sent from the server to the user's device.

[1595] 3. Display and execute the training menu

[1596] Terminal handling

[1597] The terminal displays the training menu sent from the server to the user. The user starts training and performs the training according to the details in the menu (e.g., running time, number of crunches, weight of dumbbells, etc.).

[1598] 4. Record your training and self-assess

[1599] User Behavior

[1600] After the workout, the user enters details of the workout (e.g., 50 squats using 5kg dumbbells) and their own assessment (e.g., subjective assessment of whether the workout was difficult) into the device.

[1601] Terminal handling

[1602] The device collects the training details and self-assessment entered by the user and sends the data to a server.

[1603] 5. Feedback and training advice for your next workout

[1604] Server Processing

[1605] The server sends the collected data to the generation AI, which generates feedback based on past training results and self-assessment, and provides advice for the next training. For example, if the user's self-assessment result indicates that they have done too many squats and are putting strain on their knees, the system will suggest knee-friendly training for the next training session. This feedback and advice is sent from the server to the user's device.

[1606] Terminal handling

[1607] The terminal displays the feedback and advice received from the server to the user.

[1608] Specific examples

[1609] User A (Goal: Muscle building)

[1610] Step 1

[1611] User A accesses the app and enters his / her height (180 cm), weight (70 kg), ability to go to the gym three times a week, and goal of "gaining muscle." The device then sends this data to the server.

[1612] Step 2

[1613] The server receives the data and passes it to the generation AI. The generation AI generates a training menu for User A three times a week. For example, it might provide a menu such as "Squat 60kg x 3 sets, Bench press 50kg x 3 sets, Deadlift 80kg x 3 sets." The training menu is sent to the device.

[1614] Step 3

[1615] The device displays the training menu to User A. User A then performs training at the gym.

[1616] Step 4

[1617] User A enters the details of the training he or she performed and his or her own rating. For example, he or she might enter "Squats 60kg x 3 sets, self-rating 4 / 5." The device then sends the data to the server.

[1618] Step 5

[1619] The server receives the data and passes it to the generation AI. The generation AI analyzes the data and generates feedback such as "Next time, increase the number of squat sets to 4." The feedback is sent to the device and displayed to User A.

[1620] In this way, the present invention is a system that enables a user to easily receive a training menu that is best suited to the user and to train efficiently and effectively.

[1621] The processing flow will be explained below.

[1622] Step 1:

[1623] The user accesses the generated AI personal trainer application using a device (such as a smartphone or PC). The user inputs their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and frequency of gym visits (how many times per week). The user then sets their own training goals (e.g., lose weight, gain muscle, improve physical strength).

[1624] Step 2:

[1625] The terminal collects the information entered by the user and sends the data to the server.

[1626] Step 3:

[1627] The server receives the user information sent from the device and passes the received information to the generation AI engine.

[1628] Step 4:

[1629] The generative AI engine generates the optimal training menu for each individual user based on their information and training goals. For example, if your goal is to lose weight, it will generate a menu that balances cardio and strength training.

[1630] Step 5:

[1631] The server transmits the generated training menu to the terminal.

[1632] Step 6:

[1633] The device displays a training menu to the user, who then checks the menu and follows it to train at the gym or at home.

[1634] Step 7:

[1635] After the user completes the training, they enter details of each exercise (e.g., 30 minutes of running, 5 km run) and their own assessment into the device.

[1636] Step 8:

[1637] The terminal transmits the detailed training data and self-evaluation results input by the user to the server.

[1638] Step 9:

[1639] The server passes the detailed training data and self-assessment results received from the device to the generation AI engine. The generation AI analyzes the past training history and self-assessment results and generates feedback and advice for the next training session. For example, if the user's knees are under strain, it will suggest knee-friendly training for the next session.

[1640] Step 10:

[1641] A server is generated to send feedback and advice to the terminal.

[1642] Step 11:

[1643] The device displays the feedback and advice received from the server to the user, who can then review the displayed feedback and use it for their next training session.

[1644] Example 1

[1645] 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."

[1646] Conventional training menus often provide uniform programs, which have the problem of not being able to provide an optimal menu tailored to each user's physical information or specific goals. Furthermore, there is an insufficient mechanism for users to receive feedback after training and use that feedback to improve their next training. Furthermore, the time and effort required for users to self-evaluate their training results can discourage users from continuing to train.

[1647] 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.

[1648] In this invention, the server includes: means for having a user input training goals and physical information; means for transmitting the input training goals and physical information to the server via a terminal; means for generating a training menu using a generative AI model based on the input training goals and physical information via the server; means for providing the generated training menu to the user's terminal; means for having the user input the training results and self-assessment after training according to the training menu; means for transmitting the input results and self-assessment via the terminal to the server; and means for generating feedback and advice for the next training session using the generative AI model based on the input results and self-assessment and providing the feedback and advice to the user's terminal. This makes it possible to provide a training menu optimized for the user's individual physical information and goals, and to continuously provide appropriate feedback and advice according to the training results.

[1649] "User" refers to a user who uses the Generative AI Personal Trainer System.

[1650] A "training goal" is a specific exercise objective that a user wants to achieve, such as losing weight, gaining muscle, or improving physical strength.

[1651] "Physical information" refers to basic physical data such as a user's weight, height, age, and gender.

[1652] A "terminal" is a device used by a user to access the system and input information, including a smartphone or PC.

[1653] "Server" refers to the central management system that receives user input data, generates optimal training menus using generative AI models, and provides feedback and advice.

[1654] A "generative AI model" is an artificial intelligence model that automatically generates training menus and feedback based on user information, and refers to one that utilizes natural language processing technology, for example.

[1655] A "training menu" refers to a specific exercise plan proposed by the generative AI model based on the user's training goals and physical information.

[1656] "Training results" is a detailed record of the training the user actually performed, including the number of exercises, number of sets, weight used, etc.

[1657] "Self-rating" is when a user inputs a personal evaluation of the training content after completing the training, and includes subjective impressions and comments about the state of the body.

[1658] "Feedback" refers to the general term for improvements and advice provided by the generative AI model for the next training session based on the training results and self-assessment entered by the user.

[1659] "Advice" refers to specific training method suggestions and points of caution provided to users by the generative AI model.

[1660] In this embodiment, we will explain a personal trainer system that utilizes a generative AI model to provide an effective training menu tailored to each individual's training goals. First, the system collects data from the user, such as physical information and training goals, and generates an optimal menu based on the generative AI model. After the training, the system then provides feedback and advice for the next training session.

[1661] Collection of User Information

[1662] User Behavior

[1663] Users access the generated AI personal trainer application using their own devices. Specific hardware examples include smartphones and PCs, and software examples include dedicated applications that can be accessed via a browser.

[1664] The user enters the following information within the application:

[1665] Physical information (e.g., weight, height, age, gender)

[1666] Lifestyle habits (e.g., eating habits, sleep duration)

[1667] How often you can go to the gym (e.g., how many times a week)

[1668] Training goals (e.g., lose weight, gain muscle, improve strength)

[1669] Training menu generation

[1670] Terminal handling

[1671] The device sends the collected user information to the server, using a secure communication protocol such as HTTPS.

[1672] Server Processing

[1673] The server runs the received data on a cloud infrastructure (e.g., AWS, Google Cloud Platform) because it requires high-performance computing resources. The server then sends the data to a generative AI model (e.g., OpenAI's GPT-3), which generates an optimal training menu based on the input information. The generated training menu is then sent from the server to the user's device.

[1674] Displaying and executing training menus

[1675] Terminal handling

[1676] The device displays the received training menu to the user, who then performs the training according to the menu. Training items include running time, number of crunches, weight of dumbbells, etc.

[1677] Record and self-assess your training

[1678] User Behavior

[1679] After the training, the user inputs the details of the training (e.g., 50 squats using 5kg dumbbells) and their own assessment (e.g., how difficult the training was) into the terminal.

[1680] Terminal handling

[1681] The terminal collects the user's input and sends the data back to the server.

[1682] Feedback and advice for your next training session

[1683] Server Processing

[1684] The server sends the collected training data and self-assessment to the generative AI model, which then generates feedback and advice for the next training session. For example, if the user's knees are under strain, the model will suggest training that is gentler on the knees. The generated feedback and advice are then sent from the server to the user's device.

[1685] Terminal handling

[1686] The terminal displays feedback and advice to the user.

[1687] Specific examples

[1688] User A (Goal: Muscle building)

[1689] 1. User A accesses the app and enters his / her information: height 180 cm, weight 70 kg, ability to go to the gym three times a week, and goal of "gaining muscle."

[1690] 2. The device sends this data to the server.

[1691] 3. The server receives the data and passes it to the generation AI, which then generates a menu such as "Squat 60kg x 3 sets, Bench press 50kg x 3 sets, Deadlift 80kg x 3 sets."

[1692] 4. The training menu is sent to the device and displayed on User A. User A then performs the training at the gym.

[1693] 5. User A enters the details of the training he or she performed and his or her own evaluation. For example, he or she enters "Squats 60kg x 3 sets, self-evaluation 4 / 5." The device sends the input data to the server.

[1694] 6. The server receives the data and passes it to the generation AI. The generation AI analyzes the data and generates feedback such as "Next time, increase the number of squat sets to 4." This feedback is sent to the device and displayed to User A.

[1695] Prompt Sentence Examples

[1696] "User A is 180cm tall, weighs 70kg, can go to the gym three times a week, and wants to build muscle. Please create an optimal training menu based on this information."

[1697] or

[1698] "Generate a training menu based on the following user information: height 180cm, weight 70kg, gym visits 3 times a week, goal is to build muscle."

[1699] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1700] Step 1:

[1701] Entering user information

[1702] User Behavior

[1703] Users access the AI-generated personal trainer application using their own devices (smartphones or PCs). Within the application, users input their physical information (weight, height, age, gender), lifestyle habits (eating habits, sleep time, etc.), frequency of gym visits (how many times a week they can go), and training goals (lose weight, gain muscle, improve physical strength).

[1704] Terminal handling

[1705] The terminal stores the input user information in a database format and transmits it to the server as structured data.

[1706] Input: User's physical information, lifestyle habits, gym visit frequency, and training goals.

[1707] Output: Structured data to send to the server.

[1708] Step 2:

[1709] Training menu generation

[1710] Server Processing

[1711] The server sends data to a generative AI model based on the received user information. The generative AI model (e.g., GPT-3) generates an optimal training menu based on the user's physical information and goals. For example, if the user's goal is to "lose weight," the generative AI model will provide a menu that takes into account the balance of aerobic exercise and strength training.

[1712] Input: Structured user information.

[1713] Output: A training menu optimized for the user.

[1714] Server Processing

[1715] The generated training menu is sent from the server to the user's terminal.

[1716] Step 3:

[1717] Displaying and executing training menus

[1718] Terminal handling

[1719] The terminal displays the training menu received from the server to the user. The user follows the displayed menu and performs training based on details of, for example, running or strength training (running time, number of crunches, weight of dumbbells).

[1720] Input: Training menu from the server.

[1721] Output: Display of training menu, notification to user.

[1722] Step 4:

[1723] Record and self-assess your training

[1724] User Behavior

[1725] After the training, the user inputs details of the training into the device, such as 50 squats using 5kg dumbbells, and also inputs a self-evaluation of the difficulty of the training.

[1726] Terminal handling

[1727] The device collects these training results and self-assessment and sends them to the server.

[1728] Input: Training details from user, self-assessment.

[1729] Output: Training data to send to the server.

[1730] Step 5:

[1731] Generate feedback and next training advice

[1732] Server Processing

[1733] The server then sends the received training data and self-evaluation back to the generative AI model, which then generates feedback and advice for the next training session. For example, if the user feels strain on their knees, the generative AI model will suggest knee-friendly training for the next session.

[1734] Input: Collected training results and self-assessment.

[1735] Output: Feedback and next training advice.

[1736] Server Processing

[1737] The generated feedback and advice are sent from the server to the user's terminal.

[1738] Step 6:

[1739] View feedback and advice

[1740] Terminal handling

[1741] The device receives feedback and advice from the server and displays it to the user, giving them specific instructions for their next workout.

[1742] Input: Feedback and advice from the server.

[1743] Output: Displaying feedback and advice to the user.

[1744] (Application example 1)

[1745] 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."

[1746] Conventional training menu provision systems lack the functionality to generate optimal training plans based on an individual's specific goals and physical information, making it difficult to maximize effectiveness. In particular, they lacked a mechanism to dynamically adjust the next training menu and provide feedback based on an individual's training results and self-evaluation.

[1747] 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.

[1748] In this invention, the server includes: means for having the user input training goals and personal physical information; means for generating a training menu based on the input training goals and personal physical information; means for providing the generated training menu to the user's terminal; means for having the user input the training results and self-assessment after training according to the training menu; means for generating feedback and advice for the next training session based on the input results and self-assessment and providing the feedback and advice to the user's terminal; and means for using a generative AI model to generate the feedback and advice. This allows for the provision of an optimal training menu based on the user's individual goals and condition, and dynamic feedback and advice, enabling highly effective training.

[1749] "User" refers to an individual who receives the training menu in the invention.

[1750] "Training goal" refers to a specific fitness goal that a user wishes to achieve, such as losing weight, building muscle, or improving strength.

[1751] "Physical information" refers to physical data such as a user's height, weight, age, and gender.

[1752] "Server" refers to a central control device that receives and processes information sent by users, generates training menus based on the information, and provides feedback.

[1753] "Generative AI model" refers to artificial intelligence technology that generates optimal training menus and feedback based on user information.

[1754] "User's terminal" refers to a device used by the user for input and display, such as a smartphone, PC, or tablet.

[1755] A "training menu" refers to a specific exercise or plan that a user should perform, including, for example, the type of exercise, number of repetitions, number of sets, weight, etc.

[1756] "Training Results" refers to details of the training a user actually performed, including, for example, the number of sets performed and the weight used.

[1757] "Self-rating" refers to a subjective evaluation made by the user after completing a workout, including, for example, the difficulty of the workout and the level of fatigue.

[1758] "Feedback" refers to improvements and advice for the next training session based on the training results and self-assessment entered by the user.

[1759] An embodiment of the present invention will be described.

[1760] Overall system overview

[1761] The system works by combining the user's device, a server, and a generative AI model.

[1762] Collection of User Information

[1763] First, a user accesses the application using a device such as a smartphone or tablet. The application provides a user input form and asks the user to enter the following information:

[1764] Height, weight, age, gender (physical information)

[1765] Eating habits, sleep time, etc. (lifestyle)

[1766] How often can you go to the gym per week?

[1767] Training goals (e.g., lose weight, gain muscle, improve strength)

[1768] Training menu generation

[1769] The device sends the input information to the server. The server receives this data and generates an optimal training menu based on a generative AI model. The generative AI model uses, for example, ChatGPT or GPT-4. The generated training menu is then provided to the user's device. The menu includes the type of exercise, number of repetitions, number of sets, weight, etc.

[1770] Displaying and executing training menus

[1771] The terminal displays the training menu sent from the server to the user, who then trains at the gym according to the training menu.

[1772] Record and self-assess your training

[1773] After the training, the user inputs details of the training (e.g., 50 squats using 5 kg dumbbells) and their own evaluation (e.g., subjective evaluation of whether the training was hard or not) into the device. The device then sends this data back to the server.

[1774] Feedback and advice for your next training session

[1775] The server sends the collected data to the generative AI model, which generates feedback and advice for the next training session based on past training results and self-evaluation. The advice includes specific areas for improvement, such as "Next time, increase the number of squat sets to four." The feedback and advice are sent to the user's device and displayed to the user.

[1776] Specific examples

[1777] User A launches the app and enters the following information:

[1778] Height: 180cm

[1779] Weight: 75kg

[1780] Age: 30

[1781] Gender: Male

[1782] How often can you go to the gym per week: 4 times

[1783] Training goal: Gain muscle

[1784] This information is sent to the server, and the generative AI model creates a training menu of "60kg squats x 3 sets, 50kg bench press x 3 sets, 80kg deadlift x 3 sets." User A executes this menu and inputs the results as "60kg squats x 3 sets, self-rating 4 / 5." Based on these results, the server returns feedback such as "Increase the number of squat sets to 4 next time."

[1785] Prompt Sentence Examples

[1786] An example of a prompt to input to a generative AI model is as follows:

[1787] User Information:

[1788] Height: 180cm

[1789] Weight: 75kg

[1790] Age: 30

[1791] Gender: Male

[1792] How often can you go to the gym per week: 4 times

[1793] Training goal: Gain muscle

[1794] Based on this, generate the following training menu:

[1795] Amount and type of aerobic exercise

[1796] Strength training type, number of sets, and weight

[1797] As described above, by implementing the present invention, it becomes possible to provide an optimized training menu to the user and provide feedback thereto.

[1798] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1799] Step 1:

[1800] Users access the application using a device such as a smartphone or tablet. They enter their height, weight, age, gender, eating habits, sleep time, frequency of gym visits, and training goals in the form displayed on the device. The entered data is then sent from the device to the server.

[1801] Input: height, weight, age, gender, eating habits, sleep time, frequency of gym visits, training goals

[1802] Output: User information sent to the server

[1803] Step 2:

[1804] The server analyzes the received user information and generates an optimal training menu based on the generative AI model. Specifically, it determines the type of exercise, number of sets, repetitions, weight, etc. based on the user's physical information and training goals. The generated training menu is sent from the server to the device.

[1805] Input: User information

[1806] Data processing: Generative AI model generates training menu

[1807] Output: Generated training menu

[1808] Step 3:

[1809] The terminal displays the generated training menu to the user, who then goes to the gym and performs the training according to the displayed menu.

[1810] Input: Generated training menu

[1811] Output: Training menu displayed to the user

[1812] Step 4:

[1813] After completing a workout, the user inputs details of the workout into the device, such as the number of sets, weight, number of repetitions, and self-evaluation for each exercise. The input data is then sent from the device to the server.

[1814] Input: Training results (number of sets, weight, number of repetitions, self-evaluation)

[1815] Output: Training run results sent to the server

[1816] Step 5:

[1817] The server uses the generative AI model to generate feedback and training advice for the next time based on the received training results and self-evaluation. This includes specific advice such as "Increase the number of sets for your next squat to four." The generated feedback and advice are sent from the server to the device.

[1818] Input: Training execution results, self-evaluation

[1819] Data Transformation: Generative AI Models Generate Feedback and Advice

[1820] Output: Generated feedback and advice

[1821] Step 6:

[1822] The terminal displays the feedback and next training advice sent from the server to the user, who can then plan his next training session.

[1823] Input: Generated feedback and advice

[1824] Output: Feedback and advice displayed to the user

[1825] 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.

[1826] As an embodiment of the present invention, a personal trainer system that combines a generative AI and an emotion engine will be described. This system generates an individually optimized training menu based on user input information, and also recognizes the user's emotional state and reflects this in feedback and advice. The following describes in detail the operation flow of this system and its specific processing.

[1827] 1. Collection of User Information

[1828] User Behavior

[1829] First, a user accesses the AI ​​personal trainer application using their own device (such as a smartphone or PC). Next, the user enters their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and frequency of gym visits (how many times per week) into the application. The user also sets their training goals (e.g., to lose weight, gain muscle, or improve physical strength).

[1830] Terminal handling

[1831] The terminal collects the information entered by the user and transmits the data to the server.

[1832] 2. Creation of training menu

[1833] Server Processing

[1834] The server receives the user's data and sends it to the generative AI engine. The generative AI engine generates an optimal training menu based on the user's information and goals. For example, if the user's goal is to "lose weight," the generative AI will provide a menu that takes into account the balance of aerobic exercise (running and cycling) and strength training (squats and dumbbell exercises, etc.). The generated training menu is sent from the server to the user's device.

[1835] 3. Display and execute the training menu

[1836] Terminal handling

[1837] The terminal displays the training menu sent from the server to the user. The user starts training and performs the training according to the details in the menu (e.g., running time, number of crunches, weight of dumbbells, etc.).

[1838] 4. Record your training and self-assess

[1839] User Behavior

[1840] After the workout, the user enters details of the workout (e.g., 50 squats using 5kg dumbbells) and their own assessment (e.g., subjective assessment of whether the workout was difficult) into the device.

[1841] Terminal handling

[1842] The device collects the training details and self-assessment entered by the user and sends the data to a server.

[1843] 5. Emotional Recognition

[1844] User Behavior

[1845] While the user is performing the training and after the training, the device collects the user's facial expression, voice, and text data.

[1846] Terminal handling

[1847] The device's built-in emotion engine analyzes the user's emotional state based on the collected data, recognizing, for example, whether the user is tired, motivated, or stressed.

[1848] 6. Feedback and advice for your next training session

[1849] Server Processing

[1850] The server sends the collected training data, self-evaluation results, and emotion analysis results from the emotion engine to the generation AI. The generation AI generates feedback based on the user's past training history and emotional state, and provides advice for the next training session. For example, if the user felt stressed during training, it will suggest more relaxing exercises for the next session.

[1851] Server Processing

[1852] Send generated feedback and advice to the device.

[1853] Terminal handling

[1854] The device receives feedback and advice from the server and displays it to the user, who can then review the feedback and use it to improve their next training session.

[1855] Specific examples

[1856] User B (Goal: Weight loss)

[1857] Step 1

[1858] User B accesses the app and enters information such as his height of 165 cm, his weight of 80 kg, the ability to go to the gym four times a week, and his goal of "losing weight." The device then sends this data to the server.

[1859] Step 2

[1860] The server receives the data and passes it to the generation AI. The generation AI generates a training menu for User B four times a week. For example, it may provide a menu such as "30 minutes of running, 20 squats, and 10 burpee jumps." The training menu is sent to the device.

[1861] Step 3

[1862] The device displays the training menu to User B. User B then performs the training at the gym.

[1863] Step 4

[1864] User B enters details of the workout he or she performed. For example, he or she might enter "30 minutes of running, 5km run, self-rating 5 / 5." The emotion engine analyzes User B's facial expressions and voice and recognizes the emotion "motivated" based on the microexpression. The data is sent from the device to the server.

[1865] Step 5

[1866] The server receives the data and passes it to the generation AI. The generation AI analyzes the data and generates advice for the next training menu. For example, "Extend your running time to 40 minutes next time." The feedback is sent to User B's device and displayed.

[1867] In this way, the generative AI personal trainer system using the emotion engine can provide an individually optimized training menu taking into account the user's emotional state, maximizing efficiency and effectiveness.

[1868] The processing flow will be explained below.

[1869] Step 1:

[1870] A user accesses the generated AI personal trainer application using a device (such as a smartphone or PC). The user inputs their physical information (e.g., weight, height, age, gender) and lifestyle habits (e.g., eating habits, sleep time), as well as the frequency of gym visits (e.g., how many times per week they can go). In addition, the user sets training goals (e.g., to lose weight, gain muscle, improve physical strength).

[1871] Step 2:

[1872] The terminal collects the information entered by the user and transmits the data to the server.

[1873] Step 3:

[1874] The server receives the user information sent from the device and passes the received information to the generation AI engine.

[1875] Step 4:

[1876] The generative AI engine generates the optimal training menu for each individual user based on their information and training goals. For example, if your goal is to lose weight, it will generate a menu that balances cardio and strength training.

[1877] Step 5:

[1878] The server transmits the generated training menu to the terminal.

[1879] Step 6:

[1880] The device displays the training menu sent from the server to the user, who then checks the training menu and follows it to train at the gym or at home.

[1881] Step 7:

[1882] After the user completes the training, they enter details of each exercise (e.g., 30 minutes of running, 5 km run) and their own assessment (e.g., subjective assessment of whether the training was hard) into the device.

[1883] Step 8:

[1884] The terminal transmits the detailed training data and self-evaluation results input by the user to the server.

[1885] Step 9:

[1886] While the user is training and afterward, the device collects facial, voice, and text data from the user. The device's built-in emotion engine analyzes the user's emotional state based on the collected data. For example, it can recognize emotions such as tiredness, motivation, and stress.

[1887] Step 10:

[1888] The server receives detailed training data, self-assessment results, and emotion analysis results from the emotion engine from the device, and passes them to the generative AI engine. The generative AI generates feedback based on the user's past training history and emotional state, and provides advice for the next training session. For example, if the user felt stressed during training, it will suggest more relaxing exercises for the next session.

[1889] Step 11:

[1890] The server sends the generated feedback and advice to the device.

[1891] Step 12:

[1892] The device displays the feedback and advice received from the server to the user, who can then review the feedback and use it to improve their next training session.

[1893] Example 2

[1894] 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."

[1895] Conventional personal trainer systems provide training menus based on a user's physical information and training goals, but they are unable to take into account the user's emotional state or performance during training, resulting in insufficient individual optimization. As a result, users often find it difficult to continue training and maintain motivation. The present invention aims to solve this problem by providing feedback and training advice that takes into account the user's emotional state.

[1896] 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.

[1897] In this invention, the server includes: means for having the user input training goals and personal physical information; means for transmitting the input physical information, lifestyle habits, and training frequency to the server via a terminal; means for generating a training menu based on the input training goals and personal physical information via the server; means for providing the generated training menu to the user's terminal; means for having the user input training results and self-evaluation after training according to the training menu; means for collecting facial expressions, voice, and text data of the user during and after the training and recognizing emotions via the terminal; and means for generating feedback and advice for the next training session based on the input results, self-evaluation, and emotional data via the server and providing the feedback and advice to the user's terminal. This makes it possible to provide feedback that takes the user's emotional state into account and individually optimized training advice.

[1898] "User" refers to an individual who uses the generative AI personal trainer system to generate a training menu and receive feedback.

[1899] A "training goal" is a physical goal that a user wants to achieve, examples of which include "lose weight" or "gain muscle."

[1900] "Physical information" refers to basic personal data such as a user's height, weight, age, and gender.

[1901] "Lifestyle habits" refers to information such as the user's eating habits and sleeping hours in their daily lives.

[1902] "Training frequency" refers to the number of times or frequency with which a user trains, and examples include "how many times per week they train."

[1903] A "terminal" is a device used by a user to input data and receive training menus and feedback, and examples include smartphones and PCs.

[1904] "Server" refers to the computer at the core of the system that receives data sent by users and uses generation AI to generate training menus and provide feedback.

[1905] A "generative AI engine" refers to an artificial intelligence model that generates optimal training menus based on user input information and training goals.

[1906] "Self-rating" refers to data that allows users to subjectively evaluate their own performance and impressions after training.

[1907] "Emotional data" refers to information about a user's emotional state analyzed from facial expressions, voice, text data, and the like.

[1908] "Feedback" refers to the advice and evaluation provided by the generative AI engine based on the results of the training the user has performed.

[1909] "Training menu" refers to the specific training content generated by the AI ​​engine based on the user's goals, and includes the number of exercises, number of sets, weight, etc.

[1910] An "emotion engine" is software built into the device that analyzes the user's emotional state based on collected data.

[1911] "Feedback and advice" refers to providing specific instructions and improvements for the next workout based on the user's workout results and emotional state.

[1912] "Training results" refers to detailed data when a user performs training, including, for example, the number of squats and the weight used.

[1913] This invention provides a personal trainer system that combines generative AI and an emotion engine to provide feedback and individually optimized training advice that takes into account the user's emotional state. This system is implemented in the following specific steps.

[1914] First, the user accesses the AI ​​personal trainer application from their own device (such as a smartphone or PC). The user enters their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and training frequency (how many times per week) into the application. The user then sets training goals, such as "lose weight" or "gain muscle."

[1915] The device collects the information entered by the user and sends the data to a server in an appropriate format, such as JSON. The server receives this data and passes it to a generative AI engine, which then generates an optimal training menu based on the user's information and goals. The generative AI engine can then use cloud-based services or dedicated AI models for this processing.

[1916] The generated training menu is sent from the server to the user's device. The device displays the training menu received from the server to the user, and the user performs the training according to the displayed menu. After the training, the user enters details of the training they performed (e.g., 50 squats using 5kg dumbbells) and their self-evaluation (difficulty and satisfaction of the training) into the device.

[1917] The device also collects the user's facial expressions, voice, and text data during and after the user's training. The collected data is analyzed by the device's built-in emotion engine to recognize the user's emotional state (e.g., fatigue, motivation, stress, etc.). This emotion data is also sent to the server.

[1918] The server receives the training results, self-evaluation, and emotional data, and passes them to the generative AI engine to generate feedback and advice for the next training session. For example, if the user felt stressed during training, the server will suggest more relaxing exercises for the next session. This feedback and advice is sent from the server to the user's device and displayed to the user.

[1919] Specific examples

[1920] User B accesses a personal trainer application and enters their height (165 cm), weight (80 kg), ability to go to the gym four times a week, and goal of "losing weight." The device sends this data to the server. The server receives the data and passes it to the generation AI. The generation AI generates a training menu for User B four times a week. For example, it may provide a menu such as "30 minutes of running, 20 squats, and 10 burpee jumps." The training menu is sent to the device, which displays it to User B. User B trains at the gym and then enters "30 minutes of running, 5 km run, self-rating 5 / 5." The emotion engine analyzes User B's facial expressions and voice and recognizes the emotion "motivated." This data is sent from the device to the server, which passes it to the generation AI. The generation AI analyzes the data and generates advice such as "extend your running time to 40 minutes next time." This feedback is sent to the device and displayed to User B.

[1921] Prompt Sentence Examples

[1922] Below are some examples of prompts that could be passed to the generation AI when the user uses the application.

[1923] "Generate a weekly training plan for weight loss based on user data. The data is as follows: height 170cm, weight 70kg, able to train 3 times a week."

[1924] The system provides more personalized training menus and feedback that take into account the user's emotional state, maximizing the effectiveness of training.

[1925] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1926] Step 1:

[1927] The user enters information

[1928] User Behavior

[1929] Users access the AI ​​personal trainer application from their own devices and input their physical information (weight, height, age, gender), lifestyle habits (e.g., eating habits, sleep time), and training frequency. Users also set training goals (e.g., losing weight, gaining muscle).

[1930] input

[1931] Physical information, lifestyle, training frequency, training goals

[1932] output

[1933] Temporarily save the input data as a JSON format file

[1934] Step 2:

[1935] The device sends the input information to the server

[1936] Terminal handling

[1937] The device collects the information entered by the user and sends it to the server in an appropriate format, such as JSON, including the user's height, weight, age, gender, lifestyle, training frequency, and training goals.

[1938] input

[1939] User's physical information, lifestyle habits, training frequency, and training goals stored on the device

[1940] output

[1941] JSON format data sent to the server

[1942] Step 3:

[1943] The server receives the data and passes it to the generative AI engine

[1944] Server Processing

[1945] The server receives user information sent from the device and passes this data to the generation AI engine.

[1946] input

[1947] JSON format data sent from the device

[1948] output

[1949] User information passed to the generation AI engine

[1950] Step 4:

[1951] Generative AI engine generates training menus

[1952] Generative AI engine processing

[1953] The generative AI engine generates an optimal training menu based on the received user information and training goals, and also takes into account past data and training data of similar users.

[1954] input

[1955] User information, training goals, generative AI model

[1956] output

[1957] Generated training menu

[1958] Step 5:

[1959] Send the training menu to the device and provide it to the user

[1960] Server Processing

[1961] The server sends the training menu received from the AI ​​generation engine to the user's device, which then displays it to the user.

[1962] input

[1963] Generated training menu

[1964] output

[1965] Training menu displayed on the user's device

[1966] Step 6:

[1967] The user performs the training and enters the results

[1968] User Behavior

[1969] The user follows the training menu displayed on the device and performs the training. After the training, the user enters the details of the training and their own evaluation into the device.

[1970] input

[1971] Training results, self-assessment

[1972] output

[1973] Input training results and self-assessment data

[1974] Step 7:

[1975] The device sends the training results and self-evaluation to the server.

[1976] Terminal handling

[1977] The terminal collects the training results and self-assessment entered by the user and transmits them to the server.

[1978] input

[1979] User-entered training results and self-assessment data

[1980] output

[1981] Training results and self-assessment data sent to the server

[1982] Step 8:

[1983] The device collects and analyzes emotional data

[1984] Terminal handling

[1985] The device collects the user's facial expressions, voice, and text data during and after training, which is then analyzed by the device's built-in emotion engine to determine the user's emotional state.

[1986] input

[1987] User facial expressions, voice, and text data

[1988] output

[1989] Analyzed emotion data

[1990] Step 9:

[1991] Send emotion data to the server

[1992] Terminal handling

[1993] The device transmits the analyzed emotion data to the server.

[1994] input

[1995] Analyzed emotion data

[1996] output

[1997] Emotion data sent to the server

[1998] Step 10:

[1999] The server generates feedback and advice for the next training session

[2000] Server Processing

[2001] The server instructs the AI ​​engine to analyze the training results, self-assessment, and emotional data, and generates feedback and advice for the next training session.

[2002] input

[2003] Training results, self-rating, emotion data, generative AI model

[2004] output

[2005] Generated feedback and next training advice

[2006] Step 11:

[2007] Send feedback and advice to the device and provide it to the user

[2008] Server Processing

[2009] The server sends the generated feedback and next training advice to the user's terminal, which displays it to the user.

[2010] input

[2011] Generated feedback and next training advice

[2012] output

[2013] Feedback displayed on the user's device and advice for the next training session

[2014] (Application example 2)

[2015] 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."

[2016] Conventional personal trainer systems typically generate training menus and feedback based on the user's physical data and training results. However, they do not take the user's emotional state into consideration, making it difficult to maximize the effectiveness of training. In particular, in the field of food delivery, users' moods and emotions have a significant impact on their appetite and choices, so there is a demand for suggestions based on emotions. Therefore, realizing a system that incorporates emotional data has been a challenge.

[2017] 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.

[2018] In this invention, the server includes: means for having the user input training goals and personal physical information; means for generating a training menu based on the input training goals and personal physical information; means for providing the generated training menu to the user's terminal; means for having the user input training results and self-evaluation after training according to the training menu; means for generating feedback and advice for the next training session based on the input results and self-evaluation and providing the feedback and advice to the user's terminal; and means for incorporating an emotion engine that analyzes the user's emotional state and adjusting the training menu and feedback based on the emotional state, thereby making it possible to propose optimal training and meal menus according to the user's emotional state.

[2019] "User" refers to an individual who uses the system.

[2020] "Training goal" refers to a specific goal in exercise that a user wants to achieve.

[2021] "Personal physical information" refers to data about a user's body, such as weight, height, age, and gender.

[2022] The term "server" refers to a central processing unit that processes information input by a user, generates a training menu and feedback, and transmits the menu and feedback to a user terminal.

[2023] A "training menu" refers to a training plan or plan that is generated based on the user's goals.

[2024] "User's device" refers to a device used by a user to access the system and input or provide information, such as a smartphone or tablet.

[2025] The "generated training menu" refers to an exercise program created by the server based on the user's input data.

[2026] "Training results" refers to the content and results of the training that the user actually undertook.

[2027] "Self-assessment" refers to a user's self-evaluation of the training they have completed.

[2028] "Feedback" refers to advice and areas for improvement generated based on training results and self-assessment.

[2029] "Emotional state" refers to a user's current mood or emotions.

[2030] An "emotion engine" refers to a system that analyzes a user's facial expressions and voice data to recognize the user's emotional state.

[2031] "Means for adjusting training menus and feedback" refers to means for optimizing exercise programs and advice by reflecting the user's emotional state.

[2032] This invention is a system that generates an optimal training menu based on a user's training goals and personal physical information, and further analyzes the user's emotional state to adjust feedback and advice. This system can be applied to the food delivery field to provide an optimal meal menu according to the user's emotional state.

[2033] System Program Overview

[2034] 1. Collection of User Information

[2035] Users use a smartphone app to input information such as their training goals, personal physical information, food preferences, allergy information, and meal timings.

[2036] The terminal transmits this information to the server.

[2037] 2. Recognizing emotional states

[2038] When a user accesses the app, the smartphone's camera and microphone are used to collect facial expressions and voice, and the emotion engine analyzes the user's current emotional state.

[2039] Images collected by the camera are processed using the OpenCV library and input into an emotion recognition model (using TensorFlow).

[2040] The audio data collected by the microphone is converted from audio to text using the SpeechRecognition library, and emotions are recognized based on the text data.

[2041] 3. Creation of training and meal menus

[2042] The server sends the user's input information and data from the emotion engine to the generation AI engine, and generates training and meal menus.

[2043] For example, if the user feels "tired," a menu of relaxing meals (soup, salad, herbal tea, etc.) will be generated.

[2044] 4. Providing Feedback

[2045] After the user completes a workout or meal, they enter their results and self-evaluation into the app.

[2046] The terminal collects this data and sends it to the server.

[2047] The server then refers back to the analysis results of the emotion engine and uses generative AI to generate feedback and advice for the next workout or meal.

[2048] Hardware and Software Use Cases

[2049] Smartphones: Used by users to input information and recognize emotional states.

[2050] Server: Processes user information, generates training menus and meal menus, and generates feedback.

[2051] Software: OpenCV (for image processing), TensorFlow (for emotion recognition models), SpeechRecognition (for voice recognition).

[2052] Specific examples

[2053] When User A opens the app, takes a picture of their face with the camera and says "I'm tired," the app suggests "soup" and "herbal tea." After User A confirms this, they place their order and enter their impressions after eating and drinking as feedback. An example of a prompt sentence using the generative AI model is as follows:

[2054] Prompt Sentence Examples

[2055] "I'm feeling unmotivated. Please suggest some relaxing meals. User information is as follows: I like Japanese food, I have no allergies, and I always eat at 12:00 and 18:00."

[2056] In this way, the present invention can provide optimal training and meal menus based on the user's emotional state, thereby improving the user's health maintenance and meal satisfaction.

[2057] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2058] Step 1:

[2059] The user launches the smartphone app and inputs their training goals, personal physical information, food preferences, allergy information, meal timing, etc. Based on this, the device organizes this data and sends it to the server. The input data includes specific training goals (e.g., losing weight) and physical data (e.g., height, weight, age, gender).

[2060] Input: Training goals, personal physical information, food preferences, allergy information, meal timing

[2061] Output: Structured user data

[2062] Step 2:

[2063] The server processes the received user data and generates a training menu using a generative AI engine based on the user's training goals and personal physical information. The generated training menu is optimized for the user's goals.

[2064] Input: Structured user data

[2065] Output: Training menu

[2066] Step 3:

[2067] The server sends the generated training menu to the user's terminal, which displays it to the user. The user checks the training menu and performs the training.

[2068] Input: Generated training menu

[2069] Output: Training menu displayed to the user

[2070] Step 4:

[2071] After completing the training, the user enters the results of the training and their self-evaluation into the smartphone app. The device collects this data and sends it to the server.

[2072] Input: Training results and self-assessment

[2073] Output: Structured training data and self-scoring data

[2074] Step 5:

[2075] The device captures the user's facial expressions with a camera and collects audio with a microphone. It then uses an emotion engine to analyze this data and recognize the user's emotional state. Specifically, it analyzes facial expressions using the image processing library OpenCV and determines emotions using an emotion recognition model using TensorFlow. It also converts audio into text using the speech recognition library SpeechRecognition and determines emotions.

[2076] Input: facial expression image data, voice data

[2077] Output: Perceived emotional state

[2078] Step 6:

[2079] The server inputs the collected training data, self-assessment data, and emotional state data into a generative AI engine to generate the next training menu and feedback. For example, if the server determines that the user is feeling tired, it will suggest relaxing exercises.

[2080] Input: training data, self-rating data, emotional state data

[2081] Output: Next training menu and feedback

[2082] Step 7:

[2083] The server sends the generated next training menu and feedback to the user's terminal, which displays it to the user. The user can then check the feedback and use it in their next training session.

[2084] Input: Next training menu and feedback

[2085] Output: The next training menu displayed to the user and feedback

[2086] 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.

[2087] 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.

[2088] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2089] 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.

[2090] 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.

[2091] 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.

[2092] 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).

[2093] 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.

[2094] 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."

[2095] 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.

[2096] 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).

[2097] 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.

[2098] 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.

[2099] 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.

[2100] 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.

[2101] 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.

[2102] 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.

[2103] 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.

[2104] 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.

[2105] 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.

[2106] 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.

[2107] The following is further disclosed regarding the above embodiment.

[2108] (Claim 1)

[2109] means for allowing a user to input training goals and personal physical information;

[2110] a means for generating a training menu based on the input training goal and personal physical information by a server;

[2111] means for providing the generated training menu to a user's terminal;

[2112] a means for allowing a user to input the results of said training and a self-evaluation thereof after the user has performed said training in accordance with said training menu;

[2113] A means for generating feedback and advice for the next training based on the input results and self-evaluation, and providing the feedback and advice to the user's terminal;

[2114] A system including:

[2115] (Claim 2)

[2116] 2. The system according to claim 1, wherein the training menu generated by the server includes the number of repetitions, number of sets, weight, etc. of exercises that are optimal for the training goal.

[2117] (Claim 3)

[2118] The system of claim 1 , wherein the user's input information includes physical information, lifestyle habits, and frequency of gym visits.

[2119] "Example 1"

[2120] (Claim 1)

[2121] means for allowing a user to input training goals and physical information;

[2122] means for transmitting the input training goal and physical information to a server by a terminal;

[2123] a means for generating a training menu by a server using a generation AI model based on the input training goal and physical information;

[2124] means for providing the generated training menu to a user's terminal;

[2125] a means for allowing a user to input the results of said training and a self-evaluation thereof after the user has performed said training in accordance with said training menu;

[2126] means for transmitting the input results and self-assessment to a server by the terminal;

[2127] A means for generating feedback and advice for the next training session based on the input results and self-assessment using a generative AI model and providing the feedback and advice to the user's terminal;

[2128] A system including:

[2129] (Claim 2)

[2130] 2. The system of claim 1, wherein the training menu generated by the server using the generation AI model includes the number of exercises, number of sets, weight, etc. that are optimal for the training goal.

[2131] (Claim 3)

[2132] The system of claim 1 , wherein the user's input information includes physical information, lifestyle habits, and frequency of gym visits.

[2133] "Application Example 1"

[2134] (Claim 1)

[2135] means for allowing a user to input training goals and personal physical information;

[2136] a means for generating a training menu based on the input training goal and personal physical information by a server;

[2137] means for providing the generated training menu to a user's terminal;

[2138] a means for allowing a user to input the results of said training and a self-evaluation thereof after the user has performed said training in accordance with said training menu;

[2139] A means for generating feedback and advice for the next training based on the input results and self-evaluation, and providing the feedback and advice to the user's terminal;

[2140] a means for using generative AI models to generate feedback and advice; and

[2141] A system including:

[2142] (Claim 2)

[2143] 2. The system according to claim 1, wherein the training menu generated by the server includes the number of repetitions, number of sets, weight, etc. of exercises that are optimal for the training goal.

[2144] (Claim 3)

[2145] The system of claim 1 , wherein the user's input information includes physical information, lifestyle habits, and frequency of gym visits.

[2146] "Example 2: Combining Emotion Engines"

[2147] (Claim 1)

[2148] means for allowing a user to input training goals and personal physical information;

[2149] means for transmitting the input physical information, lifestyle habits, and training frequency to a server by a terminal;

[2150] a means for generating a training menu based on the input training goal and personal physical information by a server;

[2151] means for providing the generated training menu to a user's terminal;

[2152] a means for allowing a user to input the results of said training and a self-evaluation thereof after the user has performed said training in accordance with said training menu;

[2153] means for collecting facial expression, voice, and text data of the user during and after the training and recognizing emotions by the terminal;

[2154] A means for generating feedback and advice for the next training session based on the input results, self-rating, and emotion data by the server, and providing the feedback and advice to the user's terminal;

[2155] A system including:

[2156] (Claim 2)

[2157] 2. The system according to claim 1, wherein the training menu generated by the server includes the number of repetitions, number of sets, weight, etc. of exercises that are optimal for the training goal.

[2158] (Claim 3)

[2159] 2. The system according to claim 1, wherein the emotion recognition means analyzes emotions such as fatigue, motivation, and stress based on the user's facial expressions, voice, and text data.

[2160] "Application example 2 when combining emotion engines"

[2161] (Claim 1)

[2162] means for allowing a user to input training goals and personal physical information;

[2163] a means for generating a training menu based on the input training goal and personal physical information by a server;

[2164] means for providing the generated training menu to a user's terminal;

[2165] a means for allowing a user to input the results of said training and a self-evaluation thereof after the user has performed said training in accordance with said training menu;

[2166] A means for generating feedback and advice for the next training based on the input results and self-evaluation, and providing the feedback and advice to the user's terminal;

[2167] a means for adjusting a training menu and feedback based on an emotion engine that analyzes the user's emotion state;

[2168] A system including:

[2169] (Claim 2)

[2170] 2. The system according to claim 1, wherein the training menu generated by the server includes the number of repetitions, number of sets, weight, etc. of exercises that are optimal for the training goal.

[2171] (Claim 3)

[2172] 2. The system of claim 1, wherein the user's input information includes physical information, lifestyle habits, and frequency of gym visits, and further includes means for analyzing the user's emotional state. [Explanation of symbols]

[2173] 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 allowing a user to input training goals and personal physical information; a means for generating a training menu based on the input training goal and personal physical information by a server; means for providing the generated training menu to a user's terminal; a means for allowing a user to input the results of said training and a self-evaluation thereof after the user has performed said training in accordance with said training menu; A means for generating feedback and advice for the next training based on the input results and self-evaluation, and providing the feedback and advice to the user's terminal; A system including:

2. The system according to claim 1 , wherein the training menu generated by the server includes the number of repetitions, number of sets, weight, etc. of exercises that are optimal for a training goal.

3. The system of claim 1 , wherein the user's input information includes physical information, lifestyle habits, and frequency of gym visits.

Images