System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving fitness goals and physical information from a user; means for generating a customized training program based on the user's fitness goals and physical information; means for generating customized nutrition advice based on the user's fitness goals and physical information; means for providing the customized training program and nutrition advice to the user; and means for receiving feedback from the user on the progress of the training program and changes in physical condition and adjusting the training program and nutrition advice based on the feedback.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, consumer interest in fitness and health management has grown rapidly. However, providing training programs and nutritional advice tailored to individual users requires a high level of expertise and human resources. This has created a demand for a system that can efficiently and accurately provide customized fitness instruction. Current training instruction services often struggle to provide immediate feedback to users and are insufficiently personalized based on their individual physical information and progress. This reduces user satisfaction and hinders the achievement of fitness goals. While it would be desirable to be able to refer users to specialized trainers and nutritionists in a timely manner, this is difficult to achieve. [Means for solving the problem]

[0005] The present invention provides a system that receives fitness goals and physical information from users and then provides customized training programs and nutritional advice based on that information. Specifically, the system provides a means for users to input their fitness goals and physical information on a dedicated website or mobile app, and then uses a generative AI model to automatically generate optimal training programs and nutritional advice from the user information. The system then provides this information to the user and incorporates a means for receiving feedback from the user on their training progress and changes in their physical condition and adjusting the training program and nutritional advice in real time accordingly. The system also provides a means for referrals to professional trainers and nutritionists as needed, ensuring greater satisfaction and effective achievement of fitness goals.

[0006] "Means for receiving fitness goals and physical information from the user" refers to a function that allows the user to input or provide information about their fitness goals and physical information (such as age, weight, height, body fat percentage, and past exercise history).

[0007] "Customized Training Program" refers to an individualized exercise plan optimized based on the user's provided fitness goals and physical information, including specific exercises, sets, repetitions, etc.

[0008] "Customized nutrition advice" refers to advice that includes suggested meal plans and nutritional instructions based on a user's fitness goals and physical information.

[0009] "Generative AI models" refer to algorithms or software that use artificial intelligence technology to automatically generate optimal training programs and nutritional advice based on input data.

[0010] "Means for providing to the user" refers to a function for displaying or notifying the user of the generated training program and nutritional advice.

[0011] "Means for receiving and adjusting feedback from the user" refers to functionality for collecting information from the user regarding training progress and changes in physical condition, and adapting training programs and nutritional advice in real time based on that information.

[0012] "Means for referral to professional trainers and nutritionists" refers to functions and methods for guiding users to professional fitness trainers and nutritionists as needed.

[0013] "Website or Mobile App" means an online platform accessible over the internet or a mobile network that provides an interface for Users to access Fitness Services. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] System Configuration

[0036] The present invention includes a system that provides customized training programs and nutritional advice based on a user's fitness goals and physical information. The system mainly consists of a user terminal, a server, and a generative AI model.

[0037] Program processing explanation

[0038] 1. User Input

[0039] Users access a dedicated website or mobile app and enter their fitness goals (e.g., building muscle, losing weight, improving endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[0040] 2. Transmission of information

[0041] The terminal converts the entered user information into JSON format and sends it to the server.

[0042] 3. Receiving a Request

[0043] The server analyzes the received request and obtains the user's fitness goals and physical information.

[0044] 4. Training program generation

[0045] The server uses a generative AI model to generate an optimal training program based on the user's information.

[0046] Specifically, the system processes the user's goals and physical information as input data and generates detailed training content, such as "15 push-ups x 3 sets."

[0047] 5. Nutrition advice generation

[0048] The server similarly uses the generative AI model to generate nutritional advice tailored to the user.

[0049] For example, if a user's fitness goal is to "lose weight," a low-calorie, high-protein meal plan is suggested.

[0050] 6. Submitting the results

[0051] The server compiles the generated training program and nutritional advice into a JSON-formatted response and sends it to the user's device.

[0052] 7. Displaying the results

[0053] The device analyzes the responses it receives and displays training programs and nutritional advice on a dedicated chat screen.

[0054] 8. Feedback

[0055] Users report their training progress and changes in their physical condition to the server via a dedicated chat screen.

[0056] 9. Processing Feedback

[0057] Based on the feedback received, the server again uses the generative AI model to adjust the training program and nutrition advice.

[0058] For example, if a user reports knee pain, other low-impact exercises may be suggested instead of squats.

[0059] 10. Providing adjusted results

[0060] The server sends the adjusted training program and nutrition advice back to the user's terminal, which displays it.

[0061] Specific examples

[0062] 1. Input example

[0063] The user inputs his / her fitness goal and physical information: "25 years old, weighs 70 kg, and wants to build muscle."

[0064] 2. Generation example

[0065] The server receives the user's information and uses a generative AI model to generate a training program of "3 sets of 15 push-ups" and nutritional advice of "oats and fruit for breakfast, chicken salad for lunch."

[0066] 3. Feedback Examples

[0067] A user reports, "My knee hurt during my workout today."

[0068] The server receives feedback and suggests alternative exercises that put less strain on the knees.

[0069] As described above, the present invention provides a system that quickly and appropriately provides individualized training programs and nutritional advice based on user input, helping users achieve their fitness goals.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] Users access a dedicated website or mobile app and click the "Start Training" button.

[0073] Step 2:

[0074] Users input their fitness goals (e.g., build muscle, lose weight, improve endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[0075] Step 3:

[0076] The device converts the fitness goals and physical information entered by the user into JSON format.

[0077] Step 4:

[0078] The terminal sends user information in JSON format to the server as a POST request.

[0079] Step 5:

[0080] The server parses the received POST request and obtains the user's fitness goals and physical information.

[0081] Step 6:

[0082] The server calls the generative AI model and instructs it to generate a training program using the user's information as input data.

[0083] Step 7:

[0084] The generative AI model generates a customized training program based on the user information and returns the results to the server.

[0085] Step 8:

[0086] The server then invokes the generative AI model again, this time instructing it to generate customized nutritional advice.

[0087] Step 9:

[0088] The generative AI model generates nutritional advice based on user information and returns the results to the server.

[0089] Step 10:

[0090] The server compiles the training program and nutrition advice into a JSON-formatted response and sends it to the device.

[0091] Step 11:

[0092] The device analyzes the response received from the server and displays the training program and nutritional advice on a dedicated chat screen.

[0093] Step 12:

[0094] Users can report their training progress and changes in their physical condition through a dedicated chat screen.

[0095] Step 13:

[0096] The terminal transmits the feedback from the user to the server.

[0097] Step 14:

[0098] The server analyzes the feedback it receives and uses generative AI models to direct adjustments to training programs and nutritional advice.

[0099] Step 15:

[0100] Based on the feedback, the generative AI model generates appropriately adjusted training programs and nutritional advice and returns the results to the server.

[0101] Step 16:

[0102] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device.

[0103] Step 17:

[0104] The terminal displays the adjusted information on a dedicated chat screen and provides it to the user.

[0105] Example 1

[0106] 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."

[0107] Currently, many fitness program and nutrition advice systems only provide general information and are not sufficiently customized to each user's physical information and fitness goals. Furthermore, it is difficult to provide dynamic training programs and nutrition advice that reflect user feedback. Therefore, there is a need for a system that can provide training programs and nutrition advice optimized for each user and flexibly adjust them based on feedback.

[0108] 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.

[0109] In this invention, the server includes means for receiving fitness goals and physical information from a user, means for converting the user's fitness goals and physical information into a data format and sending it to the server, means for generating a customized training program using a generative AI model based on the user's fitness goals and physical information, means for generating customized nutritional advice using the generative AI model based on the user's fitness goals and physical information, means for converting the customized training program and nutritional advice into a data format and providing it to the user, and means for receiving feedback from the user regarding progress in the training program and changes in physical condition and adjusting the training program and nutritional advice based on the feedback, thereby making it possible to provide an optimal training program and nutritional advice tailored to the user's individual needs and flexibly respond to the feedback.

[0110] "User" refers to the individual or end user who inputs fitness goals and physical information.

[0111] "Fitness goal" refers to a physical goal a user wishes to achieve (e.g., building muscle, losing weight, improving endurance, etc.).

[0112] "Physical information" refers to the user's individual physical characteristics (e.g., age, weight, height, body fat percentage, etc.).

[0113] "Data format" refers to a format (e.g., JSON format) that structures information entered by a user and converts it into a form that can be handled as digital data.

[0114] "Server" refers to the computer system that analyzes the data received from the User and utilizes the generative AI model to generate training programs and nutritional advice.

[0115] "Generative AI model" refers to an artificial intelligence model that is trained on large amounts of data and generates optimal training programs and nutritional advice based on user information.

[0116] "Customized training program" refers to a specific exercise plan tailored to an individual user based on their fitness goals and physical information.

[0117] "Customized nutrition advice" refers to a meal plan that is tailored based on an individual user's fitness goals and physical information.

[0118] "Feedback" refers to the act of the user providing the system with information about the progress of training and changes in physical condition.

[0119] "Adjustment" refers to the process of reevaluating and adapting existing training programs and nutritional advice based on feedback received.

[0120] MODE FOR CARRYING OUT THE INVENTION

[0121] This invention describes a concrete implementation of a system that provides customized training programs and nutritional advice based on a user's fitness goals and physical information. The entire system mainly consists of a user terminal, a server, and a generative AI model.

[0122] 1. User Input

[0123] Users access the system through a dedicated website or mobile app. The application runs on popular platforms such as iOS and Android. Users enter their fitness goals and physical information. For example, if a 25-year-old user weighs 70 kg and wants to build muscle, they can enter that information.

[0124] 2. Transmission of information

[0125] The device converts the information entered by the user into JSON format and sends it to the server using Internet Protocol. The JSON format data includes fitness goals and physical information. For example, it might look like this:

[0126] json

[0127] {

[0128] "age": 25,

[0129] "weight": 70,

[0130] "goal": "muscle_gain"

[0131] }

[0132] 3. Receiving a Request

[0133] The server parses the received request to obtain the user's fitness goals and physical information, which involves parsing the data to extract keys and values.

[0134] 4. Training program generation

[0135] The server uses a generative AI model (e.g., GPT-3) to generate an optimal training program based on the user's information. Specifically, the user's data is input to the generative AI model as a prompt sentence like the following:

[0136] User information: 25 years old, weight 70kg, goal: muscle building. Please provide a suitable training program for the user.

[0137] Based on this prompt, the generative AI model generates specific training content such as "15 push-ups x 3 sets."

[0138] 5. Nutrition advice generation

[0139] The server uses the same generative AI model to generate nutrition advice tailored to the user, using prompts like:

[0140] User information: 25 years old, weight 70kg, goal: to build muscle. Please provide a suitable nutrition plan for the user.

[0141] Based on this prompt, the generative AI model generates nutritional advice such as "oats and fruit for breakfast, chicken salad for lunch."

[0142] 6. Submitting the results

[0143] The server then compiles the generated training program and nutrition advice into a JSON response and sends it to the user's device, for example in the following JSON format:

[0144] json

[0145] {

[0146] "training_program": "3 sets of 15 push-ups",

[0147] "nutrition_advice": "Oats and fruit for breakfast, chicken salad for lunch"

[0148] }

[0149] 7. Displaying the results

[0150] The device analyzes the received response and displays the training program and nutrition advice on a dedicated chat screen. This analysis process includes parsing the JSON of the response and preparing it for display in the GUI.

[0151] 8. Feedback

[0152] Users can report their training progress and changes in their physical condition to the server via a dedicated chat screen. For example, they can write, "My knee started hurting during today's training."

[0153] 9. Processing Feedback

[0154] The server analyzes the received feedback and determines the appropriate response. For example, if the user feedback is "knee pain," it will again use the generative AI model to generate a new training program. The prompt text is as follows:

[0155] User information: Age 25, Weight 70kg, Goal: Build muscle. User reported knee pain. Provide alternative exercises that are less stressful on the knees.

[0156] 10. Providing adjusted results

[0157] The server then compiles the adjusted training program and nutrition advice into a JSON response and sends it to the user's device, which then displays the new information on the chat screen.

[0158] The invention allows users to receive customized training programs and nutritional advice tailored to their fitness goals, with the flexibility to adjust based on feedback.

[0159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0160] Step 1: User enters fitness goals and physical information

[0161] Users access a dedicated website or mobile app and enter their fitness goals (e.g., muscle building, weight loss, endurance improvement) and physical information (e.g., age, weight, height, body fat percentage), which is then prepared as data to be sent to the system.

[0162] Input: Fitness goals and physical information (age, weight, height, body fat percentage, etc.)

[0163] Output: Input data converted to JSON format

[0164] Step 2: The device sends the user information

[0165] The device converts the information entered by the user into JSON format and sends it to the server using Internet Protocol, with the data transmitted over a secure communication channel.

[0166] Input: User information in JSON format

[0167] Output: User information sent to the server

[0168] Step 3: The server receives and analyzes the request

[0169] The server analyzes the received request to obtain the user's fitness goals and physical information. The analysis process involves parsing the received data to extract keys and values.

[0170] Input: JSON format user information received by the server

[0171] Output: Parsed fitness goals and body information

[0172] Step 4: The server generates a training program using the generated AI model

[0173] The server uses a generative AI model (e.g., GPT-3) to generate an optimal training program based on the parsed user information. The server inputs the following prompt to the generative AI model:

[0174] User information: 25 years old, weight 70kg, goal: muscle building. Please provide a suitable training program for the user.

[0175] Input: Fitness goal and physical information, prompt

[0176] Output: Generated training program (e.g., "3 sets of 15 push-ups")

[0177] Step 5: The server uses the generative AI model to generate nutrition advice

[0178] The server also uses a generative AI model to generate nutrition advice tailored to the user, using prompts like:

[0179] User information: 25 years old, weight 70kg, goal: to build muscle. Please provide a suitable nutrition plan for the user.

[0180] Input: Fitness goal and physical information, prompt

[0181] Output: Generated nutrition advice (e.g. "Oats and fruit for breakfast, chicken salad for lunch")

[0182] Step 6: Server sends results

[0183] The server then compiles the generated training program and nutrition advice into a JSON response and sends it to the user's device, for example in the following JSON format:

[0184] json

[0185] {

[0186] "training_program": "3 sets of 15 push-ups",

[0187] "nutrition_advice": "Oats and fruit for breakfast, chicken salad for lunch"

[0188] }

[0189] Input: Generated training programs and nutrition advice

[0190] Output: Sent to the terminal as a JSON response

[0191] Step 7: Your device will display the results

[0192] The device analyzes the received response and displays the training program and nutrition advice on a dedicated chat screen. This analysis process includes parsing the JSON of the response and preparing it for display in the GUI.

[0193] Input: JSON response (training program and nutrition advice)

[0194] Output: Training program and nutrition advice displayed on the chat screen

[0195] Step 8: User enters feedback

[0196] Users can report their training progress and changes in their physical condition to the server via a dedicated chat screen. For example, they can write, "My knee started hurting during today's training."

[0197] Input: Feedback on your training progress and changes in your fitness

[0198] Output: Information sent to the server as feedback

[0199] Step 9: Server processes feedback

[0200] The server analyzes the received feedback and determines the appropriate response. For example, if the user feedback is "knee pain," it will again use the generative AI model to generate a new training program. The prompt text is as follows:

[0201] User information: Age 25, Weight 70kg, Goal: Build muscle. User reported knee pain. Provide alternative exercises that are less stressful on the knees.

[0202] Input: Feedback, prompt

[0203] Output: Tailored training program

[0204] Step 10: The server sends the adjusted results

[0205] The server then compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the user's device.

[0206] Input: tailored training programs and nutritional advice

[0207] Output: Sent to the terminal as a JSON response

[0208] Step 11: Your device will display the adjusted results.

[0209] The device then analyzes the received response and displays the adjusted training program and nutritional advice on a dedicated chat screen.

[0210] Input: JSON response (adjusted training program and nutrition advice)

[0211] Output: Adjusted training program and nutrition advice displayed on the chat screen

[0212] (Application example 1)

[0213] 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."

[0214] The present invention aims to reduce the complexity of conventional systems and improve user convenience by automatically ordering meals customized based on the physical information of each user through a food delivery service and providing the user with the order results and nutritional advice in a system that provides training programs and nutritional advice to help users achieve their fitness goals. In conventional systems, after receiving a training program and nutritional advice, the user must choose for themselves what meals to actually eat, which can be a significant burden in terms of effort and time.

[0215] 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.

[0216] In this invention, the server includes means for receiving fitness goals and physical information from a user, means for generating a customized training program based on the user's fitness goals and physical information, means for generating customized nutritional advice based on the user's fitness goals and physical information, means for providing the customized training program and nutritional advice to the user, means for receiving feedback from the user regarding progress in the training program and changes in physical condition and adjusting the training program and nutritional advice based on the feedback, means for automatically ordering meals through a food delivery service based on the nutritional advice, and means for providing the user with the order results and nutritional advice from the food delivery service, thereby enabling the user to automatically order appropriate meals based on the individual nutritional advice and more effectively support achieving their fitness goals.

[0217] A "user" is an individual who utilizes the system and inputs fitness goals and physical information.

[0218] "Fitness Goal" means a physical or health goal that a user wishes to achieve, such as losing weight, building muscle, or improving endurance.

[0219] "Physical information" refers to physical data such as the user's age, weight, height, and body fat percentage.

[0220] A "training program" is a customized exercise plan generated based on a user's fitness goals and physical information.

[0221] "Nutrition Advice" means customized meal suggestions and plans provided based on a user's fitness goals and physical information.

[0222] "Feedback" refers to information provided by a user regarding progress in a training program and changes in physical condition.

[0223] A "food delivery service" is a service that allows you to order meals online and have them delivered.

[0224] "Generative AI Model" refers to the artificial intelligence algorithms used to generate optimal training programs and nutritional advice based on user information.

[0225] "Order Result" means the confirmation information regarding a meal ordered automatically through the food delivery service.

[0226] The term "means" refers to functions or components for executing various processes in this invention.

[0227] System Configuration

[0228] The present invention is a system that provides a user with a customized training program and nutritional advice based on their fitness goals and physical information, and automatically orders appropriate meals through a food delivery service. The system consists of a user terminal, a server, and a generative AI model.

[0229] Hardware and software used

[0230] Smartphone: User device on which the app is installed

[0231] Server: Data processing and AI model hosting

[0232] Generative AI models: generating nutrition advice and meal plans

[0233] Food Delivery API: Integration for automated meal ordering

[0234] Processing Description

[0235] 1. User Input

[0236] Users access a dedicated application on their smartphone and enter their fitness goals (e.g., weight loss, muscle building, endurance improvement, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.), which then inputs data tailored to the user's individual needs.

[0237] 2. Information Transmission

[0238] The user terminal converts the information entered by the user into JSON format and sends it to the server, which receives and analyzes this data.

[0239] 3. Nutrition advice generation

[0240] The server uses the generative AI model to generate optimal nutrition advice and meal plans based on the user's fitness goals and physical information, such as providing a low-calorie, high-protein meal plan for a user aiming to lose weight.

[0241] 4. Food delivery collaboration

[0242] Based on the meal plan, the server calls the API of the partner food delivery service and automatically orders the corresponding meal menu, eliminating the need for the user to choose their own meals.

[0243] 5. Sending and displaying results

[0244] The server converts the order details and nutrition advice back into JSON format and sends it to the user's device. The user's device analyzes this data and displays it on a dedicated screen. The user can then review the order details and make any necessary changes.

[0245] Specific examples

[0246] For example, if a user enters the following information:

[0247] Example prompt sentence:

[0248] Age: 30

[0249] Weight: 80kg

[0250] Height: 175cm

[0251] Body fat percentage: 20%

[0252] Fitness Goal: Muscle Building

[0253] Based on this information, the server uses a generative AI model to generate a meal plan such as "oats and fruit for breakfast, chicken salad for lunch" and automatically places an order with a food delivery service. The ordering results and nutrition advice are sent to the user's device, where they can view them.

[0254] In this way, the present invention can provide comprehensive support to users in achieving their fitness goals.

[0255] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0256] Step 1:

[0257] Users access a dedicated application on their smartphone and enter their fitness goals and physical information.

[0258] Input: Fitness goals (e.g., weight loss, muscle building), physical information (e.g., age, weight, height, body fat percentage, etc.)

[0259] Output: The input data is saved in the application.

[0260] Specific operation: The user enters the required information using the input form within the app and presses the submit button.

[0261] Step 2:

[0262] The terminal converts the information entered by the user into JSON format and sends it to the server.

[0263] Input: User-entered fitness goals and physical information

[0264] Output: JSON format data is sent to the server

[0265] Specific behavior: The application converts input data into JSON format and sends it to the server using an HTTP request.

[0266] Step 3:

[0267] The server parses the request received as JSON and retrieves the user's fitness goals and physical information.

[0268] Input: User data in JSON format

[0269] Output: Fitness goals and body information captured

[0270] What happens: The server receives the HTTP request and parses the data using a JSON parser.

[0271] Step 4:

[0272] The server uses the generative AI model to generate optimal nutritional advice and meal plans based on the user's fitness goals and physical information.

[0273] Input: Fitness goals and physical information

[0274] Output: Nutrition advice and meal plans

[0275] How it works: The server inputs the user's data into a generative AI model to generate training programs and nutritional advice.

[0276] Step 5:

[0277] Based on the generated meal plan, the server calls the API of a partner food delivery service and automatically orders the corresponding meal menu.

[0278] Enter: Nutritional advice and meal plans

[0279] Output: An order request to a food delivery service

[0280] Specific operation: The server calls the food delivery service's API and sends the order details.

[0281] Step 6:

[0282] The server converts the order details and nutrition advice back into JSON format and sends it to the user's terminal.

[0283] Input: Order details and nutrition advice

[0284] Output: JSON format data is sent to the user's device.

[0285] Specific operation: The server compiles the order results and nutrition advice and sends them to the user's terminal via an HTTP response.

[0286] Step 7:

[0287] The user terminal analyzes the received data and displays the order details and nutritional advice on a dedicated screen.

[0288] Input: Order details and nutrition advice in JSON format

[0289] Output: Order details and nutrition advice displayed on a dedicated screen

[0290] What happens: The application parses the JSON data and displays it in the user interface.

[0291] Step 8:

[0292] Users provide feedback through a dedicated screen.

[0293] Input: Feedback content (e.g., satisfaction, changes in physical condition)

[0294] Output: Feedback is sent to the server

[0295] Specific operation: The user enters their status and opinions using the feedback form within the app and submits it.

[0296] 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.

[0297] System Configuration

[0298] The present invention combines a system that provides customized training programs and nutritional advice based on a user's fitness goals and physical information with an emotion engine that recognizes the user's emotions. The system mainly consists of a user's device, a server, a generative AI model, and an emotion engine.

[0299] Program processing explanation

[0300] 1. User Input

[0301] Users access a dedicated website or mobile app and enter their fitness goals (e.g., building muscle, losing weight, improving endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[0302] 2. Transmission of information

[0303] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server.

[0304] 3. Receiving a Request

[0305] The server parses the received POST request and obtains the user's fitness goals and physical information.

[0306] 4. Training program generation

[0307] The server uses a generative AI model to generate an optimal training program based on the user's information.

[0308] Specifically, the system processes the user's goals and physical information as input data and generates detailed training content, such as "15 push-ups x 3 sets."

[0309] 5. Nutrition advice generation

[0310] The server similarly uses the generative AI model to generate nutritional advice tailored to the user.

[0311] For example, if a user's fitness goal is to "lose weight," a low-calorie, high-protein meal plan is suggested.

[0312] 6. Acquiring Emotion Data

[0313] The device runs an emotion engine to read emotions from the user's facial expressions, voice, and input text.

[0314] For example, analyzing a user's emotions through a webcam or microphone.

[0315] 7. Emotional Data Transmission

[0316] The device transmits the analyzed emotion data to the server.

[0317] 8. Submitting the results

[0318] The server compiles the generated training program, nutritional advice, and emotional data into a JSON-formatted response and sends it to the device.

[0319] 9. Displaying the results

[0320] The device analyzes the responses it receives and displays training programs and nutritional advice on a dedicated chat screen.

[0321] 10. Feedback

[0322] Users can report their training progress, changes in their physical condition, and their emotions through a dedicated chat screen.

[0323] 11. Processing Feedback

[0324] The server analyzes the feedback it receives and uses generative AI models and an emotion engine to direct adjustments to training programs and nutritional advice.

[0325] For example, if a user reports that "today's training was tough" and the emotion engine simultaneously detects a decline in the user's motivation, the system will either change the training content to something lighter or provide feedback to increase motivation.

[0326] 12. Provision of Adjusted Results

[0327] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device.

[0328] 13. Redisplay

[0329] The terminal displays the adjusted information on a dedicated chat screen and provides it to the user.

[0330] Specific examples

[0331] 1. Input example

[0332] The user inputs his / her fitness goal and physical information: "25 years old, weighs 70 kg, and wants to build muscle."

[0333] 2. Generation example

[0334] The server receives the user's information and uses a generative AI model to generate a training program of "3 sets of 15 push-ups" and nutritional advice of "oats and fruit for breakfast, chicken salad for lunch."

[0335] 3. Emotion recognition example

[0336] The emotion engine recognizes from the user's facial expressions and voice that the user is "motivated."

[0337] Based on this emotional information, the server generates additional encouraging messages to further motivate the user.

[0338] 4. Feedback Example

[0339] The user reports that "my knee hurt during training today" and looks depressed.

[0340] The server receives feedback and emotional data and suggests alternative exercises that put less strain on the knees.

[0341] By combining an emotion engine, the present invention can provide more personalized fitness guidance based on the user's emotional state, improving user motivation and satisfaction.

[0342] The processing flow will be explained below.

[0343] Step 1:

[0344] Users access a dedicated website or mobile app and click the "Start Training" button.

[0345] Step 2:

[0346] Users input their fitness goals (e.g., build muscle, lose weight, improve endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[0347] Step 3:

[0348] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server.

[0349] Step 4:

[0350] The server parses the received POST request and obtains the user's fitness goals and physical information.

[0351] Step 5:

[0352] The server calls the generative AI model and instructs it to generate a training program using the user's information as input. Specifically, it generates a customized exercise plan (e.g., "3 sets of 15 push-ups") based on the user's goals and physical information.

[0353] Step 6:

[0354] The server then calls the generative AI model again to generate customized nutrition advice based on the user's information, such as a meal plan like "oats and fruit for breakfast, chicken salad for lunch," taking into account the user's goals and physical information.

[0355] Step 7:

[0356] The device runs an emotion engine to read emotions from the user's facial expressions, voice, and input text. For example, it uses a webcam and microphone to detect the user's emotional state (e.g., joy, sadness, fatigue, etc.).

[0357] Step 8:

[0358] The device transmits the analyzed emotion data to the server.

[0359] Step 9:

[0360] The server compiles the generated training program, nutritional advice, and emotional data into a JSON-formatted response and sends it to the device.

[0361] Step 10:

[0362] The device analyzes the responses and displays training programs and nutritional advice on a dedicated chat screen, such as "3 sets of 15 push-ups" and "Oats and fruit for breakfast, chicken salad for lunch."

[0363] Step 11:

[0364] Users can report their training progress, changes in their physical condition, and their own emotions through a dedicated chat screen, for example, by providing feedback such as, "Today, my whole body feels tired."

[0365] Step 12:

[0366] The terminal transmits the feedback from the user to the server.

[0367] Step 13:

[0368] The server analyzes the received feedback and uses a generative AI model and emotion engine to direct adjustments to training programs and nutrition advice. For example, if a user reports feeling "tired all over," the emotion engine will detect the user's stress and fatigue and generate a lighter exercise program.

[0369] Step 14:

[0370] The generative AI model generates appropriately tailored training programs and nutritional advice based on the feedback and emotional data, and returns the results to the server.

[0371] Step 15:

[0372] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device.

[0373] Step 16:

[0374] The device displays the adjusted information on a dedicated chat screen and provides it to the user, for example, suggesting a new training program such as "Do 15 minutes of light stretching today."

[0375] The above are the specific processing steps of the invention that combines the emotion engine, which can effectively support the user in achieving their fitness goals and increasing their motivation.

[0376] Example 2

[0377] 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."

[0378] While conventional fitness systems provide customized training programs and nutritional advice based on a user's fitness goals and physical information, they lack the ability to provide personalized guidance that takes into account the user's emotional state. As a result, they lack the support to motivate users and encourage them to continue fitness.

[0379] 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.

[0380] In this invention, the server includes: means for receiving fitness goals and physical information from a user; means for transmitting the user's fitness goals and physical information from a terminal to the server; means for generating a customized training program using a generative AI model based on the user's fitness goals and physical information; means for generating customized nutritional advice using the generative AI model based on the user's fitness goals and physical information; means for operating an emotion engine that analyzes the user's emotions and acquiring emotion data; means for providing the customized training program and nutritional advice to the user; means for receiving feedback from the user regarding progress in the training program and changes in physical condition and adjusting the training program and nutritional advice based on the feedback and emotion data; and means for re-providing the adjusted training program and nutritional advice to the user. This enables more personalized fitness guidance based on the user's emotional state, maintaining user motivation and improving satisfaction.

[0381] "User" refers to an individual who utilizes the system to input fitness goals and physical information and receive customized training programs and nutritional advice.

[0382] "Fitness goal" refers to a physical goal a user wishes to achieve (e.g., building muscle, losing weight, improving endurance, etc.).

[0383] "Physical information" refers to information necessary for customizing a fitness program, such as a user's age, weight, height, and body fat percentage.

[0384] "Terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) through which a user inputs fitness goals and physical information and communicates with a server.

[0385] "Server" refers to a computer system that receives user input information, uses a generative AI model to generate training programs and nutritional advice, and provides them to the user.

[0386] "Generative AI Model" refers to an artificial intelligence model that automatically generates customized training programs and nutritional advice based on input user information.

[0387] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[0388] "Training Program" refers to the specific exercise content generated by the generative AI model based on the user's fitness goals and physical information.

[0389] "Nutrition Advice" refers to dietary guidance generated by the generative AI model based on the user's fitness goals and physical information.

[0390] "Emotion engine" refers to software or hardware for analyzing emotions from a user's facial expressions, voice, and input text.

[0391] "Emotion data" refers to information about the user's emotional state obtained as a result of analysis by the emotion engine.

[0392] "Feedback" refers to information that users report through a dedicated chat screen about their training progress, changes in physical condition, and their emotions.

[0393] "Adjustment" refers to restructuring training programs and nutrition advice based on user feedback and sentiment data.

[0394] The present invention is a system that provides a user with a customized training program and nutritional advice based on their fitness goals and physical information, and further combines it with an emotion engine that analyzes the user's emotions. Specific methods for implementing the invention are described below.

[0395] The system mainly consists of a user's device, a server, a generative AI model, and an emotion engine. The user uses the device to input their fitness goals and physical information.

[0396] A user accesses a dedicated website or mobile app and logs in. The user selects their fitness goal (e.g., muscle building, weight loss, endurance improvement, etc.) and enters their physical information (age, weight, height, body fat percentage, etc.) into a form. For example, the user might enter information such as "25 years old, weight 70 kg, muscle building."

[0397] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server as an HTTP POST request, which transmits the user information to the server.

[0398] The server parses the POST request and extracts the user's fitness goals and physical information, such as "age = 25," "weight = 70," and "goal = 'muscle_gain'."

[0399] The server inputs a prompt based on user information to the generative AI model. For example, a prompt such as "I'm 25 years old, weigh 70 kg, and want to build a lot of muscle. What kind of training program would be suitable?" is used. This causes the generative AI model to output a training program such as "15 push-ups x 3 sets."

[0400] Similarly, to generate nutrition advice, the server inputs a prompt to the generative AI model, such as "What is a good nutrition plan for a 25-year-old male to build muscle?", which then outputs the advice "Oats and fruit for breakfast, chicken salad for lunch."

[0401] Next, the device activates an emotion engine to read emotions from the user's facial expressions, voice, and input text. For example, the device may analyze the user's facial expressions and voice using a webcam or microphone, and the emotion engine may obtain emotion data such as "motivated."

[0402] The device sends the analyzed emotional data to the server, which then generates prompts based on the received emotional data and uses the generative AI model to provide feedback that motivates the user. For example, based on emotional data such as "I'm full of motivation," the server can generate an encouraging message such as "Do your best today!"

[0403] Users train and report their progress and changes in their physical condition via their device. For example, they can send feedback such as, "My knees hurt during today's training." The server analyzes this feedback and, using an emotion engine and generative AI model, suggests alternative exercises that put less strain on the knees.

[0404] For example, a prompt such as "Please suggest another exercise that puts less strain on the knees" can be input into a generative AI model, which will output a new training program such as "10 squats x 3 sets."

[0405] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device. The device analyzes this and displays the new training program and nutritional advice on a dedicated chat screen. For example, it might display "New training program: 3 sets of 10 squats. New nutritional advice: Protein shake for breakfast, chicken salad for lunch."

[0406] In this way, the present invention can provide more personalized fitness instruction based on the user's emotional state, maintaining user motivation and increasing satisfaction.

[0407] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0408] Step 1:

[0409] A user accesses a dedicated website or mobile app and logs in. Here, the user enters their fitness goals (e.g., muscle building, weight loss, endurance improvement, etc.) and physical information (age, weight, height, body fat percentage, etc.) into a form. For example, the user provides information such as "25 years old, weight 70 kg, muscle building." This is the input data. The device converts this input data into JSON format. Specifically, it generates the following JSON data:

[0410] json

[0411] {

[0412] "age": 25,

[0413] "weight": 70,

[0414] "goal": "muscle_gain"

[0415] }

[0416] Step 2:

[0417] The device sends the converted JSON data to the server as an HTTP POST request. This is the output data and is transferred to the server. Specifically, the device sends the data as an HTTP request.

[0418] Step 3:

[0419] The server analyzes the received POST request and extracts the user's fitness goals and physical information. The input data is the JSON data sent from the device, which is analyzed to obtain extracted data such as "age = 25", "weight = 70", and "goal = 'muscle_gain'". This is the output data. Specifically, the server analyzes the JSON data and stores the necessary information in variables.

[0420] Step 4:

[0421] The server uses the extracted information to generate a training program using a generative AI model. The input data includes the extracted "age = 25," "weight = 70," and "goal = 'muscle_gain'." The server converts this into a prompt and inputs it into the generative AI model. Specifically, the prompt used is "I'm 25 years old, weigh 70 kg, and would like to gain a lot of muscle. What kind of training program would be suitable for me?" The output data is a training program such as "15 push-ups x 3 sets."

[0422] Step 5:

[0423] The server uses the generative AI model to generate nutritional advice appropriate for the user. The input data is the user's fitness goals and physical information. Based on this, the server inputs a prompt such as "What is a suitable nutrition plan for a 25-year-old male to build muscle?" into the generative AI model. The output data is nutritional advice such as "Oats and fruit for breakfast, chicken salad for lunch."

[0424] Step 6:

[0425] The device operates an emotion engine to read emotions from the user's facial expressions, voice, and input text. The input data is sensory data such as the user's facial expressions, voice, and text. Specifically, the device captures this sensory data through a webcam or microphone and analyzes it with the emotion engine. Emotional data such as "motivated" is obtained as output data.

[0426] Step 7:

[0427] The device converts the analyzed emotion data into JSON format and sends it to the server. The input data is emotion data analyzed by the emotion engine, and includes emotions such as "motivated." Specifically, the device converts this emotion data into JSON format and sends it to the server as an HTTP POST request. The following JSON data is generated as output data:

[0428] json

[0429] {

[0430] "emotion": "motivated"

[0431] }

[0432] Step 8:

[0433] The server compiles the generated training program, nutritional advice, and emotional data into a JSON-formatted response and sends it to the device. The input data includes the generated training program, nutritional advice, and emotional data. Specifically, the server compiles this data, converts it into JSON format, and sends it to the device as an HTTP response. The following JSON response is generated as output data:

[0434] json

[0435] {

[0436] "training_program": "15 push-ups x 3 sets",

[0437] "nutrition_advice": "Oats and fruit for breakfast, chicken salad for lunch",

[0438] "emotion": "motivated"

[0439] }

[0440] Step 9:

[0441] The device analyzes the received response and displays a training program and nutritional advice on a dedicated chat screen. The input data is the JSON response sent from the server. Specifically, the device analyzes this response and displays on the chat screen, "Training program: 15 push-ups x 3 sets. Nutritional advice: Oats and fruit for breakfast, chicken salad for lunch."

[0442] Step 10:

[0443] Users report their training progress, changes in their physical condition, and their own emotions through a dedicated chat screen. The input data is feedback information entered by the user (e.g., "My knee hurt during today's training"). Specific actions involve the user entering feedback into the chat screen.

[0444] Step 11:

[0445] The server uses a generative AI model and emotion engine to adjust the training program and nutrition advice based on the received feedback and emotion data. The input data is the user's feedback information and emotion data. Specifically, the server inputs a prompt such as "Please suggest another exercise that puts less strain on the knees" into the generative AI model and outputs a new training program such as "10 squats x 3 sets."

[0446] Step 12:

[0447] The server compiles the adjusted training program and nutrition advice into a JSON format response and sends it to the device. The input data is the adjusted training program and nutrition advice. Specifically, the server compiles this data into JSON format and sends it to the device as an HTTP response. The following JSON response is generated as output data:

[0448] json

[0449] {

[0450] "training_program": "10 squats x 3 sets",

[0451] "nutrition_advice": "Protein shake for breakfast, chicken salad for lunch"

[0452] }

[0453] Step 13:

[0454] The device displays the adjusted information on a dedicated chat screen and provides it to the user. The input data is the JSON response sent from the server. Specifically, the device analyzes this response and displays on the chat screen, "New training program: 3 sets of 10 squats. New nutrition advice: Protein shake for breakfast, chicken salad for lunch."

[0455] (Application example 2)

[0456] 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."

[0457] Conventional training programs and nutrition advice are customized based on the user's physical information and fitness goals, but they cannot take into account the user's emotional state, and have the problem of not being able to appropriately respond to users' declining motivation or fatigue.In addition, it is difficult to provide individual support to factory workers to improve their work efficiency, so there is a need to optimize work plans based on the workers' health status and motivation.

[0458] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving fitness goals and physical information from a user, means for generating a customized training program based on the user's fitness goals and physical information, means for generating customized nutritional advice based on the user's fitness goals and physical information, means for analyzing the user's emotional state from facial expressions and voice, means for providing the customized training program and nutritional advice to the user, and means for adjusting the training program and nutritional advice based on feedback on progress in the training program and changes in physical condition and the user's emotional state. This makes it possible to provide an individually optimized training program and nutritional advice that takes the user's emotional state into consideration.

[0459] A "fitness goal" is a physical goal or objective that a user wishes to achieve.

[0460] "Physical information" refers to physical data such as the user's age, weight, height, and body fat percentage.

[0461] A "training program" is an exercise plan created based on a user's fitness goals and physical information.

[0462] "Nutrition Advice" refers to dietary and nutritional guidelines recommended based on a user's fitness goals and physical information.

[0463] "Emotional state" refers to the mental state or mood of the user that is analyzed from facial expressions and voice.

[0464] "Means of analysis" refers to methods or devices for analyzing data and deriving specific results or information.

[0465] "Feedback" refers to reports on changes in the user's physical condition and training progress.

[0466] "Adjusting means" refers to a method or device for receiving feedback and reconfiguring training programs or nutritional advice.

[0467] The present invention is a system for supporting the improvement of work efficiency and health management of factory workers, and provides optimal work schedules and nutritional advice based on feedback including the worker's emotional state.

[0468] System Configuration

[0469] This system receives the user's (factory worker's) fitness goals and physical information, and combines it with an emotion engine that analyzes the user's emotional state from facial expressions and voice. The system mainly consists of the following components:

[0470] Terminal: Sensor devices such as cameras and voice recognition microphones installed on factory robots

[0471] Server: a central processing unit that processes data

[0472] Generative AI Models: Artificial Intelligence Models for Generating Training Programs and Nutritional Advice

[0473] Emotion engine: An engine that analyzes the worker's facial expression and voice data to estimate their emotional state

[0474] Program processing explanation

[0475] 1. User Input

[0476] During the initial setup, the user (worker) enters their age, weight, goals for improving work efficiency, and other physical information.

[0477] 2. Transmission of information

[0478] The terminal (factory robot) sends the information entered by the user to the server.

[0479] 3. Acquiring Emotion Data

[0480] The terminal (factory robot) uses a camera and a voice recognition microphone to collect the worker's facial expressions and voice, which are then analyzed using an emotion engine.

[0481] 4. Sending analysis results

[0482] The device transmits the analyzed emotion data to the server.

[0483] 5. Generating training programs and nutritional advice

[0484] The server uses the generative AI model to generate optimal training programs (work schedules) and nutritional advice based on the user's physical information, goals, and emotional state.

[0485] 6. Sending and Displaying Results

[0486] The server sends the generated data to the terminal, which displays the results to the user.

[0487] 7. Feedback and Adjustments

[0488] Users report their training progress and changes in their physical condition, and the device sends this feedback to the server, which again uses the generative AI model and emotion engine to adjust the training program and nutrition advice.

[0489] Hardware and software used

[0490] Camera and voice recognition microphone: Collects facial and voice data from workers.

[0491] Sensor device: Measures workers' physical condition information.

[0492] Emotion engine: Uses Python libraries and emotion recognition APIs (e.g., OpenCV, DeepFace).

[0493] Generative AI models: Generative AI models use natural language processing and machine learning models (e.g., GPT).

[0494] Server: Cloud-based data processing (e.g., AWS, Google Cloud).

[0495] Specific examples

[0496] Example: The emotion engine recognizes that Worker A is "fatigued" and "unmotivated." The generative AI model suggests schedule changes such as "increasing break time" and provides nutritional advice such as "eat bananas and nuts to replenish energy."

[0497] Example prompt sentence:

[0498] Worker's age: 30, weight: 75kg, emotional state: fatigue, motivation: low

[0499] Generate optimal work schedules and nutritional advice to improve worker health.

[0500] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0501] Step 1:

[0502] User Input

[0503] During the initial setup, users enter their fitness goals and physical information, such as age, weight, and work efficiency improvement, into the device. This input data is converted into JSON format, which is used to send the user's basic information and goals to the server.

[0504] Step 2:

[0505] Sending information

[0506] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server. The input data (user information and goals) is sent to the server.

[0507] Step 3:

[0508] Acquiring emotion data

[0509] The terminal (factory robot) uses a camera and a voice recognition microphone to collect the worker's facial expressions and voice. This collected data is analyzed through an emotion engine to determine the worker's emotional state. The input data is image data and voice data, and the output data is the worker's emotional state.

[0510] Step 4:

[0511] Sending emotional data

[0512] The device sends the analyzed emotion data to the server. The input data (emotion data) is sent to the server, and the analysis results from the emotion engine are compiled.

[0513] Step 5:

[0514] Generate training programs and nutritional advice

[0515] The server uses a generative AI model to generate optimal training programs and nutritional advice based on the user's physical information, goals, and emotional state. This process involves natural language processing and machine learning to process the data and generate specific training and meal plans. The input data is physical information, fitness goals, and emotional data, and the output data is the training program and nutritional advice.

[0516] Step 6:

[0517] Sending and viewing results

[0518] The server sends the generated training program and nutrition advice to the terminal, which receives it and displays the results to the user. The displayed results are the adjusted training program and nutrition advice.

[0519] Step 7:

[0520] Feedback and Adjustments

[0521] Users report their training progress and changes in their physical condition, and the device sends this feedback to the server. The server uses a generative AI model and emotion engine to adjust the training program and nutritional advice, and then sends it back to the device. In this process, user feedback is collected and the training program and nutritional advice are adjusted accordingly.

[0522] 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.

[0523] 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.

[0524] 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.

[0525] [Second embodiment]

[0526] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0527] 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.

[0528] 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).

[0529] 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.

[0530] 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.

[0531] 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).

[0532] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0533] 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.

[0534] 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.

[0535] 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.

[0536] 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.

[0537] 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."

[0538] System Configuration

[0539] The present invention includes a system that provides customized training programs and nutritional advice based on a user's fitness goals and physical information. The system mainly consists of a user terminal, a server, and a generative AI model.

[0540] Program processing explanation

[0541] 1. User Input

[0542] Users access a dedicated website or mobile app and enter their fitness goals (e.g., building muscle, losing weight, improving endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[0543] 2. Transmission of information

[0544] The terminal converts the entered user information into JSON format and sends it to the server.

[0545] 3. Receiving a Request

[0546] The server analyzes the received request and obtains the user's fitness goals and physical information.

[0547] 4. Training program generation

[0548] The server uses a generative AI model to generate an optimal training program based on the user's information.

[0549] Specifically, the system processes the user's goals and physical information as input data and generates detailed training content, such as "15 push-ups x 3 sets."

[0550] 5. Nutrition advice generation

[0551] The server similarly uses the generative AI model to generate nutritional advice tailored to the user.

[0552] For example, if a user's fitness goal is to "lose weight," a low-calorie, high-protein meal plan is suggested.

[0553] 6. Submitting the results

[0554] The server compiles the generated training program and nutritional advice into a JSON-formatted response and sends it to the user's device.

[0555] 7. Displaying the results

[0556] The device analyzes the responses it receives and displays training programs and nutritional advice on a dedicated chat screen.

[0557] 8. Feedback

[0558] Users report their training progress and changes in their physical condition to the server via a dedicated chat screen.

[0559] 9. Processing Feedback

[0560] Based on the feedback received, the server again uses the generative AI model to adjust the training program and nutrition advice.

[0561] For example, if a user reports knee pain, other low-impact exercises may be suggested instead of squats.

[0562] 10. Providing adjusted results

[0563] The server sends the adjusted training program and nutrition advice back to the user's terminal, which displays it.

[0564] Specific examples

[0565] 1. Input example

[0566] The user inputs his / her fitness goal and physical information: "25 years old, weighs 70 kg, and wants to build muscle."

[0567] 2. Generation example

[0568] The server receives the user's information and uses a generative AI model to generate a training program of "3 sets of 15 push-ups" and nutritional advice of "oats and fruit for breakfast, chicken salad for lunch."

[0569] 3. Feedback Examples

[0570] A user reports, "My knee hurt during my workout today."

[0571] The server receives feedback and suggests alternative exercises that put less strain on the knees.

[0572] As described above, the present invention provides a system that quickly and appropriately provides individualized training programs and nutritional advice based on user input, helping users achieve their fitness goals.

[0573] The processing flow will be explained below.

[0574] Step 1:

[0575] Users access a dedicated website or mobile app and click the "Start Training" button.

[0576] Step 2:

[0577] Users input their fitness goals (e.g., build muscle, lose weight, improve endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[0578] Step 3:

[0579] The device converts the fitness goals and physical information entered by the user into JSON format.

[0580] Step 4:

[0581] The terminal sends user information in JSON format to the server as a POST request.

[0582] Step 5:

[0583] The server parses the received POST request and obtains the user's fitness goals and physical information.

[0584] Step 6:

[0585] The server calls the generative AI model and instructs it to generate a training program using the user's information as input data.

[0586] Step 7:

[0587] The generative AI model generates a customized training program based on the user information and returns the results to the server.

[0588] Step 8:

[0589] The server then invokes the generative AI model again, this time instructing it to generate customized nutritional advice.

[0590] Step 9:

[0591] The generative AI model generates nutritional advice based on user information and returns the results to the server.

[0592] Step 10:

[0593] The server compiles the training program and nutrition advice into a JSON-formatted response and sends it to the device.

[0594] Step 11:

[0595] The device analyzes the response received from the server and displays the training program and nutritional advice on a dedicated chat screen.

[0596] Step 12:

[0597] Users can report their training progress and changes in their physical condition through a dedicated chat screen.

[0598] Step 13:

[0599] The terminal transmits the feedback from the user to the server.

[0600] Step 14:

[0601] The server analyzes the feedback it receives and uses generative AI models to direct adjustments to training programs and nutritional advice.

[0602] Step 15:

[0603] Based on the feedback, the generative AI model generates appropriately adjusted training programs and nutritional advice and returns the results to the server.

[0604] Step 16:

[0605] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device.

[0606] Step 17:

[0607] The terminal displays the adjusted information on a dedicated chat screen and provides it to the user.

[0608] Example 1

[0609] 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."

[0610] Currently, many fitness program and nutrition advice systems only provide general information and are not sufficiently customized to each user's physical information and fitness goals. Furthermore, it is difficult to provide dynamic training programs and nutrition advice that reflect user feedback. Therefore, there is a need for a system that can provide training programs and nutrition advice optimized for each user and flexibly adjust them based on feedback.

[0611] 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.

[0612] In this invention, the server includes means for receiving fitness goals and physical information from a user, means for converting the user's fitness goals and physical information into a data format and sending it to the server, means for generating a customized training program using a generative AI model based on the user's fitness goals and physical information, means for generating customized nutritional advice using the generative AI model based on the user's fitness goals and physical information, means for converting the customized training program and nutritional advice into a data format and providing it to the user, and means for receiving feedback from the user regarding progress in the training program and changes in physical condition and adjusting the training program and nutritional advice based on the feedback, thereby making it possible to provide an optimal training program and nutritional advice tailored to the user's individual needs and flexibly respond to the feedback.

[0613] "User" refers to the individual or end user who inputs fitness goals and physical information.

[0614] "Fitness goal" refers to a physical goal a user wishes to achieve (e.g., building muscle, losing weight, improving endurance, etc.).

[0615] "Physical information" refers to the user's individual physical characteristics (e.g., age, weight, height, body fat percentage, etc.).

[0616] "Data format" refers to a format (e.g., JSON format) that structures information entered by a user and converts it into a form that can be handled as digital data.

[0617] "Server" refers to the computer system that analyzes the data received from the User and utilizes the generative AI model to generate training programs and nutritional advice.

[0618] "Generative AI model" refers to an artificial intelligence model that is trained on large amounts of data and generates optimal training programs and nutritional advice based on user information.

[0619] "Customized training program" refers to a specific exercise plan tailored to an individual user based on their fitness goals and physical information.

[0620] "Customized nutrition advice" refers to a meal plan that is tailored based on an individual user's fitness goals and physical information.

[0621] "Feedback" refers to the act of the user providing the system with information about the progress of training and changes in physical condition.

[0622] "Adjustment" refers to the process of reevaluating and adapting existing training programs and nutritional advice based on feedback received.

[0623] MODE FOR CARRYING OUT THE INVENTION

[0624] This invention describes a concrete implementation of a system that provides customized training programs and nutritional advice based on a user's fitness goals and physical information. The entire system mainly consists of a user terminal, a server, and a generative AI model.

[0625] 1. User Input

[0626] Users access the system through a dedicated website or mobile app. The application runs on popular platforms such as iOS and Android. Users enter their fitness goals and physical information. For example, if a 25-year-old user weighs 70 kg and wants to build muscle, they can enter that information.

[0627] 2. Transmission of information

[0628] The device converts the information entered by the user into JSON format and sends it to the server using Internet Protocol. The JSON format data includes fitness goals and physical information. For example, it might look like this:

[0629] json

[0630] {

[0631] "age": 25,

[0632] "weight": 70,

[0633] "goal": "muscle_gain"

[0634] }

[0635] 3. Receiving a Request

[0636] The server parses the received request to obtain the user's fitness goals and physical information, which involves parsing the data to extract keys and values.

[0637] 4. Training program generation

[0638] The server uses a generative AI model (e.g., GPT-3) to generate an optimal training program based on the user's information. Specifically, the user's data is input to the generative AI model as a prompt sentence like the following:

[0639] User information: 25 years old, weight 70kg, goal: muscle building. Please provide a suitable training program for the user.

[0640] Based on this prompt, the generative AI model generates specific training content such as "15 push-ups x 3 sets."

[0641] 5. Nutrition advice generation

[0642] The server uses the same generative AI model to generate nutrition advice tailored to the user, using prompts like:

[0643] User information: 25 years old, weight 70kg, goal: to build muscle. Please provide a suitable nutrition plan for the user.

[0644] Based on this prompt, the generative AI model generates nutritional advice such as "oats and fruit for breakfast, chicken salad for lunch."

[0645] 6. Submitting the results

[0646] The server then compiles the generated training program and nutrition advice into a JSON response and sends it to the user's device, for example in the following JSON format:

[0647] json

[0648] {

[0649] "training_program": "3 sets of 15 push-ups",

[0650] "nutrition_advice": "Oats and fruit for breakfast, chicken salad for lunch"

[0651] }

[0652] 7. Displaying the results

[0653] The device analyzes the received response and displays the training program and nutrition advice on a dedicated chat screen. This analysis process includes parsing the JSON of the response and preparing it for display in the GUI.

[0654] 8. Feedback

[0655] Users can report their training progress and changes in their physical condition to the server via a dedicated chat screen. For example, they can write, "My knee started hurting during today's training."

[0656] 9. Processing Feedback

[0657] The server analyzes the received feedback and determines the appropriate response. For example, if the user feedback is "knee pain," it will again use the generative AI model to generate a new training program. The prompt text is as follows:

[0658] User information: Age 25, Weight 70kg, Goal: Build muscle. User reported knee pain. Provide alternative exercises that are less stressful on the knees.

[0659] 10. Providing adjusted results

[0660] The server then compiles the adjusted training program and nutrition advice into a JSON response and sends it to the user's device, which then displays the new information on the chat screen.

[0661] The invention allows users to receive customized training programs and nutritional advice tailored to their fitness goals, with the flexibility to adjust based on feedback.

[0662] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0663] Step 1: User enters fitness goals and physical information

[0664] Users access a dedicated website or mobile app and enter their fitness goals (e.g., muscle building, weight loss, endurance improvement) and physical information (e.g., age, weight, height, body fat percentage), which is then prepared as data to be sent to the system.

[0665] Input: Fitness goals and physical information (age, weight, height, body fat percentage, etc.)

[0666] Output: Input data converted to JSON format

[0667] Step 2: The device sends the user information

[0668] The device converts the information entered by the user into JSON format and sends it to the server using Internet Protocol, with the data transmitted over a secure communication channel.

[0669] Input: User information in JSON format

[0670] Output: User information sent to the server

[0671] Step 3: The server receives and analyzes the request

[0672] The server analyzes the received request to obtain the user's fitness goals and physical information. The analysis process involves parsing the received data to extract keys and values.

[0673] Input: JSON format user information received by the server

[0674] Output: Parsed fitness goals and body information

[0675] Step 4: The server generates a training program using the generated AI model

[0676] The server uses a generative AI model (e.g., GPT-3) to generate an optimal training program based on the parsed user information. The server inputs the following prompt to the generative AI model:

[0677] User information: 25 years old, weight 70kg, goal: muscle building. Please provide a suitable training program for the user.

[0678] Input: Fitness goal and physical information, prompt

[0679] Output: Generated training program (e.g., "3 sets of 15 push-ups")

[0680] Step 5: The server uses the generative AI model to generate nutrition advice

[0681] The server also uses a generative AI model to generate nutrition advice tailored to the user, using prompts like:

[0682] User information: 25 years old, weight 70kg, goal: to build muscle. Please provide a suitable nutrition plan for the user.

[0683] Input: Fitness goal and physical information, prompt

[0684] Output: Generated nutrition advice (e.g. "Oats and fruit for breakfast, chicken salad for lunch")

[0685] Step 6: Server sends results

[0686] The server then compiles the generated training program and nutrition advice into a JSON response and sends it to the user's device, for example in the following JSON format:

[0687] json

[0688] {

[0689] "training_program": "3 sets of 15 push-ups",

[0690] "nutrition_advice": "Oats and fruit for breakfast, chicken salad for lunch"

[0691] }

[0692] Input: Generated training programs and nutrition advice

[0693] Output: Sent to the terminal as a JSON response

[0694] Step 7: Your device will display the results

[0695] The device analyzes the received response and displays the training program and nutrition advice on a dedicated chat screen. This analysis process includes parsing the JSON of the response and preparing it for display in the GUI.

[0696] Input: JSON response (training program and nutrition advice)

[0697] Output: Training program and nutrition advice displayed on the chat screen

[0698] Step 8: User enters feedback

[0699] Users can report their training progress and changes in their physical condition to the server via a dedicated chat screen. For example, they can write, "My knee started hurting during today's training."

[0700] Input: Feedback on your training progress and changes in your fitness

[0701] Output: Information sent to the server as feedback

[0702] Step 9: Server processes feedback

[0703] The server analyzes the received feedback and determines the appropriate response. For example, if the user feedback is "knee pain," it will again use the generative AI model to generate a new training program. The prompt text is as follows:

[0704] User information: Age 25, Weight 70kg, Goal: Build muscle. User reported knee pain. Provide alternative exercises that are less stressful on the knees.

[0705] Input: Feedback, prompt

[0706] Output: Tailored training program

[0707] Step 10: The server sends the adjusted results

[0708] The server then compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the user's device.

[0709] Input: tailored training programs and nutritional advice

[0710] Output: Sent to the terminal as a JSON response

[0711] Step 11: Your device will display the adjusted results.

[0712] The device then analyzes the received response and displays the adjusted training program and nutritional advice on a dedicated chat screen.

[0713] Input: JSON response (adjusted training program and nutrition advice)

[0714] Output: Adjusted training program and nutrition advice displayed on the chat screen

[0715] (Application example 1)

[0716] 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."

[0717] The present invention aims to reduce the complexity of conventional systems and improve user convenience by automatically ordering meals customized based on the physical information of each user through a food delivery service and providing the user with the order results and nutritional advice in a system that provides training programs and nutritional advice to help users achieve their fitness goals. In conventional systems, after receiving a training program and nutritional advice, the user must choose for themselves what meals to actually eat, which can be a significant burden in terms of effort and time.

[0718] 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.

[0719] In this invention, the server includes means for receiving fitness goals and physical information from a user, means for generating a customized training program based on the user's fitness goals and physical information, means for generating customized nutritional advice based on the user's fitness goals and physical information, means for providing the customized training program and nutritional advice to the user, means for receiving feedback from the user regarding progress in the training program and changes in physical condition and adjusting the training program and nutritional advice based on the feedback, means for automatically ordering meals through a food delivery service based on the nutritional advice, and means for providing the user with the order results and nutritional advice from the food delivery service, thereby enabling the user to automatically order appropriate meals based on the individual nutritional advice and more effectively support achieving their fitness goals.

[0720] A "user" is an individual who utilizes the system and inputs fitness goals and physical information.

[0721] "Fitness Goal" means a physical or health goal that a user wishes to achieve, such as losing weight, building muscle, or improving endurance.

[0722] "Physical information" refers to physical data such as the user's age, weight, height, and body fat percentage.

[0723] A "training program" is a customized exercise plan generated based on a user's fitness goals and physical information.

[0724] "Nutrition Advice" means customized meal suggestions and plans provided based on a user's fitness goals and physical information.

[0725] "Feedback" refers to information provided by a user regarding progress in a training program and changes in physical condition.

[0726] A "food delivery service" is a service that allows you to order meals online and have them delivered.

[0727] "Generative AI Model" refers to the artificial intelligence algorithms used to generate optimal training programs and nutritional advice based on user information.

[0728] "Order Result" means the confirmation information regarding a meal ordered automatically through the food delivery service.

[0729] The term "means" refers to functions or components for executing various processes in this invention.

[0730] System Configuration

[0731] The present invention is a system that provides a user with a customized training program and nutritional advice based on their fitness goals and physical information, and automatically orders appropriate meals through a food delivery service. The system consists of a user terminal, a server, and a generative AI model.

[0732] Hardware and software used

[0733] Smartphone: User device on which the app is installed

[0734] Server: Data processing and AI model hosting

[0735] Generative AI models: generating nutrition advice and meal plans

[0736] Food Delivery API: Integration for automated meal ordering

[0737] Processing Description

[0738] 1. User Input

[0739] Users access a dedicated application on their smartphone and enter their fitness goals (e.g., weight loss, muscle building, endurance improvement, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.), which then inputs data tailored to the user's individual needs.

[0740] 2. Information Transmission

[0741] The user terminal converts the information entered by the user into JSON format and sends it to the server, which receives and analyzes this data.

[0742] 3. Nutrition advice generation

[0743] The server uses the generative AI model to generate optimal nutrition advice and meal plans based on the user's fitness goals and physical information, such as providing a low-calorie, high-protein meal plan for a user aiming to lose weight.

[0744] 4. Food delivery collaboration

[0745] Based on the meal plan, the server calls the API of the partner food delivery service and automatically orders the corresponding meal menu, eliminating the need for the user to choose their own meals.

[0746] 5. Sending and displaying results

[0747] The server converts the order details and nutrition advice back into JSON format and sends it to the user's device. The user's device analyzes this data and displays it on a dedicated screen. The user can then review the order details and make any necessary changes.

[0748] Specific examples

[0749] For example, if a user enters the following information:

[0750] Example prompt sentence:

[0751] Age: 30

[0752] Weight: 80kg

[0753] Height: 175cm

[0754] Body fat percentage: 20%

[0755] Fitness Goal: Muscle Building

[0756] Based on this information, the server uses a generative AI model to generate a meal plan such as "oats and fruit for breakfast, chicken salad for lunch" and automatically places an order with a food delivery service. The ordering results and nutrition advice are sent to the user's device, where they can view them.

[0757] In this way, the present invention can provide comprehensive support to users in achieving their fitness goals.

[0758] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0759] Step 1:

[0760] Users access a dedicated application on their smartphone and enter their fitness goals and physical information.

[0761] Input: Fitness goals (e.g., weight loss, muscle building), physical information (e.g., age, weight, height, body fat percentage, etc.)

[0762] Output: The input data is saved in the application.

[0763] Specific operation: The user enters the required information using the input form within the app and presses the submit button.

[0764] Step 2:

[0765] The terminal converts the information entered by the user into JSON format and sends it to the server.

[0766] Input: User-entered fitness goals and physical information

[0767] Output: JSON format data is sent to the server

[0768] Specific behavior: The application converts input data into JSON format and sends it to the server using an HTTP request.

[0769] Step 3:

[0770] The server parses the request received as JSON and retrieves the user's fitness goals and physical information.

[0771] Input: User data in JSON format

[0772] Output: Fitness goals and body information captured

[0773] What happens: The server receives the HTTP request and parses the data using a JSON parser.

[0774] Step 4:

[0775] The server uses the generative AI model to generate optimal nutritional advice and meal plans based on the user's fitness goals and physical information.

[0776] Input: Fitness goals and physical information

[0777] Output: Nutrition advice and meal plans

[0778] How it works: The server inputs the user's data into a generative AI model to generate training programs and nutritional advice.

[0779] Step 5:

[0780] Based on the generated meal plan, the server calls the API of a partner food delivery service and automatically orders the corresponding meal menu.

[0781] Enter: Nutritional advice and meal plans

[0782] Output: An order request to a food delivery service

[0783] Specific operation: The server calls the food delivery service's API and sends the order details.

[0784] Step 6:

[0785] The server converts the order details and nutrition advice back into JSON format and sends it to the user's terminal.

[0786] Input: Order details and nutrition advice

[0787] Output: JSON format data is sent to the user's device.

[0788] Specific operation: The server compiles the order results and nutrition advice and sends them to the user's terminal via an HTTP response.

[0789] Step 7:

[0790] The user terminal analyzes the received data and displays the order details and nutritional advice on a dedicated screen.

[0791] Input: Order details and nutrition advice in JSON format

[0792] Output: Order details and nutrition advice displayed on a dedicated screen

[0793] What happens: The application parses the JSON data and displays it in the user interface.

[0794] Step 8:

[0795] Users provide feedback through a dedicated screen.

[0796] Input: Feedback content (e.g., satisfaction, changes in physical condition)

[0797] Output: Feedback is sent to the server

[0798] Specific operation: The user enters their status and opinions using the feedback form within the app and submits it.

[0799] 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.

[0800] System Configuration

[0801] The present invention combines a system that provides customized training programs and nutritional advice based on a user's fitness goals and physical information with an emotion engine that recognizes the user's emotions. The system mainly consists of a user's device, a server, a generative AI model, and an emotion engine.

[0802] Program processing explanation

[0803] 1. User Input

[0804] Users access a dedicated website or mobile app and enter their fitness goals (e.g., building muscle, losing weight, improving endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[0805] 2. Transmission of information

[0806] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server.

[0807] 3. Receiving a Request

[0808] The server parses the received POST request and obtains the user's fitness goals and physical information.

[0809] 4. Training program generation

[0810] The server uses a generative AI model to generate an optimal training program based on the user's information.

[0811] Specifically, the system processes the user's goals and physical information as input data and generates detailed training content, such as "15 push-ups x 3 sets."

[0812] 5. Nutrition advice generation

[0813] The server similarly uses the generative AI model to generate nutritional advice tailored to the user.

[0814] For example, if a user's fitness goal is to "lose weight," a low-calorie, high-protein meal plan is suggested.

[0815] 6. Acquiring Emotion Data

[0816] The device runs an emotion engine to read emotions from the user's facial expressions, voice, and input text.

[0817] For example, analyzing a user's emotions through a webcam or microphone.

[0818] 7. Emotional Data Transmission

[0819] The device transmits the analyzed emotion data to the server.

[0820] 8. Submitting the results

[0821] The server compiles the generated training program, nutritional advice, and emotional data into a JSON-formatted response and sends it to the device.

[0822] 9. Displaying the results

[0823] The device analyzes the responses it receives and displays training programs and nutritional advice on a dedicated chat screen.

[0824] 10. Feedback

[0825] Users can report their training progress, changes in their physical condition, and their emotions through a dedicated chat screen.

[0826] 11. Processing Feedback

[0827] The server analyzes the feedback it receives and uses generative AI models and an emotion engine to direct adjustments to training programs and nutritional advice.

[0828] For example, if a user reports that "today's training was tough" and the emotion engine simultaneously detects a decline in the user's motivation, the system will either change the training content to something lighter or provide feedback to increase motivation.

[0829] 12. Provision of Adjusted Results

[0830] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device.

[0831] 13. Redisplay

[0832] The terminal displays the adjusted information on a dedicated chat screen and provides it to the user.

[0833] Specific examples

[0834] 1. Input example

[0835] The user inputs his / her fitness goal and physical information: "25 years old, weighs 70 kg, and wants to build muscle."

[0836] 2. Generation example

[0837] The server receives the user's information and uses a generative AI model to generate a training program of "3 sets of 15 push-ups" and nutritional advice of "oats and fruit for breakfast, chicken salad for lunch."

[0838] 3. Emotion recognition example

[0839] The emotion engine recognizes from the user's facial expressions and voice that the user is "motivated."

[0840] Based on this emotional information, the server generates additional encouraging messages to further motivate the user.

[0841] 4. Feedback Example

[0842] The user reports that "my knee hurt during training today" and looks depressed.

[0843] The server receives feedback and emotional data and suggests alternative exercises that put less strain on the knees.

[0844] By combining an emotion engine, the present invention can provide more personalized fitness guidance based on the user's emotional state, improving user motivation and satisfaction.

[0845] The processing flow will be explained below.

[0846] Step 1:

[0847] Users access a dedicated website or mobile app and click the "Start Training" button.

[0848] Step 2:

[0849] Users input their fitness goals (e.g., build muscle, lose weight, improve endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[0850] Step 3:

[0851] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server.

[0852] Step 4:

[0853] The server parses the received POST request and obtains the user's fitness goals and physical information.

[0854] Step 5:

[0855] The server calls the generative AI model and instructs it to generate a training program using the user's information as input. Specifically, it generates a customized exercise plan (e.g., "3 sets of 15 push-ups") based on the user's goals and physical information.

[0856] Step 6:

[0857] The server then calls the generative AI model again to generate customized nutrition advice based on the user's information, such as a meal plan like "oats and fruit for breakfast, chicken salad for lunch," taking into account the user's goals and physical information.

[0858] Step 7:

[0859] The device runs an emotion engine to read emotions from the user's facial expressions, voice, and input text. For example, it uses a webcam and microphone to detect the user's emotional state (e.g., joy, sadness, fatigue, etc.).

[0860] Step 8:

[0861] The device transmits the analyzed emotion data to the server.

[0862] Step 9:

[0863] The server compiles the generated training program, nutritional advice, and emotional data into a JSON-formatted response and sends it to the device.

[0864] Step 10:

[0865] The device analyzes the responses and displays training programs and nutritional advice on a dedicated chat screen, such as "3 sets of 15 push-ups" and "Oats and fruit for breakfast, chicken salad for lunch."

[0866] Step 11:

[0867] Users can report their training progress, changes in their physical condition, and their own emotions through a dedicated chat screen, for example, by providing feedback such as, "Today, my whole body feels tired."

[0868] Step 12:

[0869] The terminal transmits the feedback from the user to the server.

[0870] Step 13:

[0871] The server analyzes the received feedback and uses a generative AI model and emotion engine to direct adjustments to training programs and nutrition advice. For example, if a user reports feeling "tired all over," the emotion engine will detect the user's stress and fatigue and generate a lighter exercise program.

[0872] Step 14:

[0873] The generative AI model generates appropriately tailored training programs and nutritional advice based on the feedback and emotional data, and returns the results to the server.

[0874] Step 15:

[0875] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device.

[0876] Step 16:

[0877] The device displays the adjusted information on a dedicated chat screen and provides it to the user, for example, suggesting a new training program such as "Do 15 minutes of light stretching today."

[0878] The above are the specific processing steps of the invention that combines the emotion engine, which can effectively support the user in achieving their fitness goals and increasing their motivation.

[0879] Example 2

[0880] 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."

[0881] While conventional fitness systems provide customized training programs and nutritional advice based on a user's fitness goals and physical information, they lack the ability to provide personalized guidance that takes into account the user's emotional state. As a result, they lack the support to motivate users and encourage them to continue fitness.

[0882] 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.

[0883] In this invention, the server includes: means for receiving fitness goals and physical information from a user; means for transmitting the user's fitness goals and physical information from a terminal to the server; means for generating a customized training program using a generative AI model based on the user's fitness goals and physical information; means for generating customized nutritional advice using the generative AI model based on the user's fitness goals and physical information; means for operating an emotion engine that analyzes the user's emotions and acquiring emotion data; means for providing the customized training program and nutritional advice to the user; means for receiving feedback from the user regarding progress in the training program and changes in physical condition and adjusting the training program and nutritional advice based on the feedback and emotion data; and means for re-providing the adjusted training program and nutritional advice to the user. This enables more personalized fitness guidance based on the user's emotional state, maintaining user motivation and improving satisfaction.

[0884] "User" refers to an individual who utilizes the system to input fitness goals and physical information and receive customized training programs and nutritional advice.

[0885] "Fitness goal" refers to a physical goal a user wishes to achieve (e.g., building muscle, losing weight, improving endurance, etc.).

[0886] "Physical information" refers to information necessary for customizing a fitness program, such as a user's age, weight, height, and body fat percentage.

[0887] "Terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) through which a user inputs fitness goals and physical information and communicates with a server.

[0888] "Server" refers to a computer system that receives user input information, uses a generative AI model to generate training programs and nutritional advice, and provides them to the user.

[0889] "Generative AI Model" refers to an artificial intelligence model that automatically generates customized training programs and nutritional advice based on input user information.

[0890] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[0891] "Training Program" refers to the specific exercise content generated by the generative AI model based on the user's fitness goals and physical information.

[0892] "Nutrition Advice" refers to dietary guidance generated by the generative AI model based on the user's fitness goals and physical information.

[0893] "Emotion engine" refers to software or hardware for analyzing emotions from a user's facial expressions, voice, and input text.

[0894] "Emotion data" refers to information about the user's emotional state obtained as a result of analysis by the emotion engine.

[0895] "Feedback" refers to information that users report through a dedicated chat screen about their training progress, changes in physical condition, and their emotions.

[0896] "Adjustment" refers to restructuring training programs and nutrition advice based on user feedback and sentiment data.

[0897] The present invention is a system that provides a user with a customized training program and nutritional advice based on their fitness goals and physical information, and further combines it with an emotion engine that analyzes the user's emotions. Specific methods for implementing the invention are described below.

[0898] The system mainly consists of a user's device, a server, a generative AI model, and an emotion engine. The user uses the device to input their fitness goals and physical information.

[0899] A user accesses a dedicated website or mobile app and logs in. The user selects their fitness goal (e.g., muscle building, weight loss, endurance improvement, etc.) and enters their physical information (age, weight, height, body fat percentage, etc.) into a form. For example, the user might enter information such as "25 years old, weight 70 kg, muscle building."

[0900] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server as an HTTP POST request, which transmits the user information to the server.

[0901] The server parses the POST request and extracts the user's fitness goals and physical information, such as "age = 25," "weight = 70," and "goal = 'muscle_gain'."

[0902] The server inputs a prompt based on user information to the generative AI model. For example, a prompt such as "I'm 25 years old, weigh 70 kg, and want to build a lot of muscle. What kind of training program would be suitable?" is used. This causes the generative AI model to output a training program such as "15 push-ups x 3 sets."

[0903] Similarly, to generate nutrition advice, the server inputs a prompt to the generative AI model, such as "What is a good nutrition plan for a 25-year-old male to build muscle?", which then outputs the advice "Oats and fruit for breakfast, chicken salad for lunch."

[0904] Next, the device activates an emotion engine to read emotions from the user's facial expressions, voice, and input text. For example, the device may analyze the user's facial expressions and voice using a webcam or microphone, and the emotion engine may obtain emotion data such as "motivated."

[0905] The device sends the analyzed emotional data to the server, which then generates prompts based on the received emotional data and uses the generative AI model to provide feedback that motivates the user. For example, based on emotional data such as "I'm full of motivation," the server can generate an encouraging message such as "Do your best today!"

[0906] Users train and report their progress and changes in their physical condition via their device. For example, they can send feedback such as, "My knees hurt during today's training." The server analyzes this feedback and, using an emotion engine and generative AI model, suggests alternative exercises that put less strain on the knees.

[0907] For example, a prompt such as "Please suggest another exercise that puts less strain on the knees" can be input into a generative AI model, which will output a new training program such as "10 squats x 3 sets."

[0908] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device. The device analyzes this and displays the new training program and nutritional advice on a dedicated chat screen. For example, it might display "New training program: 3 sets of 10 squats. New nutritional advice: Protein shake for breakfast, chicken salad for lunch."

[0909] In this way, the present invention can provide more personalized fitness instruction based on the user's emotional state, maintaining user motivation and increasing satisfaction.

[0910] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0911] Step 1:

[0912] A user accesses a dedicated website or mobile app and logs in. Here, the user enters their fitness goals (e.g., muscle building, weight loss, endurance improvement, etc.) and physical information (age, weight, height, body fat percentage, etc.) into a form. For example, the user provides information such as "25 years old, weight 70 kg, muscle building." This is the input data. The device converts this input data into JSON format. Specifically, it generates the following JSON data:

[0913] json

[0914] {

[0915] "age": 25,

[0916] "weight": 70,

[0917] "goal": "muscle_gain"

[0918] }

[0919] Step 2:

[0920] The device sends the converted JSON data to the server as an HTTP POST request. This is the output data and is transferred to the server. Specifically, the device sends the data as an HTTP request.

[0921] Step 3:

[0922] The server analyzes the received POST request and extracts the user's fitness goals and physical information. The input data is the JSON data sent from the device, which is analyzed to obtain extracted data such as "age = 25", "weight = 70", and "goal = 'muscle_gain'". This is the output data. Specifically, the server analyzes the JSON data and stores the necessary information in variables.

[0923] Step 4:

[0924] The server uses the extracted information to generate a training program using a generative AI model. The input data includes the extracted "age = 25," "weight = 70," and "goal = 'muscle_gain'." The server converts this into a prompt and inputs it into the generative AI model. Specifically, the prompt used is "I'm 25 years old, weigh 70 kg, and would like to gain a lot of muscle. What kind of training program would be suitable for me?" The output data is a training program such as "15 push-ups x 3 sets."

[0925] Step 5:

[0926] The server uses the generative AI model to generate nutritional advice appropriate for the user. The input data is the user's fitness goals and physical information. Based on this, the server inputs a prompt such as "What is a suitable nutrition plan for a 25-year-old male to build muscle?" into the generative AI model. The output data is nutritional advice such as "Oats and fruit for breakfast, chicken salad for lunch."

[0927] Step 6:

[0928] The device operates an emotion engine to read emotions from the user's facial expressions, voice, and input text. The input data is sensory data such as the user's facial expressions, voice, and text. Specifically, the device captures this sensory data through a webcam or microphone and analyzes it with the emotion engine. Emotional data such as "motivated" is obtained as output data.

[0929] Step 7:

[0930] The device converts the analyzed emotion data into JSON format and sends it to the server. The input data is emotion data analyzed by the emotion engine, and includes emotions such as "motivated." Specifically, the device converts this emotion data into JSON format and sends it to the server as an HTTP POST request. The following JSON data is generated as output data:

[0931] json

[0932] {

[0933] "emotion": "motivated"

[0934] }

[0935] Step 8:

[0936] The server compiles the generated training program, nutritional advice, and emotional data into a JSON-formatted response and sends it to the device. The input data includes the generated training program, nutritional advice, and emotional data. Specifically, the server compiles this data, converts it into JSON format, and sends it to the device as an HTTP response. The following JSON response is generated as output data:

[0937] json

[0938] {

[0939] "training_program": "15 push-ups x 3 sets",

[0940] "nutrition_advice": "Oats and fruit for breakfast, chicken salad for lunch",

[0941] "emotion": "motivated"

[0942] }

[0943] Step 9:

[0944] The device analyzes the received response and displays a training program and nutritional advice on a dedicated chat screen. The input data is the JSON response sent from the server. Specifically, the device analyzes this response and displays on the chat screen, "Training program: 15 push-ups x 3 sets. Nutritional advice: Oats and fruit for breakfast, chicken salad for lunch."

[0945] Step 10:

[0946] Users report their training progress, changes in their physical condition, and their own emotions through a dedicated chat screen. The input data is feedback information entered by the user (e.g., "My knee hurt during today's training"). Specific actions involve the user entering feedback into the chat screen.

[0947] Step 11:

[0948] The server uses a generative AI model and emotion engine to adjust the training program and nutrition advice based on the received feedback and emotion data. The input data is the user's feedback information and emotion data. Specifically, the server inputs a prompt such as "Please suggest another exercise that puts less strain on the knees" into the generative AI model and outputs a new training program such as "10 squats x 3 sets."

[0949] Step 12:

[0950] The server compiles the adjusted training program and nutrition advice into a JSON format response and sends it to the device. The input data is the adjusted training program and nutrition advice. Specifically, the server compiles this data into JSON format and sends it to the device as an HTTP response. The following JSON response is generated as output data:

[0951] json

[0952] {

[0953] "training_program": "10 squats x 3 sets",

[0954] "nutrition_advice": "Protein shake for breakfast, chicken salad for lunch"

[0955] }

[0956] Step 13:

[0957] The device displays the adjusted information on a dedicated chat screen and provides it to the user. The input data is the JSON response sent from the server. Specifically, the device analyzes this response and displays on the chat screen, "New training program: 3 sets of 10 squats. New nutrition advice: Protein shake for breakfast, chicken salad for lunch."

[0958] (Application example 2)

[0959] 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."

[0960] Conventional training programs and nutrition advice are customized based on the user's physical information and fitness goals, but they cannot take into account the user's emotional state, and have the problem of not being able to appropriately respond to users' declining motivation or fatigue.In addition, it is difficult to provide individual support to factory workers to improve their work efficiency, so there is a need to optimize work plans based on the workers' health status and motivation.

[0961] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving fitness goals and physical information from a user, means for generating a customized training program based on the user's fitness goals and physical information, means for generating customized nutritional advice based on the user's fitness goals and physical information, means for analyzing the user's emotional state from facial expressions and voice, means for providing the customized training program and nutritional advice to the user, and means for adjusting the training program and nutritional advice based on feedback on progress in the training program and changes in physical condition and the user's emotional state. This makes it possible to provide an individually optimized training program and nutritional advice that takes the user's emotional state into consideration.

[0962] A "fitness goal" is a physical goal or objective that a user wishes to achieve.

[0963] "Physical information" refers to physical data such as the user's age, weight, height, and body fat percentage.

[0964] A "training program" is an exercise plan created based on a user's fitness goals and physical information.

[0965] "Nutrition Advice" refers to dietary and nutritional guidelines recommended based on a user's fitness goals and physical information.

[0966] "Emotional state" refers to the mental state or mood of the user that is analyzed from facial expressions and voice.

[0967] "Means of analysis" refers to methods or devices for analyzing data and deriving specific results or information.

[0968] "Feedback" refers to reports on changes in the user's physical condition and training progress.

[0969] "Adjusting means" refers to a method or device for receiving feedback and reconfiguring training programs or nutritional advice.

[0970] The present invention is a system for supporting the improvement of work efficiency and health management of factory workers, and provides optimal work schedules and nutritional advice based on feedback including the worker's emotional state.

[0971] System Configuration

[0972] This system receives the user's (factory worker's) fitness goals and physical information, and combines it with an emotion engine that analyzes the user's emotional state from facial expressions and voice. The system mainly consists of the following components:

[0973] Terminal: Sensor devices such as cameras and voice recognition microphones installed on factory robots

[0974] Server: a central processing unit that processes data

[0975] Generative AI Models: Artificial Intelligence Models for Generating Training Programs and Nutritional Advice

[0976] Emotion engine: An engine that analyzes the worker's facial expression and voice data to estimate their emotional state

[0977] Program processing explanation

[0978] 1. User Input

[0979] During the initial setup, the user (worker) enters their age, weight, goals for improving work efficiency, and other physical information.

[0980] 2. Transmission of information

[0981] The terminal (factory robot) sends the information entered by the user to the server.

[0982] 3. Acquiring Emotion Data

[0983] The terminal (factory robot) uses a camera and a voice recognition microphone to collect the worker's facial expressions and voice, which are then analyzed using an emotion engine.

[0984] 4. Sending analysis results

[0985] The device transmits the analyzed emotion data to the server.

[0986] 5. Generating training programs and nutritional advice

[0987] The server uses the generative AI model to generate optimal training programs (work schedules) and nutritional advice based on the user's physical information, goals, and emotional state.

[0988] 6. Sending and Displaying Results

[0989] The server sends the generated data to the terminal, which displays the results to the user.

[0990] 7. Feedback and Adjustments

[0991] Users report their training progress and changes in their physical condition, and the device sends this feedback to the server, which again uses the generative AI model and emotion engine to adjust the training program and nutrition advice.

[0992] Hardware and software used

[0993] Camera and voice recognition microphone: Collects facial and voice data from workers.

[0994] Sensor device: Measures workers' physical condition information.

[0995] Emotion engine: Uses Python libraries and emotion recognition APIs (e.g., OpenCV, DeepFace).

[0996] Generative AI models: Generative AI models use natural language processing and machine learning models (e.g., GPT).

[0997] Server: Cloud-based data processing (e.g., AWS, Google Cloud).

[0998] Specific examples

[0999] Example: The emotion engine recognizes that Worker A is "fatigued" and "unmotivated." The generative AI model suggests schedule changes such as "increasing break time" and provides nutritional advice such as "eat bananas and nuts to replenish energy."

[1000] Example prompt sentence:

[1001] Worker's age: 30, weight: 75kg, emotional state: fatigue, motivation: low

[1002] Generate optimal work schedules and nutritional advice to improve worker health.

[1003] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1004] Step 1:

[1005] User Input

[1006] During the initial setup, users enter their fitness goals and physical information, such as age, weight, and work efficiency improvement, into the device. This input data is converted into JSON format, which is used to send the user's basic information and goals to the server.

[1007] Step 2:

[1008] Sending information

[1009] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server. The input data (user information and goals) is sent to the server.

[1010] Step 3:

[1011] Acquiring emotion data

[1012] The terminal (factory robot) uses a camera and a voice recognition microphone to collect the worker's facial expressions and voice. This collected data is analyzed through an emotion engine to determine the worker's emotional state. The input data is image data and voice data, and the output data is the worker's emotional state.

[1013] Step 4:

[1014] Sending emotional data

[1015] The device sends the analyzed emotion data to the server. The input data (emotion data) is sent to the server, and the analysis results from the emotion engine are compiled.

[1016] Step 5:

[1017] Generate training programs and nutritional advice

[1018] The server uses a generative AI model to generate optimal training programs and nutritional advice based on the user's physical information, goals, and emotional state. This process involves natural language processing and machine learning to process the data and generate specific training and meal plans. The input data is physical information, fitness goals, and emotional data, and the output data is the training program and nutritional advice.

[1019] Step 6:

[1020] Sending and viewing results

[1021] The server sends the generated training program and nutrition advice to the terminal, which receives it and displays the results to the user. The displayed results are the adjusted training program and nutrition advice.

[1022] Step 7:

[1023] Feedback and Adjustments

[1024] Users report their training progress and changes in their physical condition, and the device sends this feedback to the server. The server uses a generative AI model and emotion engine to adjust the training program and nutritional advice, and then sends it back to the device. In this process, user feedback is collected and the training program and nutritional advice are adjusted accordingly.

[1025] 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.

[1026] 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.

[1027] 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.

[1028] [Third embodiment]

[1029] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1030] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1031] 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).

[1032] 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.

[1033] 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.

[1034] 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).

[1035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1036] 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.

[1037] 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.

[1038] 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.

[1039] 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.

[1040] 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."

[1041] System Configuration

[1042] The present invention includes a system that provides customized training programs and nutritional advice based on a user's fitness goals and physical information. The system mainly consists of a user terminal, a server, and a generative AI model.

[1043] Program processing explanation

[1044] 1. User Input

[1045] Users access a dedicated website or mobile app and enter their fitness goals (e.g., building muscle, losing weight, improving endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[1046] 2. Transmission of information

[1047] The terminal converts the entered user information into JSON format and sends it to the server.

[1048] 3. Receiving a Request

[1049] The server analyzes the received request and obtains the user's fitness goals and physical information.

[1050] 4. Training program generation

[1051] The server uses a generative AI model to generate an optimal training program based on the user's information.

[1052] Specifically, the system processes the user's goals and physical information as input data and generates detailed training content, such as "15 push-ups x 3 sets."

[1053] 5. Nutrition advice generation

[1054] The server similarly uses the generative AI model to generate nutritional advice tailored to the user.

[1055] For example, if a user's fitness goal is to "lose weight," a low-calorie, high-protein meal plan is suggested.

[1056] 6. Submitting the results

[1057] The server compiles the generated training program and nutritional advice into a JSON-formatted response and sends it to the user's device.

[1058] 7. Displaying the results

[1059] The device analyzes the responses it receives and displays training programs and nutritional advice on a dedicated chat screen.

[1060] 8. Feedback

[1061] Users report their training progress and changes in their physical condition to the server via a dedicated chat screen.

[1062] 9. Processing Feedback

[1063] Based on the feedback received, the server again uses the generative AI model to adjust the training program and nutrition advice.

[1064] For example, if a user reports knee pain, other low-impact exercises may be suggested instead of squats.

[1065] 10. Providing adjusted results

[1066] The server sends the adjusted training program and nutrition advice back to the user's terminal, which displays it.

[1067] Specific examples

[1068] 1. Input example

[1069] The user inputs his / her fitness goal and physical information: "25 years old, weighs 70 kg, and wants to build muscle."

[1070] 2. Generation example

[1071] The server receives the user's information and uses a generative AI model to generate a training program of "3 sets of 15 push-ups" and nutritional advice of "oats and fruit for breakfast, chicken salad for lunch."

[1072] 3. Feedback Examples

[1073] A user reports, "My knee hurt during my workout today."

[1074] The server receives feedback and suggests alternative exercises that put less strain on the knees.

[1075] As described above, the present invention provides a system that quickly and appropriately provides individualized training programs and nutritional advice based on user input, helping users achieve their fitness goals.

[1076] The processing flow will be explained below.

[1077] Step 1:

[1078] Users access a dedicated website or mobile app and click the "Start Training" button.

[1079] Step 2:

[1080] Users input their fitness goals (e.g., build muscle, lose weight, improve endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[1081] Step 3:

[1082] The device converts the fitness goals and physical information entered by the user into JSON format.

[1083] Step 4:

[1084] The terminal sends user information in JSON format to the server as a POST request.

[1085] Step 5:

[1086] The server parses the received POST request and obtains the user's fitness goals and physical information.

[1087] Step 6:

[1088] The server calls the generative AI model and instructs it to generate a training program using the user's information as input data.

[1089] Step 7:

[1090] The generative AI model generates a customized training program based on the user information and returns the results to the server.

[1091] Step 8:

[1092] The server then invokes the generative AI model again, this time instructing it to generate customized nutritional advice.

[1093] Step 9:

[1094] The generative AI model generates nutritional advice based on user information and returns the results to the server.

[1095] Step 10:

[1096] The server compiles the training program and nutrition advice into a JSON-formatted response and sends it to the device.

[1097] Step 11:

[1098] The device analyzes the response received from the server and displays the training program and nutritional advice on a dedicated chat screen.

[1099] Step 12:

[1100] Users can report their training progress and changes in their physical condition through a dedicated chat screen.

[1101] Step 13:

[1102] The terminal transmits the feedback from the user to the server.

[1103] Step 14:

[1104] The server analyzes the feedback it receives and uses generative AI models to direct adjustments to training programs and nutritional advice.

[1105] Step 15:

[1106] Based on the feedback, the generative AI model generates appropriately adjusted training programs and nutritional advice and returns the results to the server.

[1107] Step 16:

[1108] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device.

[1109] Step 17:

[1110] The terminal displays the adjusted information on a dedicated chat screen and provides it to the user.

[1111] Example 1

[1112] 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."

[1113] Currently, many fitness program and nutrition advice systems only provide general information and are not sufficiently customized to each user's physical information and fitness goals. Furthermore, it is difficult to provide dynamic training programs and nutrition advice that reflect user feedback. Therefore, there is a need for a system that can provide training programs and nutrition advice optimized for each user and flexibly adjust them based on feedback.

[1114] 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.

[1115] In this invention, the server includes means for receiving fitness goals and physical information from a user, means for converting the user's fitness goals and physical information into a data format and sending it to the server, means for generating a customized training program using a generative AI model based on the user's fitness goals and physical information, means for generating customized nutritional advice using the generative AI model based on the user's fitness goals and physical information, means for converting the customized training program and nutritional advice into a data format and providing it to the user, and means for receiving feedback from the user regarding progress in the training program and changes in physical condition and adjusting the training program and nutritional advice based on the feedback, thereby making it possible to provide an optimal training program and nutritional advice tailored to the user's individual needs and flexibly respond to the feedback.

[1116] "User" refers to the individual or end user who inputs fitness goals and physical information.

[1117] "Fitness goal" refers to a physical goal a user wishes to achieve (e.g., building muscle, losing weight, improving endurance, etc.).

[1118] "Physical information" refers to the user's individual physical characteristics (e.g., age, weight, height, body fat percentage, etc.).

[1119] "Data format" refers to a format (e.g., JSON format) that structures information entered by a user and converts it into a form that can be handled as digital data.

[1120] "Server" refers to the computer system that analyzes the data received from the User and utilizes the generative AI model to generate training programs and nutritional advice.

[1121] "Generative AI model" refers to an artificial intelligence model that is trained on large amounts of data and generates optimal training programs and nutritional advice based on user information.

[1122] "Customized training program" refers to a specific exercise plan tailored to an individual user based on their fitness goals and physical information.

[1123] "Customized nutrition advice" refers to a meal plan that is tailored based on an individual user's fitness goals and physical information.

[1124] "Feedback" refers to the act of the user providing the system with information about the progress of training and changes in physical condition.

[1125] "Adjustment" refers to the process of reevaluating and adapting existing training programs and nutritional advice based on feedback received.

[1126] MODE FOR CARRYING OUT THE INVENTION

[1127] This invention describes a concrete implementation of a system that provides customized training programs and nutritional advice based on a user's fitness goals and physical information. The entire system mainly consists of a user terminal, a server, and a generative AI model.

[1128] 1. User Input

[1129] Users access the system through a dedicated website or mobile app. The application runs on popular platforms such as iOS and Android. Users enter their fitness goals and physical information. For example, if a 25-year-old user weighs 70 kg and wants to build muscle, they can enter that information.

[1130] 2. Transmission of information

[1131] The device converts the information entered by the user into JSON format and sends it to the server using Internet Protocol. The JSON format data includes fitness goals and physical information. For example, it might look like this:

[1132] json

[1133] {

[1134] "age": 25,

[1135] "weight": 70,

[1136] "goal": "muscle_gain"

[1137] }

[1138] 3. Receiving a Request

[1139] The server parses the received request to obtain the user's fitness goals and physical information, which involves parsing the data to extract keys and values.

[1140] 4. Training program generation

[1141] The server uses a generative AI model (e.g., GPT-3) to generate an optimal training program based on the user's information. Specifically, the user's data is input to the generative AI model as a prompt sentence like the following:

[1142] User information: 25 years old, weight 70kg, goal: muscle building. Please provide a suitable training program for the user.

[1143] Based on this prompt, the generative AI model generates specific training content such as "15 push-ups x 3 sets."

[1144] 5. Nutrition advice generation

[1145] The server uses the same generative AI model to generate nutrition advice tailored to the user, using prompts like:

[1146] User information: 25 years old, weight 70kg, goal: to build muscle. Please provide a suitable nutrition plan for the user.

[1147] Based on this prompt, the generative AI model generates nutritional advice such as "oats and fruit for breakfast, chicken salad for lunch."

[1148] 6. Submitting the results

[1149] The server then compiles the generated training program and nutrition advice into a JSON response and sends it to the user's device, for example in the following JSON format:

[1150] json

[1151] {

[1152] "training_program": "3 sets of 15 push-ups",

[1153] "nutrition_advice": "Oats and fruit for breakfast, chicken salad for lunch"

[1154] }

[1155] 7. Displaying the results

[1156] The device analyzes the received response and displays the training program and nutrition advice on a dedicated chat screen. This analysis process includes parsing the JSON of the response and preparing it for display in the GUI.

[1157] 8. Feedback

[1158] Users can report their training progress and changes in their physical condition to the server via a dedicated chat screen. For example, they can write, "My knee started hurting during today's training."

[1159] 9. Processing Feedback

[1160] The server analyzes the received feedback and determines the appropriate response. For example, if the user feedback is "knee pain," it will again use the generative AI model to generate a new training program. The prompt text is as follows:

[1161] User information: Age 25, Weight 70kg, Goal: Build muscle. User reported knee pain. Provide alternative exercises that are less stressful on the knees.

[1162] 10. Providing adjusted results

[1163] The server then compiles the adjusted training program and nutrition advice into a JSON response and sends it to the user's device, which then displays the new information on the chat screen.

[1164] The invention allows users to receive customized training programs and nutritional advice tailored to their fitness goals, with the flexibility to adjust based on feedback.

[1165] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1166] Step 1: User enters fitness goals and physical information

[1167] Users access a dedicated website or mobile app and enter their fitness goals (e.g., muscle building, weight loss, endurance improvement) and physical information (e.g., age, weight, height, body fat percentage), which is then prepared as data to be sent to the system.

[1168] Input: Fitness goals and physical information (age, weight, height, body fat percentage, etc.)

[1169] Output: Input data converted to JSON format

[1170] Step 2: The device sends the user information

[1171] The device converts the information entered by the user into JSON format and sends it to the server using Internet Protocol, with the data transmitted over a secure communication channel.

[1172] Input: User information in JSON format

[1173] Output: User information sent to the server

[1174] Step 3: The server receives and analyzes the request

[1175] The server analyzes the received request to obtain the user's fitness goals and physical information. The analysis process involves parsing the received data to extract keys and values.

[1176] Input: JSON format user information received by the server

[1177] Output: Parsed fitness goals and body information

[1178] Step 4: The server generates a training program using the generated AI model

[1179] The server uses a generative AI model (e.g., GPT-3) to generate an optimal training program based on the parsed user information. The server inputs the following prompt to the generative AI model:

[1180] User information: 25 years old, weight 70kg, goal: muscle building. Please provide a suitable training program for the user.

[1181] Input: Fitness goal and physical information, prompt

[1182] Output: Generated training program (e.g., "3 sets of 15 push-ups")

[1183] Step 5: The server uses the generative AI model to generate nutrition advice

[1184] The server also uses a generative AI model to generate nutrition advice tailored to the user, using prompts like:

[1185] User information: 25 years old, weight 70kg, goal: to build muscle. Please provide a suitable nutrition plan for the user.

[1186] Input: Fitness goal and physical information, prompt

[1187] Output: Generated nutrition advice (e.g. "Oats and fruit for breakfast, chicken salad for lunch")

[1188] Step 6: Server sends results

[1189] The server then compiles the generated training program and nutrition advice into a JSON response and sends it to the user's device, for example in the following JSON format:

[1190] json

[1191] {

[1192] "training_program": "3 sets of 15 push-ups",

[1193] "nutrition_advice": "Oats and fruit for breakfast, chicken salad for lunch"

[1194] }

[1195] Input: Generated training programs and nutrition advice

[1196] Output: Sent to the terminal as a JSON response

[1197] Step 7: Your device will display the results

[1198] The device analyzes the received response and displays the training program and nutrition advice on a dedicated chat screen. This analysis process includes parsing the JSON of the response and preparing it for display in the GUI.

[1199] Input: JSON response (training program and nutrition advice)

[1200] Output: Training program and nutrition advice displayed on the chat screen

[1201] Step 8: User enters feedback

[1202] Users can report their training progress and changes in their physical condition to the server via a dedicated chat screen. For example, they can write, "My knee started hurting during today's training."

[1203] Input: Feedback on your training progress and changes in your fitness

[1204] Output: Information sent to the server as feedback

[1205] Step 9: Server processes feedback

[1206] The server analyzes the received feedback and determines the appropriate response. For example, if the user feedback is "knee pain," it will again use the generative AI model to generate a new training program. The prompt text is as follows:

[1207] User information: Age 25, Weight 70kg, Goal: Build muscle. User reported knee pain. Provide alternative exercises that are less stressful on the knees.

[1208] Input: Feedback, prompt

[1209] Output: Tailored training program

[1210] Step 10: The server sends the adjusted results

[1211] The server then compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the user's device.

[1212] Input: tailored training programs and nutritional advice

[1213] Output: Sent to the terminal as a JSON response

[1214] Step 11: Your device will display the adjusted results.

[1215] The device then analyzes the received response and displays the adjusted training program and nutritional advice on a dedicated chat screen.

[1216] Input: JSON response (adjusted training program and nutrition advice)

[1217] Output: Adjusted training program and nutrition advice displayed on the chat screen

[1218] (Application example 1)

[1219] 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."

[1220] The present invention aims to reduce the complexity of conventional systems and improve user convenience by automatically ordering meals customized based on the physical information of each user through a food delivery service and providing the user with the order results and nutritional advice in a system that provides training programs and nutritional advice to help users achieve their fitness goals. In conventional systems, after receiving a training program and nutritional advice, the user must choose for themselves what meals to actually eat, which can be a significant burden in terms of effort and time.

[1221] 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.

[1222] In this invention, the server includes means for receiving fitness goals and physical information from a user, means for generating a customized training program based on the user's fitness goals and physical information, means for generating customized nutritional advice based on the user's fitness goals and physical information, means for providing the customized training program and nutritional advice to the user, means for receiving feedback from the user regarding progress in the training program and changes in physical condition and adjusting the training program and nutritional advice based on the feedback, means for automatically ordering meals through a food delivery service based on the nutritional advice, and means for providing the user with the order results and nutritional advice from the food delivery service, thereby enabling the user to automatically order appropriate meals based on the individual nutritional advice and more effectively support achieving their fitness goals.

[1223] A "user" is an individual who utilizes the system and inputs fitness goals and physical information.

[1224] "Fitness Goal" means a physical or health goal that a user wishes to achieve, such as losing weight, building muscle, or improving endurance.

[1225] "Physical information" refers to physical data such as the user's age, weight, height, and body fat percentage.

[1226] A "training program" is a customized exercise plan generated based on a user's fitness goals and physical information.

[1227] "Nutrition Advice" means customized meal suggestions and plans provided based on a user's fitness goals and physical information.

[1228] "Feedback" refers to information provided by a user regarding progress in a training program and changes in physical condition.

[1229] A "food delivery service" is a service that allows you to order meals online and have them delivered.

[1230] "Generative AI Model" refers to the artificial intelligence algorithms used to generate optimal training programs and nutritional advice based on user information.

[1231] "Order Result" means the confirmation information regarding a meal ordered automatically through the food delivery service.

[1232] The term "means" refers to functions or components for executing various processes in this invention.

[1233] System Configuration

[1234] The present invention is a system that provides a user with a customized training program and nutritional advice based on their fitness goals and physical information, and automatically orders appropriate meals through a food delivery service. The system consists of a user terminal, a server, and a generative AI model.

[1235] Hardware and software used

[1236] Smartphone: User device on which the app is installed

[1237] Server: Data processing and AI model hosting

[1238] Generative AI models: generating nutrition advice and meal plans

[1239] Food Delivery API: Integration for automated meal ordering

[1240] Processing Description

[1241] 1. User Input

[1242] Users access a dedicated application on their smartphone and enter their fitness goals (e.g., weight loss, muscle building, endurance improvement, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.), which then inputs data tailored to the user's individual needs.

[1243] 2. Information Transmission

[1244] The user terminal converts the information entered by the user into JSON format and sends it to the server, which receives and analyzes this data.

[1245] 3. Nutrition advice generation

[1246] The server uses the generative AI model to generate optimal nutrition advice and meal plans based on the user's fitness goals and physical information, such as providing a low-calorie, high-protein meal plan for a user aiming to lose weight.

[1247] 4. Food delivery collaboration

[1248] Based on the meal plan, the server calls the API of the partner food delivery service and automatically orders the corresponding meal menu, eliminating the need for the user to choose their own meals.

[1249] 5. Sending and displaying results

[1250] The server converts the order details and nutrition advice back into JSON format and sends it to the user's device. The user's device analyzes this data and displays it on a dedicated screen. The user can then review the order details and make any necessary changes.

[1251] Specific examples

[1252] For example, if a user enters the following information:

[1253] Example prompt sentence:

[1254] Age: 30

[1255] Weight: 80kg

[1256] Height: 175cm

[1257] Body fat percentage: 20%

[1258] Fitness Goal: Muscle Building

[1259] Based on this information, the server uses a generative AI model to generate a meal plan such as "oats and fruit for breakfast, chicken salad for lunch" and automatically places an order with a food delivery service. The ordering results and nutrition advice are sent to the user's device, where they can view them.

[1260] In this way, the present invention can provide comprehensive support to users in achieving their fitness goals.

[1261] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1262] Step 1:

[1263] Users access a dedicated application on their smartphone and enter their fitness goals and physical information.

[1264] Input: Fitness goals (e.g., weight loss, muscle building), physical information (e.g., age, weight, height, body fat percentage, etc.)

[1265] Output: The input data is saved in the application.

[1266] Specific operation: The user enters the required information using the input form within the app and presses the submit button.

[1267] Step 2:

[1268] The terminal converts the information entered by the user into JSON format and sends it to the server.

[1269] Input: User-entered fitness goals and physical information

[1270] Output: JSON format data is sent to the server

[1271] Specific behavior: The application converts input data into JSON format and sends it to the server using an HTTP request.

[1272] Step 3:

[1273] The server parses the request received as JSON and retrieves the user's fitness goals and physical information.

[1274] Input: User data in JSON format

[1275] Output: Fitness goals and body information captured

[1276] What happens: The server receives the HTTP request and parses the data using a JSON parser.

[1277] Step 4:

[1278] The server uses the generative AI model to generate optimal nutritional advice and meal plans based on the user's fitness goals and physical information.

[1279] Input: Fitness goals and physical information

[1280] Output: Nutrition advice and meal plans

[1281] How it works: The server inputs the user's data into a generative AI model to generate training programs and nutritional advice.

[1282] Step 5:

[1283] Based on the generated meal plan, the server calls the API of a partner food delivery service and automatically orders the corresponding meal menu.

[1284] Enter: Nutritional advice and meal plans

[1285] Output: An order request to a food delivery service

[1286] Specific operation: The server calls the food delivery service's API and sends the order details.

[1287] Step 6:

[1288] The server converts the order details and nutrition advice back into JSON format and sends it to the user's terminal.

[1289] Input: Order details and nutrition advice

[1290] Output: JSON format data is sent to the user's device.

[1291] Specific operation: The server compiles the order results and nutrition advice and sends them to the user's terminal via an HTTP response.

[1292] Step 7:

[1293] The user terminal analyzes the received data and displays the order details and nutritional advice on a dedicated screen.

[1294] Input: Order details and nutrition advice in JSON format

[1295] Output: Order details and nutrition advice displayed on a dedicated screen

[1296] What happens: The application parses the JSON data and displays it in the user interface.

[1297] Step 8:

[1298] Users provide feedback through a dedicated screen.

[1299] Input: Feedback content (e.g., satisfaction, changes in physical condition)

[1300] Output: Feedback is sent to the server

[1301] Specific operation: The user enters their status and opinions using the feedback form within the app and submits it.

[1302] 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.

[1303] System Configuration

[1304] The present invention combines a system that provides customized training programs and nutritional advice based on a user's fitness goals and physical information with an emotion engine that recognizes the user's emotions. The system mainly consists of a user's device, a server, a generative AI model, and an emotion engine.

[1305] Program processing explanation

[1306] 1. User Input

[1307] Users access a dedicated website or mobile app and enter their fitness goals (e.g., building muscle, losing weight, improving endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[1308] 2. Transmission of information

[1309] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server.

[1310] 3. Receiving a Request

[1311] The server parses the received POST request and obtains the user's fitness goals and physical information.

[1312] 4. Training program generation

[1313] The server uses a generative AI model to generate an optimal training program based on the user's information.

[1314] Specifically, the system processes the user's goals and physical information as input data and generates detailed training content, such as "15 push-ups x 3 sets."

[1315] 5. Nutrition advice generation

[1316] The server similarly uses the generative AI model to generate nutritional advice tailored to the user.

[1317] For example, if a user's fitness goal is to "lose weight," a low-calorie, high-protein meal plan is suggested.

[1318] 6. Acquiring Emotion Data

[1319] The device runs an emotion engine to read emotions from the user's facial expressions, voice, and input text.

[1320] For example, analyzing a user's emotions through a webcam or microphone.

[1321] 7. Emotional Data Transmission

[1322] The device transmits the analyzed emotion data to the server.

[1323] 8. Submitting the results

[1324] The server compiles the generated training program, nutritional advice, and emotional data into a JSON-formatted response and sends it to the device.

[1325] 9. Displaying the results

[1326] The device analyzes the responses it receives and displays training programs and nutritional advice on a dedicated chat screen.

[1327] 10. Feedback

[1328] Users can report their training progress, changes in their physical condition, and their emotions through a dedicated chat screen.

[1329] 11. Processing Feedback

[1330] The server analyzes the feedback it receives and uses generative AI models and an emotion engine to direct adjustments to training programs and nutritional advice.

[1331] For example, if a user reports that "today's training was tough" and the emotion engine simultaneously detects a decline in the user's motivation, the system will either change the training content to something lighter or provide feedback to increase motivation.

[1332] 12. Provision of Adjusted Results

[1333] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device.

[1334] 13. Redisplay

[1335] The terminal displays the adjusted information on a dedicated chat screen and provides it to the user.

[1336] Specific examples

[1337] 1. Input example

[1338] The user inputs his / her fitness goal and physical information: "25 years old, weighs 70 kg, and wants to build muscle."

[1339] 2. Generation example

[1340] The server receives the user's information and uses a generative AI model to generate a training program of "3 sets of 15 push-ups" and nutritional advice of "oats and fruit for breakfast, chicken salad for lunch."

[1341] 3. Emotion recognition example

[1342] The emotion engine recognizes from the user's facial expressions and voice that the user is "motivated."

[1343] Based on this emotional information, the server generates additional encouraging messages to further motivate the user.

[1344] 4. Feedback Example

[1345] The user reports that "my knee hurt during training today" and looks depressed.

[1346] The server receives feedback and emotional data and suggests alternative exercises that put less strain on the knees.

[1347] By combining an emotion engine, the present invention can provide more personalized fitness guidance based on the user's emotional state, improving user motivation and satisfaction.

[1348] The processing flow will be explained below.

[1349] Step 1:

[1350] Users access a dedicated website or mobile app and click the "Start Training" button.

[1351] Step 2:

[1352] Users input their fitness goals (e.g., build muscle, lose weight, improve endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[1353] Step 3:

[1354] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server.

[1355] Step 4:

[1356] The server parses the received POST request and obtains the user's fitness goals and physical information.

[1357] Step 5:

[1358] The server calls the generative AI model and instructs it to generate a training program using the user's information as input. Specifically, it generates a customized exercise plan (e.g., "3 sets of 15 push-ups") based on the user's goals and physical information.

[1359] Step 6:

[1360] The server then calls the generative AI model again to generate customized nutrition advice based on the user's information, such as a meal plan like "oats and fruit for breakfast, chicken salad for lunch," taking into account the user's goals and physical information.

[1361] Step 7:

[1362] The device runs an emotion engine to read emotions from the user's facial expressions, voice, and input text. For example, it uses a webcam and microphone to detect the user's emotional state (e.g., joy, sadness, fatigue, etc.).

[1363] Step 8:

[1364] The device transmits the analyzed emotion data to the server.

[1365] Step 9:

[1366] The server compiles the generated training program, nutritional advice, and emotional data into a JSON-formatted response and sends it to the device.

[1367] Step 10:

[1368] The device analyzes the responses and displays training programs and nutritional advice on a dedicated chat screen, such as "3 sets of 15 push-ups" and "Oats and fruit for breakfast, chicken salad for lunch."

[1369] Step 11:

[1370] Users can report their training progress, changes in their physical condition, and their own emotions through a dedicated chat screen, for example, by providing feedback such as, "Today, my whole body feels tired."

[1371] Step 12:

[1372] The terminal transmits the feedback from the user to the server.

[1373] Step 13:

[1374] The server analyzes the received feedback and uses a generative AI model and emotion engine to direct adjustments to training programs and nutrition advice. For example, if a user reports feeling "tired all over," the emotion engine will detect the user's stress and fatigue and generate a lighter exercise program.

[1375] Step 14:

[1376] The generative AI model generates appropriately tailored training programs and nutritional advice based on the feedback and emotional data, and returns the results to the server.

[1377] Step 15:

[1378] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device.

[1379] Step 16:

[1380] The device displays the adjusted information on a dedicated chat screen and provides it to the user, for example, suggesting a new training program such as "Do 15 minutes of light stretching today."

[1381] The above are the specific processing steps of the invention that combines the emotion engine, which can effectively support the user in achieving their fitness goals and increasing their motivation.

[1382] Example 2

[1383] 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."

[1384] While conventional fitness systems provide customized training programs and nutritional advice based on a user's fitness goals and physical information, they lack the ability to provide personalized guidance that takes into account the user's emotional state. As a result, they lack the support to motivate users and encourage them to continue fitness.

[1385] 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.

[1386] In this invention, the server includes: means for receiving fitness goals and physical information from a user; means for transmitting the user's fitness goals and physical information from a terminal to the server; means for generating a customized training program using a generative AI model based on the user's fitness goals and physical information; means for generating customized nutritional advice using the generative AI model based on the user's fitness goals and physical information; means for operating an emotion engine that analyzes the user's emotions and acquiring emotion data; means for providing the customized training program and nutritional advice to the user; means for receiving feedback from the user regarding progress in the training program and changes in physical condition and adjusting the training program and nutritional advice based on the feedback and emotion data; and means for re-providing the adjusted training program and nutritional advice to the user. This enables more personalized fitness guidance based on the user's emotional state, maintaining user motivation and improving satisfaction.

[1387] "User" refers to an individual who utilizes the system to input fitness goals and physical information and receive customized training programs and nutritional advice.

[1388] "Fitness goal" refers to a physical goal a user wishes to achieve (e.g., building muscle, losing weight, improving endurance, etc.).

[1389] "Physical information" refers to information necessary for customizing a fitness program, such as a user's age, weight, height, and body fat percentage.

[1390] "Terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) through which a user inputs fitness goals and physical information and communicates with a server.

[1391] "Server" refers to a computer system that receives user input information, uses a generative AI model to generate training programs and nutritional advice, and provides them to the user.

[1392] "Generative AI Model" refers to an artificial intelligence model that automatically generates customized training programs and nutritional advice based on input user information.

[1393] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[1394] "Training Program" refers to the specific exercise content generated by the generative AI model based on the user's fitness goals and physical information.

[1395] "Nutrition Advice" refers to dietary guidance generated by the generative AI model based on the user's fitness goals and physical information.

[1396] "Emotion engine" refers to software or hardware for analyzing emotions from a user's facial expressions, voice, and input text.

[1397] "Emotion data" refers to information about the user's emotional state obtained as a result of analysis by the emotion engine.

[1398] "Feedback" refers to information that users report through a dedicated chat screen about their training progress, changes in physical condition, and their emotions.

[1399] "Adjustment" refers to restructuring training programs and nutrition advice based on user feedback and sentiment data.

[1400] The present invention is a system that provides a user with a customized training program and nutritional advice based on their fitness goals and physical information, and further combines it with an emotion engine that analyzes the user's emotions. Specific methods for implementing the invention are described below.

[1401] The system mainly consists of a user's device, a server, a generative AI model, and an emotion engine. The user uses the device to input their fitness goals and physical information.

[1402] A user accesses a dedicated website or mobile app and logs in. The user selects their fitness goal (e.g., muscle building, weight loss, endurance improvement, etc.) and enters their physical information (age, weight, height, body fat percentage, etc.) into a form. For example, the user might enter information such as "25 years old, weight 70 kg, muscle building."

[1403] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server as an HTTP POST request, which transmits the user information to the server.

[1404] The server parses the POST request and extracts the user's fitness goals and physical information, such as "age = 25," "weight = 70," and "goal = 'muscle_gain'."

[1405] The server inputs a prompt based on user information to the generative AI model. For example, a prompt such as "I'm 25 years old, weigh 70 kg, and want to build a lot of muscle. What kind of training program would be suitable?" is used. This causes the generative AI model to output a training program such as "15 push-ups x 3 sets."

[1406] Similarly, to generate nutrition advice, the server inputs a prompt to the generative AI model, such as "What is a good nutrition plan for a 25-year-old male to build muscle?", which then outputs the advice "Oats and fruit for breakfast, chicken salad for lunch."

[1407] Next, the device activates an emotion engine to read emotions from the user's facial expressions, voice, and input text. For example, the device may analyze the user's facial expressions and voice using a webcam or microphone, and the emotion engine may obtain emotion data such as "motivated."

[1408] The device sends the analyzed emotional data to the server, which then generates prompts based on the received emotional data and uses the generative AI model to provide feedback that motivates the user. For example, based on emotional data such as "I'm full of motivation," the server can generate an encouraging message such as "Do your best today!"

[1409] Users train and report their progress and changes in their physical condition via their device. For example, they can send feedback such as, "My knees hurt during today's training." The server analyzes this feedback and, using an emotion engine and generative AI model, suggests alternative exercises that put less strain on the knees.

[1410] For example, a prompt such as "Please suggest another exercise that puts less strain on the knees" can be input into a generative AI model, which will output a new training program such as "10 squats x 3 sets."

[1411] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device. The device analyzes this and displays the new training program and nutritional advice on a dedicated chat screen. For example, it might display "New training program: 3 sets of 10 squats. New nutritional advice: Protein shake for breakfast, chicken salad for lunch."

[1412] In this way, the present invention can provide more personalized fitness instruction based on the user's emotional state, maintaining user motivation and increasing satisfaction.

[1413] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1414] Step 1:

[1415] A user accesses a dedicated website or mobile app and logs in. Here, the user enters their fitness goals (e.g., muscle building, weight loss, endurance improvement, etc.) and physical information (age, weight, height, body fat percentage, etc.) into a form. For example, the user provides information such as "25 years old, weight 70 kg, muscle building." This is the input data. The device converts this input data into JSON format. Specifically, it generates the following JSON data:

[1416] json

[1417] {

[1418] "age": 25,

[1419] "weight": 70,

[1420] "goal": "muscle_gain"

[1421] }

[1422] Step 2:

[1423] The device sends the converted JSON data to the server as an HTTP POST request. This is the output data and is transferred to the server. Specifically, the device sends the data as an HTTP request.

[1424] Step 3:

[1425] The server analyzes the received POST request and extracts the user's fitness goals and physical information. The input data is the JSON data sent from the device, which is analyzed to obtain extracted data such as "age = 25", "weight = 70", and "goal = 'muscle_gain'". This is the output data. Specifically, the server analyzes the JSON data and stores the necessary information in variables.

[1426] Step 4:

[1427] The server uses the extracted information to generate a training program using a generative AI model. The input data includes the extracted "age = 25," "weight = 70," and "goal = 'muscle_gain'." The server converts this into a prompt and inputs it into the generative AI model. Specifically, the prompt used is "I'm 25 years old, weigh 70 kg, and would like to gain a lot of muscle. What kind of training program would be suitable for me?" The output data is a training program such as "15 push-ups x 3 sets."

[1428] Step 5:

[1429] The server uses the generative AI model to generate nutritional advice appropriate for the user. The input data is the user's fitness goals and physical information. Based on this, the server inputs a prompt such as "What is a suitable nutrition plan for a 25-year-old male to build muscle?" into the generative AI model. The output data is nutritional advice such as "Oats and fruit for breakfast, chicken salad for lunch."

[1430] Step 6:

[1431] The device operates an emotion engine to read emotions from the user's facial expressions, voice, and input text. The input data is sensory data such as the user's facial expressions, voice, and text. Specifically, the device captures this sensory data through a webcam or microphone and analyzes it with the emotion engine. Emotional data such as "motivated" is obtained as output data.

[1432] Step 7:

[1433] The device converts the analyzed emotion data into JSON format and sends it to the server. The input data is emotion data analyzed by the emotion engine, and includes emotions such as "motivated." Specifically, the device converts this emotion data into JSON format and sends it to the server as an HTTP POST request. The following JSON data is generated as output data:

[1434] json

[1435] {

[1436] "emotion": "motivated"

[1437] }

[1438] Step 8:

[1439] The server compiles the generated training program, nutritional advice, and emotional data into a JSON-formatted response and sends it to the device. The input data includes the generated training program, nutritional advice, and emotional data. Specifically, the server compiles this data, converts it into JSON format, and sends it to the device as an HTTP response. The following JSON response is generated as output data:

[1440] json

[1441] {

[1442] "training_program": "15 push-ups x 3 sets",

[1443] "nutrition_advice": "Oats and fruit for breakfast, chicken salad for lunch",

[1444] "emotion": "motivated"

[1445] }

[1446] Step 9:

[1447] The device analyzes the received response and displays a training program and nutritional advice on a dedicated chat screen. The input data is the JSON response sent from the server. Specifically, the device analyzes this response and displays on the chat screen, "Training program: 15 push-ups x 3 sets. Nutritional advice: Oats and fruit for breakfast, chicken salad for lunch."

[1448] Step 10:

[1449] Users report their training progress, changes in their physical condition, and their own emotions through a dedicated chat screen. The input data is feedback information entered by the user (e.g., "My knee hurt during today's training"). Specific actions involve the user entering feedback into the chat screen.

[1450] Step 11:

[1451] The server uses a generative AI model and emotion engine to adjust the training program and nutrition advice based on the received feedback and emotion data. The input data is the user's feedback information and emotion data. Specifically, the server inputs a prompt such as "Please suggest another exercise that puts less strain on the knees" into the generative AI model and outputs a new training program such as "10 squats x 3 sets."

[1452] Step 12:

[1453] The server compiles the adjusted training program and nutrition advice into a JSON format response and sends it to the device. The input data is the adjusted training program and nutrition advice. Specifically, the server compiles this data into JSON format and sends it to the device as an HTTP response. The following JSON response is generated as output data:

[1454] json

[1455] {

[1456] "training_program": "10 squats x 3 sets",

[1457] "nutrition_advice": "Protein shake for breakfast, chicken salad for lunch"

[1458] }

[1459] Step 13:

[1460] The device displays the adjusted information on a dedicated chat screen and provides it to the user. The input data is the JSON response sent from the server. Specifically, the device analyzes this response and displays on the chat screen, "New training program: 3 sets of 10 squats. New nutrition advice: Protein shake for breakfast, chicken salad for lunch."

[1461] (Application example 2)

[1462] 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."

[1463] Conventional training programs and nutrition advice are customized based on the user's physical information and fitness goals, but they cannot take into account the user's emotional state, and have the problem of not being able to appropriately respond to users' declining motivation or fatigue.In addition, it is difficult to provide individual support to factory workers to improve their work efficiency, so there is a need to optimize work plans based on the workers' health status and motivation.

[1464] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving fitness goals and physical information from a user, means for generating a customized training program based on the user's fitness goals and physical information, means for generating customized nutritional advice based on the user's fitness goals and physical information, means for analyzing the user's emotional state from facial expressions and voice, means for providing the customized training program and nutritional advice to the user, and means for adjusting the training program and nutritional advice based on feedback on progress in the training program and changes in physical condition and the user's emotional state. This makes it possible to provide an individually optimized training program and nutritional advice that takes the user's emotional state into consideration.

[1465] A "fitness goal" is a physical goal or objective that a user wishes to achieve.

[1466] "Physical information" refers to physical data such as the user's age, weight, height, and body fat percentage.

[1467] A "training program" is an exercise plan created based on a user's fitness goals and physical information.

[1468] "Nutrition Advice" refers to dietary and nutritional guidelines recommended based on a user's fitness goals and physical information.

[1469] "Emotional state" refers to the mental state or mood of the user that is analyzed from facial expressions and voice.

[1470] "Means of analysis" refers to methods or devices for analyzing data and deriving specific results or information.

[1471] "Feedback" refers to reports on changes in the user's physical condition and training progress.

[1472] "Adjusting means" refers to a method or device for receiving feedback and reconfiguring training programs or nutritional advice.

[1473] The present invention is a system for supporting the improvement of work efficiency and health management of factory workers, and provides optimal work schedules and nutritional advice based on feedback including the worker's emotional state.

[1474] System Configuration

[1475] This system receives the user's (factory worker's) fitness goals and physical information, and combines it with an emotion engine that analyzes the user's emotional state from facial expressions and voice. The system mainly consists of the following components:

[1476] Terminal: Sensor devices such as cameras and voice recognition microphones installed on factory robots

[1477] Server: a central processing unit that processes data

[1478] Generative AI Models: Artificial Intelligence Models for Generating Training Programs and Nutritional Advice

[1479] Emotion engine: An engine that analyzes the worker's facial expression and voice data to estimate their emotional state

[1480] Program processing explanation

[1481] 1. User Input

[1482] During the initial setup, the user (worker) enters their age, weight, goals for improving work efficiency, and other physical information.

[1483] 2. Transmission of information

[1484] The terminal (factory robot) sends the information entered by the user to the server.

[1485] 3. Acquiring Emotion Data

[1486] The terminal (factory robot) uses a camera and a voice recognition microphone to collect the worker's facial expressions and voice, which are then analyzed using an emotion engine.

[1487] 4. Sending analysis results

[1488] The device transmits the analyzed emotion data to the server.

[1489] 5. Generating training programs and nutritional advice

[1490] The server uses the generative AI model to generate optimal training programs (work schedules) and nutritional advice based on the user's physical information, goals, and emotional state.

[1491] 6. Sending and Displaying Results

[1492] The server sends the generated data to the terminal, which displays the results to the user.

[1493] 7. Feedback and Adjustments

[1494] Users report their training progress and changes in their physical condition, and the device sends this feedback to the server, which again uses the generative AI model and emotion engine to adjust the training program and nutrition advice.

[1495] Hardware and software used

[1496] Camera and voice recognition microphone: Collects facial and voice data from workers.

[1497] Sensor device: Measures workers' physical condition information.

[1498] Emotion engine: Uses Python libraries and emotion recognition APIs (e.g., OpenCV, DeepFace).

[1499] Generative AI models: Generative AI models use natural language processing and machine learning models (e.g., GPT).

[1500] Server: Cloud-based data processing (e.g., AWS, Google Cloud).

[1501] Specific examples

[1502] Example: The emotion engine recognizes that Worker A is "fatigued" and "unmotivated." The generative AI model suggests schedule changes such as "increasing break time" and provides nutritional advice such as "eat bananas and nuts to replenish energy."

[1503] Example prompt sentence:

[1504] Worker's age: 30, weight: 75kg, emotional state: fatigue, motivation: low

[1505] Generate optimal work schedules and nutritional advice to improve worker health.

[1506] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1507] Step 1:

[1508] User Input

[1509] During the initial setup, users enter their fitness goals and physical information, such as age, weight, and work efficiency improvement, into the device. This input data is converted into JSON format, which is used to send the user's basic information and goals to the server.

[1510] Step 2:

[1511] Sending information

[1512] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server. The input data (user information and goals) is sent to the server.

[1513] Step 3:

[1514] Acquiring emotion data

[1515] The terminal (factory robot) uses a camera and a voice recognition microphone to collect the worker's facial expressions and voice. This collected data is analyzed through an emotion engine to determine the worker's emotional state. The input data is image data and voice data, and the output data is the worker's emotional state.

[1516] Step 4:

[1517] Sending emotional data

[1518] The device sends the analyzed emotion data to the server. The input data (emotion data) is sent to the server, and the analysis results from the emotion engine are compiled.

[1519] Step 5:

[1520] Generate training programs and nutritional advice

[1521] The server uses a generative AI model to generate optimal training programs and nutritional advice based on the user's physical information, goals, and emotional state. This process involves natural language processing and machine learning to process the data and generate specific training and meal plans. The input data is physical information, fitness goals, and emotional data, and the output data is the training program and nutritional advice.

[1522] Step 6:

[1523] Sending and viewing results

[1524] The server sends the generated training program and nutrition advice to the terminal, which receives it and displays the results to the user. The displayed results are the adjusted training program and nutrition advice.

[1525] Step 7:

[1526] Feedback and Adjustments

[1527] Users report their training progress and changes in their physical condition, and the device sends this feedback to the server. The server uses a generative AI model and emotion engine to adjust the training program and nutritional advice, and then sends it back to the device. In this process, user feedback is collected and the training program and nutritional advice are adjusted accordingly.

[1528] 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.

[1529] 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.

[1530] 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.

[1531] [Fourth embodiment]

[1532] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1533] 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.

[1534] 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).

[1535] 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.

[1536] 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.

[1537] 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).

[1538] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] 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.

[1544] 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."

[1545] System Configuration

[1546] The present invention includes a system that provides customized training programs and nutritional advice based on a user's fitness goals and physical information. The system mainly consists of a user terminal, a server, and a generative AI model.

[1547] Program processing explanation

[1548] 1. User Input

[1549] Users access a dedicated website or mobile app and enter their fitness goals (e.g., building muscle, losing weight, improving endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[1550] 2. Transmission of information

[1551] The terminal converts the entered user information into JSON format and sends it to the server.

[1552] 3. Receiving a Request

[1553] The server analyzes the received request and obtains the user's fitness goals and physical information.

[1554] 4. Training program generation

[1555] The server uses a generative AI model to generate an optimal training program based on the user's information.

[1556] Specifically, the system processes the user's goals and physical information as input data and generates detailed training content, such as "15 push-ups x 3 sets."

[1557] 5. Nutrition advice generation

[1558] The server similarly uses the generative AI model to generate nutritional advice tailored to the user.

[1559] For example, if a user's fitness goal is to "lose weight," a low-calorie, high-protein meal plan is suggested.

[1560] 6. Submitting the results

[1561] The server compiles the generated training program and nutritional advice into a JSON-formatted response and sends it to the user's device.

[1562] 7. Displaying the results

[1563] The device analyzes the responses it receives and displays training programs and nutritional advice on a dedicated chat screen.

[1564] 8. Feedback

[1565] Users report their training progress and changes in their physical condition to the server via a dedicated chat screen.

[1566] 9. Processing Feedback

[1567] Based on the feedback received, the server again uses the generative AI model to adjust the training program and nutrition advice.

[1568] For example, if a user reports knee pain, other low-impact exercises may be suggested instead of squats.

[1569] 10. Providing adjusted results

[1570] The server sends the adjusted training program and nutrition advice back to the user's terminal, which displays it.

[1571] Specific examples

[1572] 1. Input example

[1573] The user inputs his / her fitness goal and physical information: "25 years old, weighs 70 kg, and wants to build muscle."

[1574] 2. Generation example

[1575] The server receives the user's information and uses a generative AI model to generate a training program of "3 sets of 15 push-ups" and nutritional advice of "oats and fruit for breakfast, chicken salad for lunch."

[1576] 3. Feedback Examples

[1577] A user reports, "My knee hurt during my workout today."

[1578] The server receives feedback and suggests alternative exercises that put less strain on the knees.

[1579] As described above, the present invention provides a system that quickly and appropriately provides individualized training programs and nutritional advice based on user input, helping users achieve their fitness goals.

[1580] The processing flow will be explained below.

[1581] Step 1:

[1582] Users access a dedicated website or mobile app and click the "Start Training" button.

[1583] Step 2:

[1584] Users input their fitness goals (e.g., build muscle, lose weight, improve endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[1585] Step 3:

[1586] The device converts the fitness goals and physical information entered by the user into JSON format.

[1587] Step 4:

[1588] The terminal sends user information in JSON format to the server as a POST request.

[1589] Step 5:

[1590] The server parses the received POST request and obtains the user's fitness goals and physical information.

[1591] Step 6:

[1592] The server calls the generative AI model and instructs it to generate a training program using the user's information as input data.

[1593] Step 7:

[1594] The generative AI model generates a customized training program based on the user information and returns the results to the server.

[1595] Step 8:

[1596] The server then invokes the generative AI model again, this time instructing it to generate customized nutritional advice.

[1597] Step 9:

[1598] The generative AI model generates nutritional advice based on user information and returns the results to the server.

[1599] Step 10:

[1600] The server compiles the training program and nutrition advice into a JSON-formatted response and sends it to the device.

[1601] Step 11:

[1602] The device analyzes the response received from the server and displays the training program and nutritional advice on a dedicated chat screen.

[1603] Step 12:

[1604] Users can report their training progress and changes in their physical condition through a dedicated chat screen.

[1605] Step 13:

[1606] The terminal transmits the feedback from the user to the server.

[1607] Step 14:

[1608] The server analyzes the feedback it receives and uses generative AI models to direct adjustments to training programs and nutritional advice.

[1609] Step 15:

[1610] Based on the feedback, the generative AI model generates appropriately adjusted training programs and nutritional advice and returns the results to the server.

[1611] Step 16:

[1612] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device.

[1613] Step 17:

[1614] The terminal displays the adjusted information on a dedicated chat screen and provides it to the user.

[1615] Example 1

[1616] 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."

[1617] Currently, many fitness program and nutrition advice systems only provide general information and are not sufficiently customized to each user's physical information and fitness goals. Furthermore, it is difficult to provide dynamic training programs and nutrition advice that reflect user feedback. Therefore, there is a need for a system that can provide training programs and nutrition advice optimized for each user and flexibly adjust them based on feedback.

[1618] 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.

[1619] In this invention, the server includes means for receiving fitness goals and physical information from a user, means for converting the user's fitness goals and physical information into a data format and sending it to the server, means for generating a customized training program using a generative AI model based on the user's fitness goals and physical information, means for generating customized nutritional advice using the generative AI model based on the user's fitness goals and physical information, means for converting the customized training program and nutritional advice into a data format and providing it to the user, and means for receiving feedback from the user regarding progress in the training program and changes in physical condition and adjusting the training program and nutritional advice based on the feedback, thereby making it possible to provide an optimal training program and nutritional advice tailored to the user's individual needs and flexibly respond to the feedback.

[1620] "User" refers to the individual or end user who inputs fitness goals and physical information.

[1621] "Fitness goal" refers to a physical goal a user wishes to achieve (e.g., building muscle, losing weight, improving endurance, etc.).

[1622] "Physical information" refers to the user's individual physical characteristics (e.g., age, weight, height, body fat percentage, etc.).

[1623] "Data format" refers to a format (e.g., JSON format) that structures information entered by a user and converts it into a form that can be handled as digital data.

[1624] "Server" refers to the computer system that analyzes the data received from the User and utilizes the generative AI model to generate training programs and nutritional advice.

[1625] "Generative AI model" refers to an artificial intelligence model that is trained on large amounts of data and generates optimal training programs and nutritional advice based on user information.

[1626] "Customized training program" refers to a specific exercise plan tailored to an individual user based on their fitness goals and physical information.

[1627] "Customized nutrition advice" refers to a meal plan that is tailored based on an individual user's fitness goals and physical information.

[1628] "Feedback" refers to the act of the user providing the system with information about the progress of training and changes in physical condition.

[1629] "Adjustment" refers to the process of reevaluating and adapting existing training programs and nutritional advice based on feedback received.

[1630] MODE FOR CARRYING OUT THE INVENTION

[1631] This invention describes a concrete implementation of a system that provides customized training programs and nutritional advice based on a user's fitness goals and physical information. The entire system mainly consists of a user terminal, a server, and a generative AI model.

[1632] 1. User Input

[1633] Users access the system through a dedicated website or mobile app. The application runs on popular platforms such as iOS and Android. Users enter their fitness goals and physical information. For example, if a 25-year-old user weighs 70 kg and wants to build muscle, they can enter that information.

[1634] 2. Transmission of information

[1635] The device converts the information entered by the user into JSON format and sends it to the server using Internet Protocol. The JSON format data includes fitness goals and physical information. For example, it might look like this:

[1636] json

[1637] {

[1638] "age": 25,

[1639] "weight": 70,

[1640] "goal": "muscle_gain"

[1641] }

[1642] 3. Receiving a Request

[1643] The server parses the received request to obtain the user's fitness goals and physical information, which involves parsing the data to extract keys and values.

[1644] 4. Training program generation

[1645] The server uses a generative AI model (e.g., GPT-3) to generate an optimal training program based on the user's information. Specifically, the user's data is input to the generative AI model as a prompt sentence like the following:

[1646] User information: 25 years old, weight 70kg, goal: muscle building. Please provide a suitable training program for the user.

[1647] Based on this prompt, the generative AI model generates specific training content such as "15 push-ups x 3 sets."

[1648] 5. Nutrition advice generation

[1649] The server uses the same generative AI model to generate nutrition advice tailored to the user, using prompts like:

[1650] User information: 25 years old, weight 70kg, goal: to build muscle. Please provide a suitable nutrition plan for the user.

[1651] Based on this prompt, the generative AI model generates nutritional advice such as "oats and fruit for breakfast, chicken salad for lunch."

[1652] 6. Submitting the results

[1653] The server then compiles the generated training program and nutrition advice into a JSON response and sends it to the user's device, for example in the following JSON format:

[1654] json

[1655] {

[1656] "training_program": "3 sets of 15 push-ups",

[1657] "nutrition_advice": "Oats and fruit for breakfast, chicken salad for lunch"

[1658] }

[1659] 7. Displaying the results

[1660] The device analyzes the received response and displays the training program and nutrition advice on a dedicated chat screen. This analysis process includes parsing the JSON of the response and preparing it for display in the GUI.

[1661] 8. Feedback

[1662] Users can report their training progress and changes in their physical condition to the server via a dedicated chat screen. For example, they can write, "My knee started hurting during today's training."

[1663] 9. Processing Feedback

[1664] The server analyzes the received feedback and determines the appropriate response. For example, if the user feedback is "knee pain," it will again use the generative AI model to generate a new training program. The prompt text is as follows:

[1665] User information: Age 25, Weight 70kg, Goal: Build muscle. User reported knee pain. Provide alternative exercises that are less stressful on the knees.

[1666] 10. Providing adjusted results

[1667] The server then compiles the adjusted training program and nutrition advice into a JSON response and sends it to the user's device, which then displays the new information on the chat screen.

[1668] The invention allows users to receive customized training programs and nutritional advice tailored to their fitness goals, with the flexibility to adjust based on feedback.

[1669] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1670] Step 1: User enters fitness goals and physical information

[1671] Users access a dedicated website or mobile app and enter their fitness goals (e.g., muscle building, weight loss, endurance improvement) and physical information (e.g., age, weight, height, body fat percentage), which is then prepared as data to be sent to the system.

[1672] Input: Fitness goals and physical information (age, weight, height, body fat percentage, etc.)

[1673] Output: Input data converted to JSON format

[1674] Step 2: The device sends the user information

[1675] The device converts the information entered by the user into JSON format and sends it to the server using Internet Protocol, with the data transmitted over a secure communication channel.

[1676] Input: User information in JSON format

[1677] Output: User information sent to the server

[1678] Step 3: The server receives and analyzes the request

[1679] The server analyzes the received request to obtain the user's fitness goals and physical information. The analysis process involves parsing the received data to extract keys and values.

[1680] Input: JSON format user information received by the server

[1681] Output: Parsed fitness goals and body information

[1682] Step 4: The server generates a training program using the generated AI model

[1683] The server uses a generative AI model (e.g., GPT-3) to generate an optimal training program based on the parsed user information. The server inputs the following prompt to the generative AI model:

[1684] User information: 25 years old, weight 70kg, goal: muscle building. Please provide a suitable training program for the user.

[1685] Input: Fitness goal and physical information, prompt

[1686] Output: Generated training program (e.g., "3 sets of 15 push-ups")

[1687] Step 5: The server uses the generative AI model to generate nutrition advice

[1688] The server also uses a generative AI model to generate nutrition advice tailored to the user, using prompts like:

[1689] User information: 25 years old, weight 70kg, goal: to build muscle. Please provide a suitable nutrition plan for the user.

[1690] Input: Fitness goal and physical information, prompt

[1691] Output: Generated nutrition advice (e.g. "Oats and fruit for breakfast, chicken salad for lunch")

[1692] Step 6: Server sends results

[1693] The server then compiles the generated training program and nutrition advice into a JSON response and sends it to the user's device, for example in the following JSON format:

[1694] json

[1695] {

[1696] "training_program": "3 sets of 15 push-ups",

[1697] "nutrition_advice": "Oats and fruit for breakfast, chicken salad for lunch"

[1698] }

[1699] Input: Generated training programs and nutrition advice

[1700] Output: Sent to the terminal as a JSON response

[1701] Step 7: Your device will display the results

[1702] The device analyzes the received response and displays the training program and nutrition advice on a dedicated chat screen. This analysis process includes parsing the JSON of the response and preparing it for display in the GUI.

[1703] Input: JSON response (training program and nutrition advice)

[1704] Output: Training program and nutrition advice displayed on the chat screen

[1705] Step 8: User enters feedback

[1706] Users can report their training progress and changes in their physical condition to the server via a dedicated chat screen. For example, they can write, "My knee started hurting during today's training."

[1707] Input: Feedback on your training progress and changes in your fitness

[1708] Output: Information sent to the server as feedback

[1709] Step 9: Server processes feedback

[1710] The server analyzes the received feedback and determines the appropriate response. For example, if the user feedback is "knee pain," it will again use the generative AI model to generate a new training program. The prompt text is as follows:

[1711] User information: Age 25, Weight 70kg, Goal: Build muscle. User reported knee pain. Provide alternative exercises that are less stressful on the knees.

[1712] Input: Feedback, prompt

[1713] Output: Tailored training program

[1714] Step 10: The server sends the adjusted results

[1715] The server then compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the user's device.

[1716] Input: tailored training programs and nutritional advice

[1717] Output: Sent to the terminal as a JSON response

[1718] Step 11: Your device will display the adjusted results.

[1719] The device then analyzes the received response and displays the adjusted training program and nutritional advice on a dedicated chat screen.

[1720] Input: JSON response (adjusted training program and nutrition advice)

[1721] Output: Adjusted training program and nutrition advice displayed on the chat screen

[1722] (Application example 1)

[1723] 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."

[1724] The present invention aims to reduce the complexity of conventional systems and improve user convenience by automatically ordering meals customized based on the physical information of each user through a food delivery service and providing the user with the order results and nutritional advice in a system that provides training programs and nutritional advice to help users achieve their fitness goals. In conventional systems, after receiving a training program and nutritional advice, the user must choose for themselves what meals to actually eat, which can be a significant burden in terms of effort and time.

[1725] 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.

[1726] In this invention, the server includes means for receiving fitness goals and physical information from a user, means for generating a customized training program based on the user's fitness goals and physical information, means for generating customized nutritional advice based on the user's fitness goals and physical information, means for providing the customized training program and nutritional advice to the user, means for receiving feedback from the user regarding progress in the training program and changes in physical condition and adjusting the training program and nutritional advice based on the feedback, means for automatically ordering meals through a food delivery service based on the nutritional advice, and means for providing the user with the order results and nutritional advice from the food delivery service, thereby enabling the user to automatically order appropriate meals based on the individual nutritional advice and more effectively support achieving their fitness goals.

[1727] A "user" is an individual who utilizes the system and inputs fitness goals and physical information.

[1728] "Fitness Goal" means a physical or health goal that a user wishes to achieve, such as losing weight, building muscle, or improving endurance.

[1729] "Physical information" refers to physical data such as the user's age, weight, height, and body fat percentage.

[1730] A "training program" is a customized exercise plan generated based on a user's fitness goals and physical information.

[1731] "Nutrition Advice" means customized meal suggestions and plans provided based on a user's fitness goals and physical information.

[1732] "Feedback" refers to information provided by a user regarding progress in a training program and changes in physical condition.

[1733] A "food delivery service" is a service that allows you to order meals online and have them delivered.

[1734] "Generative AI Model" refers to the artificial intelligence algorithms used to generate optimal training programs and nutritional advice based on user information.

[1735] "Order Result" means the confirmation information regarding a meal ordered automatically through the food delivery service.

[1736] The term "means" refers to functions or components for executing various processes in this invention.

[1737] System Configuration

[1738] The present invention is a system that provides a user with a customized training program and nutritional advice based on their fitness goals and physical information, and automatically orders appropriate meals through a food delivery service. The system consists of a user terminal, a server, and a generative AI model.

[1739] Hardware and software used

[1740] Smartphone: User device on which the app is installed

[1741] Server: Data processing and AI model hosting

[1742] Generative AI models: generating nutrition advice and meal plans

[1743] Food Delivery API: Integration for automated meal ordering

[1744] Processing Description

[1745] 1. User Input

[1746] Users access a dedicated application on their smartphone and enter their fitness goals (e.g., weight loss, muscle building, endurance improvement, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.), which then inputs data tailored to the user's individual needs.

[1747] 2. Information Transmission

[1748] The user terminal converts the information entered by the user into JSON format and sends it to the server, which receives and analyzes this data.

[1749] 3. Nutrition advice generation

[1750] The server uses the generative AI model to generate optimal nutrition advice and meal plans based on the user's fitness goals and physical information, such as providing a low-calorie, high-protein meal plan for a user aiming to lose weight.

[1751] 4. Food delivery collaboration

[1752] Based on the meal plan, the server calls the API of the partner food delivery service and automatically orders the corresponding meal menu, eliminating the need for the user to choose their own meals.

[1753] 5. Sending and displaying results

[1754] The server converts the order details and nutrition advice back into JSON format and sends it to the user's device. The user's device analyzes this data and displays it on a dedicated screen. The user can then review the order details and make any necessary changes.

[1755] Specific examples

[1756] For example, if a user enters the following information:

[1757] Example prompt sentence:

[1758] Age: 30

[1759] Weight: 80kg

[1760] Height: 175cm

[1761] Body fat percentage: 20%

[1762] Fitness Goal: Muscle Building

[1763] Based on this information, the server uses a generative AI model to generate a meal plan such as "oats and fruit for breakfast, chicken salad for lunch" and automatically places an order with a food delivery service. The ordering results and nutrition advice are sent to the user's device, where they can view them.

[1764] In this way, the present invention can provide comprehensive support to users in achieving their fitness goals.

[1765] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1766] Step 1:

[1767] Users access a dedicated application on their smartphone and enter their fitness goals and physical information.

[1768] Input: Fitness goals (e.g., weight loss, muscle building), physical information (e.g., age, weight, height, body fat percentage, etc.)

[1769] Output: The input data is saved in the application.

[1770] Specific operation: The user enters the required information using the input form within the app and presses the submit button.

[1771] Step 2:

[1772] The terminal converts the information entered by the user into JSON format and sends it to the server.

[1773] Input: User-entered fitness goals and physical information

[1774] Output: JSON format data is sent to the server

[1775] Specific behavior: The application converts input data into JSON format and sends it to the server using an HTTP request.

[1776] Step 3:

[1777] The server parses the request received as JSON and retrieves the user's fitness goals and physical information.

[1778] Input: User data in JSON format

[1779] Output: Fitness goals and body information captured

[1780] What happens: The server receives the HTTP request and parses the data using a JSON parser.

[1781] Step 4:

[1782] The server uses the generative AI model to generate optimal nutritional advice and meal plans based on the user's fitness goals and physical information.

[1783] Input: Fitness goals and physical information

[1784] Output: Nutrition advice and meal plans

[1785] How it works: The server inputs the user's data into a generative AI model to generate training programs and nutritional advice.

[1786] Step 5:

[1787] Based on the generated meal plan, the server calls the API of a partner food delivery service and automatically orders the corresponding meal menu.

[1788] Enter: Nutritional advice and meal plans

[1789] Output: An order request to a food delivery service

[1790] Specific operation: The server calls the food delivery service's API and sends the order details.

[1791] Step 6:

[1792] The server converts the order details and nutrition advice back into JSON format and sends it to the user's terminal.

[1793] Input: Order details and nutrition advice

[1794] Output: JSON format data is sent to the user's device.

[1795] Specific operation: The server compiles the order results and nutrition advice and sends them to the user's terminal via an HTTP response.

[1796] Step 7:

[1797] The user terminal analyzes the received data and displays the order details and nutritional advice on a dedicated screen.

[1798] Input: Order details and nutrition advice in JSON format

[1799] Output: Order details and nutrition advice displayed on a dedicated screen

[1800] What happens: The application parses the JSON data and displays it in the user interface.

[1801] Step 8:

[1802] Users provide feedback through a dedicated screen.

[1803] Input: Feedback content (e.g., satisfaction, changes in physical condition)

[1804] Output: Feedback is sent to the server

[1805] Specific operation: The user enters their status and opinions using the feedback form within the app and submits it.

[1806] 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.

[1807] System Configuration

[1808] The present invention combines a system that provides customized training programs and nutritional advice based on a user's fitness goals and physical information with an emotion engine that recognizes the user's emotions. The system mainly consists of a user's device, a server, a generative AI model, and an emotion engine.

[1809] Program processing explanation

[1810] 1. User Input

[1811] Users access a dedicated website or mobile app and enter their fitness goals (e.g., building muscle, losing weight, improving endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[1812] 2. Transmission of information

[1813] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server.

[1814] 3. Receiving a Request

[1815] The server parses the received POST request and obtains the user's fitness goals and physical information.

[1816] 4. Training program generation

[1817] The server uses a generative AI model to generate an optimal training program based on the user's information.

[1818] Specifically, the system processes the user's goals and physical information as input data and generates detailed training content, such as "15 push-ups x 3 sets."

[1819] 5. Nutrition advice generation

[1820] The server similarly uses the generative AI model to generate nutritional advice tailored to the user.

[1821] For example, if a user's fitness goal is to "lose weight," a low-calorie, high-protein meal plan is suggested.

[1822] 6. Acquiring Emotion Data

[1823] The device runs an emotion engine to read emotions from the user's facial expressions, voice, and input text.

[1824] For example, analyzing a user's emotions through a webcam or microphone.

[1825] 7. Emotional Data Transmission

[1826] The device transmits the analyzed emotion data to the server.

[1827] 8. Submitting the results

[1828] The server compiles the generated training program, nutritional advice, and emotional data into a JSON-formatted response and sends it to the device.

[1829] 9. Displaying the results

[1830] The device analyzes the responses it receives and displays training programs and nutritional advice on a dedicated chat screen.

[1831] 10. Feedback

[1832] Users can report their training progress, changes in their physical condition, and their emotions through a dedicated chat screen.

[1833] 11. Processing Feedback

[1834] The server analyzes the feedback it receives and uses generative AI models and an emotion engine to direct adjustments to training programs and nutritional advice.

[1835] For example, if a user reports that "today's training was tough" and the emotion engine simultaneously detects a decline in the user's motivation, the system will either change the training content to something lighter or provide feedback to increase motivation.

[1836] 12. Provision of Adjusted Results

[1837] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device.

[1838] 13. Redisplay

[1839] The terminal displays the adjusted information on a dedicated chat screen and provides it to the user.

[1840] Specific examples

[1841] 1. Input example

[1842] The user inputs his / her fitness goal and physical information: "25 years old, weighs 70 kg, and wants to build muscle."

[1843] 2. Generation example

[1844] The server receives the user's information and uses a generative AI model to generate a training program of "3 sets of 15 push-ups" and nutritional advice of "oats and fruit for breakfast, chicken salad for lunch."

[1845] 3. Emotion recognition example

[1846] The emotion engine recognizes from the user's facial expressions and voice that the user is "motivated."

[1847] Based on this emotional information, the server generates additional encouraging messages to further motivate the user.

[1848] 4. Feedback Example

[1849] The user reports that "my knee hurt during training today" and looks depressed.

[1850] The server receives feedback and emotional data and suggests alternative exercises that put less strain on the knees.

[1851] By combining an emotion engine, the present invention can provide more personalized fitness guidance based on the user's emotional state, improving user motivation and satisfaction.

[1852] The processing flow will be explained below.

[1853] Step 1:

[1854] Users access a dedicated website or mobile app and click the "Start Training" button.

[1855] Step 2:

[1856] Users input their fitness goals (e.g., build muscle, lose weight, improve endurance, etc.) and physical information (e.g., age, weight, height, body fat percentage, etc.).

[1857] Step 3:

[1858] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server.

[1859] Step 4:

[1860] The server parses the received POST request and obtains the user's fitness goals and physical information.

[1861] Step 5:

[1862] The server calls the generative AI model and instructs it to generate a training program using the user's information as input. Specifically, it generates a customized exercise plan (e.g., "3 sets of 15 push-ups") based on the user's goals and physical information.

[1863] Step 6:

[1864] The server then calls the generative AI model again to generate customized nutrition advice based on the user's information, such as a meal plan like "oats and fruit for breakfast, chicken salad for lunch," taking into account the user's goals and physical information.

[1865] Step 7:

[1866] The device runs an emotion engine to read emotions from the user's facial expressions, voice, and input text. For example, it uses a webcam and microphone to detect the user's emotional state (e.g., joy, sadness, fatigue, etc.).

[1867] Step 8:

[1868] The device transmits the analyzed emotion data to the server.

[1869] Step 9:

[1870] The server compiles the generated training program, nutritional advice, and emotional data into a JSON-formatted response and sends it to the device.

[1871] Step 10:

[1872] The device analyzes the responses and displays training programs and nutritional advice on a dedicated chat screen, such as "3 sets of 15 push-ups" and "Oats and fruit for breakfast, chicken salad for lunch."

[1873] Step 11:

[1874] Users can report their training progress, changes in their physical condition, and their own emotions through a dedicated chat screen, for example, by providing feedback such as, "Today, my whole body feels tired."

[1875] Step 12:

[1876] The terminal transmits the feedback from the user to the server.

[1877] Step 13:

[1878] The server analyzes the received feedback and uses a generative AI model and emotion engine to direct adjustments to training programs and nutrition advice. For example, if a user reports feeling "tired all over," the emotion engine will detect the user's stress and fatigue and generate a lighter exercise program.

[1879] Step 14:

[1880] The generative AI model generates appropriately tailored training programs and nutritional advice based on the feedback and emotional data, and returns the results to the server.

[1881] Step 15:

[1882] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device.

[1883] Step 16:

[1884] The device displays the adjusted information on a dedicated chat screen and provides it to the user, for example, suggesting a new training program such as "Do 15 minutes of light stretching today."

[1885] The above are the specific processing steps of the invention that combines the emotion engine, which can effectively support the user in achieving their fitness goals and increasing their motivation.

[1886] Example 2

[1887] 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."

[1888] While conventional fitness systems provide customized training programs and nutritional advice based on a user's fitness goals and physical information, they lack the ability to provide personalized guidance that takes into account the user's emotional state. As a result, they lack the support to motivate users and encourage them to continue fitness.

[1889] 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.

[1890] In this invention, the server includes: means for receiving fitness goals and physical information from a user; means for transmitting the user's fitness goals and physical information from a terminal to the server; means for generating a customized training program using a generative AI model based on the user's fitness goals and physical information; means for generating customized nutritional advice using the generative AI model based on the user's fitness goals and physical information; means for operating an emotion engine that analyzes the user's emotions and acquiring emotion data; means for providing the customized training program and nutritional advice to the user; means for receiving feedback from the user regarding progress in the training program and changes in physical condition and adjusting the training program and nutritional advice based on the feedback and emotion data; and means for re-providing the adjusted training program and nutritional advice to the user. This enables more personalized fitness guidance based on the user's emotional state, maintaining user motivation and improving satisfaction.

[1891] "User" refers to an individual who utilizes the system to input fitness goals and physical information and receive customized training programs and nutritional advice.

[1892] "Fitness goal" refers to a physical goal a user wishes to achieve (e.g., building muscle, losing weight, improving endurance, etc.).

[1893] "Physical information" refers to information necessary for customizing a fitness program, such as a user's age, weight, height, and body fat percentage.

[1894] "Terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) through which a user inputs fitness goals and physical information and communicates with a server.

[1895] "Server" refers to a computer system that receives user input information, uses a generative AI model to generate training programs and nutritional advice, and provides them to the user.

[1896] "Generative AI Model" refers to an artificial intelligence model that automatically generates customized training programs and nutritional advice based on input user information.

[1897] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[1898] "Training Program" refers to the specific exercise content generated by the generative AI model based on the user's fitness goals and physical information.

[1899] "Nutrition Advice" refers to dietary guidance generated by the generative AI model based on the user's fitness goals and physical information.

[1900] "Emotion engine" refers to software or hardware for analyzing emotions from a user's facial expressions, voice, and input text.

[1901] "Emotion data" refers to information about the user's emotional state obtained as a result of analysis by the emotion engine.

[1902] "Feedback" refers to information that users report through a dedicated chat screen about their training progress, changes in physical condition, and their emotions.

[1903] "Adjustment" refers to restructuring training programs and nutrition advice based on user feedback and sentiment data.

[1904] The present invention is a system that provides a user with a customized training program and nutritional advice based on their fitness goals and physical information, and further combines it with an emotion engine that analyzes the user's emotions. Specific methods for implementing the invention are described below.

[1905] The system mainly consists of a user's device, a server, a generative AI model, and an emotion engine. The user uses the device to input their fitness goals and physical information.

[1906] A user accesses a dedicated website or mobile app and logs in. The user selects their fitness goal (e.g., muscle building, weight loss, endurance improvement, etc.) and enters their physical information (age, weight, height, body fat percentage, etc.) into a form. For example, the user might enter information such as "25 years old, weight 70 kg, muscle building."

[1907] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server as an HTTP POST request, which transmits the user information to the server.

[1908] The server parses the POST request and extracts the user's fitness goals and physical information, such as "age = 25," "weight = 70," and "goal = 'muscle_gain'."

[1909] The server inputs a prompt based on user information to the generative AI model. For example, a prompt such as "I'm 25 years old, weigh 70 kg, and want to build a lot of muscle. What kind of training program would be suitable?" is used. This causes the generative AI model to output a training program such as "15 push-ups x 3 sets."

[1910] Similarly, to generate nutrition advice, the server inputs a prompt to the generative AI model, such as "What is a good nutrition plan for a 25-year-old male to build muscle?", which then outputs the advice "Oats and fruit for breakfast, chicken salad for lunch."

[1911] Next, the device activates an emotion engine to read emotions from the user's facial expressions, voice, and input text. For example, the device may analyze the user's facial expressions and voice using a webcam or microphone, and the emotion engine may obtain emotion data such as "motivated."

[1912] The device sends the analyzed emotional data to the server, which then generates prompts based on the received emotional data and uses the generative AI model to provide feedback that motivates the user. For example, based on emotional data such as "I'm full of motivation," the server can generate an encouraging message such as "Do your best today!"

[1913] Users train and report their progress and changes in their physical condition via their device. For example, they can send feedback such as, "My knees hurt during today's training." The server analyzes this feedback and, using an emotion engine and generative AI model, suggests alternative exercises that put less strain on the knees.

[1914] For example, a prompt such as "Please suggest another exercise that puts less strain on the knees" can be input into a generative AI model, which will output a new training program such as "10 squats x 3 sets."

[1915] The server compiles the adjusted training program and nutritional advice into a JSON-formatted response and sends it to the device. The device analyzes this and displays the new training program and nutritional advice on a dedicated chat screen. For example, it might display "New training program: 3 sets of 10 squats. New nutritional advice: Protein shake for breakfast, chicken salad for lunch."

[1916] In this way, the present invention can provide more personalized fitness instruction based on the user's emotional state, maintaining user motivation and increasing satisfaction.

[1917] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1918] Step 1:

[1919] A user accesses a dedicated website or mobile app and logs in. Here, the user enters their fitness goals (e.g., muscle building, weight loss, endurance improvement, etc.) and physical information (age, weight, height, body fat percentage, etc.) into a form. For example, the user provides information such as "25 years old, weight 70 kg, muscle building." This is the input data. The device converts this input data into JSON format. Specifically, it generates the following JSON data:

[1920] json

[1921] {

[1922] "age": 25,

[1923] "weight": 70,

[1924] "goal": "muscle_gain"

[1925] }

[1926] Step 2:

[1927] The device sends the converted JSON data to the server as an HTTP POST request. This is the output data and is transferred to the server. Specifically, the device sends the data as an HTTP request.

[1928] Step 3:

[1929] The server analyzes the received POST request and extracts the user's fitness goals and physical information. The input data is the JSON data sent from the device, which is analyzed to obtain extracted data such as "age = 25", "weight = 70", and "goal = 'muscle_gain'". This is the output data. Specifically, the server analyzes the JSON data and stores the necessary information in variables.

[1930] Step 4:

[1931] The server uses the extracted information to generate a training program using a generative AI model. The input data includes the extracted "age = 25," "weight = 70," and "goal = 'muscle_gain'." The server converts this into a prompt and inputs it into the generative AI model. Specifically, the prompt used is "I'm 25 years old, weigh 70 kg, and would like to gain a lot of muscle. What kind of training program would be suitable for me?" The output data is a training program such as "15 push-ups x 3 sets."

[1932] Step 5:

[1933] The server uses the generative AI model to generate nutritional advice appropriate for the user. The input data is the user's fitness goals and physical information. Based on this, the server inputs a prompt such as "What is a suitable nutrition plan for a 25-year-old male to build muscle?" into the generative AI model. The output data is nutritional advice such as "Oats and fruit for breakfast, chicken salad for lunch."

[1934] Step 6:

[1935] The device operates an emotion engine to read emotions from the user's facial expressions, voice, and input text. The input data is sensory data such as the user's facial expressions, voice, and text. Specifically, the device captures this sensory data through a webcam or microphone and analyzes it with the emotion engine. Emotional data such as "motivated" is obtained as output data.

[1936] Step 7:

[1937] The device converts the analyzed emotion data into JSON format and sends it to the server. The input data is emotion data analyzed by the emotion engine, and includes emotions such as "motivated." Specifically, the device converts this emotion data into JSON format and sends it to the server as an HTTP POST request. The following JSON data is generated as output data:

[1938] json

[1939] {

[1940] "emotion": "motivated"

[1941] }

[1942] Step 8:

[1943] The server compiles the generated training program, nutritional advice, and emotional data into a JSON-formatted response and sends it to the device. The input data includes the generated training program, nutritional advice, and emotional data. Specifically, the server compiles this data, converts it into JSON format, and sends it to the device as an HTTP response. The following JSON response is generated as output data:

[1944] json

[1945] {

[1946] "training_program": "15 push-ups x 3 sets",

[1947] "nutrition_advice": "Oats and fruit for breakfast, chicken salad for lunch",

[1948] "emotion": "motivated"

[1949] }

[1950] Step 9:

[1951] The device analyzes the received response and displays a training program and nutritional advice on a dedicated chat screen. The input data is the JSON response sent from the server. Specifically, the device analyzes this response and displays on the chat screen, "Training program: 15 push-ups x 3 sets. Nutritional advice: Oats and fruit for breakfast, chicken salad for lunch."

[1952] Step 10:

[1953] Users report their training progress, changes in their physical condition, and their own emotions through a dedicated chat screen. The input data is feedback information entered by the user (e.g., "My knee hurt during today's training"). Specific actions involve the user entering feedback into the chat screen.

[1954] Step 11:

[1955] The server uses a generative AI model and emotion engine to adjust the training program and nutrition advice based on the received feedback and emotion data. The input data is the user's feedback information and emotion data. Specifically, the server inputs a prompt such as "Please suggest another exercise that puts less strain on the knees" into the generative AI model and outputs a new training program such as "10 squats x 3 sets."

[1956] Step 12:

[1957] The server compiles the adjusted training program and nutrition advice into a JSON format response and sends it to the device. The input data is the adjusted training program and nutrition advice. Specifically, the server compiles this data into JSON format and sends it to the device as an HTTP response. The following JSON response is generated as output data:

[1958] json

[1959] {

[1960] "training_program": "10 squats x 3 sets",

[1961] "nutrition_advice": "Protein shake for breakfast, chicken salad for lunch"

[1962] }

[1963] Step 13:

[1964] The device displays the adjusted information on a dedicated chat screen and provides it to the user. The input data is the JSON response sent from the server. Specifically, the device analyzes this response and displays on the chat screen, "New training program: 3 sets of 10 squats. New nutrition advice: Protein shake for breakfast, chicken salad for lunch."

[1965] (Application example 2)

[1966] 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."

[1967] Conventional training programs and nutrition advice are customized based on the user's physical information and fitness goals, but they cannot take into account the user's emotional state, and have the problem of not being able to appropriately respond to users' declining motivation or fatigue.In addition, it is difficult to provide individual support to factory workers to improve their work efficiency, so there is a need to optimize work plans based on the workers' health status and motivation.

[1968] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving fitness goals and physical information from a user, means for generating a customized training program based on the user's fitness goals and physical information, means for generating customized nutritional advice based on the user's fitness goals and physical information, means for analyzing the user's emotional state from facial expressions and voice, means for providing the customized training program and nutritional advice to the user, and means for adjusting the training program and nutritional advice based on feedback on progress in the training program and changes in physical condition and the user's emotional state. This makes it possible to provide an individually optimized training program and nutritional advice that takes the user's emotional state into consideration.

[1969] A "fitness goal" is a physical goal or objective that a user wishes to achieve.

[1970] "Physical information" refers to physical data such as the user's age, weight, height, and body fat percentage.

[1971] A "training program" is an exercise plan created based on a user's fitness goals and physical information.

[1972] "Nutrition Advice" refers to dietary and nutritional guidelines recommended based on a user's fitness goals and physical information.

[1973] "Emotional state" refers to the mental state or mood of the user that is analyzed from facial expressions and voice.

[1974] "Means of analysis" refers to methods or devices for analyzing data and deriving specific results or information.

[1975] "Feedback" refers to reports on changes in the user's physical condition and training progress.

[1976] "Adjusting means" refers to a method or device for receiving feedback and reconfiguring training programs or nutritional advice.

[1977] The present invention is a system for supporting the improvement of work efficiency and health management of factory workers, and provides optimal work schedules and nutritional advice based on feedback including the worker's emotional state.

[1978] System Configuration

[1979] This system receives the user's (factory worker's) fitness goals and physical information, and combines it with an emotion engine that analyzes the user's emotional state from facial expressions and voice. The system mainly consists of the following components:

[1980] Terminal: Sensor devices such as cameras and voice recognition microphones installed on factory robots

[1981] Server: a central processing unit that processes data

[1982] Generative AI Models: Artificial Intelligence Models for Generating Training Programs and Nutritional Advice

[1983] Emotion engine: An engine that analyzes the worker's facial expression and voice data to estimate their emotional state

[1984] Program processing explanation

[1985] 1. User Input

[1986] During the initial setup, the user (worker) enters their age, weight, goals for improving work efficiency, and other physical information.

[1987] 2. Transmission of information

[1988] The terminal (factory robot) sends the information entered by the user to the server.

[1989] 3. Acquiring Emotion Data

[1990] The terminal (factory robot) uses a camera and a voice recognition microphone to collect the worker's facial expressions and voice, which are then analyzed using an emotion engine.

[1991] 4. Sending analysis results

[1992] The device transmits the analyzed emotion data to the server.

[1993] 5. Generating training programs and nutritional advice

[1994] The server uses the generative AI model to generate optimal training programs (work schedules) and nutritional advice based on the user's physical information, goals, and emotional state.

[1995] 6. Sending and Displaying Results

[1996] The server sends the generated data to the terminal, which displays the results to the user.

[1997] 7. Feedback and Adjustments

[1998] Users report their training progress and changes in their physical condition, and the device sends this feedback to the server, which again uses the generative AI model and emotion engine to adjust the training program and nutrition advice.

[1999] Hardware and software used

[2000] Camera and voice recognition microphone: Collects facial and voice data from workers.

[2001] Sensor device: Measures workers' physical condition information.

[2002] Emotion engine: Uses Python libraries and emotion recognition APIs (e.g., OpenCV, DeepFace).

[2003] Generative AI models: Generative AI models use natural language processing and machine learning models (e.g., GPT).

[2004] Server: Cloud-based data processing (e.g., AWS, Google Cloud).

[2005] Specific examples

[2006] Example: The emotion engine recognizes that Worker A is "fatigued" and "unmotivated." The generative AI model suggests schedule changes such as "increasing break time" and provides nutritional advice such as "eat bananas and nuts to replenish energy."

[2007] Example prompt sentence:

[2008] Worker's age: 30, weight: 75kg, emotional state: fatigue, motivation: low

[2009] Generate optimal work schedules and nutritional advice to improve worker health.

[2010] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2011] Step 1:

[2012] User Input

[2013] During the initial setup, users enter their fitness goals and physical information, such as age, weight, and work efficiency improvement, into the device. This input data is converted into JSON format, which is used to send the user's basic information and goals to the server.

[2014] Step 2:

[2015] Sending information

[2016] The device converts the fitness goals and physical information entered by the user into JSON format and sends it to the server. The input data (user information and goals) is sent to the server.

[2017] Step 3:

[2018] Acquiring emotion data

[2019] The terminal (factory robot) uses a camera and a voice recognition microphone to collect the worker's facial expressions and voice. This collected data is analyzed through an emotion engine to determine the worker's emotional state. The input data is image data and voice data, and the output data is the worker's emotional state.

[2020] Step 4:

[2021] Sending emotional data

[2022] The device sends the analyzed emotion data to the server. The input data (emotion data) is sent to the server, and the analysis results from the emotion engine are compiled.

[2023] Step 5:

[2024] Generate training programs and nutritional advice

[2025] The server uses a generative AI model to generate optimal training programs and nutritional advice based on the user's physical information, goals, and emotional state. This process involves natural language processing and machine learning to process the data and generate specific training and meal plans. The input data is physical information, fitness goals, and emotional data, and the output data is the training program and nutritional advice.

[2026] Step 6:

[2027] Sending and viewing results

[2028] The server sends the generated training program and nutrition advice to the terminal, which receives it and displays the results to the user. The displayed results are the adjusted training program and nutrition advice.

[2029] Step 7:

[2030] Feedback and Adjustments

[2031] Users report their training progress and changes in their physical condition, and the device sends this feedback to the server. The server uses a generative AI model and emotion engine to adjust the training program and nutritional advice, and then sends it back to the device. In this process, user feedback is collected and the training program and nutritional advice are adjusted accordingly.

[2032] 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.

[2033] 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.

[2034] 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.

[2035] 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.

[2036] 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.

[2037] 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.

[2038] 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).

[2039] 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.

[2040] 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."

[2041] 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.

[2042] 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).

[2043] 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.

[2044] 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.

[2045] 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.

[2046] 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.

[2047] 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.

[2048] 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.

[2049] 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.

[2050] 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.

[2051] 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.

[2052] 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.

[2053] The following is further disclosed regarding the above embodiment.

[2054] (Claim 1)

[2055] means for receiving fitness goals and physical information from a user;

[2056] means for generating a customized training program based on the user's fitness goals and physical information;

[2057] means for generating customized nutrition advice based on the user's fitness goals and physical information;

[2058] means for providing said customized training program and nutritional advice to a user;

[2059] The system includes means for receiving feedback from a user regarding progress in said training program and changes in physical condition, and for adjusting said training program and nutritional advice based on said feedback.

[2060] (Claim 2)

[2061] 10. The system of claim 1, further comprising means for re-presenting the adjusted training program and nutritional advice to the user.

[2062] (Claim 3)

[2063] 10. The system of claim 1, further comprising means for using a generative AI model in generating the training program and nutritional advice.

[2064] "Example 1"

[2065] (Claim 1)

[2066] means for receiving fitness goals and physical information from a user;

[2067] means for converting the user's fitness goals and physical information into a data format and transmitting it to a server;

[2068] means for generating a customized training program using a generative AI model based on the user's fitness goals and physical information;

[2069] means for generating customized nutrition advice using a generative AI model based on the user's fitness goals and physical information;

[2070] means for converting the customized training program and nutrition advice into a data format and providing it to a user;

[2071] The system includes means for receiving feedback from a user regarding progress in said training program and changes in physical condition, and for adjusting said training program and nutritional advice based on said feedback.

[2072] (Claim 2)

[2073] 10. The system of claim 1, further comprising means for re-presenting the adjusted training program and nutritional advice to the user.

[2074] (Claim 3)

[2075] 10. The system of claim 1, further comprising means for using a generative AI model in generating the training program and nutritional advice.

[2076] "Application Example 1"

[2077] (Claim 1)

[2078] means for receiving fitness goals and physical information from a user;

[2079] means for generating a customized training program based on the user's fitness goals and physical information;

[2080] means for generating customized nutrition advice based on the user's fitness goals and physical information;

[2081] means for providing said customized training program and nutritional advice to a user;

[2082] means for receiving feedback from a user regarding progress in said training program and changes in physical condition, and for adjusting said training program and nutritional advice based on said feedback;

[2083] means for automatically ordering a meal through a food delivery service based on said nutritional advice;

[2084] The system includes a means for providing a user with ordering results and nutritional advice from the food delivery service.

[2085] (Claim 2)

[2086] 10. The system of claim 1, further comprising means for re-presenting the adjusted training program and nutritional advice to the user.

[2087] (Claim 3)

[2088] 10. The system of claim 1, further comprising means for using a generative AI model in generating the training program and nutritional advice.

[2089] "Example 2: Combining Emotion Engines"

[2090] (Claim 1)

[2091] means for receiving fitness goals and physical information from a user;

[2092] means for transmitting the user's fitness goals and physical information from a terminal to a server;

[2093] means for generating a customized training program using a generative AI model based on the user's fitness goals and physical information;

[2094] means for generating customized nutrition advice using a generative AI model based on the user's fitness goals and physical information;

[2095] means for activating an emotion engine that analyzes the emotions of a user and acquiring emotion data;

[2096] means for providing said customized training program and nutritional advice to a user;

[2097] means for receiving feedback from a user regarding progress in said training program and changes in physical condition, and for adjusting said training program and nutritional advice based on said feedback and emotional data;

[2098] a means for providing the user with the adjusted training program and nutritional advice again;

[2099] ...

[2100] A system including:

[2101] (Claim 2)

[2102] 10. The system of claim 1, further comprising means for re-presenting the adjusted training program and nutritional advice to the user.

[2103] (Claim 3)

[2104] 10. The system of claim 1, further comprising means for using a generative AI model in generating the training program and nutritional advice.

[2105] "Application example 2 when combining emotion engines"

[2106] (Claim 1)

[2107] means for receiving fitness goals and physical information from a user;

[2108] means for generating a customized training program based on the user's fitness goals and physical information;

[2109] means for generating customized nutrition advice based on the user's fitness goals and physical information;

[2110] means for analyzing the emotional state of a user from facial expressions and voice;

[2111] means for providing said customized training program and nutritional advice to a user;

[2112] The system includes means for adjusting said training program and nutritional advice based on feedback on progress of said training program and changes in physical condition, as well as emotional state.

[2113] (Claim 2)

[2114] 10. The system of claim 1, further comprising means for re-presenting the adjusted training program and nutritional advice to the user.

[2115] (Claim 3)

[2116] 10. The system of claim 1, further comprising means for using a generative AI model in generating the training program and nutritional advice. [Explanation of symbols]

[2117] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving fitness goals and physical information from a user; means for generating a customized training program based on the user's fitness goals and physical information; means for generating customized nutrition advice based on the user's fitness goals and physical information; means for providing said customized training program and nutritional advice to a user; The system includes means for receiving feedback from a user regarding progress in said training program and changes in physical condition, and for adjusting said training program and nutritional advice based on said feedback.

2. The system of claim 1 further comprising means for re-presenting the adjusted training program and nutritional advice to the user.

3. The system of claim 1 , further comprising means for using a generative AI model to generate the training program and nutritional advice.

Images