system

Abstract

To provide a system.SOLUTION: The system includes: means for collecting data on body sculpting of a user; means for analyzing the data by using a generative AI model and specifying a failure pattern of the body sculpting of the user; means for generating information of at least one of a training plan and meal guidance personalized on the basis of the specified failure pattern and proposing the information; and means for acquiring the emotion state of the user by using an emotion engine and providing a feedback based on the acquired emotion state.SELECTED DRAWING: Figure 1

Description

Technical Field

[0005] , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

[0006] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 1 of Example 1. [Figure 12]This is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 of Embodiment 2. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Form Example 2. [Figure 15] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 3 of Example 3. [Figure 16] This is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Form Example 3. [Figure 17] This is a sequence diagram showing the processing flow of the data processing system in Example 1 of the Form 1 when an emotion engine is combined. [Figure 18] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] This is a sequence diagram showing the processing flow of the data processing system in Example 2 of the Form 2 when an emotion engine is combined. [Figure 20] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] This is a sequence diagram showing the processing flow of the data processing system in Example 3 of the Form 3 when an emotion engine is combined. [Figure 22] This is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. [Modes for carrying out the invention]

[0007] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (TENSOR PROCESSING UNIT (registered trademark)), etc.

[0010] In the following embodiments, the numbered RAM (Random Access Memory) is a memory where information is temporarily stored and is used as a work memory by the processor.

[0011] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disk (e.g., hard disk), or magnetic tape, etc.

[0012] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0014] [First Embodiment]

[0015] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0016] As shown in Figure 1, the 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.

[0017] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0019] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0020] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0022] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0024] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0026] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0027] "Example of form 1"

[0028] The diet support system of the present invention combines VR technology and generative AI to provide users with personalized training and dietary guidance. Specifically, users wear a VR device at home and perform exercises according to a training program provided by the generative AI. The generative AI generates an optimal training menu based on information such as the user's body type, physical fitness, and health condition. Similarly, dietary guidance is also provided by the generative AI, taking into account the user's food preferences, health condition, and diet goals.

[0029] "Example of form 2"

[0030] The diet support system of this invention also sells special nutritional foods and training equipment. These products work in conjunction with the training and dietary guidance provided by the generating AI to more effectively support the user's diet. For example, based on the dietary guidance provided by the generating AI, it can recommend special nutritional foods and encourage their purchase. Similarly, it can recommend training equipment optimized for the training program provided by the generating AI and encourage its purchase.

[0031] "Example of form 3"

[0032] The diet support system of this invention analyzes the user's past failure data to support sustainable weight loss success. Specifically, a generating AI analyzes the user's past diet history and failure patterns, and based on this, provides personalized training and dietary guidance. This prevents the user from repeating the same failures and supports sustainable weight loss success.

[0033] The following describes the processing flow for each example of the form.

[0034] "Example of form 1"

[0035] Step 1: The user puts on the VR device at home.

[0036] Step 2: The generating AI creates an optimal training menu based on information such as the user's body type, physical fitness, and health condition.

[0037] Step 3: The user performs exercises according to the training program provided by the AI-generated program.

[0038] Step 4: The generating AI provides dietary guidance, taking into account the user's food preferences, health condition, and weight loss goals.

[0039] "Example of form 2"

[0040] Step 1: In conjunction with the training and dietary guidance provided by the AI, sell special nutritional supplements and training equipment.

[0041] Step 2: Based on the dietary guidance provided by the generating AI, recommend special nutritional supplements and encourage their purchase.

[0042] Step 3: The generated AI recommends training equipment optimized for the training program it provides and encourages its purchase.

[0043] "Example of form 3"

[0044] Step 1: The generating AI analyzes the user's past diet history and patterns of failure.

[0045] Step 2: The generating AI provides personalized training and dietary guidance based on the analysis results.

[0046] Step 3: This prevents users from repeating the same setbacks and supports sustainable weight loss success.

[0047] (Example 1)

[0048] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0049] Traditional diet support systems offer uniform training and dietary guidance to all users, failing to adequately personalize the program based on individual user body type, fitness level, health status, dietary preferences, and weight loss goals. Furthermore, a lack of sustained support that takes into account users' past failures contributes to low success rates. Additionally, the lack of integrated sales of special nutritional supplements and training equipment means users have to purchase necessary items separately, creating an inconvenient situation.

[0050] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0051] In this invention, the server includes means for using VR technology, means for providing personalized training and dietary guidance using generative AI, means for generating an optimal training menu based on the user's body type information, physical fitness information, and health status, means for generating an optimal meal plan based on the user's dietary preferences, health status, and weight loss goals, and means for selling special nutritional foods and training equipment. This makes it possible to provide individually optimized training and dietary guidance to users and to provide continuous support that takes into account past failure data. In addition, by providing necessary nutritional foods and training equipment in one package, user convenience can be improved.

[0052] "VR technology" is a technology that uses virtual reality to provide users with an immersive experience.

[0053] "Generative AI" is a technology that uses artificial intelligence to analyze data and generate optimal training and meal plans for users.

[0054] "Personalized training" means providing a training program that is individually optimized based on the user's body type, fitness level, and health status.

[0055] "Personalized meal guidance" means providing a meal plan that is individually optimized based on the user's dietary preferences, health condition, and weight loss goals.

[0056] "Body type information" refers to the user's physical data, such as height, weight, and body fat percentage.

[0057] "Physical fitness information" refers to physical data such as the user's exercise experience and current exercise habits.

[0058] "Health status" refers to data about the user's health, such as allergies and pre-existing medical conditions.

[0059] "Dietary preferences" refer to data about a user's food preferences, such as their favorite and least favorite ingredients.

[0060] A "diet goal" is a target that the user wants to achieve, such as weight loss or muscle gain.

[0061] "Special nutritional supplements" are foods specifically designed to support dieting or training.

[0062] "Training equipment" refers to the devices and equipment that users use to perform training.

[0063] "Past failure data" refers to data about users' past experiences of failing at dieting or training.

[0064] "Sustained support" means providing long-term assistance to help users continue their diet and training.

[0065] Modes for carrying out the invention

[0066] This invention is a diet support system that combines VR technology and generative AI to provide users with personalized training and dietary guidance. Specific embodiments of this system are described below.

[0067] System Configuration

[0068] This system consists of a server, terminals (VR devices or smartphones), and users. The server is responsible for generating training menus and meal plans using a generative AI model and sending them to the terminals. The terminals send information entered by the user to the server, and the training menus and meal plans received from the server are displayed to the user.

[0069] Hardware and software to be used

[0070] The server is a high-performance computer with powerful computing capabilities and software installed to run generative AI models (e.g., OpenAI's GPT-4). The terminal is a VR device or smartphone that provides an interface for users to input information and view training menus and meal plans.

[0071] Data processing and calculation

[0072] The server receives data from the user, such as body shape information, fitness level, health status, dietary preferences, and weight loss goals. Based on this data, it uses an AI model to generate optimal training menus and meal plans. The generated menus and plans are sent to the user's device and displayed to them.

[0073] Specific example

[0074] Example 1: Generating a training menu

[0075] The user inputs body type information (height 170cm, weight 70kg, body fat percentage 20%) and fitness information (no prior exercise experience, current exercise habit is walking once a week). Based on this information, the server uses a generative AI model to generate a training menu suitable for the user. For example, the following prompt text is input to the generative AI model.

[0076] Prompt message:

[0077] "Please create a training program suitable for a 30-year-old male who is 170cm tall, weighs 70kg, has a body fat percentage of 20%, and has no prior exercise experience."

[0078] Example 2: Generating a meal plan

[0079] The user inputs their dietary preferences (favorite foods are chicken and broccoli, disliked foods are fish), health status (no allergies, no chronic illnesses), and diet goal (weight loss). Based on this information, the server uses a generative AI model to generate a meal plan suitable for the user. For example, the following prompt text is input to the generative AI model.

[0080] Prompt message:

[0081] "Please create a one-week meal plan suitable for a 30-year-old man who likes chicken and broccoli, dislikes fish, has no allergies, and is aiming to lose weight."

[0082] In this way, the server, terminal, and user work together to provide personalized diet support.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] Users input their body information (height, weight, body fat percentage), physical fitness information (exercise experience, current exercise habits), and health status (allergies, pre-existing conditions) using a device (VR device or smartphone). This information is entered through the device's interface and sent to the server. The input data is stored in a database as individual user information.

[0086] Step 2:

[0087] The terminal sends the entered user information to the server. The server stores the received information in a database and generates prompts for input into the AI ​​model. For example, based on the user's body type and fitness information, it might generate a prompt such as, "Create a training menu suitable for a 30-year-old male who is 170cm tall, weighs 70kg, has a body fat percentage of 20%, and has no prior exercise experience."

[0088] Step 3:

[0089] The server inputs the generated prompt sentences into the AI ​​model, which then generates the optimal training menu for the user. The AI ​​model analyzes the data based on the input prompt sentences and outputs the training menu. The output training menu is saved on the server.

[0090] Step 4:

[0091] The server sends the generated training menu to the terminal. The terminal displays the received training menu to the user. The user performs the exercises according to the displayed training menu. The terminal tracks the user's movements in real time and provides feedback on correct form and movements.

[0092] Step 5:

[0093] Users use a terminal to input their dietary preferences (favorite and disliked foods), health status (allergies, chronic illnesses), and diet goals (weight loss, muscle gain). This information is entered through the terminal's interface and sent to the server. The input data is stored in a database as individual user information.

[0094] Step 6:

[0095] The server uses a generative AI model to generate meal plans based on stored meal information. For example, based on the user's dietary preferences and health status, it might generate a prompt message such as, "Create a 1-week meal plan suitable for a 30-year-old male who likes chicken and broccoli, dislikes fish, has no allergies, and is aiming to lose weight."

[0096] Step 7:

[0097] The server inputs the generated prompt text into the AI ​​model, which then generates the optimal meal plan for the user. The AI ​​model analyzes the data based on the input prompt text and outputs the meal plan. The output meal plan is saved on the server.

[0098] Step 8:

[0099] The server sends the generated meal plan to the device. The device displays the received meal plan to the user. The user eats according to the displayed meal plan. The device tracks whether the user is adhering to the meal plan and provides reminders and advice as needed.

[0100] In this way, the server, terminal, and user work together to provide personalized diet support.

[0101] (Application Example 1)

[0102] Next, we will describe Application Example 1 of Form 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."

[0103] Traditional diet support systems often provide users with uniform training and dietary guidance, lacking personalized support that adequately considers each user's body type, physical fitness, health condition, food preferences, and weight loss goals. Furthermore, dietary guidance requires users to procure and cook their own food, which is time-consuming and makes sustainable weight loss difficult. Additionally, the lack of continuous support utilizing users' past failure data contributes to a low success rate in weight loss programs.

[0104] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0105] This invention includes a server that utilizes VR technology, provides personalized training and dietary guidance using generative AI, sells special nutritional foods and training equipment, and proposes an optimal meal menu based on information such as the user's body type, physical fitness, health condition, dietary preferences, and weight loss goals, and allows the user to order meals through a food delivery service. This enables the provision of individually optimized training and dietary guidance to users, and further reduces the effort involved through a food delivery service, thereby making sustainable weight loss success possible.

[0106] "VR technology" is a technology that provides users with virtual reality, allowing them to experience a virtual environment different from the real world through sight and sound.

[0107] "Generative AI" is a technology that uses artificial intelligence to analyze user data and generate individually optimized training and dietary guidance.

[0108] "Personalized training" means providing an optimal training program based on individual information such as the user's body type, physical fitness, and health condition.

[0109] "Dietary guidance" involves suggesting appropriate meal menus, taking into account the user's food preferences, health condition, and weight loss goals.

[0110] "Special nutritional foods" are foods specifically designed for weight loss or maintaining health, and their nutritional balance is taken into consideration.

[0111] "Training equipment" refers to devices used for exercise and fitness, supporting users in improving their physical fitness and building muscle strength.

[0112] A "food delivery service" is a service that delivers meals ordered by users to their homes, saving users time and effort.

[0113] "User's body type" refers to the shape and size of the user's body, and serves as a basis for creating diet and training plans.

[0114] "Physical fitness" refers to the user's physical endurance and muscle strength, and is an important factor when determining the training menu.

[0115] "Health status" refers to the user's current health condition and should be taken into consideration when providing training or dietary guidance.

[0116] "Dietary preferences" refer to the foods and eating styles that users like, and are important information when providing personalized dietary guidance.

[0117] A "diet goal" refers to the weight or body shape target that the user wishes to achieve, and serves as the basis for creating training and dietary guidance plans.

[0118] As an embodiment of this invention, the following system is constructed.

[0119] First, the server provides a means using VR technology. Specifically, users can wear a VR device to train in a virtual reality environment. This VR device provides a realistic training environment through sight and sound, enhancing the user's sense of immersion.

[0120] Next, the server has the means to provide personalized training and dietary guidance using generative AI. The generative AI generates optimal training and meal plans based on information such as the user's body type, physical fitness, health status, dietary preferences, and weight loss goals. This is done by using the OpenAI API to analyze the user's individual data and provide the optimal plan.

[0121] Furthermore, the server has a means of selling special nutritional supplements and training equipment. This allows users to easily purchase the nutritional supplements and training equipment they need.

[0122] Furthermore, the server suggests optimal meal menus based on information such as the user's body type, physical fitness, health status, dietary preferences, and weight loss goals, and provides a means for users to order meals through a food delivery service. This allows users to easily receive healthy meals at home.

[0123] The specific process involves first acquiring user information. This includes data entered by the user via smartphone or computer. Next, prompt messages are sent to the generation AI model to generate optimal training and meal plans. The following is an example of a prompt message:

[0124] User's body type: Standard

[0125] User's physical condition: Medium

[0126] User's health status: Good

[0127] User's dietary preferences: Japanese food

[0128] User's diet goal: Weight loss

[0129] Based on this information, please generate an optimal training program and meal plan.

[0130] The generated menu is displayed to the user through a VR device. The user can perform training according to this menu and also order meals using a food delivery service based on the meal menu.

[0131] This system allows users to receive personalized training and dietary guidance, and further reduces the hassle through a food delivery service, making sustainable weight loss success possible.

[0132] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0133] Step 1:

[0134] Users input individual information such as body type, physical fitness, health status, dietary preferences, and weight loss goals using their smartphones or computers. This information is sent to a server. The input data includes the user's height, weight, exercise habits, and dietary preferences. The server receives this data and stores it in a database.

[0135] Step 2:

[0136] The server generates prompt messages for the AI ​​model based on stored user information. These prompt messages include information such as the user's body type, physical fitness, health status, dietary preferences, and weight loss goals. An example of a specific prompt message is as follows:

[0137] User's body type: Standard

[0138] User's physical condition: Medium

[0139] User's health status: Good

[0140] User's dietary preferences: Japanese food

[0141] User's diet goal: Weight loss

[0142] Based on this information, please generate an optimal training program and meal plan.

[0143] Step 3:

[0144] The server sends prompt messages to the generative AI model, which generates optimal training and meal plans. The generative AI model analyzes the prompt messages and generates the most suitable training and meal plans for the user. The generated plans are returned to the server.

[0145] Step 4:

[0146] The server sends the generated training and meal plans to the VR device. The user puts on the VR device and trains in a virtual reality environment. The VR device provides a realistic training environment through sight and sound, enhancing the user's immersion.

[0147] Step 5:

[0148] The server orders meals through a food delivery service based on the generated meal menu. Users use their smartphones or computers to review the suggested meal menu and confirm their order. The server sends the order information to the food delivery service, and the meals are delivered to the user's home.

[0149] Step 6:

[0150] Users receive delivered meals and eat according to the suggested meal menu. This allows users to maintain a healthy diet while saving them time and effort.

[0151] Step 7:

[0152] The server collects users' training and dietary history data and uses it to inform future training and dietary guidance. This allows the system to track user progress and provide more effective weight loss support.

[0153] (Example 2)

[0154] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0155] Traditional diet support systems have struggled to provide personalized dietary guidance and training programs for individual users, resulting in ineffective weight loss support. Furthermore, the lack of appropriate recommendations for special nutritional foods and training equipment has led to low user success rates in weight loss.

[0156] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for the user to input personal data using a terminal, means for the server to receive and store the input data, means for the server to analyze the data using a generated AI model and generate dietary guidance and training programs, means for the server to recommend special nutritional foods based on the generated dietary guidance, means for the server to recommend training equipment based on the generated training program, and means for the terminal to display the advice and recommended products received from the server to the user. This makes it possible to provide personalized dietary guidance and training programs to the user and to make appropriate recommendations for special nutritional foods and training equipment, thereby improving the user's success rate in dieting.

[0157] A "user" refers to an individual who uses the system to input personal data and receive dietary guidance or training programs.

[0158] A "device" refers to a device used by a user to input personal data and receive and display advice and recommended products from a server. Specifically, this includes smartphones and personal computers.

[0159] A "server" refers to a computer system that stores data received from users, analyzes that data using a generated AI model, and creates dietary guidance and training programs.

[0160] A "generative AI model" refers to an artificial intelligence model that receives a user's personal data and prompt text as input and generates appropriate dietary guidance and training programs.

[0161] "Dietary guidance" refers to providing advice on appropriate dietary content and nutritional intake methods based on the user's weight loss goals and health condition.

[0162] A "training program" refers to providing advice on appropriate exercise content and training methods based on the user's weight loss goals and exercise habits.

[0163] "Special nutritional foods" refer to foods recommended based on the user's dietary guidance that are effective for weight loss and maintaining health. Specifically, these include protein bars and low-calorie smoothies.

[0164] "Training equipment" refers to equipment recommended based on the user's training program to effectively perform exercise and training. Specifically, this includes items such as treadmills and dumbbell sets.

[0165] "Advice" refers to specific instructions and recommendations regarding dietary guidance and training programs that the generative AI model provides based on the user's personal data.

[0166] "Recommended products" refer to special nutritional foods and training equipment that the generating AI model recommends based on the user's dietary guidance and training program.

[0167] This invention is a diet support system in which a user inputs personal data using a terminal, and a server analyzes that data to provide personalized dietary guidance and training programs. Specific embodiments of this system are described below.

[0168] First, users access the system using devices such as smartphones or personal computers. Through a dedicated application or web form, users enter personal data such as height, weight, age, gender, exercise habits, and diet. For example, a user might enter "Height 160cm, weight 70kg, age 30, gender female, exercise twice a week, breakfast is bread and coffee, lunch is salad, dinner is fish and vegetables."

[0169] Next, the terminal sends the entered data to the server. The server stores the received data using a relational database management system (RDBMS) such as MySQL® or PostgreSQL. For example, it executes the following SQL query: "INSERT INTO user_data (height, weight, age, gender, exercise_habits, diet) VALUES (160, 70, 30, 'female', '2 times a week', 'bread and coffee for breakfast, salad for lunch, fish and vegetables for dinner');"

[0170] The server uses data analysis software such as Python® or R to analyze stored user data. The server uses a generative AI model (e.g., GPT-4) to generate optimal dietary guidance and training programs for the user's weight loss goals. The generative AI model takes prompt sentences as input and generates appropriate advice. For example, the following prompt sentences are input to the generative AI model.

[0171] "I am a 30-year-old woman, weighing 70kg, 160cm tall, and I exercise twice a week. My weight loss goal is to lose 5kg in 3 months. Please provide me with the optimal dietary guidance and training program."

[0172] The AI ​​model generates dietary advice based on this prompt. For example, it might generate advice such as, "We recommend consuming high-protein foods for breakfast and plenty of vegetables for lunch and dinner. For snacks, nuts and yogurt are good choices." It might also make recommendations such as, "We recommend purchasing protein bars or low-calorie smoothies."

[0173] Similarly, the generative AI model generates training programs. For example, it might generate advice such as, "Do 30 minutes of aerobic exercise (e.g., jogging or cycling) three times a week, and add strength training twice a week." It might also make recommendations such as, "We recommend purchasing a treadmill or dumbbell set."

[0174] Finally, the server sends the generated advice and recommended products to the device. The device then displays the advice and recommended products to the user using the application's dashboard or notification features. For example, it might display specific advice and recommended products along with a message such as, "A meal plan and training program based on your weight loss goals has been generated. Details are below."

[0175] In this way, users can receive personalized dietary guidance and training programs, as well as appropriate recommendations for special nutritional foods and training equipment. This system makes it possible to improve users' success rates in dieting.

[0176] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0177] Step 1:

[0178] Users access the system using their devices and enter personal data. Specifically, they enter information such as height, weight, age, gender, exercise habits, and diet through a dedicated application or web form. For example, they might enter "Height 160cm, weight 70kg, age 30, gender female, exercise twice a week, breakfast is bread and coffee, lunch is salad, dinner is fish and vegetables." The entered data is saved on the device in JSON format or as form data.

[0179] Step 2:

[0180] The terminal sends the entered data to the server. Specifically, it sends user data to the server using an HTTP POST request. For example, it sends JSON data to an endpoint called " / submitUserData". The server stores the received data in a relational database management system (RDBMS) such as MySQL or PostgreSQL. For example, it executes an SQL query such as "INSERT INTO user_data (height, weight, age, gender, exercise_habits, diet) VALUES (160, 70, 30, 'female', '2 times a week', 'bread and coffee for breakfast, salad for lunch, fish and vegetables for dinner');".

[0181] Step 3:

[0182] The server analyzes the stored user data. Specifically, it uses data analysis software such as Python or R to calculate the user's BMI (Body Mass Index) and calorie consumption. For example, it uses the formula "BMI = weight / (height / 100)^2" to calculate BMI. The analysis results are used to generate prompt statements for input into the generative AI model.

[0183] Step 4:

[0184] The server uses a generative AI model (e.g., GPT-4) to generate optimal dietary guidance and training programs for the user's weight loss goals. Specifically, it inputs prompt sentences into the generative AI model and generates appropriate advice. For example, it inputs the prompt sentence, "I am a 30-year-old woman, weighing 70kg, 160cm tall, and I exercise twice a week. My weight loss goal is to lose 5kg in 3 months. Please provide optimal dietary guidance and training programs." The generative AI model then generates dietary guidance and training programs based on this prompt sentence.

[0185] Step 5:

[0186] The server recommends specific nutritional foods based on the generated dietary guidance. Specifically, it selects nutritional foods suitable for the user based on the dietary guidance provided by the generating AI model. For example, along with advice such as, "We recommend consuming high-protein foods for breakfast and plenty of vegetables for lunch and dinner. For snacks, nuts and yogurt would be good choices," it might also recommend, "We recommend purchasing protein bars or low-calorie smoothies."

[0187] Step 6:

[0188] The server recommends training equipment based on the generated training program. Specifically, it selects training equipment suitable for the user based on the training program provided by the generating AI model. For example, along with advice such as, "Do 30 minutes of aerobic exercise (e.g., jogging or cycling) three times a week, and add strength training twice a week," it might recommend, "We recommend purchasing a treadmill or dumbbell set."

[0189] Step 7:

[0190] The server sends the generated advice and recommended products to the device. Specifically, it uses an HTTP response to send the generated advice and recommended products to the device. The device displays the received information to the user using the application's dashboard or notification function. For example, it might display specific advice and recommended products along with a message such as, "A meal plan and training program based on your diet goals has been generated. Details are as follows."

[0191] (Application Example 2)

[0192] Next, we will describe Application Example 2 of Form 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."

[0193] Traditional diet support systems have difficulty providing individualized dietary guidance and training programs, and have also struggled to effectively recommend special nutritional foods and training equipment. Furthermore, they lack support for sustained diet success that takes into account users' past failures, resulting in a low long-term success rate for dieting.

[0194] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0195] This invention includes a server that includes means for collecting user data, means for analyzing the data using a generating AI to generate optimal dietary guidance and training programs, and means for recommending special nutritional foods and training equipment based on the programs provided by the generating AI and encouraging their purchase. This enables the provision of an optimal diet plan for each individual user and the effective recommendation of special nutritional foods and training equipment. Furthermore, by analyzing the user's past failure data, it is possible to support sustainable weight loss success.

[0196] "User data" refers to information such as the user's weight loss goals, current physical condition, eating habits, and exercise habits.

[0197] "Generative AI" refers to a system that uses artificial intelligence technology to analyze data and generate optimal dietary guidance and training programs.

[0198] "Dietary guidance" refers to suggesting appropriate meal content and timing based on the user's health condition and weight loss goals.

[0199] A "training program" refers to suggesting appropriate exercise content and frequency based on the user's physical fitness level and weight loss goals.

[0200] "Nutritional foods" refer to foods specifically designed for weight loss or maintaining health.

[0201] "Training equipment" refers to tools and devices used to effectively perform exercise or training.

[0202] "Recommendation" refers to the process where the generating AI suggests specific nutritional foods or training equipment to the user based on its analysis results.

[0203] "Encouraging purchase" refers to making it easy for users to buy recommended nutritional supplements or training equipment.

[0204] "Past failure data" refers to information about users' past experiences of failing at dieting and the reasons for those failures.

[0205] "Sustainable weight loss success" refers to users continuing their diet over a long period of time and achieving their goals.

[0206] The following system configuration and processing procedure will be described as embodiments for carrying out this invention.

[0207] System Configuration

[0208] 1. Collection of user data

[0209] Hardware: Smartphone

[0210] Software: Application user interface

[0211] Data: User's diet goals, current physical condition, eating habits, exercise habits

[0212] 2. Data analysis using generative AI

[0213] Hardware: Cloud Servers

[0214] Software: Generative AI models (e.g., GPT-4)

[0215] Data Processing: Analyze user data to generate optimal dietary guidance and training programs.

[0216] 3. Selection of Recommended Products

[0217] Hardware: Cloud Servers

[0218] Software: Product database, recommendation engine

[0219] Data processing: Based on programs provided by the generation AI, special nutritional supplements and training equipment are selected.

[0220] 4. Suggestions for users

[0221] Hardware: Smartphone

[0222] Software: Application user interface

[0223] Data display: Recommended dietary guidance, training programs, and related product information.

[0224] 5. Purchase Process

[0225] Hardware: Smartphone

[0226] Software: Electronic payment system

[0227] Data processing: Processing and verification of purchase procedures

[0228] Explanation of the process

[0229] 1. Collection of user data:

[0230] Users input information such as their diet goals, current physical condition, eating habits, and exercise habits through a smartphone application. This data is sent to a cloud server and stored for analysis by generating AI.

[0231] 2. Data analysis using generative AI:

[0232] The AI ​​model on the cloud server (e.g., GPT-4) analyzes the collected user data and generates personalized dietary guidance and training programs for each user. This analysis also takes into account the user's past failures.

[0233] 3. Selection of recommended products:

[0234] Based on a program provided by the AI, a recommendation engine on a cloud server selects specific nutritional supplements and training equipment. This ensures that the user receives recommendations for the most suitable products.

[0235] 4. Suggestions for users:

[0236] Through a smartphone application, users will be shown generated dietary guidance, training programs, and recommended nutritional foods and training equipment.

[0237] 5. Purchase Process:

[0238] Users can easily purchase recommended nutritional supplements and training equipment through the application. Purchases are processed using an electronic payment system.

[0239] Specific example

[0240] The user opens the application and enters the following information:

[0241] Diet goal: Lose 5kg

[0242] Current health condition: Healthy

[0243] Eating habits: 3 meals a day, with snacks.

[0244] Exercise habits: Jogging twice a week

[0245] The generating AI analyzes this data and provides the following dietary guidance and training programs:

[0246] Dietary guidance: High-protein, low-calorie diet, replace snacks with nuts.

[0247] Training program: Add strength training three times a week.

[0248] Furthermore, the following special nutritional supplements and training equipment are recommended:

[0249] Nutritional foods: High-protein bars, protein shakes

[0250] Training equipment: Dumbbell set, yoga mat

[0251] Example of a prompt

[0252] "Based on the user's weight loss goals, current physical condition, eating habits, and exercise habits, generate an optimal diet plan and training program, and recommend the most suitable nutritional supplements and training equipment."

[0253] In this way, users can easily find and purchase the diet plan and related products that are best suited to them.

[0254] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0255] Step 1:

[0256] The user opens a smartphone application and enters information such as their weight loss goals, current physical condition, eating habits, and exercise habits.

[0257] Input: Diet goal, current physical condition, eating habits, exercise habits

[0258] Output: User data

[0259] Specific action: The user enters the required information into the application's input form and presses the submit button.

[0260] Step 2:

[0261] The device sends the user data it collects to a cloud server.

[0262] Input: User data

[0263] Output: User data stored on the cloud server

[0264] Specific operation: The application calls an API to send user data to the cloud server.

[0265] Step 3:

[0266] The server uses a generated AI model (e.g., GPT-4) to analyze the collected user data and generate optimal dietary guidance and training programs.

[0267] Input: User data

[0268] Output: Dietary guidance, training program

[0269] Specific operation: A generation AI model on a cloud server analyzes user data and generates optimal dietary guidance and training programs based on prompt messages.

[0270] Step 4:

[0271] The server selects special nutritional supplements and training equipment based on a program provided by the AI.

[0272] Input: Dietary guidance, training program

[0273] Output: Recommended nutritional foods, training equipment

[0274] Specific operation: A recommendation engine on a cloud server selects the most suitable nutritional foods and training equipment from a product database based on dietary guidance and training programs.

[0275] Step 5:

[0276] The server proposes recommended diet guidance, training programs, and related products to the user.

[0277] Input: Recommended nutritional foods, training equipment

[0278] Output: Content of the proposal to the user

[0279] Specific operation: The content of the proposal generated by the cloud server is sent to the application on the smartphone and displayed to the user.

[0280] Step 6:

[0281] The user purchases the recommended nutritional foods and training equipment through the application.

[0282] Input: User's purchase intention

[0283] Output: Purchase confirmation, payment completion

[0284] Specific operation: The user presses the purchase button and completes the payment through the electronic payment system.

[0285] In this way, the user can easily find and purchase the optimal diet plan and related products for themselves.

[0286] (Example 3)

[0287] Next, Example 3 of Form Example 3 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0288] Traditional diet support systems failed to fully utilize users' past failure data, making it difficult to support sustainable weight loss success. Furthermore, the lack of personalized training and dietary guidance increased the likelihood of users repeating the same mistakes. Additionally, the insufficient mechanisms for effectively collecting and analyzing user feedback and updating plans resulted in the problem of insufficient sustained weight loss effectiveness.

[0289] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0290] In this invention, the server includes means for collecting user data, means for storing and managing the collected data, means for using a generative AI model to analyze the stored data, means for generating personalized training and dietary guidance based on the analysis results, means for delivering the generated plans to users, means for collecting user feedback, and means for analyzing the collected feedback and updating the plans. This makes it possible to utilize the user's past failure data to support sustainable weight loss success.

[0291] "User data" refers to information entered by the user, such as their past dieting history, patterns of failure, current weight, target weight, dietary habits, and exercise routine.

[0292] "Means of collection" refers to a system in which users input data using smartphone apps or web forms and send it to a server.

[0293] "Means of storage and management" refers to a system that stores data received by a server in a database and manages it appropriately.

[0294] A "generative AI model" is an artificial intelligence model that analyzes collected data to generate personalized training and dietary guidance.

[0295] The "means for analysis" is a mechanism that analyzes the data stored using a generative AI model to identify the user's past frustration patterns and success patterns.

[0296] The "personalized training and diet guidance" refers to training plans and diet advice that are customized individually based on the analysis results.

[0297] The "means for distribution" is a mechanism that transmits the generated training plan and diet guidance from the server to the terminal and notifies the user.

[0298] The "means for collecting feedback" is a mechanism that allows the user to input daily progress and new data into the terminal and transmit it to the server.

[0299] The "means for analyzing feedback and updating the plan" is a mechanism that inputs the collected feedback into the generative AI model again and updates the training plan and diet guidance based on the analysis results.

[0300] This invention is a system that analyzes the user's past frustration data and supports sustainable diet success. The following describes specific embodiments of this system.

[0301] Collection of User Data

[0302] The user uses a smartphone app or web form to input information such as past diet history, frustration patterns, current weight, target weight, diet content, and exercise habits. For example, the user inputs that they "used to eat snacks late at night frequently in the past".

[0303] Storage and Management of Data

[0304] The terminal transmits the data input by the user to the server. The server stores the received data in a database (e.g., MySQL or PostgreSQL) and manages it appropriately. <00009> ​​

[0305] Data Analysis

[0306] The server inputs the stored data into a generating AI model (e.g., OpenAI's GPT-4) and performs analysis. Specifically, it identifies the user's past failure and success patterns and gains insights based on the data. For example, it might conclude that "this user tends to eat sweets late at night."

[0307] Generating personalized plans

[0308] The server uses a generative AI model to generate optimal training plans and dietary guidance for the user. Specifically, it considers the user's past data to provide individually customized advice. For example, it might generate specific advice such as, "Prepare low-calorie snacks to suppress appetite late at night."

[0309] Plan distribution

[0310] The server sends the generated training plan and dietary guidance to the device. The device then displays the received plan to the user. Specifically, it provides information using the notification function and dashboard of a smartphone app. For example, it might notify the user, "Prepare a low-calorie snack to curb your appetite late at night."

[0311] Collecting user feedback

[0312] Users input their daily progress and new data (such as weight changes and dietary information) into their device. Specifically, they enter records of their daily meals and exercise into the app. For example, they might enter, "Today I ate a low-calorie snack late at night."

[0313] Feedback analysis and plan updates

[0314] The terminal sends the new data entered by the user to the server. The server inputs the received data back into the generating AI model and performs analysis. Based on the analysis results, it updates the training plan and dietary guidance and sends it back to the terminal. For example, if the analysis results indicate that "low-calorie snacks are effective," the training plan and dietary guidance may be updated.

[0315] Example of a prompt

[0316] "Based on the user's past dieting history and failure patterns, please generate an optimal training plan and dietary guidance. The user tends to eat sweets late at night. Please take this failure pattern into consideration and provide specific advice."

[0317] In this way, the diet support system utilizes the user's past data to support sustainable weight loss success. The flow of the specific processing in Example 3 will be explained using Figure 15.

[0318] Step 1:

[0319] Users enter information such as their past dieting history, patterns of failure, current weight, target weight, diet, and exercise habits using a smartphone app or web form.

[0320] Input: Past dieting history, patterns of failure, current weight, target weight, diet, exercise habits

[0321] Output: Input user data

[0322] Step 2:

[0323] The terminal sends the data entered by the user to the server.

[0324] Input: User data entered by the user

[0325] Output: User data sent to the server

[0326] Step 3:

[0327] The server stores the received data in a database and manages it appropriately. Specifically, it uses a database management system such as MySQL or PostgreSQL.

[0328] Input: User data sent to the server

[0329] Output: User data stored in the database

[0330] Step 4:

[0331] The server inputs the stored data into a generating AI model (e.g., OpenAI's GPT-4) and performs analysis. Specifically, it identifies the user's past failure and success patterns and gains insights based on the data.

[0332] Input: User data stored in the database

[0333] Output: Analysis results (Example: "This user tends to eat sweets late at night")

[0334] Step 5:

[0335] The server uses a generative AI model to generate optimal training plans and dietary guidance for the user. Specifically, it takes the user's past data into consideration to provide individually customized advice.

[0336] Input: Analysis results

[0337] Output: Personalized training plans and dietary guidance (e.g., "Prepare low-calorie snacks to curb your appetite late at night").

[0338] Step 6:

[0339] The server sends the generated training plan and dietary guidance to the device. The device then displays the received plan to the user. Specifically, it provides information using the notification function and dashboard of a smartphone app.

[0340] Input: Personalized training plans and dietary guidance

[0341] Output: Training plans and dietary guidance displayed to the user (e.g., "Prepare low-calorie snacks to curb your appetite late at night").

[0342] Step 7:

[0343] Users input their daily progress and new data (such as weight changes and dietary information) into their device. Specifically, they enter records of their daily meals and exercise into the app.

[0344] Input: Daily progress and new data (e.g., "I ate a low-calorie snack late tonight")

[0345] Output: New data entered

[0346] Step 8:

[0347] The terminal sends the newly entered data to the server. The server inputs the received data back into the AI ​​model and performs analysis. Based on the analysis results, it updates the training plan and dietary guidance and sends them back to the terminal.

[0348] Input: New data

[0349] Output: Updated training plans and dietary advice (e.g., "Low-calorie snacks are effective")

[0350] In this way, the diet support system utilizes the user's past data to support sustainable weight loss success.

[0351] (Application Example 3)

[0352] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0353] Traditional diet support systems often failed to provide personalized guidance that adequately considered users' past dieting history and patterns of failure, leading to repeated setbacks. Furthermore, the lack of specialized nutritional supplements and training equipment made it difficult for users to access necessary resources in one place. Additionally, the absence of features to suggest optimal meal plans made it challenging to support sustainable weight loss success.

[0354] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means using VR technology, means providing personalized training and dietary guidance using generative AI, means selling special nutritional foods and training equipment, and means analyzing the user's past diet history and failure patterns and proposing a personalized meal menu. This makes it possible to prevent the user from repeating the same failures and to support sustainable diet success.

[0355] "VR technology" is a technology that uses virtual reality to provide users with a visual and experiential training environment.

[0356] "Generative AI" is an artificial intelligence technology that analyzes a user's past data to generate personalized training and dietary guidance.

[0357] "Personalized training and dietary guidance" means providing customized training and meal plans based on each user's individual needs and past history.

[0358] "Special nutritional foods" are foods specifically designed for purposes such as weight loss or maintaining health.

[0359] "Training equipment" refers to equipment used by users for physical training.

[0360] "User's past diet history" refers to records and data of diets the user has attempted in the past.

[0361] A "failure pattern" refers to the reasons or tendencies behind users having previously stopped or failed at dieting.

[0362] A "personalized meal plan" is a customized meal plan based on the user's past dieting history and patterns of failure.

[0363] The system for carrying out this invention is configured as follows: The server includes means using VR technology, means for providing personalized training and dietary guidance using generative AI, means for selling special nutritional foods and training equipment, and means for analyzing the user's past diet history and failure patterns and proposing personalized meal menus.

[0364] The server first retrieves the user's past diet history and failure patterns from a database. This data includes records of past diets the user has attempted and the reasons for their failures. Next, it uses a generative AI to analyze this data and generate an optimal training plan and meal plan for the user. The generative AI can utilize the OpenAI API.

[0365] Specifically, the server inputs the following prompt message into the generating AI:

[0366] Analyze the user's past dieting history and failure patterns to suggest personalized meal plans.

[0367] User data: {'age': 30, 'gender': 'female', 'height': 160, 'weight': 65, 'diet_history': [{'date': '2022-01-01', 'weight': 70, 'calories': 2000, 'exercise': 'running', 'success': False}, {'date': '2022-02-01', 'weight': 68, 'calories': 1800, 'exercise': 'yoga', 'success': True}], 'failure_patterns': ['stress eating', 'lack of motivation']}

[0368] The AI ​​generates the optimal meal menu for the user based on this prompt. The generated meal menu is then displayed on the user's smartphone or tablet.

[0369] Furthermore, the server also sells special nutritional supplements and training equipment. Users can purchase the necessary nutritional supplements and training equipment in one place based on the generated meal plan.

[0370] This system supports users in achieving sustainable weight loss success without repeating past setbacks. Furthermore, it makes it easier to stick to a diet by providing access to all necessary resources in one place.

[0371] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[0372] Step 1:

[0373] The server retrieves the user's past diet history and failure patterns from a database. The input is the user's ID, and the output is data on the user's past diet history and failure patterns. This data includes records of past diets the user has attempted and the reasons for their failure.

[0374] Step 2:

[0375] The server generates prompt messages to be input to the AI ​​based on the acquired data. The input is data on the user's past dieting history and failure patterns, and the output is the prompt messages to be input to the AI. Specifically, it generates prompt messages that include information such as the user's age, gender, height, weight, past dieting history, and failure patterns.

[0376] Step 3:

[0377] The server sends the generated prompt text to the generating AI, which then generates a personalized meal menu. The input is the generated prompt text, and the output is the personalized meal menu returned by the generating AI. The generating AI uses the OpenAI API to generate the optimal meal menu for the user.

[0378] Step 4:

[0379] The server sends the generated meal menu to the user's smartphone or tablet. The input is the personalized meal menu returned by the generating AI, and the output is the meal menu displayed on the user's device. The user can then view the generated meal menu via their smartphone or tablet.

[0380] Step 5:

[0381] The server sells specialized nutritional supplements and training equipment. Inputs are generated meal plans and user purchase requests, while outputs are links and information for users to make purchases. Users can centrally purchase the necessary nutritional supplements and training equipment based on the generated meal plans.

[0382] Step 6:

[0383] Users follow the provided meal menus and training plans to lose weight. The input is the meal menus and training plans provided by the server, and the output is the user's weight loss progress data. Users can receive further personalized guidance by feeding back their progress data to the server.

[0384] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0385] "Example of form 1"

[0386] One embodiment of the present invention is a diet support system incorporating an emotion engine. In this system, the user wears a VR device and receives personalized training and dietary guidance provided by a generating AI. The emotion engine uses the user's facial expressions, tone of voice, and language

[0387] The system recognizes the user's emotional state based on factors such as their leaf selection and feeds this information back to a generating AI. The generating AI then adjusts training menus and dietary guidance based on this emotional information. For example, if it determines that the user is feeling stressed, it might suggest a training menu with relaxation effects or recommend foods that are effective in relieving stress.

[0388] "Example of form 2"

[0389] Furthermore, recommendations for special nutritional supplements and training equipment are adjusted according to the user's emotional state. For example, if a user is perceived as depressed, nutritional supplements that boost their energy or training equipment that helps them change their mood may be recommended. This makes it possible to provide optimal diet support tailored to the user's emotional state.

[0390] "Example of form 3"

[0391] Furthermore, this system will be offered on a monthly subscription basis, aiming for future scaling and sales exceeding 10 billion yen. By incorporating an emotion engine, it will be possible to increase user satisfaction and encourage long-term use. This will ensure stable revenue and enable large-scale business development.

[0392] The following describes the processing flow for each example of the form.

[0393] "Example of form 1"

[0394] Step 1: The user puts on the VR device.

[0395] Step 2: The generating AI provides users with personalized training and dietary guidance.

[0396] Step 3: The emotion engine recognizes the user's emotional state based on their facial expressions, tone of voice, and word choice.

[0397] Step 4: The emotion engine feeds that information back to the generating AI.

[0398] Step 5: The generating AI adjusts the training menu and dietary guidance based on this emotional information.

[0399] "Example of form 2"

[0400] Step 1: The emotion engine determines that the user's emotional state is depressed.

[0401] Step 2: The generating AI recommends nutritional foods that will give you energy.

[0402] Step 3: The generating AI recommends training equipment that will help you relax and unwind.

[0403] "Example of form 3"

[0404] Step 1: The system is provided on a monthly subscription basis.

[0405] Step 2: Incorporate an emotional engine to increase user satisfaction and encourage long-term use.

[0406] Step 3: Secure stable revenue and achieve large-scale business expansion.

[0407] (Example 1)

[0408] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0409] Traditional diet support systems do not adequately provide personalized training and dietary guidance based on the individual user's body type, physical fitness, and health condition. Furthermore, they do not adjust training and dietary guidance to take into account the user's emotional state, making sustainable weight loss difficult. Additionally, there is a lack of comprehensive support that combines the sale of special nutritional supplements and training equipment.

[0410] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0411] In this invention, the server includes means for using VR technology, means for providing personalized training and dietary guidance using generative AI, means for analyzing the user's emotional state using an emotion engine and feeding that information back to the generative AI, and means for selling special nutritional foods and training equipment. This not only provides personalized training and dietary guidance based on the user's individual body type, physical strength, and health condition, but also allows for adjustments that take into account the user's emotional state, thereby supporting sustainable weight loss success. Furthermore, by combining this with the sale of special nutritional foods and training equipment, comprehensive weight loss support is realized.

[0412] "VR technology" is a technology that uses virtual reality to provide users with an immersive experience.

[0413] "Generative AI" is a technology that uses artificial intelligence to analyze user data and generate personalized training and dietary guidance.

[0414] "Personalized training" refers to a training program that is individually optimized based on the user's body type, fitness level, and health condition.

[0415] "Dietary guidance" refers to advice on meals provided based on the user's dietary preferences, health condition, and weight loss goals.

[0416] An "emotion engine" is a technology that analyzes a user's emotional state based on their facial expressions, tone of voice, and word choice.

[0417] "Feedback" is the process by which a system provides appropriate actions to a user based on analyzed information.

[0418] "Special nutritional foods" are foods specifically designed for purposes such as weight loss or maintaining health.

[0419] "Training equipment" refers to equipment used by users for training.

[0420] "Sales" is the act of providing goods or services and receiving payment in return.

[0421] "Sustainable weight loss success" refers to achieving and maintaining weight loss goals over a long period of time.

[0422] The diet support system of the present invention is a system that combines VR technology and generative AI to provide users with personalized training and dietary guidance. Specific embodiments of this system are described below.

[0423] Hardware and software to be used

[0424] Hardware: VR device

[0425] Software: Generative AI models (e.g., OpenAI GPT-4), emotion engine

[0426] Program processing

[0427] Data collection and analysis

[0428] When a user wears a VR device, the system collects user movement data and environmental data in real time. The server collects basic information such as the user's body type (height, weight), physical fitness, and health status (e.g., blood pressure, heart rate). This information is either entered by the user in advance or obtained from the wearable device.

[0429] Generating training menus using generative AI models

[0430] The server sends prompt messages to the generating AI model based on the basic user information it has collected. For example, it might send a prompt message such as, "Generate an optimal training menu for a user who is 170cm tall, weighs 70kg, and has moderate fitness." The generating AI model receives the prompt message and generates an optimal training menu for the user. For example, it might generate a menu that combines 30 minutes of aerobic exercise with strength training.

[0431] Training menu provided

[0432] The server sends the training menu received from the generated AI model to the user's device (VR device). The user reviews the training menu through the VR device and begins exercising. The VR device tracks the user's movements in real time and provides feedback.

[0433] Analysis of emotional states using an emotion engine

[0434] The server uses an emotion engine to analyze the user's emotional state from their facial expressions, tone of voice, and word choice. For example, it can determine whether the user is feeling stressed. The analyzed emotional information is then fed back to a generative AI model.

[0435] Adjustment based on emotional information

[0436] The generative AI model adjusts training menus and dietary guidance based on the emotional feedback it receives. For example, it might suggest yoga routines with relaxation effects or recommend foods that are effective for stress relief. The server then sends the adjusted training menus and dietary guidance to the user's device.

[0437] Specific example

[0438] Training menu generation:

[0439] User's body data: Height 170cm, Weight 70kg

[0440] User's physical fitness data: Moderate fitness

[0441] Based on this data, the generating AI creates a workout plan that combines 30 minutes of aerobic exercise with strength training.

[0442] Providing dietary guidance:

[0443] User's dietary preferences: Likes vegetables, eats meat in moderation.

[0444] User's health status: High blood pressure

[0445] Based on this data, the generating AI suggests low-sodium, vegetable-centered meal menus.

[0446] Emotional engine feedback:

[0447] The emotion engine recognizes that the user is feeling stressed.

[0448] The generated AI suggests yoga routines with relaxation effects and recommends foods effective for stress relief (e.g., dark chocolate, nuts).

[0449] Example of a prompt

[0450] "Please generate an optimal training program based on the user's body type and fitness data."

[0451] "Provide personalized dietary guidance that takes into account the user's dietary preferences and health condition."

[0452] "Recognize the user's emotional state and adjust the training program and dietary guidance accordingly."

[0453] The above describes specific embodiments of the diet support system of the present invention.

[0454] The flow of the specific processing in Example 1 will be explained using Figure 17.

[0455] Step 1:

[0456] The user puts on a VR device.

[0457] In terms of specific actions, the user puts on a VR device at home and logs into the system. This prepares the system to collect the user's movement data and environmental data in real time.

[0458] Input: User login information, VR device connection

[0459] Output: Start of user activity data and environmental data collection

[0460] Step 2:

[0461] The server collects the user's basic information.

[0462] Specifically, the server collects basic information about the user, such as their body type (height, weight), physical fitness, and health status (e.g., blood pressure, heart rate). This information is either entered by the user beforehand or obtained from a wearable device.

[0463] Input: User's basic information, wearable device data

[0464] Output: Collected basic user information

[0465] Step 3:

[0466] The server sends a prompt message to the generated AI model.

[0467] In terms of specific operations, the server sends prompt messages to the generating AI model based on the basic user information it has collected. For example, it might send a prompt message such as, "Generate an optimal training menu for a user who is 170cm tall, weighs 70kg, and has moderate fitness."

[0468] Input: User's basic information, prompt text

[0469] Output: Sending prompt messages to the generating AI model

[0470] Step 4:

[0471] The generative AI model generates the training menu.

[0472] In terms of specific operation, the generative AI model (e.g., OpenAI GPT-4) receives a prompt and generates an optimal training menu for the user. For example, it might generate a menu that combines 30 minutes of aerobic exercise with strength training.

[0473] Input: Prompt message

[0474] Output: Generated training menu

[0475] Step 5:

[0476] The server sends the generated training menu to the terminal.

[0477] Specifically, the server sends the training menu received from the generated AI model to the user's device (VR device). The user can then view the training menu through the VR device.

[0478] Input: Generated training menu

[0479] Output: Sending the training menu to the user's device.

[0480] Step 6:

[0481] The user begins training.

[0482] Specifically, the user begins exercising according to a training menu provided through the VR device. The VR device tracks the user's movements in real time and provides feedback.

[0483] Input: Training Menu

[0484] Output: User training data, feedback

[0485] Step 7:

[0486] The server analyzes the user's emotional state using an emotion engine.

[0487] In terms of specific operations, the server uses an emotion engine to analyze the user's emotional state from their facial expressions, tone of voice, and word choice. For example, it can determine whether the user is feeling stressed.

[0488] Input: User's facial expression data, voice tone, word choice

[0489] Output: Analyzed sentiment information

[0490] Step 8:

[0491] The server feeds emotional information back into the AI ​​model that generates it.

[0492] In terms of specific operations, the server feeds back the analyzed emotional information to the generating AI model. For example, it sends information such as "the user is feeling stressed."

[0493] Input: Analyzed emotional information

[0494] Output: Feedback to the Generative AI Model

[0495] Step 9:

[0496] The generative AI model adjusts training menus and dietary guidance based on emotional information.

[0497] In terms of specific actions, the generative AI model adjusts training menus and dietary guidance based on the emotional information it receives as feedback. For example, it might suggest yoga routines with relaxation effects or recommend foods that are effective for stress relief.

[0498] Input: Feedback on emotional information

[0499] Output: Customized training menu and dietary guidance

[0500] Step 10:

[0501] The server sends the adjusted menu and instructions to the terminal.

[0502] Specifically, the server sends a customized training menu and dietary guidance to the user's device. The user receives the new menu and guidance through a VR device.

[0503] Input: Customized training menu and dietary guidance

[0504] Output: Send to the user's terminal

[0505] (Application Example 1)

[0506] Next, we will describe Application Example 1 of Form 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."

[0507] Traditional diet support systems do not provide personalized training or dietary guidance that fully considers the individual needs and emotional states of users. Furthermore, few systems are designed for use in physical locations, limiting opportunities for users to experience them firsthand. Additionally, the lack of systems that recognize and respond to users' emotional states in real time makes it difficult to maintain user motivation.

[0508] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means using VR technology, means providing personalized training and dietary guidance using a generative AI, means selling special nutritional foods and training equipment, means recognizing the user's emotional state using an emotion engine and feeding that information back to the generative AI, and means for the user to wear a VR device in a physical store and receive personalized training and dietary guidance provided by the generative AI. This makes it possible to provide personalized training and dietary guidance that meets the individual needs and emotional state of the user, and makes it easier to maintain the user's motivation through the experience at the physical store.

[0509] "VR technology" is a technology that realizes virtual reality, enabling users to immerse themselves in a virtual environment.

[0510] "Generative AI" is a technology that uses artificial intelligence to automatically generate optimal training and dietary guidance for users.

[0511] "Personalized training and dietary guidance" means providing training programs and meal plans that are customized based on the individual needs and condition of the user.

[0512] "Special nutritional foods" are foods specifically designed for purposes such as weight loss or maintaining health.

[0513] "Training equipment" refers to equipment used for fitness and exercise.

[0514] An "emotional engine" is a technology that recognizes a user's emotional state from their facial expressions, tone of voice, and choice of words.

[0515] A "physical store" is a store that exists in a physical location and where customers can visit in person to receive services.

[0516] A "VR device" is a hardware device used to experience virtual reality, and includes head-mounted displays, controllers, and other similar devices.

[0517] "Feedback" refers to the process of adjusting training and dietary guidance based on information the system receives from users.

[0518] This invention is a system in which users wear a VR device in a physical store and receive personalized training and dietary guidance provided by a generated AI. The specific form of this system is described below.

[0519] System Configuration

[0520] hardware

[0521] VR devices: These use head-mounted displays, allowing users to immerse themselves in a virtual reality environment.

[0522] Camera: Used to capture the user's facial expressions in real time. This allows the emotion engine to recognize the user's emotional state.

[0523] Server: Provides computing resources to run the generated AI model and generate training and dietary guidance.

[0524] software

[0525] Generative AI Model: An artificial intelligence model for generating training and dietary guidance based on the individual needs and circumstances of the user.

[0526] Emotion Engine: Software that recognizes a user's emotional state based on their facial expressions, tone of voice, and word choice.

[0527] VR application: An application that allows users to receive training and dietary guidance through a VR device.

[0528] System operation

[0529] 1. Acquisition of user information: The server acquires information such as the user's body type, physical fitness, health status, dietary preferences, and diet goals.

[0530] 2. Recognition of emotional state: The camera captures the user's facial expressions, and the emotion engine analyzes the data to recognize the emotional state.

[0531] 3. Generation of training and dietary guidance: The generation AI model generates optimal training menus and dietary guidance based on acquired user information and emotional state.

[0532] 4. Display on VR devices: The generated training menu and dietary guidance are displayed on the VR device, and the user experiences them in a virtual reality environment.

[0533] Specific example

[0534] For example, consider the following scenario regarding user information.

[0535] Body type: Standard

[0536] Physical fitness: moderate

[0537] Health condition: Good

[0538] Food preferences: Japanese food

[0539] Diet goal: Weight loss

[0540] Based on this information, the generative AI model generates the following prompt message.

[0541] The user has a standard build, moderate physical fitness, and good health. They prefer Japanese food and are aiming to lose weight. Currently, the user is experiencing stress. Based on this information, please generate an optimal training program and dietary guidance.

[0542] By inputting this prompt into the AI ​​model, an optimal training menu and dietary guidance for the user are generated. The generated content is provided to the user via a VR device, allowing the user to receive training and dietary guidance in a virtual reality environment.

[0543] This enables personalized training and dietary guidance tailored to the individual needs and emotional state of users, and makes it easier to maintain user motivation through in-store experiences.

[0544] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[0545] Step 1:

[0546] The server acquires information such as the user's body type, physical fitness, health status, dietary preferences, and weight loss goals. This information is collected from data previously entered by the user and from past historical data. The input data is stored as the user's profile information and used as input for the generated AI model.

[0547] Step 2:

[0548] The terminal (a camera connected to the VR device) captures the user's facial expressions in real time. The captured video data is sent to the emotion engine. The emotion engine analyzes the video data and recognizes the user's emotional state (e.g., stress, joy, fatigue). The recognized emotional state is then generated as output.

[0549] Step 3:

[0550] The server generates prompt messages for the AI ​​model based on the acquired user information and emotional state. The prompt messages are generated in the following format:

[0551] The user has a standard build, moderate physical fitness, and good health. They prefer Japanese food and are aiming to lose weight. Currently, the user is experiencing stress. Based on this information, please generate an optimal training program and dietary guidance.

[0552] The generated prompt sentences are used as input for the generative AI model.

[0553] Step 4:

[0554] The server inputs prompt messages into the generating AI model, which then generates an optimal training menu and dietary guidance. The generating AI model considers user information and emotional state to output a personalized training menu and dietary guidance. The outputted training menu and dietary guidance are then stored on the server.

[0555] Step 5:

[0556] The server sends the generated training menu and dietary guidance to the VR device. The VR device displays the received training menu and dietary guidance to the user. The user can receive training and dietary guidance in a virtual reality environment through the VR device.

[0557] Step 6:

[0558] Users wear a VR device and perform exercises according to a generated training menu. Exercise progress and feedback are sent to the server in real time. The server uses this data to adjust the training menu and dietary guidance as needed.

[0559] Step 7:

[0560] The server analyzes users' exercise data and feedback, and uses this information to inform future training menus and dietary guidance. This ensures that users receive continuous, optimal guidance tailored to their progress and emotional state.

[0561] (Example 2)

[0562] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0563] Traditional diet support systems lack personalized support tailored to the individual needs and emotional states of users. Furthermore, they often recommend specific nutritional foods and training equipment that are not optimized for the user's specific situation. Additionally, they fail to utilize users' past failure data to provide sustained support for successful weight loss, making it difficult to maintain user motivation.

[0564] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0565] In this invention, the server includes means for receiving and storing data entered by the user, means for generating an optimal meal plan and training plan for the user using a generative AI model, means for recommending special nutritional foods and training equipment based on the generated plans, and means for analyzing the user's emotional state and recommending nutritional foods and training equipment according to that emotional state. This enables personalized support that is tailored to the user's individual needs and emotional state, thereby supporting sustainable weight loss success.

[0566] "Means for receiving and storing user-entered data" refers to a function in which a server receives data such as weight, height, target weight, dietary preferences, exercise habits, and emotional state entered by the user via a terminal, and stores it in a database.

[0567] "A means of generating optimal meal plans and training plans for users using a generative AI model" refers to a function that uses a generative AI model to create individually optimized meal plans and training plans based on the user's input data.

[0568] "A means of recommending special nutritional foods and training equipment based on the generated plan" refers to a function that analyzes the meal plan and training plan created by the generating AI model, selects the most suitable nutritional foods and training equipment from a database, and recommends them to the user.

[0569] "A means of analyzing a user's emotional state and recommending nutritional foods and training equipment appropriate to that emotional state" refers to a function that uses emotion analysis software to analyze a user's emotional state and, based on the results, recommends nutritional foods and training equipment suitable for that emotional state.

[0570] "Means to support sustainable weight loss success" refers to a function that analyzes the user's past failure data and provides support to help the user continue their diet.

[0571] This invention is a diet support system that includes means for receiving and storing data entered by a user, means for generating an optimal meal plan and training plan for the user using a generative AI model, means for recommending special nutritional foods and training equipment based on the generated plan, and means for analyzing the user's emotional state and recommending nutritional foods and training equipment according to that emotional state.

[0572] 1. User data entry and saving

[0573] Users access the diet support system application using their device (smartphone or PC). Users input data such as weight, height, target weight, dietary preferences, exercise habits, and current emotional state. The device sends the input data to the server. The server stores the received data in a database. This data is used for subsequent processing.

[0574] 2. Nutritional guidance and creation of training plans

[0575] The server sends prompt messages to a generative AI model (e.g., OpenAI's GPT-4) based on stored user data. These prompt messages include the user's weight, target weight, dietary preferences, and exercise habits. Based on these prompt messages, the generative AI model generates an optimal meal plan and training plan for the user.

[0576] Example of a prompt:

[0577] "The user's current weight is 70kg, and their target weight is 65kg. The user prefers a high-protein diet and exercises three times a week. Please propose an optimal meal plan and training plan for this user."

[0578] Based on this prompt, the generating AI model creates specific meal plans (e.g., oatmeal and protein shake for breakfast, chicken breast and vegetable salad for lunch, salmon and broccoli for dinner) and training plans (e.g., strength training and cardio three times a week).

[0579] 3. Recommendations for special nutritional supplements and training equipment

[0580] The server analyzes the generated meal and training plans and consults a database of specialized nutritional foods and training equipment. The server selects the most suitable products for each plan and recommends them to the user. For example, if a high-protein meal plan is generated, the server will recommend high-protein protein bars. It will also recommend training equipment best suited to a specific training program.

[0581] 4. Analysis and adjustment of emotional states

[0582] The server analyzes the user's emotional state using sentiment analysis software (e.g., IBM Watson® sentiment analysis API) based on the user's input data and past behavioral data. If the server determines that the user is depressed, it recommends energy-boosting foods or exercise equipment to help them change their mood.

[0583] 5. Displaying recommendations and promoting purchases.

[0584] The server sends the generated meal plan, training plan, and recommended special nutritional foods and training equipment to the terminal. The terminal displays this information to the user. The user can review the displayed information and purchase the recommended products as needed.

[0585] In this way, the server provides the optimal plan and products to effectively support the user's diet.

[0586] The flow of the specific processing in Example 2 will be explained using Figure 19.

[0587] Step 1:

[0588] Users access the diet support system application using their device and input data such as weight, height, target weight, dietary preferences, exercise habits, and current emotional state. This input data is then transmitted from the device to the server. The input data includes the user's individual needs and circumstances.

[0589] Step 2:

[0590] The server receives user data sent from the terminal and stores it in the database. The stored data is used for subsequent processing. Specifically, it is stored in the database associated with the user ID.

[0591] Step 3:

[0592] The server sends prompt messages to the generative AI model based on stored user data. These prompt messages include the user's weight, target weight, dietary preferences, and exercise habits. Based on these prompt messages, the generative AI model generates an optimal meal plan and training plan for the user.

[0593] Example of a prompt:

[0594] "The user's current weight is 70kg, and their target weight is 65kg. The user prefers a high-protein diet and exercises three times a week. Please propose an optimal meal plan and training plan for this user."

[0595] Step 4:

[0596] The generation AI model generates specific meal plans and training plans based on the prompt text. The generated plans are sent to the server. The specific meal plan includes menus for breakfast, lunch, and dinner, and the training plan includes the type and frequency of exercise to be performed per week.

[0597] Step 5:

[0598] The server analyzes the generated meal plan and training plan and consults a database of specialized nutritional foods and training equipment. The server selects the most suitable products for each plan and recommends them to the user. For example, if a high-protein meal plan is generated, the server will recommend high-protein protein bars. A list of recommended products is generated as output.

[0599] Step 6:

[0600] The server analyzes the user's emotional state using emotion analysis software based on user input data and past behavioral data. If the server determines that the user is depressed, it recommends energy-boosting nutritional supplements or exercise equipment to help them change their mood. A list of recommendations tailored to the user's emotional state is output.

[0601] Step 7:

[0602] The server sends the generated meal plan, training plan, and recommended special nutritional foods and training equipment to the terminal. The terminal displays this information to the user. The user can review the displayed information and purchase recommended products as needed. The output generated is the information displayed to the user.

[0603] (Application Example 2)

[0604] Next, we will describe Application Example 2 of Form 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."

[0605] Traditional diet support systems lack personalized support tailored to the individual needs and emotional states of users. Furthermore, they typically recommend specific nutritional supplements and training equipment, failing to provide optimal product recommendations based on the user's emotional state. Additionally, purchasing recommended products often requires separate procedures, creating an inconvenient and cumbersome process for users.

[0606] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0607] In this invention, the server includes means for using VR technology, means for providing personalized training and dietary guidance using generative AI, means for selling special nutritional foods and training equipment, means for analyzing the user's emotional state and recommending the most suitable nutritional foods and training equipment, and means for making the recommended products available for purchase within the application. This enables optimal diet support tailored to the user's individual needs and emotional state, and simplifies the purchase process for recommended products.

[0608] "VR technology" is a technology that uses virtual reality to provide users with an immersive experience.

[0609] "Generative AI" is a technology that uses artificial intelligence to analyze data and generate training and dietary guidance tailored to individual needs.

[0610] "Personalized training and dietary guidance" means providing customized training programs and meal plans based on the individual data and needs of the user.

[0611] "Special nutritional foods" are foods specifically designed for purposes such as weight loss or maintaining health.

[0612] "Training equipment" refers to equipment used for fitness and exercise.

[0613] "Analyzing emotional states" means analyzing a user's text and voice data to quantify or classify their emotions at that time.

[0614] "Recommending optimal nutritional foods and training equipment" means suggesting the most suitable nutritional foods and training equipment based on the user's emotional state and individual needs.

[0615] "Making products available for purchase within the application" means allowing users to complete the purchase process for recommended products directly within the application.

[0616] The following system configuration is used as an embodiment of this invention. The system includes a server, a user terminal, and a generated AI model.

[0617] The server includes means of using VR technology, means of providing personalized training and dietary guidance using generative AI, means of selling special nutritional foods and training equipment, means of analyzing the user's emotional state and recommending the most suitable nutritional foods and training equipment, and means of making recommended products available for purchase within the application.

[0618] User devices may include smartphones, smart glasses, head-mounted displays, or robots. These devices communicate with a server to provide users with personalized training and dietary guidance.

[0619] The generative AI model analyzes the user's diet and training history, as well as their emotional state, to recommend optimal nutritional supplements and training equipment. The TextBlob library is used for analyzing emotional state, and the Requests library is used for sending and receiving data.

[0620] As a concrete example, if a user types "I'm tired today" on their smartphone, TextBlob analyzes their emotions, and the generating AI recommends nutritional supplements that promote relaxation. Similarly, if a user logs "I went for a 30-minute run," the generating AI recommends the most suitable training equipment.

[0621] The following is an example of a prompt statement:

[0622] User ID: 12345

[0623] Food log: [{'food_item': 'Apple', 'calories': 95, 'date': '2023-10-01T12:00:00'}]

[0624] Training log: [{'workout_type': 'Running', 'duration': 30, 'date': '2023-10-01T12:30:00'}]

[0625] Emotion log: [{'text': 'I feel great today!', 'polarity': 0.8, 'date': '2023-10-01T13:00:00'}]

[0626] By inputting this prompt into the AI ​​model, you can receive recommendations for optimal nutritional supplements and training equipment.

[0627] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[0628] Step 1:

[0629] Users log their meals and workouts using their smartphones. This data includes details such as the type of meal, calories, type of workout, and duration. This records the user's meal and workout history.

[0630] Step 2:

[0631] The user inputs their emotional state. For example, they might enter text such as "I'm tired today." This text data becomes the input data for emotion analysis.

[0632] Step 3:

[0633] The device uses the TextBlob library to analyze the text of the input emotional state. As a result of the analysis, the emotional polarity (positive or negative) is quantified. This allows the user's emotional state to be recorded as numerical data.

[0634] Step 4:

[0635] The device sends meal logs, training logs, and emotion logs to the server. The transmitted data includes the user ID, meal logs, training logs, and emotion logs. This allows the server to receive the user's most up-to-date data.

[0636] Step 5:

[0637] The server uses a generated AI model to analyze the received data. This analysis takes into account the user's past data and emotional state. Based on this, the system recommends the most suitable nutritional supplements and training equipment for the user.

[0638] Step 6:

[0639] The server sends information about recommended nutritional foods and training equipment to the terminal. The transmitted data includes detailed information about the recommended products. This allows the terminal to display the recommended products to the user.

[0640] Step 7:

[0641] Users purchase recommended products within the application. When a user presses the purchase button, their device sends a purchase request to the server. This allows users to easily purchase products.

[0642] Step 8:

[0643] The server receives the purchase request and processes the purchase. This process includes checking inventory, processing payment, and arranging delivery. As a result, the user receives the purchased product.

[0644] (Example 3)

[0645] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0646] Traditional diet support systems have faced challenges in achieving sustainable weight loss success because they do not provide personalized support that adequately considers each user's individual failure patterns and emotional state. Furthermore, there was a lack of effective means to increase user satisfaction and encourage long-term use.

[0647] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0648] In this invention, the server includes means for collecting user data, means for storing and managing the collected data, means for analyzing the data using a generative AI model to identify the user's failure patterns, means for generating personalized training plans and dietary guidance based on the analysis results, means for monitoring the user's emotional state using an emotion engine and providing appropriate feedback, and means for notifying the user of suggestions and support. This enables personalized support that takes into account the user's individual failure patterns and emotional state, thereby supporting sustainable weight loss success.

[0649] "Means for collecting user data" refers to devices or software that provide an interface for users to input their past diet history and experiences of failure.

[0650] "Means for storing and managing collected data" refers to devices or software for storing data collected from users in a database and managing the data while maintaining its integrity.

[0651] "A means of analyzing data using a generative AI model to identify user failure patterns" refers to a device or software that uses machine learning algorithms to analyze a user's past data and identify the causes and patterns of failure.

[0652] "Means for generating personalized training plans and dietary guidance based on analysis results" refers to a device or software that automatically generates optimal training plans and dietary guidance for users based on the results of data analysis.

[0653] "Means for monitoring a user's emotional state using an emotion engine and providing appropriate feedback" refers to a device or software that monitors a user's emotional state in real time and provides feedback according to that state.

[0654] "Means of notifying users of suggestions and support" refers to devices or software that notify users of generated plans and feedback and encourage them to take action.

[0655] This invention is a system that analyzes a user's past dieting history and failure patterns to support sustainable weight loss success. Specific embodiments of this system are described below.

[0656] First, the server provides a means to collect user data. Users use devices such as smartphones or PCs to input their past diet history and failures through a dedicated application or web interface. This data includes information such as dietary content, exercise history, weight fluctuations, and reasons for failure.

[0657] Next, the server employs means to store and manage the collected data. The data is stored in a relational database such as MySQL or PostgreSQL. The server performs data validation to maintain data integrity.

[0658] The server then analyzes the data using a generative AI model. Specifically, it builds a machine learning model using Python and TENSORFLOW® to identify user frustration patterns. Based on past data, the server predicts the situations in which users are likely to become frustrated.

[0659] Based on the analysis results, the server generates personalized training plans and dietary guidance. For example, if a user tends to eat sweets late at night, the server will suggest low-calorie snacks. It also provides exercise plans tailored to the user's lifestyle and preferences.

[0660] Furthermore, the server uses an emotion engine to monitor the user's emotional state. The emotion engine estimates emotions based on the user's input data and behavioral patterns, and monitors them in real time. For example, if a user is feeling stressed, the server will suggest yoga or meditation to help them relax.

[0661] Finally, the server notifies the user of the generated plan and feedback. The device receives the notification and displays it to the user. The user acts according to the proposed plan and re-enters their progress, allowing the server to continuously update the data and provide support.

[0662] Examples of specific prompt messages include the following:

[0663] "Analyze the user's past dieting history and failure patterns, and suggest low-calorie snacks that are acceptable to eat late at night. Also, if the user is experiencing stress, suggest yoga or meditation to help them relax."

[0664] In this way, the server can prevent users from repeating the same setbacks and support their sustained weight loss success. The flow of the specific processing in Example 3 will be explained using Figure 21.

[0665] Step 1:

[0666] Users enter their past dieting history and experiences of failure.

[0667] Input: Data such as dietary content, exercise history, weight fluctuations, and reasons for failure.

[0668] Output: The input data is sent from the terminal to the server.

[0669] Specific operation: Users input data using a smartphone or PC via a dedicated application or web interface.

[0670] Step 2:

[0671] The server stores and manages the collected data.

[0672] Input: Data submitted by the user.

[0673] Output: Data stored in the database.

[0674] Specific operation: The server uses relational databases such as MySQL or PostgreSQL to store data and performs validation to maintain data integrity.

[0675] Step 3:

[0676] The server analyzes the data using a generative AI model.

[0677] Input: Saved user data.

[0678] Output: Failure patterns as analysis results.

[0679] Specific operation: The server uses Python and TensorFlow to build machine learning models and analyzes the user's past data to identify patterns of frustration.

[0680] Step 4:

[0681] The server generates personalized training plans and dietary guidance based on the analysis results.

[0682] Input: Failure patterns as analysis results.

[0683] Output: Personalized training plans and dietary guidance.

[0684] Specific operation: Based on the user's patterns of failure, the server suggests low-calorie snacks and exercise plans tailored to their lifestyle.

[0685] Step 5:

[0686] The server uses an emotion engine to monitor the user's emotional state and provide appropriate feedback.

[0687] Input: User input data and behavioral patterns.

[0688] Output: Feedback tailored to emotional state.

[0689] Specific operation: The server uses an emotion engine to monitor the user's emotional state in real time and suggests yoga or meditation to help them relax if they are feeling stressed.

[0690] Step 6:

[0691] The server notifies the user of the generated plan and feedback.

[0692] Input: Generated training plans, dietary guidance, and feedback tailored to emotional state.

[0693] Output: Suggestions and support notified to the user.

[0694] Specific operation: The server sends a notification to the terminal, which receives it and displays it to the user. The user acts according to the proposed plan and re-enters their progress.

[0695] (Application Example 3)

[0696] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0697] Traditional diet support systems have struggled to effectively utilize users' past failure data, making it difficult to support sustainable weight loss success. Furthermore, a lack of feedback and advice to maintain user motivation hindered long-term adoption. Additionally, physical fitness gyms and diet cafes lacked the means to provide personalized training plans and meal menus.

[0698] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means using VR technology, means providing personalized training and dietary guidance using generative AI, means selling special nutritional foods and training equipment, means analyzing the user's past diet history and failure patterns at a physical fitness gym or diet cafe and providing personalized training plans and meal menus, and means providing feedback and advice to maintain the user's motivation using an emotion engine. This makes it possible to prevent users from repeating the same failures, support sustainable diet success, and promote long-term use.

[0699] "VR technology" is a technology that uses virtual reality to provide users with visual and experiential feedback.

[0700] "Generative AI" is a technology that uses artificial intelligence to analyze user data and generate personalized training and dietary guidance.

[0701] "Personalized training and dietary guidance" means providing training plans and meal menus optimized based on each user's individual data.

[0702] "Special nutritional foods" are foods that contain specific nutrients intended for weight loss or maintaining health.

[0703] "Training equipment" refers to equipment used for fitness and exercise.

[0704] A "physical store" refers to a facility that exists in a physical location, such as a fitness gym or a diet cafe.

[0705] A "fitness gym" is a facility equipped with equipment for exercise and training.

[0706] A "diet cafe" is a cafe that offers healthy meals and drinks to support weight loss.

[0707] "User's past diet history" refers to records and data of diets the user has attempted in the past.

[0708] "Failure patterns" refer to data that shows the causes and tendencies of users' past diet failures.

[0709] An "emotional engine" is a technology that analyzes the user's emotional state and provides feedback and advice to maintain motivation.

[0710] "Feedback" refers to evaluations and advice given regarding a user's behavior or condition.

[0711] "Advice" refers to guidance and suggestions provided to users in order to achieve their goals.

[0712] To implement this invention, the following system configuration and processing procedure are used.

[0713] System Configuration

[0714] 1. Hardware

[0715] Server: A high-performance server for running data analysis and generative AI models.

[0716] Device: The user's smartphone, tablet, or personal computer.

[0717] Physical store facilities: Sales facilities for training equipment and nutritional foods, installed in fitness gyms and diet cafes.

[0718] 2. Software

[0719] Generative AI Model: An AI model that analyzes a user's past dieting history and failure patterns to generate personalized training plans and meal menus.

[0720] Emotional Engine: Software that analyzes the user's emotional state and provides feedback and advice to maintain motivation.

[0721] Data analysis tools: Data analysis libraries such as Pandas and Scikit-learn.

[0722] Processing procedure

[0723] 1. Data collection and preprocessing

[0724] The server collects the user's past dieting history and failure patterns. This includes data such as weight, calorie intake, and exercise time.

[0725] The collected data is preprocessed and standardized using Pandas.

[0726] 2. Clustering

[0727] The server uses the KMeans algorithm from Scikit-learn to cluster user frustration patterns.

[0728] 3. Plan generation using AI

[0729] The server uses a generative AI model to generate personalized training plans and meal menus for each cluster.

[0730] A concrete example of a prompt would be: "Create a personalized training plan based on user cluster 1. The user has previously failed due to lack of exercise and poor diet management. Provide specific advice to help him successfully lose weight sustainably."

[0731] 4. Feedback from the Emotion Engine

[0732] The server uses an emotion engine to analyze the user's emotional state and provides feedback and advice to help maintain motivation.

[0733] Specific example

[0734] User A has tried dieting many times in the past, but has failed each time for the same reasons. This system will analyze his past data and provide him with an optimal training plan and meal plan. For example, the generating AI model will generate a specific plan using the prompt message: "Create a personalized training plan based on user cluster 1. The user has failed in the past due to lack of exercise and failure in diet management. Provide specific advice to help him succeed in dieting in the long term."

[0735] In this way, it becomes possible to prevent users from repeating the same setbacks, support sustainable weight loss success, and encourage long-term use.

[0736] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[0737] Step 1:

[0738] The server collects users' past dieting history and patterns of failure. Specifically, it stores data such as weight, calorie intake, and exercise time entered by users using smartphones or tablets in a database. The input data is saved in CSV file or database format.

[0739] Step 2:

[0740] The server preprocesses the collected data. Specifically, it uses the Pandas library to read the data, impute missing values, and remove outliers. After that, it standardizes the data using StandardScaler. The input is the user's raw data, and the output is preprocessed, standardized data.

[0741] Step 3:

[0742] The server performs clustering using pre-processed data. Specifically, it uses the KMeans algorithm from Scikit-learn to cluster user frustration patterns. The input is standardized data, and the output is the cluster label to which each user belongs.

[0743] Step 4:

[0744] The server uses a generative AI model to generate personalized training plans and meal menus for each cluster. Specifically, it generates prompts based on cluster labels and inputs them into the AI ​​model using the OpenAI API. The input consists of cluster labels and prompts, while the output is the generated training plan and meal menu.

[0745] Step 5:

[0746] The server uses an emotion engine to analyze the user's emotional state. Specifically, it analyzes feedback and diary data entered by the user to estimate their emotional state. The input is the user's feedback data, and the output is the estimated emotional state.

[0747] Step 6:

[0748] The server provides feedback and advice to maintain user motivation based on the analysis results of the emotion engine. Specifically, it generates appropriate feedback messages according to the estimated emotional state and sends them to the user's device. The input is the estimated emotional state, and the output is the feedback message.

[0749] Step 7:

[0750] Users follow personalized training plans and meal menus provided by the server and input feedback. Specifically, they use smartphones or tablets to record their training progress and meal details and send them to the server. The input is the user's execution data, and the output is updated diet history data.

[0751] In this way, it becomes possible to prevent users from repeating the same setbacks, support sustainable weight loss success, and encourage long-term use.

[0752] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0753] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0754] Other examples of generative AI include Gemini® (registered trademark) (Internet search). <url: https: gemini.google.com ?hl="ja">) are some examples.

[0755] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0756] [Second Embodiment]

[0757] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0758] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0759] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0760] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0761] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0762] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0763] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0764] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0765] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0766] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0767] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0768] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0769] "Example of form 1"

[0770] The diet support system of the present invention combines VR technology and generative AI to provide users with personalized training and dietary guidance. Specifically, users wear a VR device at home and perform exercises according to a training program provided by the generative AI. The generative AI generates an optimal training menu based on information such as the user's body type, physical fitness, and health condition. Similarly, dietary guidance is also provided by the generative AI, taking into account the user's food preferences, health condition, and diet goals.

[0771] "Example of form 2"

[0772] The diet support system of this invention also sells special nutritional foods and training equipment. These products work in conjunction with the training and dietary guidance provided by the generating AI to more effectively support the user's diet. For example, based on the dietary guidance provided by the generating AI, it can recommend special nutritional foods and encourage their purchase. Similarly, it can recommend training equipment optimized for the training program provided by the generating AI and encourage its purchase.

[0773] "Example of form 3"

[0774] The diet support system of this invention analyzes the user's past failure data to support sustainable weight loss success. Specifically, a generating AI analyzes the user's past diet history and failure patterns, and based on this, provides personalized training and dietary guidance. This prevents the user from repeating the same failures and supports sustainable weight loss success.

[0775] The following describes the processing flow for each example of the form.

[0776] "Example of form 1"

[0777] Step 1: The user puts on the VR device at home.

[0778] Step 2: The generating AI creates an optimal training menu based on information such as the user's body type, physical fitness, and health condition.

[0779] Step 3: The user performs exercises according to the training program provided by the AI-generated program.

[0780] Step 4: The generating AI provides dietary guidance, taking into account the user's food preferences, health condition, and weight loss goals.

[0781] "Example of form 2"

[0782] Step 1: In conjunction with the training and dietary guidance provided by the AI, sell special nutritional supplements and training equipment.

[0783] Step 2: Based on the dietary guidance provided by the generating AI, recommend special nutritional supplements and encourage their purchase.

[0784] Step 3: The generated AI recommends training equipment optimized for the training program it provides and encourages its purchase.

[0785] "Example of form 3"

[0786] Step 1: The generating AI analyzes the user's past diet history and patterns of failure.

[0787] Step 2: The generating AI provides personalized training and dietary guidance based on the analysis results.

[0788] Step 3: This prevents users from repeating the same setbacks and supports sustainable weight loss success.

[0789] (Example 1)

[0790] Next, we will describe Example 1 of Form Example 1. 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".

[0791] Traditional diet support systems offer uniform training and dietary guidance to all users, failing to adequately personalize the program based on individual user body type, fitness level, health status, dietary preferences, and weight loss goals. Furthermore, a lack of sustained support that takes into account users' past failures contributes to low success rates. Additionally, the lack of integrated sales of special nutritional supplements and training equipment means users have to purchase necessary items separately, creating an inconvenient situation.

[0792] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0793] In this invention, the server includes means for using VR technology, means for providing personalized training and dietary guidance using generative AI, means for generating an optimal training menu based on the user's body type information, physical fitness information, and health status, means for generating an optimal meal plan based on the user's dietary preferences, health status, and weight loss goals, and means for selling special nutritional foods and training equipment. This makes it possible to provide individually optimized training and dietary guidance to users and to provide continuous support that takes into account past failure data. In addition, by providing necessary nutritional foods and training equipment in one package, user convenience can be improved.

[0794] "VR technology" is a technology that uses virtual reality to provide users with an immersive experience.

[0795] "Generative AI" is a technology that uses artificial intelligence to analyze data and generate optimal training and meal plans for users.

[0796] "Personalized training" means providing a training program that is individually optimized based on the user's body type, fitness level, and health status.

[0797] "Personalized meal guidance" means providing a meal plan that is individually optimized based on the user's dietary preferences, health condition, and weight loss goals.

[0798] "Body type information" refers to the user's physical data, such as height, weight, and body fat percentage.

[0799] "Physical fitness information" refers to physical data such as the user's exercise experience and current exercise habits.

[0800] "Health status" refers to data about the user's health, such as allergies and pre-existing medical conditions.

[0801] "Dietary preferences" refer to data about a user's food preferences, such as their favorite and least favorite ingredients.

[0802] A "diet goal" is a target that the user wants to achieve, such as weight loss or muscle gain.

[0803] "Special nutritional supplements" are foods specifically designed to support dieting or training.

[0804] "Training equipment" refers to the devices and equipment that users use to perform training.

[0805] "Past failure data" refers to data about users' past experiences of failing at dieting or training.

[0806] "Sustained support" means providing long-term assistance to help users continue their diet and training.

[0807] Modes for carrying out the invention

[0808] This invention is a diet support system that combines VR technology and generative AI to provide users with personalized training and dietary guidance. Specific embodiments of this system are described below.

[0809] System Configuration

[0810] This system consists of a server, terminals (VR devices or smartphones), and users. The server is responsible for generating training menus and meal plans using a generative AI model and sending them to the terminals. The terminals send information entered by the user to the server, and the training menus and meal plans received from the server are displayed to the user.

[0811] Hardware and software to be used

[0812] The server is a high-performance computer with powerful computing capabilities and software installed to run generative AI models (e.g., OpenAI's GPT-4). The terminal is a VR device or smartphone that provides an interface for users to input information and view training menus and meal plans.

[0813] Data processing and calculation

[0814] The server receives data from the user, such as body shape information, fitness level, health status, dietary preferences, and weight loss goals. Based on this data, it uses an AI model to generate optimal training menus and meal plans. The generated menus and plans are sent to the user's device and displayed to them.

[0815] Specific example

[0816] Example 1: Generating a training menu

[0817] The user inputs body type information (height 170cm, weight 70kg, body fat percentage 20%) and fitness information (no prior exercise experience, current exercise habit is walking once a week). Based on this information, the server uses a generative AI model to generate a training menu suitable for the user. For example, the following prompt text is input to the generative AI model.

[0818] Prompt message:

[0819] "Please create a training program suitable for a 30-year-old male who is 170cm tall, weighs 70kg, has a body fat percentage of 20%, and has no prior exercise experience."

[0820] Example 2: Generating a meal plan

[0821] The user inputs their dietary preferences (favorite foods are chicken and broccoli, disliked foods are fish), health status (no allergies, no chronic illnesses), and diet goal (weight loss). Based on this information, the server uses a generative AI model to generate a meal plan suitable for the user. For example, the following prompt text is input to the generative AI model.

[0822] Prompt message:

[0823] "Please create a one-week meal plan suitable for a 30-year-old man who likes chicken and broccoli, dislikes fish, has no allergies, and is aiming to lose weight."

[0824] In this way, the server, terminal, and user work together to provide personalized diet support.

[0825] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0826] Step 1:

[0827] Users input their body information (height, weight, body fat percentage), physical fitness information (exercise experience, current exercise habits), and health status (allergies, pre-existing conditions) using a device (VR device or smartphone). This information is entered through the device's interface and sent to the server. The input data is stored in a database as individual user information.

[0828] Step 2:

[0829] The terminal sends the entered user information to the server. The server stores the received information in a database and generates prompts for input into the AI ​​model. For example, based on the user's body type and fitness information, it might generate a prompt such as, "Create a training menu suitable for a 30-year-old male who is 170cm tall, weighs 70kg, has a body fat percentage of 20%, and has no prior exercise experience."

[0830] Step 3:

[0831] The server inputs the generated prompt sentences into the AI ​​model, which then generates the optimal training menu for the user. The AI ​​model analyzes the data based on the input prompt sentences and outputs the training menu. The output training menu is saved on the server.

[0832] Step 4:

[0833] The server sends the generated training menu to the terminal. The terminal displays the received training menu to the user. The user performs the exercises according to the displayed training menu. The terminal tracks the user's movements in real time and provides feedback on correct form and movements.

[0834] Step 5:

[0835] Users use a terminal to input their dietary preferences (favorite and disliked foods), health status (allergies, chronic illnesses), and diet goals (weight loss, muscle gain). This information is entered through the terminal's interface and sent to the server. The input data is stored in a database as individual user information.

[0836] Step 6:

[0837] The server uses a generative AI model to generate meal plans based on stored meal information. For example, based on the user's dietary preferences and health status, it might generate a prompt message such as, "Create a 1-week meal plan suitable for a 30-year-old male who likes chicken and broccoli, dislikes fish, has no allergies, and is aiming to lose weight."

[0838] Step 7:

[0839] The server inputs the generated prompt text into the AI ​​model, which then generates the optimal meal plan for the user. The AI ​​model analyzes the data based on the input prompt text and outputs the meal plan. The output meal plan is saved on the server.

[0840] Step 8:

[0841] The server sends the generated meal plan to the device. The device displays the received meal plan to the user. The user eats according to the displayed meal plan. The device tracks whether the user is adhering to the meal plan and provides reminders and advice as needed.

[0842] In this way, the server, terminal, and user work together to provide personalized diet support.

[0843] (Application Example 1)

[0844] Next, we will describe Application Example 1 of Form Example 1. 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."

[0845] Traditional diet support systems often provide users with uniform training and dietary guidance, lacking personalized support that adequately considers each user's body type, physical fitness, health condition, food preferences, and weight loss goals. Furthermore, dietary guidance requires users to procure and cook their own food, which is time-consuming and makes sustainable weight loss difficult. Additionally, the lack of continuous support utilizing users' past failure data contributes to a low success rate in weight loss programs.

[0846] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0847] This invention includes a server that utilizes VR technology, provides personalized training and dietary guidance using generative AI, sells special nutritional foods and training equipment, and proposes an optimal meal menu based on information such as the user's body type, physical fitness, health condition, dietary preferences, and weight loss goals, and allows the user to order meals through a food delivery service. This enables the provision of individually optimized training and dietary guidance to users, and further reduces the effort involved through a food delivery service, thereby making sustainable weight loss success possible.

[0848] "VR technology" is a technology that provides users with virtual reality, allowing them to experience a virtual environment different from the real world through sight and sound.

[0849] "Generative AI" is a technology that uses artificial intelligence to analyze user data and generate individually optimized training and dietary guidance.

[0850] "Personalized training" means providing an optimal training program based on individual information such as the user's body type, physical fitness, and health condition.

[0851] "Dietary guidance" involves suggesting appropriate meal menus, taking into account the user's food preferences, health condition, and weight loss goals.

[0852] "Special nutritional foods" are foods specifically designed for weight loss or maintaining health, and their nutritional balance is taken into consideration.

[0853] "Training equipment" refers to devices used for exercise and fitness, supporting users in improving their physical fitness and building muscle strength.

[0854] A "food delivery service" is a service that delivers meals ordered by users to their homes, saving users time and effort.

[0855] "User's body type" refers to the shape and size of the user's body, and serves as a basis for creating diet and training plans.

[0856] "Physical fitness" refers to the user's physical endurance and muscle strength, and is an important factor when determining the training menu.

[0857] "Health status" refers to the user's current health condition and should be taken into consideration when providing training or dietary guidance.

[0858] "Dietary preferences" refer to the foods and eating styles that users like, and are important information when providing personalized dietary guidance.

[0859] A "diet goal" refers to the weight or body shape target that the user wishes to achieve, and serves as the basis for creating training and dietary guidance plans.

[0860] As an embodiment of this invention, the following system is constructed.

[0861] First, the server provides a means using VR technology. Specifically, users can wear a VR device to train in a virtual reality environment. This VR device provides a realistic training environment through sight and sound, enhancing the user's sense of immersion.

[0862] Next, the server has the means to provide personalized training and dietary guidance using generative AI. The generative AI generates optimal training and meal plans based on information such as the user's body type, physical fitness, health status, dietary preferences, and weight loss goals. This is done by using the OpenAI API to analyze the user's individual data and provide the optimal plan.

[0863] Furthermore, the server has a means of selling special nutritional supplements and training equipment. This allows users to easily purchase the nutritional supplements and training equipment they need.

[0864] Furthermore, the server suggests optimal meal menus based on information such as the user's body type, physical fitness, health status, dietary preferences, and weight loss goals, and provides a means for users to order meals through a food delivery service. This allows users to easily receive healthy meals at home.

[0865] The specific process involves first acquiring user information. This includes data entered by the user via smartphone or computer. Next, prompt messages are sent to the generation AI model to generate optimal training and meal plans. The following is an example of a prompt message:

[0866] User's body type: Standard

[0867] User's physical condition: Medium

[0868] User's health status: Good

[0869] User's dietary preferences: Japanese food

[0870] User's diet goal: Weight loss

[0871] Based on this information, please generate an optimal training program and meal plan.

[0872] The generated menu is displayed to the user through a VR device. The user can perform training according to this menu and also order meals using a food delivery service based on the meal menu.

[0873] This system allows users to receive personalized training and dietary guidance, and further reduces the hassle through a food delivery service, making sustainable weight loss success possible.

[0874] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0875] Step 1:

[0876] Users input individual information such as body type, physical fitness, health status, dietary preferences, and weight loss goals using their smartphones or computers. This information is sent to a server. The input data includes the user's height, weight, exercise habits, and dietary preferences. The server receives this data and stores it in a database.

[0877] Step 2:

[0878] The server generates prompt messages for the AI ​​model based on stored user information. These prompt messages include information such as the user's body type, physical fitness, health status, dietary preferences, and weight loss goals. An example of a specific prompt message is as follows:

[0879] User's body type: Standard

[0880] User's physical condition: Medium

[0881] User's health status: Good

[0882] User's dietary preferences: Japanese food

[0883] User's diet goal: Weight loss

[0884] Based on this information, please generate an optimal training program and meal plan.

[0885] Step 3:

[0886] The server sends prompt messages to the generative AI model, which generates optimal training and meal plans. The generative AI model analyzes the prompt messages and generates the most suitable training and meal plans for the user. The generated plans are returned to the server.

[0887] Step 4:

[0888] The server sends the generated training and meal plans to the VR device. The user puts on the VR device and trains in a virtual reality environment. The VR device provides a realistic training environment through sight and sound, enhancing the user's immersion.

[0889] Step 5:

[0890] The server orders meals through a food delivery service based on the generated meal menu. Users use their smartphones or computers to review the suggested meal menu and confirm their order. The server sends the order information to the food delivery service, and the meals are delivered to the user's home.

[0891] Step 6:

[0892] Users receive delivered meals and eat according to the suggested meal menu. This allows users to maintain a healthy diet while saving them time and effort.

[0893] Step 7:

[0894] The server collects users' training and dietary history data and uses it to inform future training and dietary guidance. This allows the system to track user progress and provide more effective weight loss support.

[0895] (Example 2)

[0896] Next, we will describe Example 2 of Form Example 2. 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".

[0897] Traditional diet support systems have struggled to provide personalized dietary guidance and training programs for individual users, resulting in ineffective weight loss support. Furthermore, the lack of appropriate recommendations for special nutritional foods and training equipment has led to low user success rates in weight loss.

[0898] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for the user to input personal data using a terminal, means for the server to receive and store the input data, means for the server to analyze the data using a generated AI model and generate dietary guidance and training programs, means for the server to recommend special nutritional foods based on the generated dietary guidance, means for the server to recommend training equipment based on the generated training program, and means for the terminal to display the advice and recommended products received from the server to the user. This makes it possible to provide personalized dietary guidance and training programs to the user and to make appropriate recommendations for special nutritional foods and training equipment, thereby improving the user's success rate in dieting.

[0899] A "user" refers to an individual who uses the system to input personal data and receive dietary guidance or training programs.

[0900] A "device" refers to a device used by a user to input personal data and receive and display advice and recommended products from a server. Specifically, this includes smartphones and personal computers.

[0901] A "server" refers to a computer system that stores data received from users, analyzes that data using a generated AI model, and creates dietary guidance and training programs.

[0902] A "generative AI model" refers to an artificial intelligence model that receives a user's personal data and prompt text as input and generates appropriate dietary guidance and training programs.

[0903] "Dietary guidance" refers to providing advice on appropriate dietary content and nutritional intake methods based on the user's weight loss goals and health condition.

[0904] A "training program" refers to providing advice on appropriate exercise content and training methods based on the user's weight loss goals and exercise habits.

[0905] "Special nutritional foods" refer to foods recommended based on the user's dietary guidance that are effective for weight loss and maintaining health. Specifically, these include protein bars and low-calorie smoothies.

[0906] "Training equipment" refers to equipment recommended based on the user's training program to effectively perform exercise and training. Specifically, this includes items such as treadmills and dumbbell sets.

[0907] "Advice" refers to specific instructions and recommendations regarding dietary guidance and training programs that the generative AI model provides based on the user's personal data.

[0908] "Recommended products" refer to special nutritional foods and training equipment that the generating AI model recommends based on the user's dietary guidance and training program.

[0909] This invention is a diet support system in which a user inputs personal data using a terminal, and a server analyzes that data to provide personalized dietary guidance and training programs. Specific embodiments of this system are described below.

[0910] First, users access the system using devices such as smartphones or personal computers. Through a dedicated application or web form, users enter personal data such as height, weight, age, gender, exercise habits, and diet. For example, a user might enter "Height 160cm, weight 70kg, age 30, gender female, exercise twice a week, breakfast is bread and coffee, lunch is salad, dinner is fish and vegetables."

[0911] Next, the terminal sends the entered data to the server. The server stores the received data using a relational database management system (RDBMS) such as MySQL or PostgreSQL. For example, it might execute the following SQL query: "INSERT INTO user_data (height, weight, age, gender, exercise_habits, diet) VALUES (160, 70, 30, 'female', '2 times a week', 'bread and coffee for breakfast, salad for lunch, fish and vegetables for dinner');"

[0912] The server uses data analysis software such as Python or R to analyze stored user data. The server uses a generative AI model (e.g., GPT-4) to generate optimal dietary guidance and training programs for the user's weight loss goals. The generative AI model receives prompt statements as input and generates appropriate advice. For example, the following prompt statements are input to the generative AI model:

[0913] "I am a 30-year-old woman, weighing 70kg, 160cm tall, and I exercise twice a week. My weight loss goal is to lose 5kg in 3 months. Please provide me with the optimal dietary guidance and training program."

[0914] The AI ​​model generates dietary advice based on this prompt. For example, it might generate advice such as, "We recommend consuming high-protein foods for breakfast and plenty of vegetables for lunch and dinner. For snacks, nuts and yogurt are good choices." It might also make recommendations such as, "We recommend purchasing protein bars or low-calorie smoothies."

[0915] Similarly, the generative AI model generates training programs. For example, it might generate advice such as, "Do 30 minutes of aerobic exercise (e.g., jogging or cycling) three times a week, and add strength training twice a week." It might also make recommendations such as, "We recommend purchasing a treadmill or dumbbell set."

[0916] Finally, the server sends the generated advice and recommended products to the device. The device then displays the advice and recommended products to the user using the application's dashboard or notification features. For example, it might display specific advice and recommended products along with a message such as, "A meal plan and training program based on your weight loss goals has been generated. Details are below."

[0917] In this way, users can receive personalized dietary guidance and training programs, as well as appropriate recommendations for special nutritional foods and training equipment. This system makes it possible to improve users' success rates in dieting.

[0918] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0919] Step 1:

[0920] Users access the system using their devices and enter personal data. Specifically, they enter information such as height, weight, age, gender, exercise habits, and diet through a dedicated application or web form. For example, they might enter "Height 160cm, weight 70kg, age 30, gender female, exercise twice a week, breakfast is bread and coffee, lunch is salad, dinner is fish and vegetables." The entered data is saved on the device in JSON format or as form data.

[0921] Step 2:

[0922] The terminal sends the entered data to the server. Specifically, it sends user data to the server using an HTTP POST request. For example, it sends JSON data to an endpoint called " / submitUserData". The server stores the received data in a relational database management system (RDBMS) such as MySQL or PostgreSQL. For example, it executes an SQL query such as "INSERT INTO user_data (height, weight, age, gender, exercise_habits, diet) VALUES (160, 70, 30, 'female', '2 times a week', 'bread and coffee for breakfast, salad for lunch, fish and vegetables for dinner');".

[0923] Step 3:

[0924] The server analyzes the stored user data. Specifically, it uses data analysis software such as Python or R to calculate the user's BMI (Body Mass Index) and calorie consumption. For example, it uses the formula "BMI = weight / (height / 100)^2" to calculate BMI. The analysis results are used to generate prompt statements for input into the generative AI model.

[0925] Step 4:

[0926] The server uses a generative AI model (e.g., GPT-4) to generate optimal dietary guidance and training programs for the user's weight loss goals. Specifically, it inputs prompt sentences into the generative AI model and generates appropriate advice. For example, it inputs the prompt sentence, "I am a 30-year-old woman, weighing 70kg, 160cm tall, and I exercise twice a week. My weight loss goal is to lose 5kg in 3 months. Please provide optimal dietary guidance and training programs." The generative AI model then generates dietary guidance and training programs based on this prompt sentence.

[0927] Step 5:

[0928] The server recommends specific nutritional foods based on the generated dietary guidance. Specifically, it selects nutritional foods suitable for the user based on the dietary guidance provided by the generating AI model. For example, along with advice such as, "We recommend consuming high-protein foods for breakfast and plenty of vegetables for lunch and dinner. For snacks, nuts and yogurt would be good choices," it might also recommend, "We recommend purchasing protein bars or low-calorie smoothies."

[0929] Step 6:

[0930] The server recommends training equipment based on the generated training program. Specifically, it selects training equipment suitable for the user based on the training program provided by the generating AI model. For example, along with advice such as, "Do 30 minutes of aerobic exercise (e.g., jogging or cycling) three times a week, and add strength training twice a week," it might recommend, "We recommend purchasing a treadmill or dumbbell set."

[0931] Step 7:

[0932] The server sends the generated advice and recommended products to the device. Specifically, it uses an HTTP response to send the generated advice and recommended products to the device. The device displays the received information to the user using the application's dashboard or notification function. For example, it might display specific advice and recommended products along with a message such as, "A meal plan and training program based on your diet goals has been generated. Details are as follows."

[0933] (Application Example 2)

[0934] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0935] Traditional diet support systems have difficulty providing individualized dietary guidance and training programs, and have also struggled to effectively recommend special nutritional foods and training equipment. Furthermore, they lack support for sustained diet success that takes into account users' past failures, resulting in a low long-term success rate for dieting.

[0936] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0937] This invention includes a server that includes means for collecting user data, means for analyzing the data using a generating AI to generate optimal dietary guidance and training programs, and means for recommending special nutritional foods and training equipment based on the programs provided by the generating AI and encouraging their purchase. This enables the provision of an optimal diet plan for each individual user and the effective recommendation of special nutritional foods and training equipment. Furthermore, by analyzing the user's past failure data, it is possible to support sustainable weight loss success.

[0938] "User data" refers to information such as the user's weight loss goals, current physical condition, eating habits, and exercise habits.

[0939] "Generative AI" refers to a system that uses artificial intelligence technology to analyze data and generate optimal dietary guidance and training programs.

[0940] "Dietary guidance" refers to suggesting appropriate meal content and timing based on the user's health condition and weight loss goals.

[0941] A "training program" refers to suggesting appropriate exercise content and frequency based on the user's physical fitness level and weight loss goals.

[0942] "Nutritional foods" refer to foods specifically designed for weight loss or maintaining health.

[0943] "Training equipment" refers to tools and devices used to effectively perform exercise or training.

[0944] "Recommendation" refers to the process where the generating AI suggests specific nutritional foods or training equipment to the user based on its analysis results.

[0945] "Encouraging purchase" refers to making it easy for users to buy recommended nutritional supplements or training equipment.

[0946] "Past failure data" refers to information about users' past experiences of failing at dieting and the reasons for those failures.

[0947] "Sustainable weight loss success" refers to users continuing their diet over a long period of time and achieving their goals.

[0948] The following system configuration and processing procedure will be described as embodiments for carrying out this invention.

[0949] System Configuration

[0950] 1. Collection of user data

[0951] Hardware: Smartphone

[0952] Software: Application user interface

[0953] Data: User's diet goals, current physical condition, eating habits, exercise habits

[0954] 2. Data analysis using generative AI

[0955] Hardware: Cloud Servers

[0956] Software: Generative AI models (e.g., GPT-4)

[0957] Data Processing: Analyze user data to generate optimal dietary guidance and training programs.

[0958] 3. Selection of Recommended Products

[0959] Hardware: Cloud Servers

[0960] Software: Product database, recommendation engine

[0961] Data processing: Based on programs provided by the generation AI, special nutritional supplements and training equipment are selected.

[0962] 4. Suggestions for users

[0963] Hardware: Smartphone

[0964] Software: Application user interface

[0965] Data display: Recommended dietary guidance, training programs, and related product information.

[0966] 5. Purchase Process

[0967] Hardware: Smartphone

[0968] Software: Electronic payment system

[0969] Data processing: Processing and verification of purchase procedures

[0970] Explanation of the process

[0971] 1. Collection of user data:

[0972] Users input information such as their diet goals, current physical condition, eating habits, and exercise habits through a smartphone application. This data is sent to a cloud server and stored for analysis by generating AI.

[0973] 2. Data analysis using generative AI:

[0974] The AI ​​model on the cloud server (e.g., GPT-4) analyzes the collected user data and generates personalized dietary guidance and training programs for each user. This analysis also takes into account the user's past failures.

[0975] 3. Selection of recommended products:

[0976] Based on a program provided by the AI, a recommendation engine on a cloud server selects specific nutritional supplements and training equipment. This ensures that the user receives recommendations for the most suitable products.

[0977] 4. Suggestions for users:

[0978] Through a smartphone application, users will be shown generated dietary guidance, training programs, and recommended nutritional foods and training equipment.

[0979] 5. Purchase Process:

[0980] Users can easily purchase recommended nutritional supplements and training equipment through the application. Purchases are processed using an electronic payment system.

[0981] Specific example

[0982] The user opens the application and enters the following information:

[0983] Diet goal: Lose 5kg

[0984] Current health condition: Healthy

[0985] Eating habits: 3 meals a day, with snacks.

[0986] Exercise habits: Jogging twice a week

[0987] The generating AI analyzes this data and provides the following dietary guidance and training programs:

[0988] Dietary guidance: High-protein, low-calorie diet, replace snacks with nuts.

[0989] Training program: Add strength training three times a week.

[0990] Furthermore, the following special nutritional supplements and training equipment are recommended:

[0991] Nutritional foods: High-protein bars, protein shakes

[0992] Training equipment: Dumbbell set, yoga mat

[0993] Example of a prompt

[0994] "Based on the user's weight loss goals, current physical condition, eating habits, and exercise habits, generate an optimal diet plan and training program, and recommend the most suitable nutritional supplements and training equipment."

[0995] In this way, users can easily find and purchase the diet plan and related products that are best suited to them.

[0996] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0997] Step 1:

[0998] The user opens a smartphone application and enters information such as their weight loss goals, current physical condition, eating habits, and exercise habits.

[0999] Input: Diet goal, current physical condition, eating habits, exercise habits

[1000] Output: User data

[1001] Specific action: The user enters the required information into the application's input form and presses the submit button.

[1002] Step 2:

[1003] The device sends the user data it collects to a cloud server.

[1004] Input: User data

[1005] Output: User data stored on the cloud server

[1006] Specific operation: The application calls an API to send user data to the cloud server.

[1007] Step 3:

[1008] The server uses a generated AI model (e.g., GPT-4) to analyze the collected user data and generate optimal dietary guidance and training programs.

[1009] Input: User data

[1010] Output: Dietary guidance, training program

[1011] Specific operation: A generation AI model on a cloud server analyzes user data and generates optimal dietary guidance and training programs based on prompt messages.

[1012] Step 4:

[1013] The server selects special nutritional supplements and training equipment based on a program provided by the AI.

[1014] Input: Dietary guidance, training program

[1015] Output: Recommended nutritional foods, training equipment

[1016] Specific operation: A recommendation engine on a cloud server selects the most suitable nutritional foods and training equipment from a product database based on dietary guidance and training programs.

[1017] Step 5:

[1018] The server suggests recommended dietary guidance, training programs, and related products to the user.

[1019] Input: Recommended nutritional supplements, training equipment

[1020] Output: Suggestions for the user

[1021] Specific operation: The cloud server generates suggestions, which are then sent to a smartphone application and displayed to the user.

[1022] Step 6:

[1023] Users purchase recommended nutritional foods and training equipment through the application.

[1024] Input: User's purchase intention

[1025] Output: Purchase confirmation, payment complete

[1026] Specific action: The user presses the purchase button and completes the payment through the electronic payment system.

[1027] In this way, users can easily find and purchase the diet plan and related products that are best suited to them.

[1028] (Example 3)

[1029] Next, we will describe Embodiment 3 of Embodiment Example 3. 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".

[1030] Traditional diet support systems failed to fully utilize users' past failure data, making it difficult to support sustainable weight loss success. Furthermore, the lack of personalized training and dietary guidance increased the likelihood of users repeating the same mistakes. Additionally, the insufficient mechanisms for effectively collecting and analyzing user feedback and updating plans resulted in the problem of insufficient sustained weight loss effectiveness.

[1031] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1032] In this invention, the server includes means for collecting user data, means for storing and managing the collected data, means for using a generative AI model to analyze the stored data, means for generating personalized training and dietary guidance based on the analysis results, means for delivering the generated plans to users, means for collecting user feedback, and means for analyzing the collected feedback and updating the plans. This makes it possible to utilize the user's past failure data to support sustainable weight loss success.

[1033] "User data" refers to information entered by the user, such as their past dieting history, patterns of failure, current weight, target weight, dietary habits, and exercise routine.

[1034] "Means of collection" refers to a system in which users input data using smartphone apps or web forms and send it to a server.

[1035] "Means of storage and management" refers to a system that stores data received by a server in a database and manages it appropriately.

[1036] A "generative AI model" is an artificial intelligence model that analyzes collected data to generate personalized training and dietary guidance.

[1037] The "means of analysis" refer to a system that uses a generative AI model to analyze stored data and identify the user's past patterns of failure and success.

[1038] "Personalized training and dietary guidance" refers to training plans and dietary advice that are individually customized based on analysis results.

[1039] The "means of delivery" refer to a system that sends the generated training plan and dietary guidance from the server to the terminal and notifies the user.

[1040] "Methods for collecting feedback" refer to a system where users input their daily progress and new data into their devices and send it to a server.

[1041] The "means of analyzing feedback and updating plans" refer to a system that inputs the collected feedback back into a regenerating AI model and updates training plans and dietary guidance based on the analysis results.

[1042] This invention is a system that analyzes users' past failure data to support sustainable weight loss success. A specific embodiment of this system is described below.

[1043] Collection of user data

[1044] Users enter information such as their past dieting history, patterns of failure, current weight, target weight, diet, and exercise habits using a smartphone app or web form. For example, a user might enter, "In the past, I often ate sweets late at night."

[1045] Data storage and management

[1046] The terminal sends the data entered by the user to the server. The server stores the received data in a database (e.g., MySQL or PostgreSQL) and manages it appropriately.

[1047] Data Analysis

[1048] The server inputs the stored data into a generating AI model (e.g., OpenAI's GPT-4) and performs analysis. Specifically, it identifies the user's past failure and success patterns and gains insights based on the data. For example, it might conclude that "this user tends to eat sweets late at night."

[1049] Generating personalized plans

[1050] The server uses a generative AI model to generate optimal training plans and dietary guidance for the user. Specifically, it considers the user's past data to provide individually customized advice. For example, it might generate specific advice such as, "Prepare low-calorie snacks to suppress appetite late at night."

[1051] Plan distribution

[1052] The server sends the generated training plan and dietary guidance to the device. The device then displays the received plan to the user. Specifically, it provides information using the notification function and dashboard of a smartphone app. For example, it might notify the user, "Prepare a low-calorie snack to curb your appetite late at night."

[1053] Collecting user feedback

[1054] Users input their daily progress and new data (such as weight changes and dietary information) into their device. Specifically, they enter records of their daily meals and exercise into the app. For example, they might enter, "Today I ate a low-calorie snack late at night."

[1055] Feedback analysis and plan updates

[1056] The terminal sends the new data entered by the user to the server. The server inputs the received data back into the generating AI model and performs analysis. Based on the analysis results, it updates the training plan and dietary guidance and sends it back to the terminal. For example, if the analysis results indicate that "low-calorie snacks are effective," the training plan and dietary guidance may be updated.

[1057] Example of a prompt

[1058] "Based on the user's past dieting history and failure patterns, please generate an optimal training plan and dietary guidance. The user tends to eat sweets late at night. Please take this failure pattern into consideration and provide specific advice."

[1059] In this way, the diet support system utilizes the user's past data to support sustainable weight loss success. The flow of the specific processing in Example 3 will be explained using Figure 15.

[1060] Step 1:

[1061] Users enter information such as their past dieting history, patterns of failure, current weight, target weight, diet, and exercise habits using a smartphone app or web form.

[1062] Input: Past dieting history, patterns of failure, current weight, target weight, diet, exercise habits

[1063] Output: Input user data

[1064] Step 2:

[1065] The terminal sends the data entered by the user to the server.

[1066] Input: User data entered by the user

[1067] Output: User data sent to the server

[1068] Step 3:

[1069] The server stores the received data in a database and manages it appropriately. Specifically, it uses a database management system such as MySQL or PostgreSQL.

[1070] Input: User data sent to the server

[1071] Output: User data stored in the database

[1072] Step 4:

[1073] The server inputs the stored data into a generating AI model (e.g., OpenAI's GPT-4) and performs analysis. Specifically, it identifies the user's past failure and success patterns and gains insights based on the data.

[1074] Input: User data stored in the database

[1075] Output: Analysis results (Example: "This user tends to eat sweets late at night")

[1076] Step 5:

[1077] The server uses a generative AI model to generate optimal training plans and dietary guidance for the user. Specifically, it takes the user's past data into consideration to provide individually customized advice.

[1078] Input: Analysis results

[1079] Output: Personalized training plans and dietary guidance (e.g., "Prepare low-calorie snacks to curb your appetite late at night").

[1080] Step 6:

[1081] The server sends the generated training plan and dietary guidance to the device. The device then displays the received plan to the user. Specifically, it provides information using the notification function and dashboard of a smartphone app.

[1082] Input: Personalized training plans and dietary guidance

[1083] Output: Training plans and dietary guidance displayed to the user (e.g., "Prepare low-calorie snacks to curb your appetite late at night").

[1084] Step 7:

[1085] Users input their daily progress and new data (such as weight changes and dietary information) into their device. Specifically, they enter records of their daily meals and exercise into the app.

[1086] Input: Daily progress and new data (e.g., "I ate a low-calorie snack late tonight")

[1087] Output: New data entered

[1088] Step 8:

[1089] The terminal sends the newly entered data to the server. The server inputs the received data back into the AI ​​model and performs analysis. Based on the analysis results, it updates the training plan and dietary guidance and sends them back to the terminal.

[1090] Input: New data

[1091] Output: Updated training plans and dietary advice (e.g., "Low-calorie snacks are effective")

[1092] In this way, the diet support system utilizes the user's past data to support sustainable weight loss success.

[1093] (Application Example 3)

[1094] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[1095] Traditional diet support systems often failed to provide personalized guidance that adequately considered users' past dieting history and patterns of failure, leading to repeated setbacks. Furthermore, the lack of specialized nutritional supplements and training equipment made it difficult for users to access necessary resources in one place. Additionally, the absence of features to suggest optimal meal plans made it challenging to support sustainable weight loss success.

[1096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means using VR technology, means providing personalized training and dietary guidance using generative AI, means selling special nutritional foods and training equipment, and means analyzing the user's past diet history and failure patterns and proposing a personalized meal menu. This makes it possible to prevent the user from repeating the same failures and to support sustainable diet success.

[1097] "VR technology" is a technology that uses virtual reality to provide users with a visual and experiential training environment.

[1098] "Generative AI" is an artificial intelligence technology that analyzes a user's past data to generate personalized training and dietary guidance.

[1099] "Personalized training and dietary guidance" means providing customized training and meal plans based on each user's individual needs and past history.

[1100] "Special nutritional foods" are foods specifically designed for purposes such as weight loss or maintaining health.

[1101] "Training equipment" refers to equipment used by users for physical training.

[1102] "User's past diet history" refers to records and data of diets the user has attempted in the past.

[1103] A "failure pattern" refers to the reasons or tendencies behind users having previously stopped or failed at dieting.

[1104] A "personalized meal plan" is a customized meal plan based on the user's past dieting history and patterns of failure.

[1105] The system for carrying out this invention is configured as follows: The server includes means using VR technology, means for providing personalized training and dietary guidance using generative AI, means for selling special nutritional foods and training equipment, and means for analyzing the user's past diet history and failure patterns and proposing personalized meal menus.

[1106] The server first retrieves the user's past diet history and failure patterns from a database. This data includes records of past diets the user has attempted and the reasons for their failures. Next, it uses a generative AI to analyze this data and generate an optimal training plan and meal plan for the user. The generative AI can utilize the OpenAI API.

[1107] Specifically, the server inputs the following prompt message into the generating AI:

[1108] Analyze the user's past dieting history and failure patterns to suggest personalized meal plans.

[1109] User data: {'age': 30, 'gender': 'female', 'height': 160, 'weight': 65, 'diet_history': [{'date': '2022-01-01', 'weight': 70, 'calories': 2000, 'exercise': 'running', 'success': False}, {'date': '2022-02-01', 'weight': 68, 'calories': 1800, 'exercise': 'yoga', 'success': True}], 'failure_patterns': ['stress eating', 'lack of motivation']}

[1110] The AI ​​generates the optimal meal menu for the user based on this prompt. The generated meal menu is then displayed on the user's smartphone or tablet.

[1111] Furthermore, the server also sells special nutritional supplements and training equipment. Users can purchase the necessary nutritional supplements and training equipment in one place based on the generated meal plan.

[1112] This system supports users in achieving sustainable weight loss success without repeating past setbacks. Furthermore, it makes it easier to stick to a diet by providing access to all necessary resources in one place.

[1113] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[1114] Step 1:

[1115] The server retrieves the user's past diet history and failure patterns from a database. The input is the user's ID, and the output is data on the user's past diet history and failure patterns. This data includes records of past diets the user has attempted and the reasons for their failure.

[1116] Step 2:

[1117] The server generates prompt messages to be input to the AI ​​based on the acquired data. The input is data on the user's past dieting history and failure patterns, and the output is the prompt messages to be input to the AI. Specifically, it generates prompt messages that include information such as the user's age, gender, height, weight, past dieting history, and failure patterns.

[1118] Step 3:

[1119] The server sends the generated prompt text to the generating AI, which then generates a personalized meal menu. The input is the generated prompt text, and the output is the personalized meal menu returned by the generating AI. The generating AI uses the OpenAI API to generate the optimal meal menu for the user.

[1120] Step 4:

[1121] The server sends the generated meal menu to the user's smartphone or tablet. The input is the personalized meal menu returned by the generating AI, and the output is the meal menu displayed on the user's device. The user can then view the generated meal menu via their smartphone or tablet.

[1122] Step 5:

[1123] The server sells specialized nutritional supplements and training equipment. Inputs are generated meal plans and user purchase requests, while outputs are links and information for users to make purchases. Users can centrally purchase the necessary nutritional supplements and training equipment based on the generated meal plans.

[1124] Step 6:

[1125] Users follow the provided meal menus and training plans to lose weight. The input is the meal menus and training plans provided by the server, and the output is the user's weight loss progress data. Users can receive further personalized guidance by feeding back their progress data to the server.

[1126] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1127] "Example of form 1"

[1128] One embodiment of this system is a diet support system incorporating an emotion engine. In this system, the user wears a VR device and receives personalized training and dietary guidance provided by a generative AI. The emotion engine recognizes the user's emotional state from their facial expressions, tone of voice, and word choice, and feeds this information back to the generative AI. The generative AI adjusts the training menu and dietary guidance based on this emotional information. For example, if it determines that the user is feeling stressed, it may suggest a training menu with relaxation effects or recommend foods that are effective in relieving stress.

[1129] "Example of form 2"

[1130] Furthermore, recommendations for special nutritional supplements and training equipment are adjusted according to the user's emotional state. For example, if a user is perceived as depressed, nutritional supplements that boost their energy or training equipment that helps them change their mood may be recommended. This makes it possible to provide optimal diet support tailored to the user's emotional state.

[1131] "Example of form 3"

[1132] Furthermore, this system will be offered on a monthly subscription basis, aiming for future scaling and sales exceeding 10 billion yen. By incorporating an emotion engine, it will be possible to increase user satisfaction and encourage long-term use. This will ensure stable revenue and enable large-scale business development.

[1133] The following describes the processing flow for each example of the form.

[1134] "Example of form 1"

[1135] Step 1: The user puts on the VR device.

[1136] Step 2: The generating AI provides users with personalized training and dietary guidance.

[1137] Step 3: The emotion engine recognizes the user's emotional state based on their facial expressions, tone of voice, and word choice.

[1138] Step 4: The emotion engine feeds that information back to the generating AI.

[1139] Step 5: The generating AI adjusts the training menu and dietary guidance based on this emotional information.

[1140] "Example of form 2"

[1141] Step 1: The emotion engine determines that the user's emotional state is depressed.

[1142] Step 2: The generating AI recommends nutritional foods that will give you energy.

[1143] Step 3: The generating AI recommends training equipment that will help you relax and unwind.

[1144] "Example of form 3"

[1145] Step 1: The system is provided on a monthly subscription basis.

[1146] Step 2: Incorporate an emotional engine to increase user satisfaction and encourage long-term use.

[1147] Step 3: Secure stable revenue and achieve large-scale business expansion.

[1148] (Example 1)

[1149] Next, we will describe Example 1 of Form Example 1. 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".

[1150] Traditional diet support systems do not adequately provide personalized training and dietary guidance based on the individual user's body type, physical fitness, and health condition. Furthermore, they do not adjust training and dietary guidance to take into account the user's emotional state, making sustainable weight loss difficult. Additionally, there is a lack of comprehensive support that combines the sale of special nutritional supplements and training equipment.

[1151] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1152] In this invention, the server includes means for using VR technology, means for providing personalized training and dietary guidance using generative AI, means for analyzing the user's emotional state using an emotion engine and feeding that information back to the generative AI, and means for selling special nutritional foods and training equipment. This not only provides personalized training and dietary guidance based on the user's individual body type, physical strength, and health condition, but also allows for adjustments that take into account the user's emotional state, thereby supporting sustainable weight loss success. Furthermore, by combining this with the sale of special nutritional foods and training equipment, comprehensive weight loss support is realized.

[1153] "VR technology" is a technology that uses virtual reality to provide users with an immersive experience.

[1154] "Generative AI" is a technology that uses artificial intelligence to analyze user data and generate personalized training and dietary guidance.

[1155] "Personalized training" refers to a training program that is individually optimized based on the user's body type, fitness level, and health condition.

[1156] "Dietary guidance" refers to advice on meals provided based on the user's dietary preferences, health condition, and weight loss goals.

[1157] An "emotion engine" is a technology that analyzes a user's emotional state based on their facial expressions, tone of voice, and word choice.

[1158] "Feedback" is the process by which a system provides appropriate actions to a user based on analyzed information.

[1159] "Special nutritional foods" are foods specifically designed for purposes such as weight loss or maintaining health.

[1160] "Training equipment" refers to equipment used by users for training.

[1161] "Sales" is the act of providing goods or services and receiving payment in return.

[1162] "Sustainable weight loss success" refers to achieving and maintaining weight loss goals over a long period of time.

[1163] The diet support system of the present invention is a system that combines VR technology and generative AI to provide users with personalized training and dietary guidance. Specific embodiments of this system are described below.

[1164] Hardware and software to be used

[1165] Hardware: VR device

[1166] Software: Generative AI models (e.g., OpenAI GPT-4), emotion engine

[1167] Program processing

[1168] Data collection and analysis

[1169] When a user wears a VR device, the system collects user movement data and environmental data in real time. The server collects basic information such as the user's body type (height, weight), physical fitness, and health status (e.g., blood pressure, heart rate). This information is either entered by the user in advance or obtained from the wearable device.

[1170] Generating training menus using generative AI models

[1171] The server sends prompt messages to the generating AI model based on the basic user information it has collected. For example, it might send a prompt message such as, "Generate an optimal training menu for a user who is 170cm tall, weighs 70kg, and has moderate fitness." The generating AI model receives the prompt message and generates an optimal training menu for the user. For example, it might generate a menu that combines 30 minutes of aerobic exercise with strength training.

[1172] Training menu provided

[1173] The server sends the training menu received from the generated AI model to the user's device (VR device). The user reviews the training menu through the VR device and begins exercising. The VR device tracks the user's movements in real time and provides feedback.

[1174] Analysis of emotional states using an emotion engine

[1175] The server uses an emotion engine to analyze the user's emotional state from their facial expressions, tone of voice, and word choice. For example, it can determine whether the user is feeling stressed. The analyzed emotional information is then fed back to a generative AI model.

[1176] Adjustment based on emotional information

[1177] The generative AI model adjusts training menus and dietary guidance based on the emotional feedback it receives. For example, it might suggest yoga routines with relaxation effects or recommend foods that are effective for stress relief. The server then sends the adjusted training menus and dietary guidance to the user's device.

[1178] Specific example

[1179] Training menu generation:

[1180] User's body data: Height 170cm, Weight 70kg

[1181] User's physical fitness data: Moderate fitness

[1182] Based on this data, the generating AI creates a workout plan that combines 30 minutes of aerobic exercise with strength training.

[1183] Providing dietary guidance:

[1184] User's dietary preferences: Likes vegetables, eats meat in moderation.

[1185] User's health status: High blood pressure

[1186] Based on this data, the generating AI suggests low-sodium, vegetable-centered meal menus.

[1187] Emotional engine feedback:

[1188] The emotion engine recognizes that the user is feeling stressed.

[1189] The generated AI suggests yoga routines with relaxation effects and recommends foods effective for stress relief (e.g., dark chocolate, nuts).

[1190] Example of a prompt

[1191] "Please generate an optimal training program based on the user's body type and fitness data."

[1192] "Provide personalized dietary guidance that takes into account the user's dietary preferences and health condition."

[1193] "Recognize the user's emotional state and adjust the training program and dietary guidance accordingly."

[1194] The above describes specific embodiments of the diet support system of the present invention.

[1195] The flow of the specific processing in Example 1 will be explained using Figure 17.

[1196] Step 1:

[1197] The user puts on a VR device.

[1198] In terms of specific actions, the user puts on a VR device at home and logs into the system. This prepares the system to collect the user's movement data and environmental data in real time.

[1199] Input: User login information, VR device connection

[1200] Output: Start of user activity data and environmental data collection

[1201] Step 2:

[1202] The server collects the user's basic information.

[1203] Specifically, the server collects basic information about the user, such as their body type (height, weight), physical fitness, and health status (e.g., blood pressure, heart rate). This information is either entered by the user beforehand or obtained from a wearable device.

[1204] Input: User's basic information, wearable device data

[1205] Output: Collected basic user information

[1206] Step 3:

[1207] The server sends a prompt message to the generated AI model.

[1208] In terms of specific operations, the server sends prompt messages to the generating AI model based on the basic user information it has collected. For example, it might send a prompt message such as, "Generate an optimal training menu for a user who is 170cm tall, weighs 70kg, and has moderate fitness."

[1209] Input: User's basic information, prompt text

[1210] Output: Sending prompt messages to the generating AI model

[1211] Step 4:

[1212] The generative AI model generates the training menu.

[1213] In terms of specific operation, the generative AI model (e.g., OpenAI GPT-4) receives a prompt and generates an optimal training menu for the user. For example, it might generate a menu that combines 30 minutes of aerobic exercise with strength training.

[1214] Input: Prompt message

[1215] Output: Generated training menu

[1216] Step 5:

[1217] The server sends the generated training menu to the terminal.

[1218] Specifically, the server sends the training menu received from the generated AI model to the user's device (VR device). The user can then view the training menu through the VR device.

[1219] Input: Generated training menu

[1220] Output: Sending the training menu to the user's device.

[1221] Step 6:

[1222] The user begins training.

[1223] Specifically, the user begins exercising according to a training menu provided through the VR device. The VR device tracks the user's movements in real time and provides feedback.

[1224] Input: Training Menu

[1225] Output: User training data, feedback

[1226] Step 7:

[1227] The server analyzes the user's emotional state using an emotion engine.

[1228] In terms of specific operations, the server uses an emotion engine to analyze the user's emotional state from their facial expressions, tone of voice, and word choice. For example, it can determine whether the user is feeling stressed.

[1229] Input: User's facial expression data, voice tone, word choice

[1230] Output: Analyzed sentiment information

[1231] Step 8:

[1232] The server feeds emotional information back into the AI ​​model that generates it.

[1233] In terms of specific operations, the server feeds back the analyzed emotional information to the generating AI model. For example, it sends information such as "the user is feeling stressed."

[1234] Input: Analyzed emotional information

[1235] Output: Feedback to the Generative AI Model

[1236] Step 9:

[1237] The generative AI model adjusts training menus and dietary guidance based on emotional information.

[1238] In terms of specific actions, the generative AI model adjusts training menus and dietary guidance based on the emotional information it receives as feedback. For example, it might suggest yoga routines with relaxation effects or recommend foods that are effective for stress relief.

[1239] Input: Feedback on emotional information

[1240] Output: Customized training menu and dietary guidance

[1241] Step 10:

[1242] The server sends the adjusted menu and instructions to the terminal.

[1243] Specifically, the server sends a customized training menu and dietary guidance to the user's device. The user receives the new menu and guidance through a VR device.

[1244] Input: Customized training menu and dietary guidance

[1245] Output: Send to the user's terminal

[1246] (Application Example 1)

[1247] Next, we will describe Application Example 1 of Form Example 1. 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."

[1248] Traditional diet support systems do not provide personalized training or dietary guidance that fully considers the individual needs and emotional states of users. Furthermore, few systems are designed for use in physical locations, limiting opportunities for users to experience them firsthand. Additionally, the lack of systems that recognize and respond to users' emotional states in real time makes it difficult to maintain user motivation.

[1249] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means using VR technology, means providing personalized training and dietary guidance using a generative AI, means selling special nutritional foods and training equipment, means recognizing the user's emotional state using an emotion engine and feeding that information back to the generative AI, and means for the user to wear a VR device in a physical store and receive personalized training and dietary guidance provided by the generative AI. This makes it possible to provide personalized training and dietary guidance that meets the individual needs and emotional state of the user, and makes it easier to maintain the user's motivation through the experience at the physical store.

[1250] "VR technology" is a technology that realizes virtual reality, enabling users to immerse themselves in a virtual environment.

[1251] "Generative AI" is a technology that uses artificial intelligence to automatically generate optimal training and dietary guidance for users.

[1252] "Personalized training and dietary guidance" means providing training programs and meal plans that are customized based on the individual needs and condition of the user.

[1253] "Special nutritional foods" are foods specifically designed for purposes such as weight loss or maintaining health.

[1254] "Training equipment" refers to equipment used for fitness and exercise.

[1255] An "emotional engine" is a technology that recognizes a user's emotional state from their facial expressions, tone of voice, and choice of words.

[1256] A "physical store" is a store that exists in a physical location and where customers can visit in person to receive services.

[1257] A "VR device" is a hardware device used to experience virtual reality, and includes head-mounted displays, controllers, and other similar devices.

[1258] "Feedback" refers to the process of adjusting training and dietary guidance based on information the system receives from users.

[1259] This invention is a system in which users wear a VR device in a physical store and receive personalized training and dietary guidance provided by a generated AI. The specific form of this system is described below.

[1260] System Configuration

[1261] hardware

[1262] VR devices: These use head-mounted displays, allowing users to immerse themselves in a virtual reality environment.

[1263] Camera: Used to capture the user's facial expressions in real time. This allows the emotion engine to recognize the user's emotional state.

[1264] Server: Provides computing resources to run the generated AI model and generate training and dietary guidance.

[1265] software

[1266] Generative AI Model: An artificial intelligence model for generating training and dietary guidance based on the individual needs and circumstances of the user.

[1267] Emotion Engine: Software that recognizes a user's emotional state based on their facial expressions, tone of voice, and word choice.

[1268] VR application: An application that allows users to receive training and dietary guidance through a VR device.

[1269] System operation

[1270] 1. Acquisition of user information: The server acquires information such as the user's body type, physical fitness, health status, dietary preferences, and diet goals.

[1271] 2. Recognition of emotional state: The camera captures the user's facial expressions, and the emotion engine analyzes the data to recognize the emotional state.

[1272] 3. Generation of training and dietary guidance: The generation AI model generates optimal training menus and dietary guidance based on acquired user information and emotional state.

[1273] 4. Display on VR devices: The generated training menu and dietary guidance are displayed on the VR device, and the user experiences them in a virtual reality environment.

[1274] Specific example

[1275] For example, consider the following scenario regarding user information.

[1276] Body type: Standard

[1277] Physical fitness: moderate

[1278] Health condition: Good

[1279] Food preferences: Japanese food

[1280] Diet goal: Weight loss

[1281] Based on this information, the generative AI model generates the following prompt message.

[1282] The user has a standard build, moderate physical fitness, and good health. They prefer Japanese food and are aiming to lose weight. Currently, the user is experiencing stress. Based on this information, please generate an optimal training program and dietary guidance.

[1283] By inputting this prompt into the AI ​​model, an optimal training menu and dietary guidance for the user are generated. The generated content is provided to the user via a VR device, allowing the user to receive training and dietary guidance in a virtual reality environment.

[1284] This enables personalized training and dietary guidance tailored to the individual needs and emotional state of users, and makes it easier to maintain user motivation through in-store experiences.

[1285] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[1286] Step 1:

[1287] The server acquires information such as the user's body type, physical fitness, health status, dietary preferences, and weight loss goals. This information is collected from data previously entered by the user and from past historical data. The input data is stored as the user's profile information and used as input for the generated AI model.

[1288] Step 2:

[1289] The terminal (a camera connected to the VR device) captures the user's facial expressions in real time. The captured video data is sent to the emotion engine. The emotion engine analyzes the video data and recognizes the user's emotional state (e.g., stress, joy, fatigue). The recognized emotional state is then generated as output.

[1290] Step 3:

[1291] The server generates prompt messages for the AI ​​model based on the acquired user information and emotional state. The prompt messages are generated in the following format:

[1292] The user has a standard build, moderate physical fitness, and good health. They prefer Japanese food and are aiming to lose weight. Currently, the user is experiencing stress. Based on this information, please generate an optimal training program and dietary guidance.

[1293] The generated prompt sentences are used as input for the generative AI model.

[1294] Step 4:

[1295] The server inputs prompt messages into the generating AI model, which then generates an optimal training menu and dietary guidance. The generating AI model considers user information and emotional state to output a personalized training menu and dietary guidance. The outputted training menu and dietary guidance are then stored on the server.

[1296] Step 5:

[1297] The server sends the generated training menu and dietary guidance to the VR device. The VR device displays the received training menu and dietary guidance to the user. The user can receive training and dietary guidance in a virtual reality environment through the VR device.

[1298] Step 6:

[1299] Users wear a VR device and perform exercises according to a generated training menu. Exercise progress and feedback are sent to the server in real time. The server uses this data to adjust the training menu and dietary guidance as needed.

[1300] Step 7:

[1301] The server analyzes users' exercise data and feedback, and uses this information to inform future training menus and dietary guidance. This ensures that users receive continuous, optimal guidance tailored to their progress and emotional state.

[1302] (Example 2)

[1303] Next, we will describe Example 2 of Form Example 2. 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".

[1304] Traditional diet support systems lack personalized support tailored to the individual needs and emotional states of users. Furthermore, they often recommend specific nutritional foods and training equipment that are not optimized for the user's specific situation. Additionally, they fail to utilize users' past failure data to provide sustained support for successful weight loss, making it difficult to maintain user motivation.

[1305] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1306] In this invention, the server includes means for receiving and storing data entered by the user, means for generating an optimal meal plan and training plan for the user using a generative AI model, means for recommending special nutritional foods and training equipment based on the generated plans, and means for analyzing the user's emotional state and recommending nutritional foods and training equipment according to that emotional state. This enables personalized support that is tailored to the user's individual needs and emotional state, thereby supporting sustainable weight loss success.

[1307] "Means for receiving and storing user-entered data" refers to a function in which a server receives data such as weight, height, target weight, dietary preferences, exercise habits, and emotional state entered by the user via a terminal, and stores it in a database.

[1308] "A means of generating optimal meal plans and training plans for users using a generative AI model" refers to a function that uses a generative AI model to create individually optimized meal plans and training plans based on the user's input data.

[1309] "A means of recommending special nutritional foods and training equipment based on the generated plan" refers to a function that analyzes the meal plan and training plan created by the generating AI model, selects the most suitable nutritional foods and training equipment from a database, and recommends them to the user.

[1310] "A means of analyzing a user's emotional state and recommending nutritional foods and training equipment appropriate to that emotional state" refers to a function that uses emotion analysis software to analyze a user's emotional state and, based on the results, recommends nutritional foods and training equipment suitable for that emotional state.

[1311] "Means to support sustainable weight loss success" refers to a function that analyzes the user's past failure data and provides support to help the user continue their diet.

[1312] This invention is a diet support system that includes means for receiving and storing data entered by a user, means for generating an optimal meal plan and training plan for the user using a generative AI model, means for recommending special nutritional foods and training equipment based on the generated plan, and means for analyzing the user's emotional state and recommending nutritional foods and training equipment according to that emotional state.

[1313] 1. User data entry and saving

[1314] Users access the diet support system application using their device (smartphone or PC). Users input data such as weight, height, target weight, dietary preferences, exercise habits, and current emotional state. The device sends the input data to the server. The server stores the received data in a database. This data is used for subsequent processing.

[1315] 2. Nutritional guidance and creation of training plans

[1316] The server sends prompt messages to a generative AI model (e.g., OpenAI's GPT-4) based on stored user data. These prompt messages include the user's weight, target weight, dietary preferences, and exercise habits. Based on these prompt messages, the generative AI model generates an optimal meal plan and training plan for the user.

[1317] Example of a prompt:

[1318] "The user's current weight is 70kg, and their target weight is 65kg. The user prefers a high-protein diet and exercises three times a week. Please propose an optimal meal plan and training plan for this user."

[1319] Based on this prompt, the generating AI model creates specific meal plans (e.g., oatmeal and protein shake for breakfast, chicken breast and vegetable salad for lunch, salmon and broccoli for dinner) and training plans (e.g., strength training and cardio three times a week).

[1320] 3. Recommendations for special nutritional supplements and training equipment

[1321] The server analyzes the generated meal and training plans and consults a database of specialized nutritional foods and training equipment. The server selects the most suitable products for each plan and recommends them to the user. For example, if a high-protein meal plan is generated, the server will recommend high-protein protein bars. It will also recommend training equipment best suited to a specific training program.

[1322] 4. Analysis and adjustment of emotional states

[1323] The server analyzes the user's emotional state using sentiment analysis software (e.g., IBM Watson's Sentiment Analysis API) based on the user's input data and past behavioral data. If the server determines that the user is depressed, it recommends energy-boosting foods or exercise equipment to help them change their mood.

[1324] 5. Displaying recommendations and promoting purchases.

[1325] The server sends the generated meal plan, training plan, and recommended special nutritional foods and training equipment to the terminal. The terminal displays this information to the user. The user can review the displayed information and purchase the recommended products as needed.

[1326] In this way, the server provides the optimal plan and products to effectively support the user's diet.

[1327] The flow of the specific processing in Example 2 will be explained using Figure 19.

[1328] Step 1:

[1329] Users access the diet support system application using their device and input data such as weight, height, target weight, dietary preferences, exercise habits, and current emotional state. This input data is then transmitted from the device to the server. The input data includes the user's individual needs and circumstances.

[1330] Step 2:

[1331] The server receives user data sent from the terminal and stores it in the database. The stored data is used for subsequent processing. Specifically, it is stored in the database associated with the user ID.

[1332] Step 3:

[1333] The server sends prompt messages to the generative AI model based on stored user data. These prompt messages include the user's weight, target weight, dietary preferences, and exercise habits. Based on these prompt messages, the generative AI model generates an optimal meal plan and training plan for the user.

[1334] Example of a prompt:

[1335] "The user's current weight is 70kg, and their target weight is 65kg. The user prefers a high-protein diet and exercises three times a week. Please propose an optimal meal plan and training plan for this user."

[1336] Step 4:

[1337] The generation AI model generates specific meal plans and training plans based on the prompt text. The generated plans are sent to the server. The specific meal plan includes menus for breakfast, lunch, and dinner, and the training plan includes the type and frequency of exercise to be performed per week.

[1338] Step 5:

[1339] The server analyzes the generated meal plan and training plan and consults a database of specialized nutritional foods and training equipment. The server selects the most suitable products for each plan and recommends them to the user. For example, if a high-protein meal plan is generated, the server will recommend high-protein protein bars. A list of recommended products is generated as output.

[1340] Step 6:

[1341] The server analyzes the user's emotional state using emotion analysis software based on user input data and past behavioral data. If the server determines that the user is depressed, it recommends energy-boosting nutritional supplements or exercise equipment to help them change their mood. A list of recommendations tailored to the user's emotional state is output.

[1342] Step 7:

[1343] The server sends the generated meal plan, training plan, and recommended special nutritional foods and training equipment to the terminal. The terminal displays this information to the user. The user can review the displayed information and purchase recommended products as needed. The output generated is the information displayed to the user.

[1344] (Application Example 2)

[1345] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[1346] Traditional diet support systems lack personalized support tailored to the individual needs and emotional states of users. Furthermore, they typically recommend specific nutritional supplements and training equipment, failing to provide optimal product recommendations based on the user's emotional state. Additionally, purchasing recommended products often requires separate procedures, creating an inconvenient and cumbersome process for users.

[1347] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1348] In this invention, the server includes means for using VR technology, means for providing personalized training and dietary guidance using generative AI, means for selling special nutritional foods and training equipment, means for analyzing the user's emotional state and recommending the most suitable nutritional foods and training equipment, and means for making the recommended products available for purchase within the application. This enables optimal diet support tailored to the user's individual needs and emotional state, and simplifies the purchase process for recommended products.

[1349] "VR technology" is a technology that uses virtual reality to provide users with an immersive experience.

[1350] "Generative AI" is a technology that uses artificial intelligence to analyze data and generate training and dietary guidance tailored to individual needs.

[1351] "Personalized training and dietary guidance" means providing customized training programs and meal plans based on the individual data and needs of the user.

[1352] "Special nutritional foods" are foods specifically designed for purposes such as weight loss or maintaining health.

[1353] "Training equipment" refers to equipment used for fitness and exercise.

[1354] "Analyzing emotional states" means analyzing a user's text and voice data to quantify or classify their emotions at that time.

[1355] "Recommending optimal nutritional foods and training equipment" means suggesting the most suitable nutritional foods and training equipment based on the user's emotional state and individual needs.

[1356] "Making products available for purchase within the application" means allowing users to complete the purchase process for recommended products directly within the application.

[1357] The following system configuration is used as an embodiment of this invention. The system includes a server, a user terminal, and a generated AI model.

[1358] The server includes means of using VR technology, means of providing personalized training and dietary guidance using generative AI, means of selling special nutritional foods and training equipment, means of analyzing the user's emotional state and recommending the most suitable nutritional foods and training equipment, and means of making recommended products available for purchase within the application.

[1359] User devices may include smartphones, smart glasses, head-mounted displays, or robots. These devices communicate with a server to provide users with personalized training and dietary guidance.

[1360] The generative AI model analyzes the user's diet and training history, as well as their emotional state, to recommend optimal nutritional supplements and training equipment. The TextBlob library is used for analyzing emotional state, and the Requests library is used for sending and receiving data.

[1361] As a concrete example, if a user types "I'm tired today" on their smartphone, TextBlob analyzes their emotions, and the generating AI recommends nutritional supplements that promote relaxation. Similarly, if a user logs "I went for a 30-minute run," the generating AI recommends the most suitable training equipment.

[1362] The following is an example of a prompt statement:

[1363] User ID: 12345

[1364] Food log: [{'food_item': 'Apple', 'calories': 95, 'date': '2023-10-01T12:00:00'}]

[1365] Training log: [{'workout_type': 'Running', 'duration': 30, 'date': '2023-10-01T12:30:00'}]

[1366] Emotion log: [{'text': 'I feel great today!', 'polarity': 0.8, 'date': '2023-10-01T13:00:00'}]

[1367] By inputting this prompt into the AI ​​model, you can receive recommendations for optimal nutritional supplements and training equipment.

[1368] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[1369] Step 1:

[1370] Users log their meals and workouts using their smartphones. This data includes details such as the type of meal, calories, type of workout, and duration. This records the user's meal and workout history.

[1371] Step 2:

[1372] The user inputs their emotional state. For example, they might enter text such as "I'm tired today." This text data becomes the input data for emotion analysis.

[1373] Step 3:

[1374] The device uses the TextBlob library to analyze the text of the input emotional state. As a result of the analysis, the emotional polarity (positive or negative) is quantified. This allows the user's emotional state to be recorded as numerical data.

[1375] Step 4:

[1376] The device sends meal logs, training logs, and emotion logs to the server. The transmitted data includes the user ID, meal logs, training logs, and emotion logs. This allows the server to receive the user's most up-to-date data.

[1377] Step 5:

[1378] The server uses a generated AI model to analyze the received data. This analysis takes into account the user's past data and emotional state. Based on this, the system recommends the most suitable nutritional supplements and training equipment for the user.

[1379] Step 6:

[1380] The server sends information about recommended nutritional foods and training equipment to the terminal. The transmitted data includes detailed information about the recommended products. This allows the terminal to display the recommended products to the user.

[1381] Step 7:

[1382] Users purchase recommended products within the application. When a user presses the purchase button, their device sends a purchase request to the server. This allows users to easily purchase products.

[1383] Step 8:

[1384] The server receives the purchase request and processes the purchase. This process includes checking inventory, processing payment, and arranging delivery. As a result, the user receives the purchased product.

[1385] (Example 3)

[1386] Next, we will describe Embodiment 3 of Embodiment Example 3. 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".

[1387] Traditional diet support systems have faced challenges in achieving sustainable weight loss success because they do not provide personalized support that adequately considers each user's individual failure patterns and emotional state. Furthermore, there was a lack of effective means to increase user satisfaction and encourage long-term use.

[1388] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1389] In this invention, the server includes means for collecting user data, means for storing and managing the collected data, means for analyzing the data using a generative AI model to identify the user's failure patterns, means for generating personalized training plans and dietary guidance based on the analysis results, means for monitoring the user's emotional state using an emotion engine and providing appropriate feedback, and means for notifying the user of suggestions and support. This enables personalized support that takes into account the user's individual failure patterns and emotional state, thereby supporting sustainable weight loss success.

[1390] "Means for collecting user data" refers to devices or software that provide an interface for users to input their past diet history and experiences of failure.

[1391] "Means for storing and managing collected data" refers to devices or software for storing data collected from users in a database and managing the data while maintaining its integrity.

[1392] "A means of analyzing data using a generative AI model to identify user failure patterns" refers to a device or software that uses machine learning algorithms to analyze a user's past data and identify the causes and patterns of failure.

[1393] "Means for generating personalized training plans and dietary guidance based on analysis results" refers to a device or software that automatically generates optimal training plans and dietary guidance for users based on the results of data analysis.

[1394] "Means for monitoring a user's emotional state using an emotion engine and providing appropriate feedback" refers to a device or software that monitors a user's emotional state in real time and provides feedback according to that state.

[1395] "Means of notifying users of suggestions and support" refers to devices or software that notify users of generated plans and feedback and encourage them to take action.

[1396] This invention is a system that analyzes a user's past dieting history and failure patterns to support sustainable weight loss success. Specific embodiments of this system are described below.

[1397] First, the server provides a means to collect user data. Users use devices such as smartphones or PCs to input their past diet history and failures through a dedicated application or web interface. This data includes information such as dietary content, exercise history, weight fluctuations, and reasons for failure.

[1398] Next, the server employs means to store and manage the collected data. The data is stored in a relational database such as MySQL or PostgreSQL. The server performs data validation to maintain data integrity.

[1399] The server then analyzes the data using a generative AI model. Specifically, it builds a machine learning model using Python and TensorFlow to identify user frustration patterns. Based on past data, the server predicts the situations in which users are likely to become frustrated.

[1400] Based on the analysis results, the server generates personalized training plans and dietary guidance. For example, if a user tends to eat sweets late at night, the server will suggest low-calorie snacks. It also provides exercise plans tailored to the user's lifestyle and preferences.

[1401] Furthermore, the server uses an emotion engine to monitor the user's emotional state. The emotion engine estimates emotions based on the user's input data and behavioral patterns, and monitors them in real time. For example, if a user is feeling stressed, the server will suggest yoga or meditation to help them relax.

[1402] Finally, the server notifies the user of the generated plan and feedback. The device receives the notification and displays it to the user. The user acts according to the proposed plan and re-enters their progress, allowing the server to continuously update the data and provide support.

[1403] Examples of specific prompt messages include the following:

[1404] "Analyze the user's past dieting history and failure patterns, and suggest low-calorie snacks that are acceptable to eat late at night. Also, if the user is experiencing stress, suggest yoga or meditation to help them relax."

[1405] In this way, the server can prevent users from repeating the same setbacks and support their sustained weight loss success. The flow of the specific processing in Example 3 will be explained using Figure 21.

[1406] Step 1:

[1407] Users enter their past dieting history and experiences of failure.

[1408] Input: Data such as dietary content, exercise history, weight fluctuations, and reasons for failure.

[1409] Output: The input data is sent from the terminal to the server.

[1410] Specific operation: Users input data using a smartphone or PC via a dedicated application or web interface.

[1411] Step 2:

[1412] The server stores and manages the collected data.

[1413] Input: Data submitted by the user.

[1414] Output: Data stored in the database.

[1415] Specific operation: The server uses relational databases such as MySQL or PostgreSQL to store data and performs validation to maintain data integrity.

[1416] Step 3:

[1417] The server analyzes the data using a generative AI model.

[1418] Input: Saved user data.

[1419] Output: Failure patterns as analysis results.

[1420] Specific operation: The server uses Python and TensorFlow to build machine learning models and analyzes the user's past data to identify patterns of frustration.

[1421] Step 4:

[1422] The server generates personalized training plans and dietary guidance based on the analysis results.

[1423] Input: Failure patterns as analysis results.

[1424] Output: Personalized training plans and dietary guidance.

[1425] Specific operation: Based on the user's patterns of failure, the server suggests low-calorie snacks and exercise plans tailored to their lifestyle.

[1426] Step 5:

[1427] The server uses an emotion engine to monitor the user's emotional state and provide appropriate feedback.

[1428] Input: User input data and behavioral patterns.

[1429] Output: Feedback tailored to emotional state.

[1430] Specific operation: The server uses an emotion engine to monitor the user's emotional state in real time and suggests yoga or meditation to help them relax if they are feeling stressed.

[1431] Step 6:

[1432] The server notifies the user of the generated plan and feedback.

[1433] Input: Generated training plans, dietary guidance, and feedback tailored to emotional state.

[1434] Output: Suggestions and support notified to the user.

[1435] Specific operation: The server sends a notification to the terminal, which receives it and displays it to the user. The user acts according to the proposed plan and re-enters their progress.

[1436] (Application Example 3)

[1437] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[1438] Traditional diet support systems have struggled to effectively utilize users' past failure data, making it difficult to support sustainable weight loss success. Furthermore, a lack of feedback and advice to maintain user motivation hindered long-term adoption. Additionally, physical fitness gyms and diet cafes lacked the means to provide personalized training plans and meal menus.

[1439] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means using VR technology, means providing personalized training and dietary guidance using generative AI, means selling special nutritional foods and training equipment, means analyzing the user's past diet history and failure patterns at a physical fitness gym or diet cafe and providing personalized training plans and meal menus, and means providing feedback and advice to maintain the user's motivation using an emotion engine. This makes it possible to prevent users from repeating the same failures, support sustainable diet success, and promote long-term use.

[1440] "VR technology" is a technology that uses virtual reality to provide users with visual and experiential feedback.

[1441] "Generative AI" is a technology that uses artificial intelligence to analyze user data and generate personalized training and dietary guidance.

[1442] "Personalized training and dietary guidance" means providing training plans and meal menus optimized based on each user's individual data.

[1443] "Special nutritional foods" are foods that contain specific nutrients intended for weight loss or maintaining health.

[1444] "Training equipment" refers to equipment used for fitness and exercise.

[1445] A "physical store" refers to a facility that exists in a physical location, such as a fitness gym or a diet cafe.

[1446] A "fitness gym" is a facility equipped with equipment for exercise and training.

[1447] A "diet cafe" is a cafe that offers healthy meals and drinks to support weight loss.

[1448] "User's past diet history" refers to records and data of diets the user has attempted in the past.

[1449] "Failure patterns" refer to data that shows the causes and tendencies of users' past diet failures.

[1450] An "emotional engine" is a technology that analyzes the user's emotional state and provides feedback and advice to maintain motivation.

[1451] "Feedback" refers to evaluations and advice given regarding a user's behavior or condition.

[1452] "Advice" refers to guidance and suggestions provided to users in order to achieve their goals.

[1453] To implement this invention, the following system configuration and processing procedure are used.

[1454] System Configuration

[1455] 1. Hardware

[1456] Server: A high-performance server for running data analysis and generative AI models.

[1457] Device: The user's smartphone, tablet, or personal computer.

[1458] Physical store facilities: Sales facilities for training equipment and nutritional foods, installed in fitness gyms and diet cafes.

[1459] 2. Software

[1460] Generative AI Model: An AI model that analyzes a user's past dieting history and failure patterns to generate personalized training plans and meal menus.

[1461] Emotional Engine: Software that analyzes the user's emotional state and provides feedback and advice to maintain motivation.

[1462] Data analysis tools: Data analysis libraries such as Pandas and Scikit-learn.

[1463] Processing procedure

[1464] 1. Data collection and preprocessing

[1465] The server collects the user's past dieting history and failure patterns. This includes data such as weight, calorie intake, and exercise time.

[1466] The collected data is preprocessed and standardized using Pandas.

[1467] 2. Clustering

[1468] The server uses the KMeans algorithm from Scikit-learn to cluster user frustration patterns.

[1469] 3. Plan generation using AI

[1470] The server uses a generative AI model to generate personalized training plans and meal menus for each cluster.

[1471] A concrete example of a prompt would be: "Create a personalized training plan based on user cluster 1. The user has previously failed due to lack of exercise and poor diet management. Provide specific advice to help him successfully lose weight sustainably."

[1472] 4. Feedback from the Emotion Engine

[1473] The server uses an emotion engine to analyze the user's emotional state and provides feedback and advice to help maintain motivation.

[1474] Specific example

[1475] User A has tried dieting many times in the past, but has failed each time for the same reasons. This system will analyze his past data and provide him with an optimal training plan and meal plan. For example, the generating AI model will generate a specific plan using the prompt message: "Create a personalized training plan based on user cluster 1. The user has failed in the past due to lack of exercise and failure in diet management. Provide specific advice to help him succeed in dieting in the long term."

[1476] In this way, it becomes possible to prevent users from repeating the same setbacks, support sustainable weight loss success, and encourage long-term use.

[1477] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[1478] Step 1:

[1479] The server collects users' past dieting history and patterns of failure. Specifically, it stores data such as weight, calorie intake, and exercise time entered by users using smartphones or tablets in a database. The input data is saved in CSV file or database format.

[1480] Step 2:

[1481] The server preprocesses the collected data. Specifically, it uses the Pandas library to read the data, impute missing values, and remove outliers. After that, it standardizes the data using StandardScaler. The input is the user's raw data, and the output is preprocessed, standardized data.

[1482] Step 3:

[1483] The server performs clustering using pre-processed data. Specifically, it uses the KMeans algorithm from Scikit-learn to cluster user frustration patterns. The input is standardized data, and the output is the cluster label to which each user belongs.

[1484] Step 4:

[1485] The server uses a generative AI model to generate personalized training plans and meal menus for each cluster. Specifically, it generates prompts based on cluster labels and inputs them into the AI ​​model using the OpenAI API. The input consists of cluster labels and prompts, while the output is the generated training plan and meal menu.

[1486] Step 5:

[1487] The server uses an emotion engine to analyze the user's emotional state. Specifically, it analyzes feedback and diary data entered by the user to estimate their emotional state. The input is the user's feedback data, and the output is the estimated emotional state.

[1488] Step 6:

[1489] The server provides feedback and advice to maintain user motivation based on the analysis results of the emotion engine. Specifically, it generates appropriate feedback messages according to the estimated emotional state and sends them to the user's device. The input is the estimated emotional state, and the output is the feedback message.

[1490] Step 7:

[1491] Users follow personalized training plans and meal menus provided by the server and input feedback. Specifically, they use smartphones or tablets to record their training progress and meal details and send them to the server. The input is the user's execution data, and the output is updated diet history data.

[1492] In this way, it becomes possible to prevent users from repeating the same setbacks, support sustainable weight loss success, and encourage long-term use.

[1493] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1494] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1495] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[1496] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1497] [Third Embodiment]

[1498] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1499] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1500] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1501] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1502] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1503] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1504] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1505] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1506] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1507] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1508] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1509] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[1510] "Example of form 1"

[1511] The diet support system of the present invention combines VR technology and generative AI to provide users with personalized training and dietary guidance. Specifically, users wear a VR device at home and perform exercises according to a training program provided by the generative AI. The generative AI generates an optimal training menu based on information such as the user's body type, physical fitness, and health condition. Similarly, dietary guidance is also provided by the generative AI, taking into account the user's food preferences, health condition, and diet goals.

[1512] "Example of form 2"

[1513] The diet support system of this invention also sells special nutritional foods and training equipment. These products work in conjunction with the training and dietary guidance provided by the generating AI to more effectively support the user's diet. For example, based on the dietary guidance provided by the generating AI, it can recommend special nutritional foods and encourage their purchase. Similarly, it can recommend training equipment optimized for the training program provided by the generating AI and encourage its purchase.

[1514] "Example of form 3"

[1515] The diet support system of this invention analyzes the user's past failure data to support sustainable weight loss success. Specifically, a generating AI analyzes the user's past diet history and failure patterns, and based on this, provides personalized training and dietary guidance. This prevents the user from repeating the same failures and supports sustainable weight loss success.

[1516] The following describes the processing flow for each example of the form.

[1517] "Example of form 1"

[1518] Step 1: The user puts on the VR device at home.

[1519] Step 2: The generating AI creates an optimal training menu based on information such as the user's body type, physical fitness, and health condition.

[1520] Step 3: The user performs exercises according to the training program provided by the AI-generated program.

[1521] Step 4: The generating AI provides dietary guidance, taking into account the user's food preferences, health condition, and weight loss goals.

[1522] "Example of form 2"

[1523] Step 1: In conjunction with the training and dietary guidance provided by the AI, sell special nutritional supplements and training equipment.

[1524] Step 2: Based on the dietary guidance provided by the generating AI, recommend special nutritional supplements and encourage their purchase.

[1525] Step 3: The generated AI recommends training equipment optimized for the training program it provides and encourages its purchase.

[1526] "Example of form 3"

[1527] Step 1: The generating AI analyzes the user's past diet history and patterns of failure.

[1528] Step 2: The generating AI provides personalized training and dietary guidance based on the analysis results.

[1529] Step 3: This prevents users from repeating the same setbacks and supports sustainable weight loss success.

[1530] (Example 1)

[1531] Next, we will describe Embodiment 1 of Example 1. 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."

[1532] Traditional diet support systems offer uniform training and dietary guidance to all users, failing to adequately personalize the program based on individual user body type, fitness level, health status, dietary preferences, and weight loss goals. Furthermore, a lack of sustained support that takes into account users' past failures contributes to low success rates. Additionally, the lack of integrated sales of special nutritional supplements and training equipment means users have to purchase necessary items separately, creating an inconvenient situation.

[1533] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1534] In this invention, the server includes means for using VR technology, means for providing personalized training and dietary guidance using generative AI, means for generating an optimal training menu based on the user's body type information, physical fitness information, and health status, means for generating an optimal meal plan based on the user's dietary preferences, health status, and weight loss goals, and means for selling special nutritional foods and training equipment. This makes it possible to provide individually optimized training and dietary guidance to users and to provide continuous support that takes into account past failure data. In addition, by providing necessary nutritional foods and training equipment in one package, user convenience can be improved.

[1535] "VR technology" is a technology that uses virtual reality to provide users with an immersive experience.

[1536] "Generative AI" is a technology that uses artificial intelligence to analyze data and generate optimal training and meal plans for users.

[1537] "Personalized training" means providing a training program that is individually optimized based on the user's body type, fitness level, and health status.

[1538] "Personalized meal guidance" means providing a meal plan that is individually optimized based on the user's dietary preferences, health condition, and weight loss goals.

[1539] "Body type information" refers to the user's physical data, such as height, weight, and body fat percentage.

[1540] "Physical fitness information" refers to physical data such as the user's exercise experience and current exercise habits.

[1541] "Health status" refers to data about the user's health, such as allergies and pre-existing medical conditions.

[1542] "Dietary preferences" refer to data about a user's food preferences, such as their favorite and least favorite ingredients.

[1543] A "diet goal" is a target that the user wants to achieve, such as weight loss or muscle gain.

[1544] "Special nutritional supplements" are foods specifically designed to support dieting or training.

[1545] "Training equipment" refers to the devices and equipment that users use to perform training.

[1546] "Past failure data" refers to data about users' past experiences of failing at dieting or training.

[1547] "Sustained support" means providing long-term assistance to help users continue their diet and training.

[1548] Modes for carrying out the invention

[1549] This invention is a diet support system that combines VR technology and generative AI to provide users with personalized training and dietary guidance. Specific embodiments of this system are described below.

[1550] System Configuration

[1551] This system consists of a server, terminals (VR devices or smartphones), and users. The server is responsible for generating training menus and meal plans using a generative AI model and sending them to the terminals. The terminals send information entered by the user to the server, and the training menus and meal plans received from the server are displayed to the user.

[1552] Hardware and software to be used

[1553] The server is a high-performance computer with powerful computing capabilities and software installed to run generative AI models (e.g., OpenAI's GPT-4). The terminal is a VR device or smartphone that provides an interface for users to input information and view training menus and meal plans.

[1554] Data processing and calculation

[1555] The server receives data from the user, such as body shape information, fitness level, health status, dietary preferences, and weight loss goals. Based on this data, it uses an AI model to generate optimal training menus and meal plans. The generated menus and plans are sent to the user's device and displayed to them.

[1556] Specific example

[1557] Example 1: Generating a training menu

[1558] The user inputs body type information (height 170cm, weight 70kg, body fat percentage 20%) and fitness information (no prior exercise experience, current exercise habit is walking once a week). Based on this information, the server uses a generative AI model to generate a training menu suitable for the user. For example, the following prompt text is input to the generative AI model.

[1559] Prompt message:

[1560] "Please create a training program suitable for a 30-year-old male who is 170cm tall, weighs 70kg, has a body fat percentage of 20%, and has no prior exercise experience."

[1561] Example 2: Generating a meal plan

[1562] The user inputs their dietary preferences (favorite foods are chicken and broccoli, disliked foods are fish), health status (no allergies, no chronic illnesses), and diet goal (weight loss). Based on this information, the server uses a generative AI model to generate a meal plan suitable for the user. For example, the following prompt text is input to the generative AI model.

[1563] Prompt message:

[1564] "Please create a one-week meal plan suitable for a 30-year-old man who likes chicken and broccoli, dislikes fish, has no allergies, and is aiming to lose weight."

[1565] In this way, the server, terminal, and user work together to provide personalized diet support.

[1566] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1567] Step 1:

[1568] Users input their body information (height, weight, body fat percentage), physical fitness information (exercise experience, current exercise habits), and health status (allergies, pre-existing conditions) using a device (VR device or smartphone). This information is entered through the device's interface and sent to the server. The input data is stored in a database as individual user information.

[1569] Step 2:

[1570] The terminal sends the entered user information to the server. The server stores the received information in a database and generates prompts for input into the AI ​​model. For example, based on the user's body type and fitness information, it might generate a prompt such as, "Create a training menu suitable for a 30-year-old male who is 170cm tall, weighs 70kg, has a body fat percentage of 20%, and has no prior exercise experience."

[1571] Step 3:

[1572] The server inputs the generated prompt sentences into the AI ​​model, which then generates the optimal training menu for the user. The AI ​​model analyzes the data based on the input prompt sentences and outputs the training menu. The output training menu is saved on the server.

[1573] Step 4:

[1574] The server sends the generated training menu to the terminal. The terminal displays the received training menu to the user. The user performs the exercises according to the displayed training menu. The terminal tracks the user's movements in real time and provides feedback on correct form and movements.

[1575] Step 5:

[1576] Users use a terminal to input their dietary preferences (favorite and disliked foods), health status (allergies, chronic illnesses), and diet goals (weight loss, muscle gain). This information is entered through the terminal's interface and sent to the server. The input data is stored in a database as individual user information.

[1577] Step 6:

[1578] The server uses a generative AI model to generate meal plans based on stored meal information. For example, based on the user's dietary preferences and health status, it might generate a prompt message such as, "Create a 1-week meal plan suitable for a 30-year-old male who likes chicken and broccoli, dislikes fish, has no allergies, and is aiming to lose weight."

[1579] Step 7:

[1580] The server inputs the generated prompt text into the AI ​​model, which then generates the optimal meal plan for the user. The AI ​​model analyzes the data based on the input prompt text and outputs the meal plan. The output meal plan is saved on the server.

[1581] Step 8:

[1582] The server sends the generated meal plan to the device. The device displays the received meal plan to the user. The user eats according to the displayed meal plan. The device tracks whether the user is adhering to the meal plan and provides reminders and advice as needed.

[1583] In this way, the server, terminal, and user work together to provide personalized diet support.

[1584] (Application Example 1)

[1585] Next, we will describe Application Example 1 of Form Example 1. 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."

[1586] Traditional diet support systems often provide users with uniform training and dietary guidance, lacking personalized support that adequately considers each user's body type, physical fitness, health condition, food preferences, and weight loss goals. Furthermore, dietary guidance requires users to procure and cook their own food, which is time-consuming and makes sustainable weight loss difficult. Additionally, the lack of continuous support utilizing users' past failure data contributes to a low success rate in weight loss programs.

[1587] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1588] This invention includes a server that utilizes VR technology, provides personalized training and dietary guidance using generative AI, sells special nutritional foods and training equipment, and proposes an optimal meal menu based on information such as the user's body type, physical fitness, health condition, dietary preferences, and weight loss goals, and allows the user to order meals through a food delivery service. This enables the provision of individually optimized training and dietary guidance to users, and further reduces the effort involved through a food delivery service, thereby making sustainable weight loss success possible.

[1589] "VR technology" is a technology that provides users with virtual reality, allowing them to experience a virtual environment different from the real world through sight and sound.

[1590] "Generative AI" is a technology that uses artificial intelligence to analyze user data and generate individually optimized training and dietary guidance.

[1591] "Personalized training" means providing an optimal training program based on individual information such as the user's body type, physical fitness, and health condition.

[1592] "Dietary guidance" involves suggesting appropriate meal menus, taking into account the user's food preferences, health condition, and weight loss goals.

[1593] "Special nutritional foods" are foods specifically designed for weight loss or maintaining health, and their nutritional balance is taken into consideration.

[1594] "Training equipment" refers to devices used for exercise and fitness, supporting users in improving their physical fitness and building muscle strength.

[1595] A "food delivery service" is a service that delivers meals ordered by users to their homes, saving users time and effort.

[1596] "User's body type" refers to the shape and size of the user's body, and serves as a basis for creating diet and training plans.

[1597] "Physical fitness" refers to the user's physical endurance and muscle strength, and is an important factor when determining the training menu.

[1598] "Health status" refers to the user's current health condition and should be taken into consideration when providing training or dietary guidance.

[1599] "Dietary preferences" refer to the foods and eating styles that users like, and are important information when providing personalized dietary guidance.

[1600] A "diet goal" refers to the weight or body shape target that the user wishes to achieve, and serves as the basis for creating training and dietary guidance plans.

[1601] As an embodiment of this invention, the following system is constructed.

[1602] First, the server provides a means using VR technology. Specifically, users can wear a VR device to train in a virtual reality environment. This VR device provides a realistic training environment through sight and sound, enhancing the user's sense of immersion.

[1603] Next, the server has the means to provide personalized training and dietary guidance using generative AI. The generative AI generates optimal training and meal plans based on information such as the user's body type, physical fitness, health status, dietary preferences, and weight loss goals. This is done by using the OpenAI API to analyze the user's individual data and provide the optimal plan.

[1604] Furthermore, the server has a means of selling special nutritional supplements and training equipment. This allows users to easily purchase the nutritional supplements and training equipment they need.

[1605] Furthermore, the server suggests optimal meal menus based on information such as the user's body type, physical fitness, health status, dietary preferences, and weight loss goals, and provides a means for users to order meals through a food delivery service. This allows users to easily receive healthy meals at home.

[1606] The specific process involves first acquiring user information. This includes data entered by the user via smartphone or computer. Next, prompt messages are sent to the generation AI model to generate optimal training and meal plans. The following is an example of a prompt message:

[1607] User's body type: Standard

[1608] User's physical condition: Medium

[1609] User's health status: Good

[1610] User's dietary preferences: Japanese food

[1611] User's diet goal: Weight loss

[1612] Based on this information, please generate an optimal training program and meal plan.

[1613] The generated menu is displayed to the user through a VR device. The user can perform training according to this menu and also order meals using a food delivery service based on the meal menu.

[1614] This system allows users to receive personalized training and dietary guidance, and further reduces the hassle through a food delivery service, making sustainable weight loss success possible.

[1615] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1616] Step 1:

[1617] Users input individual information such as body type, physical fitness, health status, dietary preferences, and weight loss goals using their smartphones or computers. This information is sent to a server. The input data includes the user's height, weight, exercise habits, and dietary preferences. The server receives this data and stores it in a database.

[1618] Step 2:

[1619] The server generates prompt messages for the AI ​​model based on stored user information. These prompt messages include information such as the user's body type, physical fitness, health status, dietary preferences, and weight loss goals. An example of a specific prompt message is as follows:

[1620] User's body type: Standard

[1621] User's physical condition: Medium

[1622] User's health status: Good

[1623] User's dietary preferences: Japanese food

[1624] User's diet goal: Weight loss

[1625] Based on this information, please generate an optimal training program and meal plan.

[1626] Step 3:

[1627] The server sends prompt messages to the generative AI model, which generates optimal training and meal plans. The generative AI model analyzes the prompt messages and generates the most suitable training and meal plans for the user. The generated plans are returned to the server.

[1628] Step 4:

[1629] The server sends the generated training and meal plans to the VR device. The user puts on the VR device and trains in a virtual reality environment. The VR device provides a realistic training environment through sight and sound, enhancing the user's immersion.

[1630] Step 5:

[1631] The server orders meals through a food delivery service based on the generated meal menu. Users use their smartphones or computers to review the suggested meal menu and confirm their order. The server sends the order information to the food delivery service, and the meals are delivered to the user's home.

[1632] Step 6:

[1633] Users receive delivered meals and eat according to the suggested meal menu. This allows users to maintain a healthy diet while saving them time and effort.

[1634] Step 7:

[1635] The server collects users' training and dietary history data and uses it to inform future training and dietary guidance. This allows the system to track user progress and provide more effective weight loss support.

[1636] (Example 2)

[1637] Next, we will describe Example 2 of the morphological example. 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."

[1638] Traditional diet support systems have struggled to provide personalized dietary guidance and training programs for individual users, resulting in ineffective weight loss support. Furthermore, the lack of appropriate recommendations for special nutritional foods and training equipment has led to low user success rates in weight loss.

[1639] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for the user to input personal data using a terminal, means for the server to receive and store the input data, means for the server to analyze the data using a generated AI model and generate dietary guidance and training programs, means for the server to recommend special nutritional foods based on the generated dietary guidance, means for the server to recommend training equipment based on the generated training program, and means for the terminal to display the advice and recommended products received from the server to the user. This makes it possible to provide personalized dietary guidance and training programs to the user and to make appropriate recommendations for special nutritional foods and training equipment, thereby improving the user's success rate in dieting.

[1640] A "user" refers to an individual who uses the system to input personal data and receive dietary guidance or training programs.

[1641] A "device" refers to a device used by a user to input personal data and receive and display advice and recommended products from a server. Specifically, this includes smartphones and personal computers.

[1642] A "server" refers to a computer system that stores data received from users, analyzes that data using a generated AI model, and creates dietary guidance and training programs.

[1643] A "generative AI model" refers to an artificial intelligence model that receives a user's personal data and prompt text as input and generates appropriate dietary guidance and training programs.

[1644] "Dietary guidance" refers to providing advice on appropriate dietary content and nutritional intake methods based on the user's weight loss goals and health condition.

[1645] A "training program" refers to providing advice on appropriate exercise content and training methods based on the user's weight loss goals and exercise habits.

[1646] "Special nutritional foods" refer to foods recommended based on the user's dietary guidance that are effective for weight loss and maintaining health. Specifically, these include protein bars and low-calorie smoothies.

[1647] "Training equipment" refers to equipment recommended based on the user's training program to effectively perform exercise and training. Specifically, this includes items such as treadmills and dumbbell sets.

[1648] "Advice" refers to specific instructions and recommendations regarding dietary guidance and training programs that the generative AI model provides based on the user's personal data.

[1649] "Recommended products" refer to special nutritional foods and training equipment that the generating AI model recommends based on the user's dietary guidance and training program.

[1650] This invention is a diet support system in which a user inputs personal data using a terminal, and a server analyzes that data to provide personalized dietary guidance and training programs. Specific embodiments of this system are described below.

[1651] First, users access the system using devices such as smartphones or personal computers. Through a dedicated application or web form, users enter personal data such as height, weight, age, gender, exercise habits, and diet. For example, a user might enter "Height 160cm, weight 70kg, age 30, gender female, exercise twice a week, breakfast is bread and coffee, lunch is salad, dinner is fish and vegetables."

[1652] Next, the terminal sends the entered data to the server. The server stores the received data using a relational database management system (RDBMS) such as MySQL or PostgreSQL. For example, it might execute the following SQL query: "INSERT INTO user_data (height, weight, age, gender, exercise_habits, diet) VALUES (160, 70, 30, 'female', '2 times a week', 'bread and coffee for breakfast, salad for lunch, fish and vegetables for dinner');"

[1653] The server uses data analysis software such as Python or R to analyze stored user data. The server uses a generative AI model (e.g., GPT-4) to generate optimal dietary guidance and training programs for the user's weight loss goals. The generative AI model receives prompt statements as input and generates appropriate advice. For example, the following prompt statements are input to the generative AI model:

[1654] "I am a 30-year-old woman, weighing 70kg, 160cm tall, and I exercise twice a week. My weight loss goal is to lose 5kg in 3 months. Please provide me with the optimal dietary guidance and training program."

[1655] The AI ​​model generates dietary advice based on this prompt. For example, it might generate advice such as, "We recommend consuming high-protein foods for breakfast and plenty of vegetables for lunch and dinner. For snacks, nuts and yogurt are good choices." It might also make recommendations such as, "We recommend purchasing protein bars or low-calorie smoothies."

[1656] Similarly, the generative AI model generates training programs. For example, it might generate advice such as, "Do 30 minutes of aerobic exercise (e.g., jogging or cycling) three times a week, and add strength training twice a week." It might also make recommendations such as, "We recommend purchasing a treadmill or dumbbell set."

[1657] Finally, the server sends the generated advice and recommended products to the device. The device then displays the advice and recommended products to the user using the application's dashboard or notification features. For example, it might display specific advice and recommended products along with a message such as, "A meal plan and training program based on your weight loss goals has been generated. Details are below."

[1658] In this way, users can receive personalized dietary guidance and training programs, as well as appropriate recommendations for special nutritional foods and training equipment. This system makes it possible to improve users' success rates in dieting.

[1659] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1660] Step 1:

[1661] Users access the system using their devices and enter personal data. Specifically, they enter information such as height, weight, age, gender, exercise habits, and diet through a dedicated application or web form. For example, they might enter "Height 160cm, weight 70kg, age 30, gender female, exercise twice a week, breakfast is bread and coffee, lunch is salad, dinner is fish and vegetables." The entered data is saved on the device in JSON format or as form data.

[1662] Step 2:

[1663] The terminal sends the entered data to the server. Specifically, it sends user data to the server using an HTTP POST request. For example, it sends JSON data to an endpoint called " / submitUserData". The server stores the received data in a relational database management system (RDBMS) such as MySQL or PostgreSQL. For example, it executes an SQL query such as "INSERT INTO user_data (height, weight, age, gender, exercise_habits, diet) VALUES (160, 70, 30, 'female', '2 times a week', 'bread and coffee for breakfast, salad for lunch, fish and vegetables for dinner');".

[1664] Step 3:

[1665] The server analyzes the stored user data. Specifically, it uses data analysis software such as Python or R to calculate the user's BMI (Body Mass Index) and calorie consumption. For example, it uses the formula "BMI = weight / (height / 100)^2" to calculate BMI. The analysis results are used to generate prompt statements for input into the generative AI model.

[1666] Step 4:

[1667] The server uses a generative AI model (e.g., GPT-4) to generate optimal dietary guidance and training programs for the user's weight loss goals. Specifically, it inputs prompt sentences into the generative AI model and generates appropriate advice. For example, it inputs the prompt sentence, "I am a 30-year-old woman, weighing 70kg, 160cm tall, and I exercise twice a week. My weight loss goal is to lose 5kg in 3 months. Please provide optimal dietary guidance and training programs." The generative AI model then generates dietary guidance and training programs based on this prompt sentence.

[1668] Step 5:

[1669] The server recommends specific nutritional foods based on the generated dietary guidance. Specifically, it selects nutritional foods suitable for the user based on the dietary guidance provided by the generating AI model. For example, along with advice such as, "We recommend consuming high-protein foods for breakfast and plenty of vegetables for lunch and dinner. For snacks, nuts and yogurt would be good choices," it might also recommend, "We recommend purchasing protein bars or low-calorie smoothies."

[1670] Step 6:

[1671] The server recommends training equipment based on the generated training program. Specifically, it selects training equipment suitable for the user based on the training program provided by the generating AI model. For example, along with advice such as, "Do 30 minutes of aerobic exercise (e.g., jogging or cycling) three times a week, and add strength training twice a week," it might recommend, "We recommend purchasing a treadmill or dumbbell set."

[1672] Step 7:

[1673] The server sends the generated advice and recommended products to the device. Specifically, it uses an HTTP response to send the generated advice and recommended products to the device. The device displays the received information to the user using the application's dashboard or notification function. For example, it might display specific advice and recommended products along with a message such as, "A meal plan and training program based on your diet goals has been generated. Details are as follows."

[1674] (Application Example 2)

[1675] Next, we will describe application example 2 of form example 2. 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."

[1676] Traditional diet support systems have difficulty providing individualized dietary guidance and training programs, and have also struggled to effectively recommend special nutritional foods and training equipment. Furthermore, they lack support for sustained diet success that takes into account users' past failures, resulting in a low long-term success rate for dieting.

[1677] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1678] This invention includes a server that includes means for collecting user data, means for analyzing the data using a generating AI to generate optimal dietary guidance and training programs, and means for recommending special nutritional foods and training equipment based on the programs provided by the generating AI and encouraging their purchase. This enables the provision of an optimal diet plan for each individual user and the effective recommendation of special nutritional foods and training equipment. Furthermore, by analyzing the user's past failure data, it is possible to support sustainable weight loss success.

[1679] "User data" refers to information such as the user's weight loss goals, current physical condition, eating habits, and exercise habits.

[1680] "Generative AI" refers to a system that uses artificial intelligence technology to analyze data and generate optimal dietary guidance and training programs.

[1681] "Dietary guidance" refers to suggesting appropriate meal content and timing based on the user's health condition and weight loss goals.

[1682] A "training program" refers to suggesting appropriate exercise content and frequency based on the user's physical fitness level and weight loss goals.

[1683] "Nutritional foods" refer to foods specifically designed for weight loss or maintaining health.

[1684] "Training equipment" refers to tools and devices used to effectively perform exercise or training.

[1685] "Recommendation" refers to the process where the generating AI suggests specific nutritional foods or training equipment to the user based on its analysis results.

[1686] "Encouraging purchase" refers to making it easy for users to buy recommended nutritional supplements or training equipment.

[1687] "Past failure data" refers to information about users' past experiences of failing at dieting and the reasons for those failures.

[1688] "Sustainable weight loss success" refers to users continuing their diet over a long period of time and achieving their goals.

[1689] The following system configuration and processing procedure will be described as embodiments for carrying out this invention.

[1690] System Configuration

[1691] 1. Collection of user data

[1692] Hardware: Smartphone

[1693] Software: Application user interface

[1694] Data: User's diet goals, current physical condition, eating habits, exercise habits

[1695] 2. Data analysis using generative AI

[1696] Hardware: Cloud Servers

[1697] Software: Generative AI models (e.g., GPT-4)

[1698] Data Processing: Analyze user data to generate optimal dietary guidance and training programs.

[1699] 3. Selection of Recommended Products

[1700] Hardware: Cloud Servers

[1701] Software: Product database, recommendation engine

[1702] Data processing: Based on programs provided by the generation AI, special nutritional supplements and training equipment are selected.

[1703] 4. Suggestions for users

[1704] Hardware: Smartphone

[1705] Software: Application user interface

[1706] Data display: Recommended dietary guidance, training programs, and related product information.

[1707] 5. Purchase Process

[1708] Hardware: Smartphone

[1709] Software: Electronic payment system

[1710] Data processing: Processing and verification of purchase procedures

[1711] Explanation of the process

[1712] 1. Collection of user data:

[1713] Users input information such as their diet goals, current physical condition, eating habits, and exercise habits through a smartphone application. This data is sent to a cloud server and stored for analysis by generating AI.

[1714] 2. Data analysis using generative AI:

[1715] The AI ​​model on the cloud server (e.g., GPT-4) analyzes the collected user data and generates personalized dietary guidance and training programs for each user. This analysis also takes into account the user's past failures.

[1716] 3. Selection of recommended products:

[1717] Based on a program provided by the AI, a recommendation engine on a cloud server selects specific nutritional supplements and training equipment. This ensures that the user receives recommendations for the most suitable products.

[1718] 4. Suggestions for users:

[1719] Through a smartphone application, users will be shown generated dietary guidance, training programs, and recommended nutritional foods and training equipment.

[1720] 5. Purchase Process:

[1721] Users can easily purchase recommended nutritional supplements and training equipment through the application. Purchases are processed using an electronic payment system.

[1722] Specific example

[1723] The user opens the application and enters the following information:

[1724] Diet goal: Lose 5kg

[1725] Current health condition: Healthy

[1726] Eating habits: 3 meals a day, with snacks.

[1727] Exercise habits: Jogging twice a week

[1728] The generating AI analyzes this data and provides the following dietary guidance and training programs:

[1729] Dietary guidance: High-protein, low-calorie diet, replace snacks with nuts.

[1730] Training program: Add strength training three times a week.

[1731] Furthermore, the following special nutritional supplements and training equipment are recommended:

[1732] Nutritional foods: High-protein bars, protein shakes

[1733] Training equipment: Dumbbell set, yoga mat

[1734] Example of a prompt

[1735] "Based on the user's weight loss goals, current physical condition, eating habits, and exercise habits, generate an optimal diet plan and training program, and recommend the most suitable nutritional supplements and training equipment."

[1736] In this way, users can easily find and purchase the diet plan and related products that are best suited to them.

[1737] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1738] Step 1:

[1739] The user opens a smartphone application and enters information such as their weight loss goals, current physical condition, eating habits, and exercise habits.

[1740] Input: Diet goal, current physical condition, eating habits, exercise habits

[1741] Output: User data

[1742] Specific action: The user enters the required information into the application's input form and presses the submit button.

[1743] Step 2:

[1744] The device sends the user data it collects to a cloud server.

[1745] Input: User data

[1746] Output: User data stored on the cloud server

[1747] Specific operation: The application calls an API to send user data to the cloud server.

[1748] Step 3:

[1749] The server uses a generated AI model (e.g., GPT-4) to analyze the collected user data and generate optimal dietary guidance and training programs.

[1750] Input: User data

[1751] Output: Dietary guidance, training program

[1752] Specific operation: A generation AI model on a cloud server analyzes user data and generates optimal dietary guidance and training programs based on prompt messages.

[1753] Step 4:

[1754] The server selects special nutritional supplements and training equipment based on a program provided by the AI.

[1755] Input: Dietary guidance, training program

[1756] Output: Recommended nutritional foods, training equipment

[1757] Specific operation: A recommendation engine on a cloud server selects the most suitable nutritional foods and training equipment from a product database based on dietary guidance and training programs.

[1758] Step 5:

[1759] The server suggests recommended dietary guidance, training programs, and related products to the user.

[1760] Input: Recommended nutritional supplements, training equipment

[1761] Output: Suggestions for the user

[1762] Specific operation: The cloud server generates suggestions, which are then sent to a smartphone application and displayed to the user.

[1763] Step 6:

[1764] Users purchase recommended nutritional foods and training equipment through the application.

[1765] Input: User's purchase intention

[1766] Output: Purchase confirmation, payment complete

[1767] Specific action: The user presses the purchase button and completes the payment through the electronic payment system.

[1768] In this way, users can easily find and purchase the diet plan and related products that are best suited to them.

[1769] (Example 3)

[1770] Next, we will describe Embodiment 3 of Embodiment Example 3. 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."

[1771] Traditional diet support systems failed to fully utilize users' past failure data, making it difficult to support sustainable weight loss success. Furthermore, the lack of personalized training and dietary guidance increased the likelihood of users repeating the same mistakes. Additionally, the insufficient mechanisms for effectively collecting and analyzing user feedback and updating plans resulted in the problem of insufficient sustained weight loss effectiveness.

[1772] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1773] In this invention, the server includes means for collecting user data, means for storing and managing the collected data, means for using a generative AI model to analyze the stored data, means for generating personalized training and dietary guidance based on the analysis results, means for delivering the generated plans to users, means for collecting user feedback, and means for analyzing the collected feedback and updating the plans. This makes it possible to utilize the user's past failure data to support sustainable weight loss success.

[1774] "User data" refers to information entered by the user, such as their past dieting history, patterns of failure, current weight, target weight, dietary habits, and exercise routine.

[1775] "Means of collection" refers to a system in which users input data using smartphone apps or web forms and send it to a server.

[1776] "Means of storage and management" refers to a system that stores data received by a server in a database and manages it appropriately.

[1777] A "generative AI model" is an artificial intelligence model that analyzes collected data to generate personalized training and dietary guidance.

[1778] The "means of analysis" refer to a system that uses a generative AI model to analyze stored data and identify the user's past patterns of failure and success.

[1779] "Personalized training and dietary guidance" refers to training plans and dietary advice that are individually customized based on analysis results.

[1780] The "means of delivery" refer to a system that sends the generated training plan and dietary guidance from the server to the terminal and notifies the user.

[1781] "Methods for collecting feedback" refer to a system where users input their daily progress and new data into their devices and send it to a server.

[1782] The "means of analyzing feedback and updating plans" refer to a system that inputs the collected feedback back into a regenerating AI model and updates training plans and dietary guidance based on the analysis results.

[1783] This invention is a system that analyzes users' past failure data to support sustainable weight loss success. A specific embodiment of this system is described below.

[1784] Collection of user data

[1785] Users enter information such as their past dieting history, patterns of failure, current weight, target weight, diet, and exercise habits using a smartphone app or web form. For example, a user might enter, "In the past, I often ate sweets late at night."

[1786] Data storage and management

[1787] The terminal sends the data entered by the user to the server. The server stores the received data in a database (e.g., MySQL or PostgreSQL) and manages it appropriately.

[1788] Data Analysis

[1789] The server inputs the stored data into a generating AI model (e.g., OpenAI's GPT-4) and performs analysis. Specifically, it identifies the user's past failure and success patterns and gains insights based on the data. For example, it might conclude that "this user tends to eat sweets late at night."

[1790] Generating personalized plans

[1791] The server uses a generative AI model to generate optimal training plans and dietary guidance for the user. Specifically, it considers the user's past data to provide individually customized advice. For example, it might generate specific advice such as, "Prepare low-calorie snacks to suppress appetite late at night."

[1792] Plan distribution

[1793] The server sends the generated training plan and dietary guidance to the device. The device then displays the received plan to the user. Specifically, it provides information using the notification function and dashboard of a smartphone app. For example, it might notify the user, "Prepare a low-calorie snack to curb your appetite late at night."

[1794] Collecting user feedback

[1795] Users input their daily progress and new data (such as weight changes and dietary information) into their device. Specifically, they enter records of their daily meals and exercise into the app. For example, they might enter, "Today I ate a low-calorie snack late at night."

[1796] Feedback analysis and plan updates

[1797] The terminal sends the new data entered by the user to the server. The server inputs the received data back into the generating AI model and performs analysis. Based on the analysis results, it updates the training plan and dietary guidance and sends it back to the terminal. For example, if the analysis results indicate that "low-calorie snacks are effective," the training plan and dietary guidance may be updated.

[1798] Example of a prompt

[1799] "Based on the user's past dieting history and failure patterns, please generate an optimal training plan and dietary guidance. The user tends to eat sweets late at night. Please take this failure pattern into consideration and provide specific advice."

[1800] In this way, the diet support system utilizes the user's past data to support sustainable weight loss success. The flow of the specific processing in Example 3 will be explained using Figure 15.

[1801] Step 1:

[1802] Users enter information such as their past dieting history, patterns of failure, current weight, target weight, diet, and exercise habits using a smartphone app or web form.

[1803] Input: Past dieting history, patterns of failure, current weight, target weight, diet, exercise habits

[1804] Output: Input user data

[1805] Step 2:

[1806] The terminal sends the data entered by the user to the server.

[1807] Input: User data entered by the user

[1808] Output: User data sent to the server

[1809] Step 3:

[1810] The server stores the received data in a database and manages it appropriately. Specifically, it uses a database management system such as MySQL or PostgreSQL.

[1811] Input: User data sent to the server

[1812] Output: User data stored in the database

[1813] Step 4:

[1814] The server inputs the stored data into a generating AI model (e.g., OpenAI's GPT-4) and performs analysis. Specifically, it identifies the user's past failure and success patterns and gains insights based on the data.

[1815] Input: User data stored in the database

[1816] Output: Analysis results (Example: "This user tends to eat sweets late at night")

[1817] Step 5:

[1818] The server uses a generative AI model to generate optimal training plans and dietary guidance for the user. Specifically, it takes the user's past data into consideration to provide individually customized advice.

[1819] Input: Analysis results

[1820] Output: Personalized training plans and dietary guidance (e.g., "Prepare low-calorie snacks to curb your appetite late at night").

[1821] Step 6:

[1822] The server sends the generated training plan and dietary guidance to the device. The device then displays the received plan to the user. Specifically, it provides information using the notification function and dashboard of a smartphone app.

[1823] Input: Personalized training plans and dietary guidance

[1824] Output: Training plans and dietary guidance displayed to the user (e.g., "Prepare low-calorie snacks to curb your appetite late at night").

[1825] Step 7:

[1826] Users input their daily progress and new data (such as weight changes and dietary information) into their device. Specifically, they enter records of their daily meals and exercise into the app.

[1827] Input: Daily progress and new data (e.g., "I ate a low-calorie snack late tonight")

[1828] Output: New data entered

[1829] Step 8:

[1830] The terminal sends the newly entered data to the server. The server inputs the received data back into the AI ​​model and performs analysis. Based on the analysis results, it updates the training plan and dietary guidance and sends them back to the terminal.

[1831] Input: New data

[1832] Output: Updated training plans and dietary advice (e.g., "Low-calorie snacks are effective")

[1833] In this way, the diet support system utilizes the user's past data to support sustainable weight loss success.

[1834] (Application Example 3)

[1835] Next, we will describe application example 3 of form example 3. 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."

[1836] Traditional diet support systems often failed to provide personalized guidance that adequately considered users' past dieting history and patterns of failure, leading to repeated setbacks. Furthermore, the lack of specialized nutritional supplements and training equipment made it difficult for users to access necessary resources in one place. Additionally, the absence of feat...

Claims

1. A means for collecting data indicating the user's past diet records, including changes in the user's weight, exercise content, and dietary content; A means for analyzing the data using a generative AI model and identifying failure patterns that indicate situations in which the user is likely to give up, A means for generating personalized training plans and dietary guidance information based on the identified failure patterns using the aforementioned generation AI model, and proposing them to the user, so as to prevent the same failures from being repeated. After proposing the training plan and dietary guidance information, the means includes an emotion engine, which is a technology that recognizes the user's emotional state based on information including the user's facial expressions, to acquire the user's emotional state and to provide the acquired user's emotional state to the generative AI model. Includes, The means for proposing the training plan and dietary guidance information to the user involves using the generative AI model to generate modified training plan and dietary guidance information based on the user's emotional state in order to maintain the user's motivation, and proposing the adjusted training plan and dietary guidance information to the user. system.

2. A means for recommending training equipment and nutritional foods based on the generated training plan and dietary guidance information. This also includes, The system according to claim 1.

3. The means for proposing the training plan and dietary guidance information to the user is to display the training plan and dietary guidance information on a virtual reality device worn by the user. The system according to claim 1.

Images