System

Abstract

A system is provided.SOLUTION: A system comprising: a data collecting unit; a preprocessing unit; a generating unit; an information providing unit; a feedback collecting unit; and a learning unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Athletes face challenges in improving their performance and maintaining their health due to the difficulty of managing their diet and inadequate nutritional intake. This problem results in an imbalance in diet and nutrition, which can ultimately shorten the athlete's career. Furthermore, developing an optimized meal plan for each individual athlete is a complex and time-consuming task, and is often not implemented. Given this background, there is a need to provide optimal meals based on each athlete's individual data, maximize performance, and maintain health. [Means for solving the problem]

[0005] The present invention provides a system including a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, and a learning means. Specifically, the data collection means collects an athlete's physical data, training information, and lifestyle data, and the preprocessing means converts the data into a unified format and cleanses it. The generation means generates an individualized nutrition plan using a generative AI model that has learned from the latest medical data. The information provision means presents the generated nutrition plan to the user, the feedback collection means collects feedback from the user, and the learning means updates the generative AI model based on this feedback, thereby continuously improving the accuracy of the model. In this way, athletes are provided with optimal daily nutrition plans, enabling them to improve their performance and maintain their health.

[0006] "Data collection means" refers to a device, system, or method for collecting an athlete's physical data, training information, and lifestyle data.

[0007] A "pre-processing means" is a device, system, or method for converting collected data into a unified format and performing any necessary data cleansing.

[0008] "Generator" means a device, system, or method for generating a personalized nutrition plan using a generative AI model that learns from current medical data.

[0009] "Information providing means" refers to a device, system or method for presenting the nutrition plan generated by the generating means to the athlete.

[0010] A "feedback collection means" is a device, system, or method for collecting feedback from athletes.

[0011] A "learning means" is a device, system, or method for updating a generative AI model based on collected feedback data to improve the accuracy of the model.

[0012] A "generative AI model" is an artificial intelligence model that is trained based on the latest medical data and used to generate personalized nutrition plans.

[0013] A "nutrition plan" is a plan that includes meal recipes and nutritional supplement suggestions that are optimized for each individual athlete based on the athlete's physical data, training information, and lifestyle data. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention relates to a system for generating and providing personalized nutrition plans for athletes, the system including a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, and a learning means.

[0036] When an athlete begins using the system, the user (athlete) enters individual physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details) through the device. The device also connects to activity monitors and fitness trackers, automatically collecting daily exercise data (e.g., number of steps, heart rate) from these devices.

[0037] The collected data is sent from the terminal to a server, which then preprocesses the data. The preprocessing method converts the collected data into a unified format (e.g., JSON) and performs data cleansing, such as filling in missing data and correcting outliers.

[0038] The server then uses a generating means to input the preprocessed data into a generative AI model. The generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The nutrition plan generated by the generative AI model is then sent to the terminal via an information providing means and presented to the user. The presented nutrition plan includes breakfast, lunch, and dinner menus, as well as recommended nutritional supplements.

[0039] The user inputs feedback on the provided nutrition plan into the device. For example, information such as satisfaction with the diet or changes in physical condition is provided as feedback. This feedback is sent from the device to the server and collected by the feedback collection means. The server then uses the collected feedback as training data for the generated AI model through the learning means, and updates the model to continuously improve the accuracy of the model.

[0040] Specific examples

[0041] For example, suppose a user (athlete) inputs data that indicates he or she is 175 cm tall, weighs 70 kg, is 28 years old, and runs three times a week. Data collected from an activity tracker also indicates that he or she takes 10,000 steps per day and has an average heart rate of 120 bpm. This data is sent from the device to a server, where it is preprocessed and then input into a generative AI model. Based on this data, the generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake as a nutritional supplement. The generated nutrition plan is presented to the user via the device, and the user can enter feedback on the plan, which will be reflected in the next plan generation.

[0042] This allows athletes to receive individually optimized nutritional plans every day, enabling them to efficiently improve their performance and maintain their health.

[0043] The processing flow will be explained below.

[0044] Step 1:

[0045] User: Enters individual physical data (height, weight, age, etc.), training information (type of exercise, time, intensity, etc.), and lifestyle habits (sleep time, diet, etc.) into the application.

[0046] Step 2:

[0047] Device: Works with activity monitors and fitness trackers to automatically collect daily exercise data (number of steps, heart rate, etc.).

[0048] Step 3:

[0049] Terminal: Sends collected data to the server.

[0050] Step 4:

[0051] Server: Converts the received data into a unified format (e.g., JSON).

[0052] Step 5:

[0053] Server: Performs data cleansing, such as checking for outliers and filling in missing data.

[0054] Step 6:

[0055] Server: Inputs preprocessed data into a generative AI model to analyze various data points.

[0056] Step 7:

[0057] Server: A generative AI model generates a personalized nutrition plan based on the latest medical data.

[0058] Step 8:

[0059] Server: Sends the generated nutrition plan to the device.

[0060] Step 9:

[0061] On the device: Displays a nutrition plan (breakfast, lunch, and dinner menus and nutritional supplements) to the user.

[0062] Step 10:

[0063] User: Enter feedback on the nutrition plan provided.

[0064] Step 11:

[0065] Terminal: Sends the entered feedback to the server.

[0066] Step 12:

[0067] Server: Collects feedback and uses it to update the training data for the generative AI model.

[0068] Step 13:

[0069] Server: Use the updated model to generate the next nutrition plan.

[0070] This provides users with an optimal daily nutrition plan, helping them improve performance and maintain good health.

[0071] Example 1

[0072] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0073] Conventional nutrition plan providing systems have difficulty in providing personalized nutrition plans to individual users and in continuously improving plans based on user feedback. As a result, they have not been effective enough in maintaining users' health and improving their performance.

[0074] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0075] In this invention, the server includes a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, a learning means, a means for sending the nutrition plan generated by the generation means to a user terminal, and a means for updating the generative AI model based on the feedback collected by the feedback collection means, thereby providing a personalized nutrition plan to each user and continuously improving the model based on user feedback.

[0076] The "data collection means" is a means for collecting physical data, training information, lifestyle habit data from a user, and exercise data from an activity monitor or fitness tracker.

[0077] "Preprocessing means" refers to means for converting collected data into a unified format and performing data cleansing such as supplementing missing data and correcting outliers.

[0078] The "generative means" is a means for generating an individual nutrition plan based on preprocessed data using a generative AI model that has learned the latest medical data.

[0079] The "information providing means" is a means for transmitting the generated nutrition plan to the user terminal and presenting it to the user.

[0080] The "feedback collection means" is a means for collecting feedback from users (e.g., satisfaction with meals or changes in physical condition).

[0081] A "learning method" is a method for continuously updating the generative AI model based on collected feedback to improve the accuracy of the plan.

[0082] A "server" is a computer system for executing the data collection means, pre-processing means, generation means, information provision means, feedback collection means and learning means.

[0083] "User terminal" means a device used by a user to enter information, review generated nutrition plans, and enter feedback.

[0084] A "generative AI model" is a machine learning model that learns from collected data and the latest medical data to generate an individualized nutrition plan.

[0085] The present invention is a system for generating and providing personalized nutrition plans for athletes, the system including a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, and a learning means.

[0086] First, the user (athlete) uses a device to input physical data, training information, and lifestyle habits, such as height, weight, age, type of exercise, exercise time, exercise intensity, sleep time, and dietary details. The device then connects to an activity monitor or fitness tracker to automatically collect daily exercise data (e.g., number of steps and heart rate). This data is then sent to a server using a secure protocol (e.g., HTTPS).

[0087] Next, the server converts the collected data into a unified format (e.g., JSON) using a preprocessing means and performs data cleansing, such as filling in missing data and correcting outliers. The preprocessed data is input into a generative AI model using a generation means. This generative AI model is trained using deep learning algorithms and generates a personalized nutrition plan based on the latest medical data and collected user data.

[0088] The generated nutrition plan is sent from the server to the terminal via the information providing means. The terminal displays the generated nutrition plan to the user, and the user uses this plan as a reference to prepare daily meals. The nutrition plan specifically describes breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0089] The user inputs feedback about the provided nutrition plan into the device. This feedback includes satisfaction with the meal and changes in physical condition. The device sends this feedback to the server, where it is collected by the feedback collection means. The server has a learning means that continuously updates the generative AI model based on the collected feedback and improves the accuracy of the plan.

[0090] Specific examples

[0091] For example, if a user (athlete) enters the following data:

[0092] Height: 175cm

[0093] Weight: 70kg

[0094] Age: 28

[0095] Exercise: Running three times a week

[0096] Also, suppose the following data is collected from an activity tracker:

[0097] Daily steps: 10,000 steps

[0098] Average heart rate: 120 bpm

[0099] This data is sent from the device to a server, where it is pre-processed and then fed into a generative AI model, which generates a nutrition plan like this:

[0100] Breakfast: Oatmeal and blueberries

[0101] Lunch: Chicken salad

[0102] Dinner: Grilled salmon and roasted vegetables

[0103] Nutritional Supplement: Protein Shake

[0104] The generated nutrition plan is presented to the user via the terminal, and the user can input feedback about the plan (e.g., "The salad for lunch wasn't filling enough"), which will be reflected in the next plan generation.

[0105] Prompt Sentence Examples

[0106] "Generate the optimal nutrition plan for a 175cm, 70kg, 28-year-old athlete who runs three times a week, takes 10,000 steps per day, and has an average heart rate of 120 bpm. What meals should I have for breakfast, lunch, and dinner, along with recommended nutritional supplements?"

[0107] This allows the system to provide users with individually optimized nutritional plans on a daily basis, enabling them to efficiently improve performance and maintain health.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] The user uses the device to input their physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details). The input data is saved on the device. This data becomes input data.

[0111] Step 2:

[0112] The device connects to activity monitors and fitness trackers via Bluetooth or Wi-Fi to automatically collect daily exercise data (e.g., steps taken, heart rate). The collected data is stored on the device. This data is also added to the input data mentioned above.

[0113] Step 3:

[0114] The device sends all collected data to the server using a secure protocol (e.g., HTTPS). Input data is transferred to the server and stored in a server-side database.

[0115] Step 4:

[0116] The server uses preprocessing means to convert the collected data into a unified format (e.g., JSON). Specifically, it parses the data, unifies the data structure, and resolves inconsistencies. Data that has undergone preprocessing is called preprocessed data.

[0117] Step 5:

[0118] The server then performs data cleansing on the preprocessed data. It adds missing data items and detects and corrects outliers. For example, if abnormally high heart rate data is included, it is corrected by referencing past data. This process generates cleansed data.

[0119] Step 6:

[0120] The server inputs the cleansed data into a generative AI model using a generation means, for example, by inputting the data into a generative AI model that uses a deep learning algorithm, and calculations begin.

[0121] Step 7:

[0122] The generative AI model generates a personalized nutrition plan based on the latest medical data and collected user data. The model calculates the nutrient balance of each meal and determines the optimal menu. The calculation results are output as nutrition plan data.

[0123] Step 8:

[0124] The server sends the generated nutrition plan data to the device via an information providing means. Specifically, the information is delivered to the device via push notifications or in-app notifications. The user can then check the nutrition plan on their device.

[0125] Step 9:

[0126] The user inputs feedback about the provided nutrition plan into the terminal. The feedback includes satisfaction with the meal, changes in physical condition, etc. This feedback data is stored in the terminal.

[0127] Step 10:

[0128] The terminal transmits the feedback data to the server using a secure protocol, and the transmitted feedback data is stored in a database on the server side.

[0129] Step 11:

[0130] The server continuously updates the generative AI model based on the collected feedback data. It uses learning methods to adjust the model parameters and improve the accuracy of future nutrition plans. This update generates an improved generative AI model.

[0131] By repeating the above steps, the system can continuously provide the user with an optimal nutrition plan.

[0132] (Application example 1)

[0133] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0134] Conventional nutrition plan delivery systems lack real-time feedback and individual personalization, making it difficult to efficiently provide nutrition plans tailored to the individual needs of athletes. In particular, they are unable to provide immediate and appropriate information on daily food selection, making it difficult to optimize athletes' performance and health.

[0135] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0136] In this invention, the server includes a data collection means, a pre-processing means, a generation means, and a means for displaying an individual nutrition plan in real time through a device such as smart glasses, thereby enabling athletes to receive the nutritional information they need for their daily food selection in real time and realizing the provision of an individually optimized nutrition plan.

[0137] "Data collection means" refers to equipment and software used to collect athletes' physical data, training information, and lifestyle data.

[0138] "Preprocessing means" refers to the process of converting collected data into a unified format and performing data cleansing, such as filling in missing data and correcting outliers.

[0139] "Generation" refers to the process of generating an individual nutrition plan based on collected and pre-processed data using a generative AI model trained on the latest medical data.

[0140] "Information delivery means" refers to the equipment or software used to provide the generated nutrition plan to the athlete.

[0141] "Feedback collection means" refers to equipment or software for collecting feedback information from athletes (e.g., satisfaction with meals, changes in physical condition, etc.).

[0142] "Learning" is the process of continuously updating the generative AI model using collected feedback information to improve its accuracy.

[0143] "Means for displaying individual nutrition plans in real time through devices such as smart glasses" refers to technology that uses smart glasses worn by athletes to display individually optimized nutrition plans and ingredient information in real time while they are shopping.

[0144] This invention is a system for providing personalized nutrition plans to athletes in real time. The system includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and a means for displaying the individual nutrition plan in real time through a device such as smart glasses. Each of these means will be described in detail below.

[0145] Data collection methods

[0146] The data collection method mainly involves collecting athletes' physical data (e.g., height, weight, age), training information (e.g., type, time, and intensity of exercise), and lifestyle habits (e.g., sleep duration, dietary content). This data may be entered directly by the user into the device, or may be collected automatically in conjunction with an activity monitor or fitness tracker. This allows for accurate and comprehensive data.

[0147] Pretreatment means

[0148] The collected data is first converted into a unified format (e.g., JSON) through pre-processing measures, followed by data cleansing, such as imputing missing data and correcting outliers, laying the foundation for the generative AI model to generate an accurate nutrition plan.

[0149] generation means

[0150] Once pre-processed, the data is passed to the generator, which uses a generative AI model trained on the latest medical data to generate a personalized nutrition plan. This plan includes breakfast, lunch, and dinner menus, as well as recommended nutritional supplements. The nutrition plans generated at this stage are optimized for the athlete's specific needs and goals.

[0151] Information provision means

[0152] The generated nutrition plan is sent to a device such as smart glasses via the information providing means. The user can view the nutrition plan and ingredient information displayed in real time on the smart glasses while shopping, making it easy to manage nutrition in everyday life.

[0153] Feedback collection methods

[0154] The user follows the provided nutrition plan and inputs feedback such as the results, satisfaction, changes in physical condition, etc. into the terminal. This feedback data is then sent to the server.

[0155] Learning tools

[0156] The collected feedback data is fed into the generative AI model by a learning method and is continuously used as training data for the model, which improves the accuracy of the generative AI model and enables the provision of more appropriate nutrition plans.

[0157] Specific examples

[0158] For example, imagine an athlete is shopping at a supermarket. As they approach the dairy section, the smart glasses display will show, "This week's recommended foods: Greek yogurt, low-fat milk," and then suggest the next step in their nutrition plan: "Refill your protein shake." This way, the athlete has real-time information they need at that moment.

[0159] Prompt Sentence Examples

[0160] "The user is an athlete with the following characteristics: height 175cm, weight 70kg, age 28, exercise frequency 3 times a week, steps taken 10,000 times, and average heart rate 120 bpm. Generate optimal breakfast, lunch, dinner, and nutritional supplement recommendations for this user."

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] The user uses the device to input their physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details), or the device connects to an activity monitor or fitness tracker to automatically collect exercise data (e.g., number of steps, heart rate). The input data is converted into a unified format such as JSON.

[0164] Input: Physical data, training information, lifestyle data

[0165] Output: Data converted into a unified format (e.g. JSON)

[0166] Specific operation: Obtains data from the terminal's input form or linked devices and converts it into JSON format.

[0167] Step 2:

[0168] The server uses preprocessing means to cleanse the collected data, impute missing data, and correct outliers, resulting in preprocessed data.

[0169] Input: Data converted into a unified format

[0170] Output: Cleansed preprocessed data

[0171] Specific operations: Reshaping data, estimating missing data, correcting outliers, etc.

[0172] Step 3:

[0173] The server uses a generating means to input the pre-processed data into a generative AI model to generate a personalized nutrition plan, which includes breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0174] Input: Preprocessed data

[0175] Output: Personalized nutrition plan

[0176] Specific operation: Data is input into the generative AI model, and calculations are performed to generate a nutrition plan.

[0177] Step 4:

[0178] The generated nutrition plan is sent to the smart glasses via the information providing means, and the user can check the nutrition plan and ingredient information displayed in real time on the smart glasses display.

[0179] Enter: personalized nutrition plan

[0180] Output: Nutrition plan displayed on smart glasses

[0181] What it does: Sends the nutrition plan to the smart glasses and displays it on the screen.

[0182] Step 5:

[0183] The user carries out the nutrition plan and inputs feedback such as the results, satisfaction, changes in physical condition, etc. into the terminal. This feedback data is sent to the server.

[0184] Input: Feedback on nutrition plan

[0185] Output: Feedback data sent to the server

[0186] Specific operation: Fill out the feedback form from the terminal and send it to the server.

[0187] Step 6:

[0188] The server uses the feedback collection means to incorporate the collected feedback into the generative AI model using the learning means, updating the model and improving its accuracy.

[0189] Input: Feedback data

[0190] Output: An updated generative AI model

[0191] Specific operation: Analyze the feedback data, incorporate it as training data for the generative AI model, and retrain the model.

[0192] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0193] The present invention relates to a system for generating and providing personalized nutrition plans for athletes, which includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and an emotion engine that recognizes the emotions of a user.

[0194] System Overview

[0195] First, when a user (athlete) starts using the system, they input their individual physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details) through their device. The device also connects to activity monitors and fitness trackers, automatically collecting daily exercise data (e.g., number of steps, heart rate) from these devices. In addition, an emotion engine acquires the user's emotional data.

[0196] Data collection and preprocessing

[0197] The collected data is sent from the device to a server, which then preprocesses it. The preprocessing means converts the collected data into a unified format (e.g., JSON) and performs data cleansing, such as filling in missing data and correcting outliers. Emotion data is also collected by the emotion engine and preprocessed in the same way.

[0198] Generate a nutrition plan

[0199] The server then uses a generation means to input the preprocessed data into a generative AI model. This generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The generative AI model takes into account the user's physical data, training information, lifestyle habits, and emotional data to generate an optimal nutrition plan for each individual user. The generated nutrition plan is sent to the terminal via an information provision means and presented to the user. The presented nutrition plan includes specific breakfast, lunch, and dinner menus, as well as recommended nutritional supplements.

[0200] Gathering feedback and updating the model

[0201] The user inputs feedback on the provided nutrition plan into the device. The feedback includes information such as satisfaction with the meal and changes in physical condition. It also includes emotional data acquired by the emotion engine. This feedback is sent from the device to the server and collected by the feedback collection means. The server then uses the collected feedback and emotional data as training data for the generative AI model using the learning means, and updates the model to continuously improve the accuracy of the model.

[0202] Specific examples

[0203] For example, suppose a user (athlete) inputs data that they are 175 cm tall, weigh 70 kg, are 28 years old, and run three times a week. An activity tracker collects data indicating that they take 10,000 steps per day and have an average heart rate of 120 bpm. Furthermore, the emotion engine determines that the user's emotion indicates "fatigue." All of this data is sent from the device to the server, where it is preprocessed and then input into the generative AI model. Based on this data, the generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake as a nutritional supplement. The generated nutrition plan is presented to the user via their device, and the user can enter feedback and emotion data about the plan, which will be reflected in the next plan generation.

[0204] This allows athletes to receive individually optimized nutritional plans every day, taking into account their emotional state, allowing them to efficiently improve their performance and maintain their health.

[0205] The processing flow will be explained below.

[0206] Step 1:

[0207] User: Enters individual physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details) into the application. The device also connects to activity monitors and fitness trackers to automatically collect daily exercise data (e.g., number of steps, heart rate).

[0208] Step 2:

[0209] Device: Collected physical data, training information, lifestyle data, and exercise data are sent to the server. At the same time, the emotion engine is used to obtain the user's emotion data, which is also sent to the server.

[0210] Step 3:

[0211] Server: Converts received data into a unified format (e.g., JSON). Emotion data is also converted into a unified format, and all data is managed centrally.

[0212] Step 4:

[0213] Server: Performs data cleansing, such as checking for abnormal values ​​and filling in missing data. For example, it detects abnormal heart rates and missing data, and corrects and fills them.

[0214] Step 5:

[0215] Server: Inputs pre-processed data into the generative AI model. This data includes physical data, training information, lifestyle data, exercise data, and emotional data.

[0216] Step 6:

[0217] Server: The generative AI model is trained on the latest medical data and analyzes these inputs to generate a personalized nutrition plan.

[0218] Step 7:

[0219] Server: Sends the generated nutrition plan to the device, including specific breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0220] Step 8:

[0221] Device: Displays a nutrition plan to the user, such as oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake for supplementation.

[0222] Step 9:

[0223] User: Enters feedback on the provided nutrition plan, including satisfaction with the meal, changes in physical condition, and emotional fluctuations.

[0224] Step 10:

[0225] Terminal: Sends the input feedback data and the emotion data contained therein to the server.

[0226] Step 11:

[0227] Server: Analyzes the collected feedback using the feedback collection means and uses it, including emotional data, as training data for the generative AI model.

[0228] Step 12:

[0229] Server: Uses learning methods to update the generative AI model with collected feedback and emotion data, allowing the model to continually improve its accuracy.

[0230] Step 13:

[0231] Server: Uses the updated generative AI model to further optimize future nutrition plans for the user.

[0232] This provides users with an optimal daily nutrition plan that takes into account their emotional state, helping them improve performance and maintain good health.

[0233] Example 2

[0234] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0235] Athletes need individually optimized nutrition plans to efficiently improve their performance and maintain their health. However, current systems take into account the user's exercise information and lifestyle data, but it is difficult to generate comprehensive plans that include emotional data. Furthermore, there is a lack of mechanisms for continuously improving plans based on feedback.

[0236] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0237] In this invention, the server includes a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, a learning means, and an emotion engine means, which makes it possible to generate a nutrition plan that takes into account the user's physical data, exercise information, lifestyle data, and emotion data, and to continuously improve the plan based on the user's feedback.

[0238] The "data collection means" is a means for collecting the user's individual physical data, exercise information, lifestyle habit data, and emotional data.

[0239] The "pre-processing means" is a means for carrying out pre-processing such as standardizing the format of collected data, supplementing missing data, and correcting abnormal values.

[0240] The "generative means" refers to the means for inputting pre-processed data into a generative AI model to generate an individualized nutrition plan.

[0241] The "information providing means" is a means for presenting the generated nutrition plan to the user.

[0242] The "feedback collection means" is a means for a user to input feedback and emotional data about the nutrition plan and collect that data.

[0243] The "learning method" is a method for training a generative AI model based on collected feedback and emotional data, and continuously improving the accuracy of the model.

[0244] An "emotion engine" is a means for recognizing and collecting user emotion data.

[0245] The "generative AI model" is an artificial intelligence model that learns based on the latest medical data and generates a nutrition plan taking into account the user's physical data, exercise information, lifestyle data, and emotional data.

[0246] The present invention relates to a system for generating and providing personalized nutrition plans for athletes, which includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and an emotion engine that recognizes the emotions of a user.

[0247] Users input their individual physical data (e.g., height, weight, age), exercise information (e.g., type, time, and intensity of exercise), and lifestyle habits (e.g., sleep time, dietary details) through the device. The device is connected to activity monitors and fitness trackers, and automatically collects daily exercise data (e.g., number of steps, heart rate) from these devices. In addition, an emotion engine acquires the user's emotional data.

[0248] The collected data is sent from the device to a server, which then preprocesses it. The preprocessing means converts the collected data into a unified format (e.g., JSON) and performs data cleansing, such as filling in missing data and correcting outliers. Emotion data is also collected by the emotion engine and preprocessed in the same way.

[0249] The server then uses a generation means to input the preprocessed data into a generative AI model. This generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The generative AI model takes into account the user's physical data, exercise information, lifestyle data, and emotional data to generate an optimal nutrition plan for the individual. The generated nutrition plan is sent to the terminal via an information provision means and presented to the user. The presented nutrition plan includes specific breakfast, lunch, and dinner menus, as well as recommended nutritional supplements.

[0250] The user inputs feedback on the provided nutrition plan into the device. The feedback includes information such as satisfaction with the meal and changes in physical condition. It also includes emotional data acquired by the emotion engine. The feedback is sent from the device to the server and collected by the feedback collection means. The server then uses the collected feedback and emotional data as training data for the generative AI model using the learning means, and updates the model to continuously improve the accuracy of the model.

[0251] As a concrete example, consider the case where a user inputs data such as a height of 175 cm, weight of 70 kg, age of 28, and running three times a week. The activity tracker collects data indicating 10,000 steps per day and an average heart rate of 120 bpm. The emotion engine also recognizes the user's emotion as "fatigue." This data is sent from the device to the server, preprocessed, and then input into the generative AI model. Based on this data, the generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, and grilled salmon and roasted vegetables for dinner, along with a protein shake as a nutritional supplement. The generated nutrition plan is presented to the user via the device, and the user can enter feedback and emotion data about the plan, which will be reflected in the next plan generation.

[0252] Examples of prompts include, "Generate a nutrition plan for an athlete who is 175 cm tall, weighs 70 kg, is 28 years old, and runs three times a week. The emotional data is 'fatigue'." and "Create the optimal nutrition plan based on the user's data (e.g., height: 175 cm, weight: 70 kg, age: 28 years old, exercise: runs three times a week). The emotional data is 'fatigue'."

[0253] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0254] Step 1:

[0255] Data entry and collection

[0256] Users enter their physical data (e.g., height 175 cm, weight 70 kg, age 28), exercise information (e.g., running three times a week), and lifestyle habits (e.g., sleep time, dietary content) through the device. The entered data is temporarily stored inside the device. In addition, the device connects to an activity monitor or fitness tracker to automatically collect daily exercise data (e.g., 10,000 steps, average heart rate 120 bpm). The emotion engine also obtains emotional data (e.g., "fatigue") from the user's facial expressions and input data.

[0257] Input: physical data, exercise information, lifestyle data, emotional data

[0258] Output: Multiple datasets stored locally on the device

[0259] Step 2:

[0260] Sending data

[0261] The device sends all collected data to a server, where it is encrypted and transmitted securely using a secure protocol.

[0262] Input: Multiple datasets stored internally on the device

[0263] Output: Data transferred to the server

[0264] Step 3:

[0265] Data Preprocessing

[0266] The server uses preprocessing tools to convert the received data into a unified format (e.g., JSON). It then performs data cleansing, such as filling in missing data and correcting outliers, to ensure data quality. Emotion data is also preprocessed in the same way.

[0267] Input: A large amount of data transferred to the server

[0268] Output: Cleansed data converted into a unified format

[0269] Step 4:

[0270] Generate a nutrition plan

[0271] The server inputs the preprocessed data into a generative AI model using a generation method. The generative AI model generates an individualized nutrition plan based on the user's data (physical data, exercise information, lifestyle data, and emotional data) while referencing the latest medical data. The generated plan includes specific breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0272] Input: Data converted into a unified format and cleansed

[0273] Output: Generated personalized nutrition plan

[0274] Step 5:

[0275] Nutrition plan provided

[0276] The server transmits the generated nutrition plan to the terminal via the information providing means, and the nutrition plan is displayed on the user terminal and provided in a form that the user can easily access.

[0277] Input: Generated personalized nutrition plan

[0278] Output: Nutrition plan displayed on device

[0279] Step 6:

[0280] Enter your feedback

[0281] The user inputs feedback on the provided nutrition plan into the terminal. The feedback includes information such as satisfaction with the meal and changes in physical condition, as well as the latest emotional data obtained by the emotion engine.

[0282] Input: Feedback data from users

[0283] Output: Feedback saved on the device

[0284] Step 7:

[0285] Send Feedback

[0286] The terminal sends the collected feedback data to the server, which encrypts the data and transmits it securely to the server.

[0287] Input: Feedback data from users

[0288] Output: Feedback data transmitted to the server

[0289] Step 8:

[0290] Updating a Model

[0291] The server uses the feedback and emotion data collected by the feedback collection means as learning data for the generated AI model by the learning means, thereby improving the accuracy of the model and providing more accurate data when generating the next nutrition plan.

[0292] Input: Feedback data transferred to the server

[0293] Output: Updated generative AI model

[0294] As a result of the above, the present invention can continuously provide an optimal nutrition plan for each individual user and support the improvement of health and performance.

[0295] (Application example 2)

[0296] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0297] Today's athletes and health-conscious people strongly feel the need for individually optimized nutrition plans to achieve efficient training results. However, traditional systems cannot fully meet individual needs and rely on uniform nutritional guidelines, making it difficult to provide meals tailored to individual physical conditions, lifestyles, and emotional states. Furthermore, there is a lack of a system for quickly providing meals based on the generated nutrition plan. This creates challenges in putting personalized nutrition plans into practice in a timely manner.

[0298] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0299] In this invention, the server includes a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, a learning means, and a service provision means for providing meals based on a personalized nutrition plan. This enables the creation of an optimal nutrition plan based on individual physical information, training information, lifestyle habits, and emotional data, and the consistent provision of meals according to that plan.

[0300] The "data collection means" is a means for collecting the user's physical data, training information, lifestyle habits, and emotional data.

[0301] The "preprocessing means" is a means for converting collected data into a unified format and performing data cleansing such as supplementing missing data and correcting outliers.

[0302] "Generating means" means for generating an individualized nutrition plan using a generative AI model based on the pre-processed data.

[0303] The "information providing means" is a means for presenting the generated nutrition plan to the user.

[0304] The "feedback collection means" is a means for collecting feedback from the user regarding the nutrition plan and reflecting this in the next plan generation.

[0305] The "learning means" is a means of updating the generative AI model by using collected feedback and emotional data as training data.

[0306] The "service provision means" is a means for providing meals based on a personalized nutrition plan and delivering them to the user.

[0307] MODE FOR CARRYING OUT THE INVENTION

[0308] The present invention relates to a system for generating and providing personalized nutrition plans for athletes and health-conscious individuals, which includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and a service provision means.

[0309] System Overview

[0310] When a user uses the system, they enter their physical data (height, weight, age), training information (type of exercise, time, intensity), and lifestyle habits (sleep time, dietary details) through a smartphone app. The smartphone app also connects to fitness trackers and activity monitors to automatically collect daily exercise data (number of steps, heart rate). Emotional data is also collected by the emotion engine.

[0311] Data collection and preprocessing

[0312] The collected data is sent from the smartphone app to a server, where it is preprocessed. The preprocessing means converts the collected data into a unified format, complements missing data, and corrects outliers. Emotion data is also collected by the emotion engine and preprocessed in the same way.

[0313] Generate a nutrition plan

[0314] The server then uses a generation means to input the preprocessed data into a generative AI model. This generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The generated nutrition plan is sent to a smartphone app via an information provision means and presented to the user. The presented nutrition plan includes specific breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0315] Gathering feedback and updating the model

[0316] Users input feedback about the provided nutrition plan into the smartphone app. The feedback includes information such as satisfaction with the meal and changes in physical condition. The feedback also includes emotional data acquired by the emotion engine. This feedback is sent from the smartphone app to the server, and the data is collected by the feedback collection means. Based on the collected feedback and emotional data, the server uses the learning means to update the generative AI model and continuously improve the accuracy of the model.

[0317] Specific examples

[0318] For example, if the user enters the following parameters:

[0319] Height: 175cm

[0320] Weight: 70kg

[0321] Age: 28

[0322] Regular exercise: Running three times a week

[0323] Emotional state: Fatigue

[0324] Based on this data, the following prompt is input to the generative AI model:

[0325] Generate a meal plan for an athlete: {height: 175, weight: 70, age: 28, training_info: {frequency: 3, type: 'running'}, lifestyle: {hours of sleep: 8, diet: 'balanced diet'}, emotion_data: 'fatigue'}

[0326] The generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake as a nutritional supplement. The plan is presented to the user via a smartphone app, and the user can enter feedback on the plan.

[0327] As a result, users can efficiently obtain a personalized nutrition plan and be provided with appropriate meals quickly, thereby improving performance and maintaining health.

[0328] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0329] Step 1:

[0330] Using a smartphone app, users input physical data such as height, weight, and age, as well as training information, lifestyle habits, and emotional data, which are then stored in the app according to the input format.

[0331] Input: physical data, training information, lifestyle data, emotional data

[0332] Output: The entered data is saved in the app.

[0333] Step 2:

[0334] In addition to data entered by the user, the smartphone app works with fitness trackers and activity monitors to automatically collect daily exercise data (e.g., number of steps, heart rate), which is then periodically sent to a server.

[0335] Input: Exercise data from fitness trackers and activity monitors

[0336] Output: The exercise data is sent to the server.

[0337] Step 3:

[0338] The server preprocesses the received data using preprocessing means, specifically converting the data into a unified format (e.g., JSON), filling in missing data, and correcting outliers.

[0339] Input: Collected data (physical data, exercise data, lifestyle data, emotional data)

[0340] Output: Preprocessed data

[0341] Step 4:

[0342] The server inputs the preprocessed data into the generative AI model via a generating means, and generates a personalized nutrition plan by forming a prompt sentence and sending it to the generative AI model.

[0343] Input: Preprocessed data

[0344] Output: A personalized nutrition plan generated by the generative AI model

[0345] Step 5:

[0346] The server sends the generated nutrition plan to the smartphone app via the information providing means, and the user can check their own nutrition plan through the smartphone app.

[0347] Input: Generated nutrition plan

[0348] Output: Nutrition plan sent to smartphone app

[0349] Step 6:

[0350] Users follow the provided nutrition plan and then enter feedback into a smartphone app, including their satisfaction with the meal and any changes in their physical condition.

[0351] Input: User feedback

[0352] Output: Feedback stored in the smartphone app

[0353] Step 7:

[0354] The server receives feedback from the smartphone app and collects it using a feedback collection means, which is then used as reference data for the nutrition plan that is generated.

[0355] Input: Feedback from smartphone app

[0356] Output: Collected feedback data

[0357] Step 8:

[0358] Finally, the server uses learning methods to continuously update the generative AI model based on collected feedback and emotion data, improving the model's accuracy.

[0359] Input: Collected feedback and sentiment data

[0360] Output: Updated generative AI model

[0361] Through the above processing steps, the user can always obtain the latest individually optimized nutrition plan, enabling them to efficiently improve their performance and maintain their health.

[0362] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0363] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0364] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0365] [Second embodiment]

[0366] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0367] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0368] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0369] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0370] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0371] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0372] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0373] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0374] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0375] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0376] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0377] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0378] The present invention relates to a system for generating and providing personalized nutrition plans for athletes, the system including a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, and a learning means.

[0379] When an athlete begins using the system, the user (athlete) enters individual physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details) through the device. The device also connects to activity monitors and fitness trackers, automatically collecting daily exercise data (e.g., number of steps, heart rate) from these devices.

[0380] The collected data is sent from the terminal to a server, which then preprocesses the data. The preprocessing method converts the collected data into a unified format (e.g., JSON) and performs data cleansing, such as filling in missing data and correcting outliers.

[0381] The server then uses a generating means to input the preprocessed data into a generative AI model. The generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The nutrition plan generated by the generative AI model is then sent to the terminal via an information providing means and presented to the user. The presented nutrition plan includes breakfast, lunch, and dinner menus, as well as recommended nutritional supplements.

[0382] The user inputs feedback on the provided nutrition plan into the device. For example, information such as satisfaction with the diet or changes in physical condition is provided as feedback. This feedback is sent from the device to the server and collected by the feedback collection means. The server then uses the collected feedback as training data for the generated AI model through the learning means, and updates the model to continuously improve the accuracy of the model.

[0383] Specific examples

[0384] For example, suppose a user (athlete) inputs data that indicates he or she is 175 cm tall, weighs 70 kg, is 28 years old, and runs three times a week. Data collected from an activity tracker also indicates that he or she takes 10,000 steps per day and has an average heart rate of 120 bpm. This data is sent from the device to a server, where it is preprocessed and then input into a generative AI model. Based on this data, the generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake as a nutritional supplement. The generated nutrition plan is presented to the user via the device, and the user can enter feedback on the plan, which will be reflected in the next plan generation.

[0385] This allows athletes to receive individually optimized nutritional plans every day, enabling them to efficiently improve their performance and maintain their health.

[0386] The processing flow will be explained below.

[0387] Step 1:

[0388] User: Enters individual physical data (height, weight, age, etc.), training information (type of exercise, time, intensity, etc.), and lifestyle habits (sleep time, diet, etc.) into the application.

[0389] Step 2:

[0390] Device: Works with activity monitors and fitness trackers to automatically collect daily exercise data (number of steps, heart rate, etc.).

[0391] Step 3:

[0392] Terminal: Sends collected data to the server.

[0393] Step 4:

[0394] Server: Converts the received data into a unified format (e.g., JSON).

[0395] Step 5:

[0396] Server: Performs data cleansing, such as checking for outliers and filling in missing data.

[0397] Step 6:

[0398] Server: Inputs preprocessed data into a generative AI model to analyze various data points.

[0399] Step 7:

[0400] Server: A generative AI model generates a personalized nutrition plan based on the latest medical data.

[0401] Step 8:

[0402] Server: Sends the generated nutrition plan to the device.

[0403] Step 9:

[0404] On the device: Displays a nutrition plan (breakfast, lunch, and dinner menus and nutritional supplements) to the user.

[0405] Step 10:

[0406] User: Enter feedback on the nutrition plan provided.

[0407] Step 11:

[0408] Terminal: Sends the entered feedback to the server.

[0409] Step 12:

[0410] Server: Collects feedback and uses it to update the training data for the generative AI model.

[0411] Step 13:

[0412] Server: Use the updated model to generate the next nutrition plan.

[0413] This provides users with an optimal daily nutrition plan, helping them improve performance and maintain good health.

[0414] Example 1

[0415] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0416] Conventional nutrition plan providing systems have difficulty in providing personalized nutrition plans to individual users and in continuously improving plans based on user feedback. As a result, they have not been effective enough in maintaining users' health and improving their performance.

[0417] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0418] In this invention, the server includes a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, a learning means, a means for sending the nutrition plan generated by the generation means to a user terminal, and a means for updating the generative AI model based on the feedback collected by the feedback collection means, thereby providing a personalized nutrition plan to each user and continuously improving the model based on user feedback.

[0419] The "data collection means" is a means for collecting physical data, training information, lifestyle habit data from a user, and exercise data from an activity monitor or fitness tracker.

[0420] "Preprocessing means" refers to means for converting collected data into a unified format and performing data cleansing such as supplementing missing data and correcting outliers.

[0421] The "generative means" is a means for generating an individual nutrition plan based on preprocessed data using a generative AI model that has learned the latest medical data.

[0422] The "information providing means" is a means for transmitting the generated nutrition plan to the user terminal and presenting it to the user.

[0423] The "feedback collection means" is a means for collecting feedback from users (e.g., satisfaction with meals or changes in physical condition).

[0424] A "learning method" is a method for continuously updating the generative AI model based on collected feedback to improve the accuracy of the plan.

[0425] A "server" is a computer system for executing the data collection means, pre-processing means, generation means, information provision means, feedback collection means and learning means.

[0426] "User terminal" means a device used by a user to enter information, review generated nutrition plans, and enter feedback.

[0427] A "generative AI model" is a machine learning model that learns from collected data and the latest medical data to generate an individualized nutrition plan.

[0428] The present invention is a system for generating and providing personalized nutrition plans for athletes, the system including a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, and a learning means.

[0429] First, the user (athlete) uses a device to input physical data, training information, and lifestyle habits, such as height, weight, age, type of exercise, exercise time, exercise intensity, sleep time, and dietary details. The device then connects to an activity monitor or fitness tracker to automatically collect daily exercise data (e.g., number of steps and heart rate). This data is then sent to a server using a secure protocol (e.g., HTTPS).

[0430] Next, the server converts the collected data into a unified format (e.g., JSON) using a preprocessing means and performs data cleansing, such as filling in missing data and correcting outliers. The preprocessed data is input into a generative AI model using a generation means. This generative AI model is trained using deep learning algorithms and generates a personalized nutrition plan based on the latest medical data and collected user data.

[0431] The generated nutrition plan is sent from the server to the terminal via the information providing means. The terminal displays the generated nutrition plan to the user, and the user uses this plan as a reference to prepare daily meals. The nutrition plan specifically describes breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0432] The user inputs feedback about the provided nutrition plan into the device. This feedback includes satisfaction with the meal and changes in physical condition. The device sends this feedback to the server, where it is collected by the feedback collection means. The server has a learning means that continuously updates the generative AI model based on the collected feedback and improves the accuracy of the plan.

[0433] Specific examples

[0434] For example, if a user (athlete) enters the following data:

[0435] Height: 175cm

[0436] Weight: 70kg

[0437] Age: 28

[0438] Exercise: Running three times a week

[0439] Also, suppose the following data is collected from an activity tracker:

[0440] Daily steps: 10,000 steps

[0441] Average heart rate: 120 bpm

[0442] This data is sent from the device to a server, where it is pre-processed and then fed into a generative AI model, which generates a nutrition plan like this:

[0443] Breakfast: Oatmeal and blueberries

[0444] Lunch: Chicken salad

[0445] Dinner: Grilled salmon and roasted vegetables

[0446] Nutritional Supplement: Protein Shake

[0447] The generated nutrition plan is presented to the user via the terminal, and the user can input feedback about the plan (e.g., "The salad for lunch wasn't filling enough"), which will be reflected in the next plan generation.

[0448] Prompt Sentence Examples

[0449] "Generate the optimal nutrition plan for a 175cm, 70kg, 28-year-old athlete who runs three times a week, takes 10,000 steps per day, and has an average heart rate of 120 bpm. What meals should I have for breakfast, lunch, and dinner, along with recommended nutritional supplements?"

[0450] This allows the system to provide users with individually optimized nutritional plans on a daily basis, enabling them to efficiently improve performance and maintain health.

[0451] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0452] Step 1:

[0453] The user uses the device to input their physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details). The input data is saved on the device. This data becomes input data.

[0454] Step 2:

[0455] The device connects to activity monitors and fitness trackers via Bluetooth or Wi-Fi to automatically collect daily exercise data (e.g., steps taken, heart rate). The collected data is stored on the device. This data is also added to the input data mentioned above.

[0456] Step 3:

[0457] The device sends all collected data to the server using a secure protocol (e.g., HTTPS). Input data is transferred to the server and stored in a server-side database.

[0458] Step 4:

[0459] The server uses preprocessing means to convert the collected data into a unified format (e.g., JSON). Specifically, it parses the data, unifies the data structure, and resolves inconsistencies. Data that has undergone preprocessing is called preprocessed data.

[0460] Step 5:

[0461] The server then performs data cleansing on the preprocessed data. It adds missing data items and detects and corrects outliers. For example, if abnormally high heart rate data is included, it is corrected by referencing past data. This process generates cleansed data.

[0462] Step 6:

[0463] The server inputs the cleansed data into a generative AI model using a generation means, for example, by inputting the data into a generative AI model that uses a deep learning algorithm, and calculations begin.

[0464] Step 7:

[0465] The generative AI model generates a personalized nutrition plan based on the latest medical data and collected user data. The model calculates the nutrient balance of each meal and determines the optimal menu. The calculation results are output as nutrition plan data.

[0466] Step 8:

[0467] The server sends the generated nutrition plan data to the device via an information providing means. Specifically, the information is delivered to the device via push notifications or in-app notifications. The user can then check the nutrition plan on their device.

[0468] Step 9:

[0469] The user inputs feedback about the provided nutrition plan into the terminal. The feedback includes satisfaction with the meal, changes in physical condition, etc. This feedback data is stored in the terminal.

[0470] Step 10:

[0471] The terminal transmits the feedback data to the server using a secure protocol, and the transmitted feedback data is stored in a database on the server side.

[0472] Step 11:

[0473] The server continuously updates the generative AI model based on the collected feedback data. It uses learning methods to adjust the model parameters and improve the accuracy of future nutrition plans. This update generates an improved generative AI model.

[0474] By repeating the above steps, the system can continuously provide the user with an optimal nutrition plan.

[0475] (Application example 1)

[0476] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0477] Conventional nutrition plan delivery systems lack real-time feedback and individual personalization, making it difficult to efficiently provide nutrition plans tailored to the individual needs of athletes. In particular, they are unable to provide immediate and appropriate information on daily food selection, making it difficult to optimize athletes' performance and health.

[0478] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0479] In this invention, the server includes a data collection means, a pre-processing means, a generation means, and a means for displaying an individual nutrition plan in real time through a device such as smart glasses, thereby enabling athletes to receive the nutritional information they need for their daily food selection in real time and realizing the provision of an individually optimized nutrition plan.

[0480] "Data collection means" refers to equipment and software used to collect athletes' physical data, training information, and lifestyle data.

[0481] "Preprocessing means" refers to the process of converting collected data into a unified format and performing data cleansing, such as filling in missing data and correcting outliers.

[0482] "Generation" refers to the process of generating an individual nutrition plan based on collected and pre-processed data using a generative AI model trained on the latest medical data.

[0483] "Information delivery means" refers to the equipment or software used to provide the generated nutrition plan to the athlete.

[0484] "Feedback collection means" refers to equipment or software for collecting feedback information from athletes (e.g., satisfaction with meals, changes in physical condition, etc.).

[0485] "Learning" is the process of continuously updating the generative AI model using collected feedback information to improve its accuracy.

[0486] "Means for displaying individual nutrition plans in real time through devices such as smart glasses" refers to technology that uses smart glasses worn by athletes to display individually optimized nutrition plans and ingredient information in real time while they are shopping.

[0487] This invention is a system for providing personalized nutrition plans to athletes in real time. The system includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and a means for displaying the individual nutrition plan in real time through a device such as smart glasses. Each of these means will be described in detail below.

[0488] Data collection methods

[0489] The data collection method mainly involves collecting athletes' physical data (e.g., height, weight, age), training information (e.g., type, time, and intensity of exercise), and lifestyle habits (e.g., sleep duration, dietary content). This data may be entered directly by the user into the device, or may be collected automatically in conjunction with an activity monitor or fitness tracker. This allows for accurate and comprehensive data.

[0490] Pretreatment means

[0491] The collected data is first converted into a unified format (e.g., JSON) through pre-processing measures, followed by data cleansing, such as imputing missing data and correcting outliers, laying the foundation for the generative AI model to generate an accurate nutrition plan.

[0492] generation means

[0493] Once pre-processed, the data is passed to the generator, which uses a generative AI model trained on the latest medical data to generate a personalized nutrition plan. This plan includes breakfast, lunch, and dinner menus, as well as recommended nutritional supplements. The nutrition plans generated at this stage are optimized for the athlete's specific needs and goals.

[0494] Information provision means

[0495] The generated nutrition plan is sent to a device such as smart glasses via the information providing means. The user can view the nutrition plan and ingredient information displayed in real time on the smart glasses while shopping, making it easy to manage nutrition in everyday life.

[0496] Feedback collection methods

[0497] The user follows the provided nutrition plan and inputs feedback such as the results, satisfaction, changes in physical condition, etc. into the terminal. This feedback data is then sent to the server.

[0498] Learning tools

[0499] The collected feedback data is fed into the generative AI model by a learning method and is continuously used as training data for the model, which improves the accuracy of the generative AI model and enables the provision of more appropriate nutrition plans.

[0500] Specific examples

[0501] For example, imagine an athlete is shopping at a supermarket. As they approach the dairy section, the smart glasses display will show, "This week's recommended foods: Greek yogurt, low-fat milk," and then suggest the next step in their nutrition plan: "Refill your protein shake." This way, the athlete has real-time information they need at that moment.

[0502] Prompt Sentence Examples

[0503] "The user is an athlete with the following characteristics: height 175cm, weight 70kg, age 28, exercise frequency 3 times a week, steps taken 10,000 times, and average heart rate 120 bpm. Generate optimal breakfast, lunch, dinner, and nutritional supplement recommendations for this user."

[0504] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0505] Step 1:

[0506] The user uses the device to input their physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details), or the device connects to an activity monitor or fitness tracker to automatically collect exercise data (e.g., number of steps, heart rate). The input data is converted into a unified format such as JSON.

[0507] Input: Physical data, training information, lifestyle data

[0508] Output: Data converted into a unified format (e.g. JSON)

[0509] Specific operation: Obtains data from the terminal's input form or linked devices and converts it into JSON format.

[0510] Step 2:

[0511] The server uses preprocessing means to cleanse the collected data, impute missing data, and correct outliers, resulting in preprocessed data.

[0512] Input: Data converted into a unified format

[0513] Output: Cleansed preprocessed data

[0514] Specific operations: Reshaping data, estimating missing data, correcting outliers, etc.

[0515] Step 3:

[0516] The server uses a generating means to input the pre-processed data into a generative AI model to generate a personalized nutrition plan, which includes breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0517] Input: Preprocessed data

[0518] Output: Personalized nutrition plan

[0519] Specific operation: Data is input into the generative AI model, and calculations are performed to generate a nutrition plan.

[0520] Step 4:

[0521] The generated nutrition plan is sent to the smart glasses via the information providing means, and the user can check the nutrition plan and ingredient information displayed in real time on the smart glasses display.

[0522] Enter: personalized nutrition plan

[0523] Output: Nutrition plan displayed on smart glasses

[0524] What it does: Sends the nutrition plan to the smart glasses and displays it on the screen.

[0525] Step 5:

[0526] The user carries out the nutrition plan and inputs feedback such as the results, satisfaction, changes in physical condition, etc. into the terminal. This feedback data is sent to the server.

[0527] Input: Feedback on nutrition plan

[0528] Output: Feedback data sent to the server

[0529] Specific operation: Fill out the feedback form from the terminal and send it to the server.

[0530] Step 6:

[0531] The server uses the feedback collection means to incorporate the collected feedback into the generative AI model using the learning means, updating the model and improving its accuracy.

[0532] Input: Feedback data

[0533] Output: An updated generative AI model

[0534] Specific operation: Analyze the feedback data, incorporate it as training data for the generative AI model, and retrain the model.

[0535] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0536] The present invention relates to a system for generating and providing personalized nutrition plans for athletes, which includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and an emotion engine that recognizes the emotions of a user.

[0537] System Overview

[0538] First, when a user (athlete) starts using the system, they input their individual physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details) through their device. The device also connects to activity monitors and fitness trackers, automatically collecting daily exercise data (e.g., number of steps, heart rate) from these devices. In addition, an emotion engine acquires the user's emotional data.

[0539] Data collection and preprocessing

[0540] The collected data is sent from the device to a server, which then preprocesses it. The preprocessing means converts the collected data into a unified format (e.g., JSON) and performs data cleansing, such as filling in missing data and correcting outliers. Emotion data is also collected by the emotion engine and preprocessed in the same way.

[0541] Generate a nutrition plan

[0542] The server then uses a generation means to input the preprocessed data into a generative AI model. This generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The generative AI model takes into account the user's physical data, training information, lifestyle habits, and emotional data to generate an optimal nutrition plan for each individual user. The generated nutrition plan is sent to the terminal via an information provision means and presented to the user. The presented nutrition plan includes specific breakfast, lunch, and dinner menus, as well as recommended nutritional supplements.

[0543] Gathering feedback and updating the model

[0544] The user inputs feedback on the provided nutrition plan into the device. The feedback includes information such as satisfaction with the meal and changes in physical condition. It also includes emotional data acquired by the emotion engine. This feedback is sent from the device to the server and collected by the feedback collection means. The server then uses the collected feedback and emotional data as training data for the generative AI model using the learning means, and updates the model to continuously improve the accuracy of the model.

[0545] Specific examples

[0546] For example, suppose a user (athlete) inputs data that they are 175 cm tall, weigh 70 kg, are 28 years old, and run three times a week. An activity tracker collects data indicating that they take 10,000 steps per day and have an average heart rate of 120 bpm. Furthermore, the emotion engine determines that the user's emotion indicates "fatigue." All of this data is sent from the device to the server, where it is preprocessed and then input into the generative AI model. Based on this data, the generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake as a nutritional supplement. The generated nutrition plan is presented to the user via their device, and the user can enter feedback and emotion data about the plan, which will be reflected in the next plan generation.

[0547] This allows athletes to receive individually optimized nutritional plans every day, taking into account their emotional state, allowing them to efficiently improve their performance and maintain their health.

[0548] The processing flow will be explained below.

[0549] Step 1:

[0550] User: Enters individual physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details) into the application. The device also connects to activity monitors and fitness trackers to automatically collect daily exercise data (e.g., number of steps, heart rate).

[0551] Step 2:

[0552] Device: Collected physical data, training information, lifestyle data, and exercise data are sent to the server. At the same time, the emotion engine is used to obtain the user's emotion data, which is also sent to the server.

[0553] Step 3:

[0554] Server: Converts received data into a unified format (e.g., JSON). Emotion data is also converted into a unified format, and all data is managed centrally.

[0555] Step 4:

[0556] Server: Performs data cleansing, such as checking for abnormal values ​​and filling in missing data. For example, it detects abnormal heart rates and missing data, and corrects and fills them.

[0557] Step 5:

[0558] Server: Inputs pre-processed data into the generative AI model. This data includes physical data, training information, lifestyle data, exercise data, and emotional data.

[0559] Step 6:

[0560] Server: The generative AI model is trained on the latest medical data and analyzes these inputs to generate a personalized nutrition plan.

[0561] Step 7:

[0562] Server: Sends the generated nutrition plan to the device, including specific breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0563] Step 8:

[0564] Device: Displays a nutrition plan to the user, such as oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake for supplementation.

[0565] Step 9:

[0566] User: Enters feedback on the provided nutrition plan, including satisfaction with the meal, changes in physical condition, and emotional fluctuations.

[0567] Step 10:

[0568] Terminal: Sends the input feedback data and the emotion data contained therein to the server.

[0569] Step 11:

[0570] Server: Analyzes the collected feedback using the feedback collection means and uses it, including emotional data, as training data for the generative AI model.

[0571] Step 12:

[0572] Server: Uses learning methods to update the generative AI model with collected feedback and emotion data, allowing the model to continually improve its accuracy.

[0573] Step 13:

[0574] Server: Uses the updated generative AI model to further optimize future nutrition plans for the user.

[0575] This provides users with an optimal daily nutrition plan that takes into account their emotional state, helping them improve performance and maintain good health.

[0576] Example 2

[0577] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0578] Athletes need individually optimized nutrition plans to efficiently improve their performance and maintain their health. However, current systems take into account the user's exercise information and lifestyle data, but it is difficult to generate comprehensive plans that include emotional data. Furthermore, there is a lack of mechanisms for continuously improving plans based on feedback.

[0579] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0580] In this invention, the server includes a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, a learning means, and an emotion engine means, which makes it possible to generate a nutrition plan that takes into account the user's physical data, exercise information, lifestyle data, and emotion data, and to continuously improve the plan based on the user's feedback.

[0581] The "data collection means" is a means for collecting the user's individual physical data, exercise information, lifestyle habit data, and emotional data.

[0582] The "pre-processing means" is a means for carrying out pre-processing such as standardizing the format of collected data, supplementing missing data, and correcting abnormal values.

[0583] The "generative means" refers to the means for inputting pre-processed data into a generative AI model to generate an individualized nutrition plan.

[0584] The "information providing means" is a means for presenting the generated nutrition plan to the user.

[0585] The "feedback collection means" is a means for a user to input feedback and emotional data about the nutrition plan and collect that data.

[0586] The "learning method" is a method for training a generative AI model based on collected feedback and emotional data, and continuously improving the accuracy of the model.

[0587] An "emotion engine" is a means for recognizing and collecting user emotion data.

[0588] The "generative AI model" is an artificial intelligence model that learns based on the latest medical data and generates a nutrition plan taking into account the user's physical data, exercise information, lifestyle data, and emotional data.

[0589] The present invention relates to a system for generating and providing personalized nutrition plans for athletes, which includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and an emotion engine that recognizes the emotions of a user.

[0590] Users input their individual physical data (e.g., height, weight, age), exercise information (e.g., type, time, and intensity of exercise), and lifestyle habits (e.g., sleep time, dietary details) through the device. The device is connected to activity monitors and fitness trackers, and automatically collects daily exercise data (e.g., number of steps, heart rate) from these devices. In addition, an emotion engine acquires the user's emotional data.

[0591] The collected data is sent from the device to a server, which then preprocesses it. The preprocessing means converts the collected data into a unified format (e.g., JSON) and performs data cleansing, such as filling in missing data and correcting outliers. Emotion data is also collected by the emotion engine and preprocessed in the same way.

[0592] The server then uses a generation means to input the preprocessed data into a generative AI model. This generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The generative AI model takes into account the user's physical data, exercise information, lifestyle data, and emotional data to generate an optimal nutrition plan for the individual. The generated nutrition plan is sent to the terminal via an information provision means and presented to the user. The presented nutrition plan includes specific breakfast, lunch, and dinner menus, as well as recommended nutritional supplements.

[0593] The user inputs feedback on the provided nutrition plan into the device. The feedback includes information such as satisfaction with the meal and changes in physical condition. It also includes emotional data acquired by the emotion engine. The feedback is sent from the device to the server and collected by the feedback collection means. The server then uses the collected feedback and emotional data as training data for the generative AI model using the learning means, and updates the model to continuously improve the accuracy of the model.

[0594] As a concrete example, consider the case where a user inputs data such as a height of 175 cm, weight of 70 kg, age of 28, and running three times a week. The activity tracker collects data indicating 10,000 steps per day and an average heart rate of 120 bpm. The emotion engine also recognizes the user's emotion as "fatigue." This data is sent from the device to the server, preprocessed, and then input into the generative AI model. Based on this data, the generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, and grilled salmon and roasted vegetables for dinner, along with a protein shake as a nutritional supplement. The generated nutrition plan is presented to the user via the device, and the user can enter feedback and emotion data about the plan, which will be reflected in the next plan generation.

[0595] Examples of prompts include, "Generate a nutrition plan for an athlete who is 175 cm tall, weighs 70 kg, is 28 years old, and runs three times a week. The emotional data is 'fatigue'." and "Create the optimal nutrition plan based on the user's data (e.g., height: 175 cm, weight: 70 kg, age: 28 years old, exercise: runs three times a week). The emotional data is 'fatigue'."

[0596] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0597] Step 1:

[0598] Data entry and collection

[0599] Users enter their physical data (e.g., height 175 cm, weight 70 kg, age 28), exercise information (e.g., running three times a week), and lifestyle habits (e.g., sleep time, dietary content) through the device. The entered data is temporarily stored inside the device. In addition, the device connects to an activity monitor or fitness tracker to automatically collect daily exercise data (e.g., 10,000 steps, average heart rate 120 bpm). The emotion engine also obtains emotional data (e.g., "fatigue") from the user's facial expressions and input data.

[0600] Input: physical data, exercise information, lifestyle data, emotional data

[0601] Output: Multiple datasets stored locally on the device

[0602] Step 2:

[0603] Sending data

[0604] The device sends all collected data to a server, where it is encrypted and transmitted securely using a secure protocol.

[0605] Input: Multiple datasets stored internally on the device

[0606] Output: Data transferred to the server

[0607] Step 3:

[0608] Data Preprocessing

[0609] The server uses preprocessing tools to convert the received data into a unified format (e.g., JSON). It then performs data cleansing, such as filling in missing data and correcting outliers, to ensure data quality. Emotion data is also preprocessed in the same way.

[0610] Input: A large amount of data transferred to the server

[0611] Output: Cleansed data converted into a unified format

[0612] Step 4:

[0613] Generate a nutrition plan

[0614] The server inputs the preprocessed data into a generative AI model using a generation method. The generative AI model generates an individualized nutrition plan based on the user's data (physical data, exercise information, lifestyle data, and emotional data) while referencing the latest medical data. The generated plan includes specific breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0615] Input: Data converted into a unified format and cleansed

[0616] Output: Generated personalized nutrition plan

[0617] Step 5:

[0618] Nutrition plan provided

[0619] The server transmits the generated nutrition plan to the terminal via the information providing means, and the nutrition plan is displayed on the user terminal and provided in a form that the user can easily access.

[0620] Input: Generated personalized nutrition plan

[0621] Output: Nutrition plan displayed on device

[0622] Step 6:

[0623] Enter your feedback

[0624] The user inputs feedback on the provided nutrition plan into the terminal. The feedback includes information such as satisfaction with the meal and changes in physical condition, as well as the latest emotional data obtained by the emotion engine.

[0625] Input: Feedback data from users

[0626] Output: Feedback saved on the device

[0627] Step 7:

[0628] Send Feedback

[0629] The terminal sends the collected feedback data to the server, which encrypts the data and transmits it securely to the server.

[0630] Input: Feedback data from users

[0631] Output: Feedback data transmitted to the server

[0632] Step 8:

[0633] Updating a Model

[0634] The server uses the feedback and emotion data collected by the feedback collection means as learning data for the generated AI model by the learning means, thereby improving the accuracy of the model and providing more accurate data when generating the next nutrition plan.

[0635] Input: Feedback data transferred to the server

[0636] Output: Updated generative AI model

[0637] As a result of the above, the present invention can continuously provide an optimal nutrition plan for each individual user and support the improvement of health and performance.

[0638] (Application example 2)

[0639] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0640] Today's athletes and health-conscious people strongly feel the need for individually optimized nutrition plans to achieve efficient training results. However, traditional systems cannot fully meet individual needs and rely on uniform nutritional guidelines, making it difficult to provide meals tailored to individual physical conditions, lifestyles, and emotional states. Furthermore, there is a lack of a system for quickly providing meals based on the generated nutrition plan. This creates challenges in putting personalized nutrition plans into practice in a timely manner.

[0641] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0642] In this invention, the server includes a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, a learning means, and a service provision means for providing meals based on a personalized nutrition plan. This enables the creation of an optimal nutrition plan based on individual physical information, training information, lifestyle habits, and emotional data, and the consistent provision of meals according to that plan.

[0643] The "data collection means" is a means for collecting the user's physical data, training information, lifestyle habits, and emotional data.

[0644] The "preprocessing means" is a means for converting collected data into a unified format and performing data cleansing such as supplementing missing data and correcting outliers.

[0645] "Generating means" means for generating an individualized nutrition plan using a generative AI model based on the pre-processed data.

[0646] The "information providing means" is a means for presenting the generated nutrition plan to the user.

[0647] The "feedback collection means" is a means for collecting feedback from the user regarding the nutrition plan and reflecting this in the next plan generation.

[0648] The "learning means" is a means of updating the generative AI model by using collected feedback and emotional data as training data.

[0649] The "service provision means" is a means for providing meals based on a personalized nutrition plan and delivering them to the user.

[0650] MODE FOR CARRYING OUT THE INVENTION

[0651] The present invention relates to a system for generating and providing personalized nutrition plans for athletes and health-conscious individuals, which includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and a service provision means.

[0652] System Overview

[0653] When a user uses the system, they enter their physical data (height, weight, age), training information (type of exercise, time, intensity), and lifestyle habits (sleep time, dietary details) through a smartphone app. The smartphone app also connects to fitness trackers and activity monitors to automatically collect daily exercise data (number of steps, heart rate). Emotional data is also collected by the emotion engine.

[0654] Data collection and preprocessing

[0655] The collected data is sent from the smartphone app to a server, where it is preprocessed. The preprocessing means converts the collected data into a unified format, complements missing data, and corrects outliers. Emotion data is also collected by the emotion engine and preprocessed in the same way.

[0656] Generate a nutrition plan

[0657] The server then uses a generation means to input the preprocessed data into a generative AI model. This generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The generated nutrition plan is sent to a smartphone app via an information provision means and presented to the user. The presented nutrition plan includes specific breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0658] Gathering feedback and updating the model

[0659] Users input feedback about the provided nutrition plan into the smartphone app. The feedback includes information such as satisfaction with the meal and changes in physical condition. The feedback also includes emotional data acquired by the emotion engine. This feedback is sent from the smartphone app to the server, and the data is collected by the feedback collection means. Based on the collected feedback and emotional data, the server uses the learning means to update the generative AI model and continuously improve the accuracy of the model.

[0660] Specific examples

[0661] For example, if the user enters the following parameters:

[0662] Height: 175cm

[0663] Weight: 70kg

[0664] Age: 28

[0665] Regular exercise: Running three times a week

[0666] Emotional state: Fatigue

[0667] Based on this data, the following prompt is input to the generative AI model:

[0668] Generate a meal plan for an athlete: {height: 175, weight: 70, age: 28, training_info: {frequency: 3, type: 'running'}, lifestyle: {hours of sleep: 8, diet: 'balanced diet'}, emotion_data: 'fatigue'}

[0669] The generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake as a nutritional supplement. The plan is presented to the user via a smartphone app, and the user can enter feedback on the plan.

[0670] As a result, users can efficiently obtain a personalized nutrition plan and be provided with appropriate meals quickly, thereby improving performance and maintaining health.

[0671] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0672] Step 1:

[0673] Using a smartphone app, users input physical data such as height, weight, and age, as well as training information, lifestyle habits, and emotional data, which are then stored in the app according to the input format.

[0674] Input: physical data, training information, lifestyle data, emotional data

[0675] Output: The entered data is saved in the app.

[0676] Step 2:

[0677] In addition to data entered by the user, the smartphone app works with fitness trackers and activity monitors to automatically collect daily exercise data (e.g., number of steps, heart rate), which is then periodically sent to a server.

[0678] Input: Exercise data from fitness trackers and activity monitors

[0679] Output: The exercise data is sent to the server.

[0680] Step 3:

[0681] The server preprocesses the received data using preprocessing means, specifically converting the data into a unified format (e.g., JSON), filling in missing data, and correcting outliers.

[0682] Input: Collected data (physical data, exercise data, lifestyle data, emotional data)

[0683] Output: Preprocessed data

[0684] Step 4:

[0685] The server inputs the preprocessed data into the generative AI model via a generating means, and generates a personalized nutrition plan by forming a prompt sentence and sending it to the generative AI model.

[0686] Input: Preprocessed data

[0687] Output: A personalized nutrition plan generated by the generative AI model

[0688] Step 5:

[0689] The server sends the generated nutrition plan to the smartphone app via the information providing means, and the user can check their own nutrition plan through the smartphone app.

[0690] Input: Generated nutrition plan

[0691] Output: Nutrition plan sent to smartphone app

[0692] Step 6:

[0693] Users follow the provided nutrition plan and then enter feedback into a smartphone app, including their satisfaction with the meal and any changes in their physical condition.

[0694] Input: User feedback

[0695] Output: Feedback stored in the smartphone app

[0696] Step 7:

[0697] The server receives feedback from the smartphone app and collects it using a feedback collection means, which is then used as reference data for the nutrition plan that is generated.

[0698] Input: Feedback from smartphone app

[0699] Output: Collected feedback data

[0700] Step 8:

[0701] Finally, the server uses learning methods to continuously update the generative AI model based on collected feedback and emotion data, improving the model's accuracy.

[0702] Input: Collected feedback and sentiment data

[0703] Output: Updated generative AI model

[0704] Through the above processing steps, the user can always obtain the latest individually optimized nutrition plan, enabling them to efficiently improve their performance and maintain their health.

[0705] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0706] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0707] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0708] [Third embodiment]

[0709] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0710] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0711] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0712] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0713] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0714] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0715] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0716] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0717] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0718] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0719] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0720] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0721] The present invention relates to a system for generating and providing personalized nutrition plans for athletes, the system including a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, and a learning means.

[0722] When an athlete begins using the system, the user (athlete) enters individual physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details) through the device. The device also connects to activity monitors and fitness trackers, automatically collecting daily exercise data (e.g., number of steps, heart rate) from these devices.

[0723] The collected data is sent from the terminal to a server, which then preprocesses the data. The preprocessing method converts the collected data into a unified format (e.g., JSON) and performs data cleansing, such as filling in missing data and correcting outliers.

[0724] The server then uses a generating means to input the preprocessed data into a generative AI model. The generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The nutrition plan generated by the generative AI model is then sent to the terminal via an information providing means and presented to the user. The presented nutrition plan includes breakfast, lunch, and dinner menus, as well as recommended nutritional supplements.

[0725] The user inputs feedback on the provided nutrition plan into the device. For example, information such as satisfaction with the diet or changes in physical condition is provided as feedback. This feedback is sent from the device to the server and collected by the feedback collection means. The server then uses the collected feedback as training data for the generated AI model through the learning means, and updates the model to continuously improve the accuracy of the model.

[0726] Specific examples

[0727] For example, suppose a user (athlete) inputs data that indicates he or she is 175 cm tall, weighs 70 kg, is 28 years old, and runs three times a week. Data collected from an activity tracker also indicates that he or she takes 10,000 steps per day and has an average heart rate of 120 bpm. This data is sent from the device to a server, where it is preprocessed and then input into a generative AI model. Based on this data, the generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake as a nutritional supplement. The generated nutrition plan is presented to the user via the device, and the user can enter feedback on the plan, which will be reflected in the next plan generation.

[0728] This allows athletes to receive individually optimized nutritional plans every day, enabling them to efficiently improve their performance and maintain their health.

[0729] The processing flow will be explained below.

[0730] Step 1:

[0731] User: Enters individual physical data (height, weight, age, etc.), training information (type of exercise, time, intensity, etc.), and lifestyle habits (sleep time, diet, etc.) into the application.

[0732] Step 2:

[0733] Device: Works with activity monitors and fitness trackers to automatically collect daily exercise data (number of steps, heart rate, etc.).

[0734] Step 3:

[0735] Terminal: Sends collected data to the server.

[0736] Step 4:

[0737] Server: Converts the received data into a unified format (e.g., JSON).

[0738] Step 5:

[0739] Server: Performs data cleansing, such as checking for outliers and filling in missing data.

[0740] Step 6:

[0741] Server: Inputs preprocessed data into a generative AI model to analyze various data points.

[0742] Step 7:

[0743] Server: A generative AI model generates a personalized nutrition plan based on the latest medical data.

[0744] Step 8:

[0745] Server: Sends the generated nutrition plan to the device.

[0746] Step 9:

[0747] On the device: Displays a nutrition plan (breakfast, lunch, and dinner menus and nutritional supplements) to the user.

[0748] Step 10:

[0749] User: Enter feedback on the nutrition plan provided.

[0750] Step 11:

[0751] Terminal: Sends the entered feedback to the server.

[0752] Step 12:

[0753] Server: Collects feedback and uses it to update the training data for the generative AI model.

[0754] Step 13:

[0755] Server: Use the updated model to generate the next nutrition plan.

[0756] This provides users with an optimal daily nutrition plan, helping them improve performance and maintain good health.

[0757] Example 1

[0758] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0759] Conventional nutrition plan providing systems have difficulty in providing personalized nutrition plans to individual users and in continuously improving plans based on user feedback. As a result, they have not been effective enough in maintaining users' health and improving their performance.

[0760] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0761] In this invention, the server includes a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, a learning means, a means for sending the nutrition plan generated by the generation means to a user terminal, and a means for updating the generative AI model based on the feedback collected by the feedback collection means, thereby providing a personalized nutrition plan to each user and continuously improving the model based on user feedback.

[0762] The "data collection means" is a means for collecting physical data, training information, lifestyle habit data from a user, and exercise data from an activity monitor or fitness tracker.

[0763] "Preprocessing means" refers to means for converting collected data into a unified format and performing data cleansing such as supplementing missing data and correcting outliers.

[0764] The "generative means" is a means for generating an individual nutrition plan based on preprocessed data using a generative AI model that has learned the latest medical data.

[0765] The "information providing means" is a means for transmitting the generated nutrition plan to the user terminal and presenting it to the user.

[0766] The "feedback collection means" is a means for collecting feedback from users (e.g., satisfaction with meals or changes in physical condition).

[0767] A "learning method" is a method for continuously updating the generative AI model based on collected feedback to improve the accuracy of the plan.

[0768] A "server" is a computer system for executing the data collection means, pre-processing means, generation means, information provision means, feedback collection means and learning means.

[0769] "User terminal" means a device used by a user to enter information, review generated nutrition plans, and enter feedback.

[0770] A "generative AI model" is a machine learning model that learns from collected data and the latest medical data to generate an individualized nutrition plan.

[0771] The present invention is a system for generating and providing personalized nutrition plans for athletes, the system including a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, and a learning means.

[0772] First, the user (athlete) uses a device to input physical data, training information, and lifestyle habits, such as height, weight, age, type of exercise, exercise time, exercise intensity, sleep time, and dietary details. The device then connects to an activity monitor or fitness tracker to automatically collect daily exercise data (e.g., number of steps and heart rate). This data is then sent to a server using a secure protocol (e.g., HTTPS).

[0773] Next, the server converts the collected data into a unified format (e.g., JSON) using a preprocessing means and performs data cleansing, such as filling in missing data and correcting outliers. The preprocessed data is input into a generative AI model using a generation means. This generative AI model is trained using deep learning algorithms and generates a personalized nutrition plan based on the latest medical data and collected user data.

[0774] The generated nutrition plan is sent from the server to the terminal via the information providing means. The terminal displays the generated nutrition plan to the user, and the user uses this plan as a reference to prepare daily meals. The nutrition plan specifically describes breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0775] The user inputs feedback about the provided nutrition plan into the device. This feedback includes satisfaction with the meal and changes in physical condition. The device sends this feedback to the server, where it is collected by the feedback collection means. The server has a learning means that continuously updates the generative AI model based on the collected feedback and improves the accuracy of the plan.

[0776] Specific examples

[0777] For example, if a user (athlete) enters the following data:

[0778] Height: 175cm

[0779] Weight: 70kg

[0780] Age: 28

[0781] Exercise: Running three times a week

[0782] Also, suppose the following data is collected from an activity tracker:

[0783] Daily steps: 10,000 steps

[0784] Average heart rate: 120 bpm

[0785] This data is sent from the device to a server, where it is pre-processed and then fed into a generative AI model, which generates a nutrition plan like this:

[0786] Breakfast: Oatmeal and blueberries

[0787] Lunch: Chicken salad

[0788] Dinner: Grilled salmon and roasted vegetables

[0789] Nutritional Supplement: Protein Shake

[0790] The generated nutrition plan is presented to the user via the terminal, and the user can input feedback about the plan (e.g., "The salad for lunch wasn't filling enough"), which will be reflected in the next plan generation.

[0791] Prompt Sentence Examples

[0792] "Generate the optimal nutrition plan for a 175cm, 70kg, 28-year-old athlete who runs three times a week, takes 10,000 steps per day, and has an average heart rate of 120 bpm. What meals should I have for breakfast, lunch, and dinner, along with recommended nutritional supplements?"

[0793] This allows the system to provide users with individually optimized nutritional plans on a daily basis, enabling them to efficiently improve performance and maintain health.

[0794] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0795] Step 1:

[0796] The user uses the device to input their physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details). The input data is saved on the device. This data becomes input data.

[0797] Step 2:

[0798] The device connects to activity monitors and fitness trackers via Bluetooth or Wi-Fi to automatically collect daily exercise data (e.g., steps taken, heart rate). The collected data is stored on the device. This data is also added to the input data mentioned above.

[0799] Step 3:

[0800] The device sends all collected data to the server using a secure protocol (e.g., HTTPS). Input data is transferred to the server and stored in a server-side database.

[0801] Step 4:

[0802] The server uses preprocessing means to convert the collected data into a unified format (e.g., JSON). Specifically, it parses the data, unifies the data structure, and resolves inconsistencies. Data that has undergone preprocessing is called preprocessed data.

[0803] Step 5:

[0804] The server then performs data cleansing on the preprocessed data. It adds missing data items and detects and corrects outliers. For example, if abnormally high heart rate data is included, it is corrected by referencing past data. This process generates cleansed data.

[0805] Step 6:

[0806] The server inputs the cleansed data into a generative AI model using a generation means, for example, by inputting the data into a generative AI model that uses a deep learning algorithm, and calculations begin.

[0807] Step 7:

[0808] The generative AI model generates a personalized nutrition plan based on the latest medical data and collected user data. The model calculates the nutrient balance of each meal and determines the optimal menu. The calculation results are output as nutrition plan data.

[0809] Step 8:

[0810] The server sends the generated nutrition plan data to the device via an information providing means. Specifically, the information is delivered to the device via push notifications or in-app notifications. The user can then check the nutrition plan on their device.

[0811] Step 9:

[0812] The user inputs feedback about the provided nutrition plan into the terminal. The feedback includes satisfaction with the meal, changes in physical condition, etc. This feedback data is stored in the terminal.

[0813] Step 10:

[0814] The terminal transmits the feedback data to the server using a secure protocol, and the transmitted feedback data is stored in a database on the server side.

[0815] Step 11:

[0816] The server continuously updates the generative AI model based on the collected feedback data. It uses learning methods to adjust the model parameters and improve the accuracy of future nutrition plans. This update generates an improved generative AI model.

[0817] By repeating the above steps, the system can continuously provide the user with an optimal nutrition plan.

[0818] (Application example 1)

[0819] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0820] Conventional nutrition plan delivery systems lack real-time feedback and individual personalization, making it difficult to efficiently provide nutrition plans tailored to the individual needs of athletes. In particular, they are unable to provide immediate and appropriate information on daily food selection, making it difficult to optimize athletes' performance and health.

[0821] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0822] In this invention, the server includes a data collection means, a pre-processing means, a generation means, and a means for displaying an individual nutrition plan in real time through a device such as smart glasses, thereby enabling athletes to receive the nutritional information they need for their daily food selection in real time and realizing the provision of an individually optimized nutrition plan.

[0823] "Data collection means" refers to equipment and software used to collect athletes' physical data, training information, and lifestyle data.

[0824] "Preprocessing means" refers to the process of converting collected data into a unified format and performing data cleansing, such as filling in missing data and correcting outliers.

[0825] "Generation" refers to the process of generating an individual nutrition plan based on collected and pre-processed data using a generative AI model trained on the latest medical data.

[0826] "Information delivery means" refers to the equipment or software used to provide the generated nutrition plan to the athlete.

[0827] "Feedback collection means" refers to equipment or software for collecting feedback information from athletes (e.g., satisfaction with meals, changes in physical condition, etc.).

[0828] "Learning" is the process of continuously updating the generative AI model using collected feedback information to improve its accuracy.

[0829] "Means for displaying individual nutrition plans in real time through devices such as smart glasses" refers to technology that uses smart glasses worn by athletes to display individually optimized nutrition plans and ingredient information in real time while they are shopping.

[0830] This invention is a system for providing personalized nutrition plans to athletes in real time. The system includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and a means for displaying the individual nutrition plan in real time through a device such as smart glasses. Each of these means will be described in detail below.

[0831] Data collection methods

[0832] The data collection method mainly involves collecting athletes' physical data (e.g., height, weight, age), training information (e.g., type, time, and intensity of exercise), and lifestyle habits (e.g., sleep duration, dietary content). This data may be entered directly by the user into the device, or may be collected automatically in conjunction with an activity monitor or fitness tracker. This allows for accurate and comprehensive data.

[0833] Pretreatment means

[0834] The collected data is first converted into a unified format (e.g., JSON) through pre-processing measures, followed by data cleansing, such as imputing missing data and correcting outliers, laying the foundation for the generative AI model to generate an accurate nutrition plan.

[0835] generation means

[0836] Once pre-processed, the data is passed to the generator, which uses a generative AI model trained on the latest medical data to generate a personalized nutrition plan. This plan includes breakfast, lunch, and dinner menus, as well as recommended nutritional supplements. The nutrition plans generated at this stage are optimized for the athlete's specific needs and goals.

[0837] Information provision means

[0838] The generated nutrition plan is sent to a device such as smart glasses via the information providing means. The user can view the nutrition plan and ingredient information displayed in real time on the smart glasses while shopping, making it easy to manage nutrition in everyday life.

[0839] Feedback collection methods

[0840] The user follows the provided nutrition plan and inputs feedback such as the results, satisfaction, changes in physical condition, etc. into the terminal. This feedback data is then sent to the server.

[0841] Learning tools

[0842] The collected feedback data is fed into the generative AI model by a learning method and is continuously used as training data for the model, which improves the accuracy of the generative AI model and enables the provision of more appropriate nutrition plans.

[0843] Specific examples

[0844] For example, imagine an athlete is shopping at a supermarket. As they approach the dairy section, the smart glasses display will show, "This week's recommended foods: Greek yogurt, low-fat milk," and then suggest the next step in their nutrition plan: "Refill your protein shake." This way, the athlete has real-time information they need at that moment.

[0845] Prompt Sentence Examples

[0846] "The user is an athlete with the following characteristics: height 175cm, weight 70kg, age 28, exercise frequency 3 times a week, steps taken 10,000 times, and average heart rate 120 bpm. Generate optimal breakfast, lunch, dinner, and nutritional supplement recommendations for this user."

[0847] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0848] Step 1:

[0849] The user uses the device to input their physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details), or the device connects to an activity monitor or fitness tracker to automatically collect exercise data (e.g., number of steps, heart rate). The input data is converted into a unified format such as JSON.

[0850] Input: Physical data, training information, lifestyle data

[0851] Output: Data converted into a unified format (e.g. JSON)

[0852] Specific operation: Obtains data from the terminal's input form or linked devices and converts it into JSON format.

[0853] Step 2:

[0854] The server uses preprocessing means to cleanse the collected data, impute missing data, and correct outliers, resulting in preprocessed data.

[0855] Input: Data converted into a unified format

[0856] Output: Cleansed preprocessed data

[0857] Specific operations: Reshaping data, estimating missing data, correcting outliers, etc.

[0858] Step 3:

[0859] The server uses a generating means to input the pre-processed data into a generative AI model to generate a personalized nutrition plan, which includes breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0860] Input: Preprocessed data

[0861] Output: Personalized nutrition plan

[0862] Specific operation: Data is input into the generative AI model, and calculations are performed to generate a nutrition plan.

[0863] Step 4:

[0864] The generated nutrition plan is sent to the smart glasses via the information providing means, and the user can check the nutrition plan and ingredient information displayed in real time on the smart glasses display.

[0865] Enter: personalized nutrition plan

[0866] Output: Nutrition plan displayed on smart glasses

[0867] What it does: Sends the nutrition plan to the smart glasses and displays it on the screen.

[0868] Step 5:

[0869] The user carries out the nutrition plan and inputs feedback such as the results, satisfaction, changes in physical condition, etc. into the terminal. This feedback data is sent to the server.

[0870] Input: Feedback on nutrition plan

[0871] Output: Feedback data sent to the server

[0872] Specific operation: Fill out the feedback form from the terminal and send it to the server.

[0873] Step 6:

[0874] The server uses the feedback collection means to incorporate the collected feedback into the generative AI model using the learning means, updating the model and improving its accuracy.

[0875] Input: Feedback data

[0876] Output: An updated generative AI model

[0877] Specific operation: Analyze the feedback data, incorporate it as training data for the generative AI model, and retrain the model.

[0878] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0879] The present invention relates to a system for generating and providing personalized nutrition plans for athletes, which includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and an emotion engine that recognizes the emotions of a user.

[0880] System Overview

[0881] First, when a user (athlete) starts using the system, they input their individual physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details) through their device. The device also connects to activity monitors and fitness trackers, automatically collecting daily exercise data (e.g., number of steps, heart rate) from these devices. In addition, an emotion engine acquires the user's emotional data.

[0882] Data collection and preprocessing

[0883] The collected data is sent from the device to a server, which then preprocesses it. The preprocessing means converts the collected data into a unified format (e.g., JSON) and performs data cleansing, such as filling in missing data and correcting outliers. Emotion data is also collected by the emotion engine and preprocessed in the same way.

[0884] Generate a nutrition plan

[0885] The server then uses a generation means to input the preprocessed data into a generative AI model. This generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The generative AI model takes into account the user's physical data, training information, lifestyle habits, and emotional data to generate an optimal nutrition plan for each individual user. The generated nutrition plan is sent to the terminal via an information provision means and presented to the user. The presented nutrition plan includes specific breakfast, lunch, and dinner menus, as well as recommended nutritional supplements.

[0886] Gathering feedback and updating the model

[0887] The user inputs feedback on the provided nutrition plan into the device. The feedback includes information such as satisfaction with the meal and changes in physical condition. It also includes emotional data acquired by the emotion engine. This feedback is sent from the device to the server and collected by the feedback collection means. The server then uses the collected feedback and emotional data as training data for the generative AI model using the learning means, and updates the model to continuously improve the accuracy of the model.

[0888] Specific examples

[0889] For example, suppose a user (athlete) inputs data that they are 175 cm tall, weigh 70 kg, are 28 years old, and run three times a week. An activity tracker collects data indicating that they take 10,000 steps per day and have an average heart rate of 120 bpm. Furthermore, the emotion engine determines that the user's emotion indicates "fatigue." All of this data is sent from the device to the server, where it is preprocessed and then input into the generative AI model. Based on this data, the generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake as a nutritional supplement. The generated nutrition plan is presented to the user via their device, and the user can enter feedback and emotion data about the plan, which will be reflected in the next plan generation.

[0890] This allows athletes to receive individually optimized nutritional plans every day, taking into account their emotional state, allowing them to efficiently improve their performance and maintain their health.

[0891] The processing flow will be explained below.

[0892] Step 1:

[0893] User: Enters individual physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details) into the application. The device also connects to activity monitors and fitness trackers to automatically collect daily exercise data (e.g., number of steps, heart rate).

[0894] Step 2:

[0895] Device: Collected physical data, training information, lifestyle data, and exercise data are sent to the server. At the same time, the emotion engine is used to obtain the user's emotion data, which is also sent to the server.

[0896] Step 3:

[0897] Server: Converts received data into a unified format (e.g., JSON). Emotion data is also converted into a unified format, and all data is managed centrally.

[0898] Step 4:

[0899] Server: Performs data cleansing, such as checking for abnormal values ​​and filling in missing data. For example, it detects abnormal heart rates and missing data, and corrects and fills them.

[0900] Step 5:

[0901] Server: Inputs pre-processed data into the generative AI model. This data includes physical data, training information, lifestyle data, exercise data, and emotional data.

[0902] Step 6:

[0903] Server: The generative AI model is trained on the latest medical data and analyzes these inputs to generate a personalized nutrition plan.

[0904] Step 7:

[0905] Server: Sends the generated nutrition plan to the device, including specific breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0906] Step 8:

[0907] Device: Displays a nutrition plan to the user, such as oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake for supplementation.

[0908] Step 9:

[0909] User: Enters feedback on the provided nutrition plan, including satisfaction with the meal, changes in physical condition, and emotional fluctuations.

[0910] Step 10:

[0911] Terminal: Sends the input feedback data and the emotion data contained therein to the server.

[0912] Step 11:

[0913] Server: Analyzes the collected feedback using the feedback collection means and uses it, including emotional data, as training data for the generative AI model.

[0914] Step 12:

[0915] Server: Uses learning methods to update the generative AI model with collected feedback and emotion data, allowing the model to continually improve its accuracy.

[0916] Step 13:

[0917] Server: Uses the updated generative AI model to further optimize future nutrition plans for the user.

[0918] This provides users with an optimal daily nutrition plan that takes into account their emotional state, helping them improve performance and maintain good health.

[0919] Example 2

[0920] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0921] Athletes need individually optimized nutrition plans to efficiently improve their performance and maintain their health. However, current systems take into account the user's exercise information and lifestyle data, but it is difficult to generate comprehensive plans that include emotional data. Furthermore, there is a lack of mechanisms for continuously improving plans based on feedback.

[0922] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0923] In this invention, the server includes a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, a learning means, and an emotion engine means, which makes it possible to generate a nutrition plan that takes into account the user's physical data, exercise information, lifestyle data, and emotion data, and to continuously improve the plan based on the user's feedback.

[0924] The "data collection means" is a means for collecting the user's individual physical data, exercise information, lifestyle habit data, and emotional data.

[0925] The "pre-processing means" is a means for carrying out pre-processing such as standardizing the format of collected data, supplementing missing data, and correcting abnormal values.

[0926] The "generative means" refers to the means for inputting pre-processed data into a generative AI model to generate an individualized nutrition plan.

[0927] The "information providing means" is a means for presenting the generated nutrition plan to the user.

[0928] The "feedback collection means" is a means for a user to input feedback and emotional data about the nutrition plan and collect that data.

[0929] The "learning method" is a method for training a generative AI model based on collected feedback and emotional data, and continuously improving the accuracy of the model.

[0930] An "emotion engine" is a means for recognizing and collecting user emotion data.

[0931] The "generative AI model" is an artificial intelligence model that learns based on the latest medical data and generates a nutrition plan taking into account the user's physical data, exercise information, lifestyle data, and emotional data.

[0932] The present invention relates to a system for generating and providing personalized nutrition plans for athletes, which includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and an emotion engine that recognizes the emotions of a user.

[0933] Users input their individual physical data (e.g., height, weight, age), exercise information (e.g., type, time, and intensity of exercise), and lifestyle habits (e.g., sleep time, dietary details) through the device. The device is connected to activity monitors and fitness trackers, and automatically collects daily exercise data (e.g., number of steps, heart rate) from these devices. In addition, an emotion engine acquires the user's emotional data.

[0934] The collected data is sent from the device to a server, which then preprocesses it. The preprocessing means converts the collected data into a unified format (e.g., JSON) and performs data cleansing, such as filling in missing data and correcting outliers. Emotion data is also collected by the emotion engine and preprocessed in the same way.

[0935] The server then uses a generation means to input the preprocessed data into a generative AI model. This generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The generative AI model takes into account the user's physical data, exercise information, lifestyle data, and emotional data to generate an optimal nutrition plan for the individual. The generated nutrition plan is sent to the terminal via an information provision means and presented to the user. The presented nutrition plan includes specific breakfast, lunch, and dinner menus, as well as recommended nutritional supplements.

[0936] The user inputs feedback on the provided nutrition plan into the device. The feedback includes information such as satisfaction with the meal and changes in physical condition. It also includes emotional data acquired by the emotion engine. The feedback is sent from the device to the server and collected by the feedback collection means. The server then uses the collected feedback and emotional data as training data for the generative AI model using the learning means, and updates the model to continuously improve the accuracy of the model.

[0937] As a concrete example, consider the case where a user inputs data such as a height of 175 cm, weight of 70 kg, age of 28, and running three times a week. The activity tracker collects data indicating 10,000 steps per day and an average heart rate of 120 bpm. The emotion engine also recognizes the user's emotion as "fatigue." This data is sent from the device to the server, preprocessed, and then input into the generative AI model. Based on this data, the generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, and grilled salmon and roasted vegetables for dinner, along with a protein shake as a nutritional supplement. The generated nutrition plan is presented to the user via the device, and the user can enter feedback and emotion data about the plan, which will be reflected in the next plan generation.

[0938] Examples of prompts include, "Generate a nutrition plan for an athlete who is 175 cm tall, weighs 70 kg, is 28 years old, and runs three times a week. The emotional data is 'fatigue'." and "Create the optimal nutrition plan based on the user's data (e.g., height: 175 cm, weight: 70 kg, age: 28 years old, exercise: runs three times a week). The emotional data is 'fatigue'."

[0939] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0940] Step 1:

[0941] Data entry and collection

[0942] Users enter their physical data (e.g., height 175 cm, weight 70 kg, age 28), exercise information (e.g., running three times a week), and lifestyle habits (e.g., sleep time, dietary content) through the device. The entered data is temporarily stored inside the device. In addition, the device connects to an activity monitor or fitness tracker to automatically collect daily exercise data (e.g., 10,000 steps, average heart rate 120 bpm). The emotion engine also obtains emotional data (e.g., "fatigue") from the user's facial expressions and input data.

[0943] Input: physical data, exercise information, lifestyle data, emotional data

[0944] Output: Multiple datasets stored locally on the device

[0945] Step 2:

[0946] Sending data

[0947] The device sends all collected data to a server, where it is encrypted and transmitted securely using a secure protocol.

[0948] Input: Multiple datasets stored internally on the device

[0949] Output: Data transferred to the server

[0950] Step 3:

[0951] Data Preprocessing

[0952] The server uses preprocessing tools to convert the received data into a unified format (e.g., JSON). It then performs data cleansing, such as filling in missing data and correcting outliers, to ensure data quality. Emotion data is also preprocessed in the same way.

[0953] Input: A large amount of data transferred to the server

[0954] Output: Cleansed data converted into a unified format

[0955] Step 4:

[0956] Generate a nutrition plan

[0957] The server inputs the preprocessed data into a generative AI model using a generation method. The generative AI model generates an individualized nutrition plan based on the user's data (physical data, exercise information, lifestyle data, and emotional data) while referencing the latest medical data. The generated plan includes specific breakfast, lunch, and dinner menus and recommended nutritional supplements.

[0958] Input: Data converted into a unified format and cleansed

[0959] Output: Generated personalized nutrition plan

[0960] Step 5:

[0961] Nutrition plan provided

[0962] The server transmits the generated nutrition plan to the terminal via the information providing means, and the nutrition plan is displayed on the user terminal and provided in a form that the user can easily access.

[0963] Input: Generated personalized nutrition plan

[0964] Output: Nutrition plan displayed on device

[0965] Step 6:

[0966] Enter your feedback

[0967] The user inputs feedback on the provided nutrition plan into the terminal. The feedback includes information such as satisfaction with the meal and changes in physical condition, as well as the latest emotional data obtained by the emotion engine.

[0968] Input: Feedback data from users

[0969] Output: Feedback saved on the device

[0970] Step 7:

[0971] Send Feedback

[0972] The terminal sends the collected feedback data to the server, which encrypts the data and transmits it securely to the server.

[0973] Input: Feedback data from users

[0974] Output: Feedback data transmitted to the server

[0975] Step 8:

[0976] Updating a Model

[0977] The server uses the feedback and emotion data collected by the feedback collection means as learning data for the generated AI model by the learning means, thereby improving the accuracy of the model and providing more accurate data when generating the next nutrition plan.

[0978] Input: Feedback data transferred to the server

[0979] Output: Updated generative AI model

[0980] As a result of the above, the present invention can continuously provide an optimal nutrition plan for each individual user and support the improvement of health and performance.

[0981] (Application example 2)

[0982] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0983] Today's athletes and health-conscious people strongly feel the need for individually optimized nutrition plans to achieve efficient training results. However, traditional systems cannot fully meet individual needs and rely on uniform nutritional guidelines, making it difficult to provide meals tailored to individual physical conditions, lifestyles, and emotional states. Furthermore, there is a lack of a system for quickly providing meals based on the generated nutrition plan. This creates challenges in putting personalized nutrition plans into practice in a timely manner.

[0984] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0985] In this invention, the server includes a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, a learning means, and a service provision means for providing meals based on a personalized nutrition plan. This enables the creation of an optimal nutrition plan based on individual physical information, training information, lifestyle habits, and emotional data, and the consistent provision of meals according to that plan.

[0986] The "data collection means" is a means for collecting the user's physical data, training information, lifestyle habits, and emotional data.

[0987] The "preprocessing means" is a means for converting collected data into a unified format and performing data cleansing such as supplementing missing data and correcting outliers.

[0988] "Generating means" means for generating an individualized nutrition plan using a generative AI model based on the pre-processed data.

[0989] The "information providing means" is a means for presenting the generated nutrition plan to the user.

[0990] The "feedback collection means" is a means for collecting feedback from the user regarding the nutrition plan and reflecting this in the next plan generation.

[0991] The "learning means" is a means of updating the generative AI model by using collected feedback and emotional data as training data.

[0992] The "service provision means" is a means for providing meals based on a personalized nutrition plan and delivering them to the user.

[0993] MODE FOR CARRYING OUT THE INVENTION

[0994] The present invention relates to a system for generating and providing personalized nutrition plans for athletes and health-conscious individuals, which includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and a service provision means.

[0995] System Overview

[0996] When a user uses the system, they enter their physical data (height, weight, age), training information (type of exercise, time, intensity), and lifestyle habits (sleep time, dietary details) through a smartphone app. The smartphone app also connects to fitness trackers and activity monitors to automatically collect daily exercise data (number of steps, heart rate). Emotional data is also collected by the emotion engine.

[0997] Data collection and preprocessing

[0998] The collected data is sent from the smartphone app to a server, where it is preprocessed. The preprocessing means converts the collected data into a unified format, complements missing data, and corrects outliers. Emotion data is also collected by the emotion engine and preprocessed in the same way.

[0999] Generate a nutrition plan

[1000] The server then uses a generation means to input the preprocessed data into a generative AI model. This generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The generated nutrition plan is sent to a smartphone app via an information provision means and presented to the user. The presented nutrition plan includes specific breakfast, lunch, and dinner menus and recommended nutritional supplements.

[1001] Gathering feedback and updating the model

[1002] Users input feedback about the provided nutrition plan into the smartphone app. The feedback includes information such as satisfaction with the meal and changes in physical condition. The feedback also includes emotional data acquired by the emotion engine. This feedback is sent from the smartphone app to the server, and the data is collected by the feedback collection means. Based on the collected feedback and emotional data, the server uses the learning means to update the generative AI model and continuously improve the accuracy of the model.

[1003] Specific examples

[1004] For example, if the user enters the following parameters:

[1005] Height: 175cm

[1006] Weight: 70kg

[1007] Age: 28

[1008] Regular exercise: Running three times a week

[1009] Emotional state: Fatigue

[1010] Based on this data, the following prompt is input to the generative AI model:

[1011] Generate a meal plan for an athlete: {height: 175, weight: 70, age: 28, training_info: {frequency: 3, type: 'running'}, lifestyle: {hours of sleep: 8, diet: 'balanced diet'}, emotion_data: 'fatigue'}

[1012] The generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake as a nutritional supplement. The plan is presented to the user via a smartphone app, and the user can enter feedback on the plan.

[1013] As a result, users can efficiently obtain a personalized nutrition plan and be provided with appropriate meals quickly, thereby improving performance and maintaining health.

[1014] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1015] Step 1:

[1016] Using a smartphone app, users input physical data such as height, weight, and age, as well as training information, lifestyle habits, and emotional data, which are then stored in the app according to the input format.

[1017] Input: physical data, training information, lifestyle data, emotional data

[1018] Output: The entered data is saved in the app.

[1019] Step 2:

[1020] In addition to data entered by the user, the smartphone app works with fitness trackers and activity monitors to automatically collect daily exercise data (e.g., number of steps, heart rate), which is then periodically sent to a server.

[1021] Input: Exercise data from fitness trackers and activity monitors

[1022] Output: The exercise data is sent to the server.

[1023] Step 3:

[1024] The server preprocesses the received data using preprocessing means, specifically converting the data into a unified format (e.g., JSON), filling in missing data, and correcting outliers.

[1025] Input: Collected data (physical data, exercise data, lifestyle data, emotional data)

[1026] Output: Preprocessed data

[1027] Step 4:

[1028] The server inputs the preprocessed data into the generative AI model via a generating means, and generates a personalized nutrition plan by forming a prompt sentence and sending it to the generative AI model.

[1029] Input: Preprocessed data

[1030] Output: A personalized nutrition plan generated by the generative AI model

[1031] Step 5:

[1032] The server sends the generated nutrition plan to the smartphone app via the information providing means, and the user can check their own nutrition plan through the smartphone app.

[1033] Input: Generated nutrition plan

[1034] Output: Nutrition plan sent to smartphone app

[1035] Step 6:

[1036] Users follow the provided nutrition plan and then enter feedback into a smartphone app, including their satisfaction with the meal and any changes in their physical condition.

[1037] Input: User feedback

[1038] Output: Feedback stored in the smartphone app

[1039] Step 7:

[1040] The server receives feedback from the smartphone app and collects it using a feedback collection means, which is then used as reference data for the nutrition plan that is generated.

[1041] Input: Feedback from smartphone app

[1042] Output: Collected feedback data

[1043] Step 8:

[1044] Finally, the server uses learning methods to continuously update the generative AI model based on collected feedback and emotion data, improving the model's accuracy.

[1045] Input: Collected feedback and sentiment data

[1046] Output: Updated generative AI model

[1047] Through the above processing steps, the user can always obtain the latest individually optimized nutrition plan, enabling them to efficiently improve their performance and maintain their health.

[1048] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1049] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1050] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1051] [Fourth embodiment]

[1052] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1053] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1054] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1055] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1056] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1057] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1058] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1059] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1060] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1061] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1062] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1063] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1064] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1065] The present invention relates to a system for generating and providing personalized nutrition plans for athletes, the system including a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, and a learning means.

[1066] When an athlete begins using the system, the user (athlete) enters individual physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details) through the device. The device also connects to activity monitors and fitness trackers, automatically collecting daily exercise data (e.g., number of steps, heart rate) from these devices.

[1067] The collected data is sent from the terminal to a server, which then preprocesses the data. The preprocessing method converts the collected data into a unified format (e.g., JSON) and performs data cleansing, such as filling in missing data and correcting outliers.

[1068] The server then uses a generating means to input the preprocessed data into a generative AI model. The generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The nutrition plan generated by the generative AI model is then sent to the terminal via an information providing means and presented to the user. The presented nutrition plan includes breakfast, lunch, and dinner menus, as well as recommended nutritional supplements.

[1069] The user inputs feedback on the provided nutrition plan into the device. For example, information such as satisfaction with the diet or changes in physical condition is provided as feedback. This feedback is sent from the device to the server and collected by the feedback collection means. The server then uses the collected feedback as training data for the generated AI model through the learning means, and updates the model to continuously improve the accuracy of the model.

[1070] Specific examples

[1071] For example, suppose a user (athlete) inputs data that indicates he or she is 175 cm tall, weighs 70 kg, is 28 years old, and runs three times a week. Data collected from an activity tracker also indicates that he or she takes 10,000 steps per day and has an average heart rate of 120 bpm. This data is sent from the device to a server, where it is preprocessed and then input into a generative AI model. Based on this data, the generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake as a nutritional supplement. The generated nutrition plan is presented to the user via the device, and the user can enter feedback on the plan, which will be reflected in the next plan generation.

[1072] This allows athletes to receive individually optimized nutritional plans every day, enabling them to efficiently improve their performance and maintain their health.

[1073] The processing flow will be explained below.

[1074] Step 1:

[1075] User: Enters individual physical data (height, weight, age, etc.), training information (type of exercise, time, intensity, etc.), and lifestyle habits (sleep time, diet, etc.) into the application.

[1076] Step 2:

[1077] Device: Works with activity monitors and fitness trackers to automatically collect daily exercise data (number of steps, heart rate, etc.).

[1078] Step 3:

[1079] Terminal: Sends collected data to the server.

[1080] Step 4:

[1081] Server: Converts the received data into a unified format (e.g., JSON).

[1082] Step 5:

[1083] Server: Performs data cleansing, such as checking for outliers and filling in missing data.

[1084] Step 6:

[1085] Server: Inputs preprocessed data into a generative AI model to analyze various data points.

[1086] Step 7:

[1087] Server: A generative AI model generates a personalized nutrition plan based on the latest medical data.

[1088] Step 8:

[1089] Server: Sends the generated nutrition plan to the device.

[1090] Step 9:

[1091] On the device: Displays a nutrition plan (breakfast, lunch, and dinner menus and nutritional supplements) to the user.

[1092] Step 10:

[1093] User: Enter feedback on the nutrition plan provided.

[1094] Step 11:

[1095] Terminal: Sends the entered feedback to the server.

[1096] Step 12:

[1097] Server: Collects feedback and uses it to update the training data for the generative AI model.

[1098] Step 13:

[1099] Server: Use the updated model to generate the next nutrition plan.

[1100] This provides users with an optimal daily nutrition plan, helping them improve performance and maintain good health.

[1101] Example 1

[1102] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1103] Conventional nutrition plan providing systems have difficulty in providing personalized nutrition plans to individual users and in continuously improving plans based on user feedback. As a result, they have not been effective enough in maintaining users' health and improving their performance.

[1104] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1105] In this invention, the server includes a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, a learning means, a means for sending the nutrition plan generated by the generation means to a user terminal, and a means for updating the generative AI model based on the feedback collected by the feedback collection means, thereby providing a personalized nutrition plan to each user and continuously improving the model based on user feedback.

[1106] The "data collection means" is a means for collecting physical data, training information, lifestyle habit data from a user, and exercise data from an activity monitor or fitness tracker.

[1107] "Preprocessing means" refers to means for converting collected data into a unified format and performing data cleansing such as supplementing missing data and correcting outliers.

[1108] The "generative means" is a means for generating an individual nutrition plan based on preprocessed data using a generative AI model that has learned the latest medical data.

[1109] The "information providing means" is a means for transmitting the generated nutrition plan to the user terminal and presenting it to the user.

[1110] The "feedback collection means" is a means for collecting feedback from users (e.g., satisfaction with meals or changes in physical condition).

[1111] A "learning method" is a method for continuously updating the generative AI model based on collected feedback to improve the accuracy of the plan.

[1112] A "server" is a computer system for executing the data collection means, pre-processing means, generation means, information provision means, feedback collection means and learning means.

[1113] "User terminal" means a device used by a user to enter information, review generated nutrition plans, and enter feedback.

[1114] A "generative AI model" is a machine learning model that learns from collected data and the latest medical data to generate an individualized nutrition plan.

[1115] The present invention is a system for generating and providing personalized nutrition plans for athletes, the system including a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, and a learning means.

[1116] First, the user (athlete) uses a device to input physical data, training information, and lifestyle habits, such as height, weight, age, type of exercise, exercise time, exercise intensity, sleep time, and dietary details. The device then connects to an activity monitor or fitness tracker to automatically collect daily exercise data (e.g., number of steps and heart rate). This data is then sent to a server using a secure protocol (e.g., HTTPS).

[1117] Next, the server converts the collected data into a unified format (e.g., JSON) using a preprocessing means and performs data cleansing, such as filling in missing data and correcting outliers. The preprocessed data is input into a generative AI model using a generation means. This generative AI model is trained using deep learning algorithms and generates a personalized nutrition plan based on the latest medical data and collected user data.

[1118] The generated nutrition plan is sent from the server to the terminal via the information providing means. The terminal displays the generated nutrition plan to the user, and the user uses this plan as a reference to prepare daily meals. The nutrition plan specifically describes breakfast, lunch, and dinner menus and recommended nutritional supplements.

[1119] The user inputs feedback about the provided nutrition plan into the device. This feedback includes satisfaction with the meal and changes in physical condition. The device sends this feedback to the server, where it is collected by the feedback collection means. The server has a learning means that continuously updates the generative AI model based on the collected feedback and improves the accuracy of the plan.

[1120] Specific examples

[1121] For example, if a user (athlete) enters the following data:

[1122] Height: 175cm

[1123] Weight: 70kg

[1124] Age: 28

[1125] Exercise: Running three times a week

[1126] Also, suppose the following data is collected from an activity tracker:

[1127] Daily steps: 10,000 steps

[1128] Average heart rate: 120 bpm

[1129] This data is sent from the device to a server, where it is pre-processed and then fed into a generative AI model, which generates a nutrition plan like this:

[1130] Breakfast: Oatmeal and blueberries

[1131] Lunch: Chicken salad

[1132] Dinner: Grilled salmon and roasted vegetables

[1133] Nutritional Supplement: Protein Shake

[1134] The generated nutrition plan is presented to the user via the terminal, and the user can input feedback about the plan (e.g., "The salad for lunch wasn't filling enough"), which will be reflected in the next plan generation.

[1135] Prompt Sentence Examples

[1136] "Generate the optimal nutrition plan for a 175cm, 70kg, 28-year-old athlete who runs three times a week, takes 10,000 steps per day, and has an average heart rate of 120 bpm. What meals should I have for breakfast, lunch, and dinner, along with recommended nutritional supplements?"

[1137] This allows the system to provide users with individually optimized nutritional plans on a daily basis, enabling them to efficiently improve performance and maintain health.

[1138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1139] Step 1:

[1140] The user uses the device to input their physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details). The input data is saved on the device. This data becomes input data.

[1141] Step 2:

[1142] The device connects to activity monitors and fitness trackers via Bluetooth or Wi-Fi to automatically collect daily exercise data (e.g., steps taken, heart rate). The collected data is stored on the device. This data is also added to the input data mentioned above.

[1143] Step 3:

[1144] The device sends all collected data to the server using a secure protocol (e.g., HTTPS). Input data is transferred to the server and stored in a server-side database.

[1145] Step 4:

[1146] The server uses preprocessing means to convert the collected data into a unified format (e.g., JSON). Specifically, it parses the data, unifies the data structure, and resolves inconsistencies. Data that has undergone preprocessing is called preprocessed data.

[1147] Step 5:

[1148] The server then performs data cleansing on the preprocessed data. It adds missing data items and detects and corrects outliers. For example, if abnormally high heart rate data is included, it is corrected by referencing past data. This process generates cleansed data.

[1149] Step 6:

[1150] The server inputs the cleansed data into a generative AI model using a generation means, for example, by inputting the data into a generative AI model that uses a deep learning algorithm, and calculations begin.

[1151] Step 7:

[1152] The generative AI model generates a personalized nutrition plan based on the latest medical data and collected user data. The model calculates the nutrient balance of each meal and determines the optimal menu. The calculation results are output as nutrition plan data.

[1153] Step 8:

[1154] The server sends the generated nutrition plan data to the device via an information providing means. Specifically, the information is delivered to the device via push notifications or in-app notifications. The user can then check the nutrition plan on their device.

[1155] Step 9:

[1156] The user inputs feedback about the provided nutrition plan into the terminal. The feedback includes satisfaction with the meal, changes in physical condition, etc. This feedback data is stored in the terminal.

[1157] Step 10:

[1158] The terminal transmits the feedback data to the server using a secure protocol, and the transmitted feedback data is stored in a database on the server side.

[1159] Step 11:

[1160] The server continuously updates the generative AI model based on the collected feedback data. It uses learning methods to adjust the model parameters and improve the accuracy of future nutrition plans. This update generates an improved generative AI model.

[1161] By repeating the above steps, the system can continuously provide the user with an optimal nutrition plan.

[1162] (Application example 1)

[1163] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1164] Conventional nutrition plan delivery systems lack real-time feedback and individual personalization, making it difficult to efficiently provide nutrition plans tailored to the individual needs of athletes. In particular, they are unable to provide immediate and appropriate information on daily food selection, making it difficult to optimize athletes' performance and health.

[1165] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1166] In this invention, the server includes a data collection means, a pre-processing means, a generation means, and a means for displaying an individual nutrition plan in real time through a device such as smart glasses, thereby enabling athletes to receive the nutritional information they need for their daily food selection in real time and realizing the provision of an individually optimized nutrition plan.

[1167] "Data collection means" refers to equipment and software used to collect athletes' physical data, training information, and lifestyle data.

[1168] "Preprocessing means" refers to the process of converting collected data into a unified format and performing data cleansing, such as filling in missing data and correcting outliers.

[1169] "Generation" refers to the process of generating an individual nutrition plan based on collected and pre-processed data using a generative AI model trained on the latest medical data.

[1170] "Information delivery means" refers to the equipment or software used to provide the generated nutrition plan to the athlete.

[1171] "Feedback collection means" refers to equipment or software for collecting feedback information from athletes (e.g., satisfaction with meals, changes in physical condition, etc.).

[1172] "Learning" is the process of continuously updating the generative AI model using collected feedback information to improve its accuracy.

[1173] "Means for displaying individual nutrition plans in real time through devices such as smart glasses" refers to technology that uses smart glasses worn by athletes to display individually optimized nutrition plans and ingredient information in real time while they are shopping.

[1174] This invention is a system for providing personalized nutrition plans to athletes in real time. The system includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and a means for displaying the individual nutrition plan in real time through a device such as smart glasses. Each of these means will be described in detail below.

[1175] Data collection methods

[1176] The data collection method mainly involves collecting athletes' physical data (e.g., height, weight, age), training information (e.g., type, time, and intensity of exercise), and lifestyle habits (e.g., sleep duration, dietary content). This data may be entered directly by the user into the device, or may be collected automatically in conjunction with an activity monitor or fitness tracker. This allows for accurate and comprehensive data.

[1177] Pretreatment means

[1178] The collected data is first converted into a unified format (e.g., JSON) through pre-processing measures, followed by data cleansing, such as imputing missing data and correcting outliers, laying the foundation for the generative AI model to generate an accurate nutrition plan.

[1179] generation means

[1180] Once pre-processed, the data is passed to the generator, which uses a generative AI model trained on the latest medical data to generate a personalized nutrition plan. This plan includes breakfast, lunch, and dinner menus, as well as recommended nutritional supplements. The nutrition plans generated at this stage are optimized for the athlete's specific needs and goals.

[1181] Information provision means

[1182] The generated nutrition plan is sent to a device such as smart glasses via the information providing means. The user can view the nutrition plan and ingredient information displayed in real time on the smart glasses while shopping, making it easy to manage nutrition in everyday life.

[1183] Feedback collection methods

[1184] The user follows the provided nutrition plan and inputs feedback such as the results, satisfaction, changes in physical condition, etc. into the terminal. This feedback data is then sent to the server.

[1185] Learning tools

[1186] The collected feedback data is fed into the generative AI model by a learning method and is continuously used as training data for the model, which improves the accuracy of the generative AI model and enables the provision of more appropriate nutrition plans.

[1187] Specific examples

[1188] For example, imagine an athlete is shopping at a supermarket. As they approach the dairy section, the smart glasses display will show, "This week's recommended foods: Greek yogurt, low-fat milk," and then suggest the next step in their nutrition plan: "Refill your protein shake." This way, the athlete has real-time information they need at that moment.

[1189] Prompt Sentence Examples

[1190] "The user is an athlete with the following characteristics: height 175cm, weight 70kg, age 28, exercise frequency 3 times a week, steps taken 10,000 times, and average heart rate 120 bpm. Generate optimal breakfast, lunch, dinner, and nutritional supplement recommendations for this user."

[1191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1192] Step 1:

[1193] The user uses the device to input their physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details), or the device connects to an activity monitor or fitness tracker to automatically collect exercise data (e.g., number of steps, heart rate). The input data is converted into a unified format such as JSON.

[1194] Input: Physical data, training information, lifestyle data

[1195] Output: Data converted into a unified format (e.g. JSON)

[1196] Specific operation: Obtains data from the terminal's input form or linked devices and converts it into JSON format.

[1197] Step 2:

[1198] The server uses preprocessing means to cleanse the collected data, impute missing data, and correct outliers, resulting in preprocessed data.

[1199] Input: Data converted into a unified format

[1200] Output: Cleansed preprocessed data

[1201] Specific operations: Reshaping data, estimating missing data, correcting outliers, etc.

[1202] Step 3:

[1203] The server uses a generating means to input the pre-processed data into a generative AI model to generate a personalized nutrition plan, which includes breakfast, lunch, and dinner menus and recommended nutritional supplements.

[1204] Input: Preprocessed data

[1205] Output: Personalized nutrition plan

[1206] Specific operation: Data is input into the generative AI model, and calculations are performed to generate a nutrition plan.

[1207] Step 4:

[1208] The generated nutrition plan is sent to the smart glasses via the information providing means, and the user can check the nutrition plan and ingredient information displayed in real time on the smart glasses display.

[1209] Enter: personalized nutrition plan

[1210] Output: Nutrition plan displayed on smart glasses

[1211] What it does: Sends the nutrition plan to the smart glasses and displays it on the screen.

[1212] Step 5:

[1213] The user carries out the nutrition plan and inputs feedback such as the results, satisfaction, changes in physical condition, etc. into the terminal. This feedback data is sent to the server.

[1214] Input: Feedback on nutrition plan

[1215] Output: Feedback data sent to the server

[1216] Specific operation: Fill out the feedback form from the terminal and send it to the server.

[1217] Step 6:

[1218] The server uses the feedback collection means to incorporate the collected feedback into the generative AI model using the learning means, updating the model and improving its accuracy.

[1219] Input: Feedback data

[1220] Output: An updated generative AI model

[1221] Specific operation: Analyze the feedback data, incorporate it as training data for the generative AI model, and retrain the model.

[1222] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1223] The present invention relates to a system for generating and providing personalized nutrition plans for athletes, which includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and an emotion engine that recognizes the emotions of a user.

[1224] System Overview

[1225] First, when a user (athlete) starts using the system, they input their individual physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details) through their device. The device also connects to activity monitors and fitness trackers, automatically collecting daily exercise data (e.g., number of steps, heart rate) from these devices. In addition, an emotion engine acquires the user's emotional data.

[1226] Data collection and preprocessing

[1227] The collected data is sent from the device to a server, which then preprocesses it. The preprocessing means converts the collected data into a unified format (e.g., JSON) and performs data cleansing, such as filling in missing data and correcting outliers. Emotion data is also collected by the emotion engine and preprocessed in the same way.

[1228] Generate a nutrition plan

[1229] The server then uses a generation means to input the preprocessed data into a generative AI model. This generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The generative AI model takes into account the user's physical data, training information, lifestyle habits, and emotional data to generate an optimal nutrition plan for each individual user. The generated nutrition plan is sent to the terminal via an information provision means and presented to the user. The presented nutrition plan includes specific breakfast, lunch, and dinner menus, as well as recommended nutritional supplements.

[1230] Gathering feedback and updating the model

[1231] The user inputs feedback on the provided nutrition plan into the device. The feedback includes information such as satisfaction with the meal and changes in physical condition. It also includes emotional data acquired by the emotion engine. This feedback is sent from the device to the server and collected by the feedback collection means. The server then uses the collected feedback and emotional data as training data for the generative AI model using the learning means, and updates the model to continuously improve the accuracy of the model.

[1232] Specific examples

[1233] For example, suppose a user (athlete) inputs data that they are 175 cm tall, weigh 70 kg, are 28 years old, and run three times a week. An activity tracker collects data indicating that they take 10,000 steps per day and have an average heart rate of 120 bpm. Furthermore, the emotion engine determines that the user's emotion indicates "fatigue." All of this data is sent from the device to the server, where it is preprocessed and then input into the generative AI model. Based on this data, the generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake as a nutritional supplement. The generated nutrition plan is presented to the user via their device, and the user can enter feedback and emotion data about the plan, which will be reflected in the next plan generation.

[1234] This allows athletes to receive individually optimized nutritional plans every day, taking into account their emotional state, allowing them to efficiently improve their performance and maintain their health.

[1235] The processing flow will be explained below.

[1236] Step 1:

[1237] User: Enters individual physical data (e.g., height, weight, age), training information (e.g., type of exercise, time, intensity), and lifestyle habits (e.g., sleep time, dietary details) into the application. The device also connects to activity monitors and fitness trackers to automatically collect daily exercise data (e.g., number of steps, heart rate).

[1238] Step 2:

[1239] Device: Collected physical data, training information, lifestyle data, and exercise data are sent to the server. At the same time, the emotion engine is used to obtain the user's emotion data, which is also sent to the server.

[1240] Step 3:

[1241] Server: Converts received data into a unified format (e.g., JSON). Emotion data is also converted into a unified format, and all data is managed centrally.

[1242] Step 4:

[1243] Server: Performs data cleansing, such as checking for abnormal values ​​and filling in missing data. For example, it detects abnormal heart rates and missing data, and corrects and fills them.

[1244] Step 5:

[1245] Server: Inputs pre-processed data into the generative AI model. This data includes physical data, training information, lifestyle data, exercise data, and emotional data.

[1246] Step 6:

[1247] Server: The generative AI model is trained on the latest medical data and analyzes these inputs to generate a personalized nutrition plan.

[1248] Step 7:

[1249] Server: Sends the generated nutrition plan to the device, including specific breakfast, lunch, and dinner menus and recommended nutritional supplements.

[1250] Step 8:

[1251] Device: Displays a nutrition plan to the user, such as oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake for supplementation.

[1252] Step 9:

[1253] User: Enters feedback on the provided nutrition plan, including satisfaction with the meal, changes in physical condition, and emotional fluctuations.

[1254] Step 10:

[1255] Terminal: Sends the input feedback data and the emotion data contained therein to the server.

[1256] Step 11:

[1257] Server: Analyzes the collected feedback using the feedback collection means and uses it, including emotional data, as training data for the generative AI model.

[1258] Step 12:

[1259] Server: Uses learning methods to update the generative AI model with collected feedback and emotion data, allowing the model to continually improve its accuracy.

[1260] Step 13:

[1261] Server: Uses the updated generative AI model to further optimize future nutrition plans for the user.

[1262] This provides users with an optimal daily nutrition plan that takes into account their emotional state, helping them improve performance and maintain good health.

[1263] Example 2

[1264] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1265] Athletes need individually optimized nutrition plans to efficiently improve their performance and maintain their health. However, current systems take into account the user's exercise information and lifestyle data, but it is difficult to generate comprehensive plans that include emotional data. Furthermore, there is a lack of mechanisms for continuously improving plans based on feedback.

[1266] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1267] In this invention, the server includes a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, a learning means, and an emotion engine means, which makes it possible to generate a nutrition plan that takes into account the user's physical data, exercise information, lifestyle data, and emotion data, and to continuously improve the plan based on the user's feedback.

[1268] The "data collection means" is a means for collecting the user's individual physical data, exercise information, lifestyle habit data, and emotional data.

[1269] The "pre-processing means" is a means for carrying out pre-processing such as standardizing the format of collected data, supplementing missing data, and correcting abnormal values.

[1270] The "generative means" refers to the means for inputting pre-processed data into a generative AI model to generate an individualized nutrition plan.

[1271] The "information providing means" is a means for presenting the generated nutrition plan to the user.

[1272] The "feedback collection means" is a means for a user to input feedback and emotional data about the nutrition plan and collect that data.

[1273] The "learning method" is a method for training a generative AI model based on collected feedback and emotional data, and continuously improving the accuracy of the model.

[1274] An "emotion engine" is a means for recognizing and collecting user emotion data.

[1275] The "generative AI model" is an artificial intelligence model that learns based on the latest medical data and generates a nutrition plan taking into account the user's physical data, exercise information, lifestyle data, and emotional data.

[1276] The present invention relates to a system for generating and providing personalized nutrition plans for athletes, which includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and an emotion engine that recognizes the emotions of a user.

[1277] Users input their individual physical data (e.g., height, weight, age), exercise information (e.g., type, time, and intensity of exercise), and lifestyle habits (e.g., sleep time, dietary details) through the device. The device is connected to activity monitors and fitness trackers, and automatically collects daily exercise data (e.g., number of steps, heart rate) from these devices. In addition, an emotion engine acquires the user's emotional data.

[1278] The collected data is sent from the device to a server, which then preprocesses it. The preprocessing means converts the collected data into a unified format (e.g., JSON) and performs data cleansing, such as filling in missing data and correcting outliers. Emotion data is also collected by the emotion engine and preprocessed in the same way.

[1279] The server then uses a generation means to input the preprocessed data into a generative AI model. This generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The generative AI model takes into account the user's physical data, exercise information, lifestyle data, and emotional data to generate an optimal nutrition plan for the individual. The generated nutrition plan is sent to the terminal via an information provision means and presented to the user. The presented nutrition plan includes specific breakfast, lunch, and dinner menus, as well as recommended nutritional supplements.

[1280] The user inputs feedback on the provided nutrition plan into the device. The feedback includes information such as satisfaction with the meal and changes in physical condition. It also includes emotional data acquired by the emotion engine. The feedback is sent from the device to the server and collected by the feedback collection means. The server then uses the collected feedback and emotional data as training data for the generative AI model using the learning means, and updates the model to continuously improve the accuracy of the model.

[1281] As a concrete example, consider the case where a user inputs data such as a height of 175 cm, weight of 70 kg, age of 28, and running three times a week. The activity tracker collects data indicating 10,000 steps per day and an average heart rate of 120 bpm. The emotion engine also recognizes the user's emotion as "fatigue." This data is sent from the device to the server, preprocessed, and then input into the generative AI model. Based on this data, the generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, and grilled salmon and roasted vegetables for dinner, along with a protein shake as a nutritional supplement. The generated nutrition plan is presented to the user via the device, and the user can enter feedback and emotion data about the plan, which will be reflected in the next plan generation.

[1282] Examples of prompts include, "Generate a nutrition plan for an athlete who is 175 cm tall, weighs 70 kg, is 28 years old, and runs three times a week. The emotional data is 'fatigue'." and "Create the optimal nutrition plan based on the user's data (e.g., height: 175 cm, weight: 70 kg, age: 28 years old, exercise: runs three times a week). The emotional data is 'fatigue'."

[1283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1284] Step 1:

[1285] Data entry and collection

[1286] Users enter their physical data (e.g., height 175 cm, weight 70 kg, age 28), exercise information (e.g., running three times a week), and lifestyle habits (e.g., sleep time, dietary content) through the device. The entered data is temporarily stored inside the device. In addition, the device connects to an activity monitor or fitness tracker to automatically collect daily exercise data (e.g., 10,000 steps, average heart rate 120 bpm). The emotion engine also obtains emotional data (e.g., "fatigue") from the user's facial expressions and input data.

[1287] Input: physical data, exercise information, lifestyle data, emotional data

[1288] Output: Multiple datasets stored locally on the device

[1289] Step 2:

[1290] Sending data

[1291] The device sends all collected data to a server, where it is encrypted and transmitted securely using a secure protocol.

[1292] Input: Multiple datasets stored internally on the device

[1293] Output: Data transferred to the server

[1294] Step 3:

[1295] Data Preprocessing

[1296] The server uses preprocessing tools to convert the received data into a unified format (e.g., JSON). It then performs data cleansing, such as filling in missing data and correcting outliers, to ensure data quality. Emotion data is also preprocessed in the same way.

[1297] Input: A large amount of data transferred to the server

[1298] Output: Cleansed data converted into a unified format

[1299] Step 4:

[1300] Generate a nutrition plan

[1301] The server inputs the preprocessed data into a generative AI model using a generation method. The generative AI model generates an individualized nutrition plan based on the user's data (physical data, exercise information, lifestyle data, and emotional data) while referencing the latest medical data. The generated plan includes specific breakfast, lunch, and dinner menus and recommended nutritional supplements.

[1302] Input: Data converted into a unified format and cleansed

[1303] Output: Generated personalized nutrition plan

[1304] Step 5:

[1305] Nutrition plan provided

[1306] The server transmits the generated nutrition plan to the terminal via the information providing means, and the nutrition plan is displayed on the user terminal and provided in a form that the user can easily access.

[1307] Input: Generated personalized nutrition plan

[1308] Output: Nutrition plan displayed on device

[1309] Step 6:

[1310] Enter your feedback

[1311] The user inputs feedback on the provided nutrition plan into the terminal. The feedback includes information such as satisfaction with the meal and changes in physical condition, as well as the latest emotional data obtained by the emotion engine.

[1312] Input: Feedback data from users

[1313] Output: Feedback saved on the device

[1314] Step 7:

[1315] Send Feedback

[1316] The terminal sends the collected feedback data to the server, which encrypts the data and transmits it securely to the server.

[1317] Input: Feedback data from users

[1318] Output: Feedback data transmitted to the server

[1319] Step 8:

[1320] Updating a Model

[1321] The server uses the feedback and emotion data collected by the feedback collection means as learning data for the generated AI model by the learning means, thereby improving the accuracy of the model and providing more accurate data when generating the next nutrition plan.

[1322] Input: Feedback data transferred to the server

[1323] Output: Updated generative AI model

[1324] As a result of the above, the present invention can continuously provide an optimal nutrition plan for each individual user and support the improvement of health and performance.

[1325] (Application example 2)

[1326] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1327] Today's athletes and health-conscious people strongly feel the need for individually optimized nutrition plans to achieve efficient training results. However, traditional systems cannot fully meet individual needs and rely on uniform nutritional guidelines, making it difficult to provide meals tailored to individual physical conditions, lifestyles, and emotional states. Furthermore, there is a lack of a system for quickly providing meals based on the generated nutrition plan. This creates challenges in putting personalized nutrition plans into practice in a timely manner.

[1328] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1329] In this invention, the server includes a data collection means, a preprocessing means, a generation means, an information provision means, a feedback collection means, a learning means, and a service provision means for providing meals based on a personalized nutrition plan. This enables the creation of an optimal nutrition plan based on individual physical information, training information, lifestyle habits, and emotional data, and the consistent provision of meals according to that plan.

[1330] The "data collection means" is a means for collecting the user's physical data, training information, lifestyle habits, and emotional data.

[1331] The "preprocessing means" is a means for converting collected data into a unified format and performing data cleansing such as supplementing missing data and correcting outliers.

[1332] "Generating means" means for generating an individualized nutrition plan using a generative AI model based on the pre-processed data.

[1333] The "information providing means" is a means for presenting the generated nutrition plan to the user.

[1334] The "feedback collection means" is a means for collecting feedback from the user regarding the nutrition plan and reflecting this in the next plan generation.

[1335] The "learning means" is a means of updating the generative AI model by using collected feedback and emotional data as training data.

[1336] The "service provision means" is a means for providing meals based on a personalized nutrition plan and delivering them to the user.

[1337] MODE FOR CARRYING OUT THE INVENTION

[1338] The present invention relates to a system for generating and providing personalized nutrition plans for athletes and health-conscious individuals, which includes a data collection means, a pre-processing means, a generation means, an information provision means, a feedback collection means, a learning means, and a service provision means.

[1339] System Overview

[1340] When a user uses the system, they enter their physical data (height, weight, age), training information (type of exercise, time, intensity), and lifestyle habits (sleep time, dietary details) through a smartphone app. The smartphone app also connects to fitness trackers and activity monitors to automatically collect daily exercise data (number of steps, heart rate). Emotional data is also collected by the emotion engine.

[1341] Data collection and preprocessing

[1342] The collected data is sent from the smartphone app to a server, where it is preprocessed. The preprocessing means converts the collected data into a unified format, complements missing data, and corrects outliers. Emotion data is also collected by the emotion engine and preprocessed in the same way.

[1343] Generate a nutrition plan

[1344] The server then uses a generation means to input the preprocessed data into a generative AI model. This generative AI model is trained based on the latest medical data and generates an individualized nutrition plan. The generated nutrition plan is sent to a smartphone app via an information provision means and presented to the user. The presented nutrition plan includes specific breakfast, lunch, and dinner menus and recommended nutritional supplements.

[1345] Gathering feedback and updating the model

[1346] Users input feedback about the provided nutrition plan into the smartphone app. The feedback includes information such as satisfaction with the meal and changes in physical condition. The feedback also includes emotional data acquired by the emotion engine. This feedback is sent from the smartphone app to the server, and the data is collected by the feedback collection means. Based on the collected feedback and emotional data, the server uses the learning means to update the generative AI model and continuously improve the accuracy of the model.

[1347] Specific examples

[1348] For example, if the user enters the following parameters:

[1349] Height: 175cm

[1350] Weight: 70kg

[1351] Age: 28

[1352] Regular exercise: Running three times a week

[1353] Emotional state: Fatigue

[1354] Based on this data, the following prompt is input to the generative AI model:

[1355] Generate a meal plan for an athlete: {height: 175, weight: 70, age: 28, training_info: {frequency: 3, type: 'running'}, lifestyle: {hours of sleep: 8, diet: 'balanced diet'}, emotion_data: 'fatigue'}

[1356] The generative AI model generates a nutrition plan that recommends oatmeal and blueberries for breakfast, chicken salad for lunch, grilled salmon and roasted vegetables for dinner, and a protein shake as a nutritional supplement. The plan is presented to the user via a smartphone app, and the user can enter feedback on the plan.

[1357] As a result, users can efficiently obtain a personalized nutrition plan and be provided with appropriate meals quickly, thereby improving performance and maintaining health.

[1358] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1359] Step 1:

[1360] Using a smartphone app, users input physical data such as height, weight, and age, as well as training information, lifestyle habits, and emotional data, which are then stored in the app according to the input format.

[1361] Input: physical data, training information, lifestyle data, emotional data

[1362] Output: The entered data is saved in the app.

[1363] Step 2:

[1364] In addition to data entered by the user, the smartphone app works with fitness trackers and activity monitors to automatically collect daily exercise data (e.g., number of steps, heart rate), which is then periodically sent to a server.

[1365] Input: Exercise data from fitness trackers and activity monitors

[1366] Output: The exercise data is sent to the server.

[1367] Step 3:

[1368] The server preprocesses the received data using preprocessing means, specifically converting the data into a unified format (e.g., JSON), filling in missing data, and correcting outliers.

[1369] Input: Collected data (physical data, exercise data, lifestyle data, emotional data)

[1370] Output: Preprocessed data

[1371] Step 4:

[1372] The server inputs the preprocessed data into the generative AI model via a generating means, and generates a personalized nutrition plan by forming a prompt sentence and sending it to the generative AI model.

[1373] Input: Preprocessed data

[1374] Output: A personalized nutrition plan generated by the generative AI model

[1375] Step 5:

[1376] The server sends the generated nutrition plan to the smartphone app via the information providing means, and the user can check their own nutrition plan through the smartphone app.

[1377] Input: Generated nutrition plan

[1378] Output: Nutrition plan sent to smartphone app

[1379] Step 6:

[1380] Users follow the provided nutrition plan and then enter feedback into a smartphone app, including their satisfaction with the meal and any changes in their physical condition.

[1381] Input: User feedback

[1382] Output: Feedback stored in the smartphone app

[1383] Step 7:

[1384] The server receives feedback from the smartphone app and collects it using a feedback collection means, which is then used as reference data for the nutrition plan that is generated.

[1385] Input: Feedback from smartphone app

[1386] Output: Collected feedback data

[1387] Step 8:

[1388] Finally, the server uses learning methods to continuously update the generative AI model based on collected feedback and emotion data, improving the model's accuracy.

[1389] Input: Collected feedback and sentiment data

[1390] Output: Updated generative AI model

[1391] Through the above processing steps, the user can always obtain the latest individually optimized nutrition plan, enabling them to efficiently improve their performance and maintain their health.

[1392] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1393] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1394] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1395] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1396] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1397] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1398] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1399] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1400] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1401] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1402] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1403] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1404] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1405] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1406] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1407] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1408] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1409] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1410] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1411] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1412] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1413] The following is further disclosed regarding the above embodiment.

[1414] (Claim 1)

[1415] data collection means;

[1416] A pre-processing means;

[1417] generating means;

[1418] Means of providing information;

[1419] a feedback collection means;

[1420] Learning tools and

[1421] A system including:

[1422] (Claim 2)

[1423] 2. The system according to claim 1, wherein the data collection means is means for collecting physical data, training information, and lifestyle habit data.

[1424] (Claim 3)

[1425] The system of claim 1, wherein the generating means is a means for generating an individualized nutrition plan based on a generative AI model that learns the latest medical data.

[1426] (Claim 4)

[1427] 2. The system according to claim 1, wherein the information providing means is a means for presenting the nutrition plan generated by the generating means.

[1428] (Claim 5)

[1429] 2. The system according to claim 1, wherein the feedback collection means is a means for collecting feedback from users and updating the generative AI model in the learning means.

[1430] "Example 1"

[1431] (Claim 1)

[1432] data collection means;

[1433] A pre-processing means;

[1434] generating means;

[1435] Means of providing information;

[1436] a feedback collection means;

[1437] Learning tools and

[1438] A means for transmitting the nutrition plan generated by the generating means to a user terminal;

[1439] A means for updating the generative AI model based on the feedback collected by the feedback collection means;

[1440] A system including:

[1441] (Claim 2)

[1442] The system of claim 1, wherein the data collection means is a means for collecting physical data, training information, lifestyle data entered by a user, and exercise data automatically collected from an activity monitor or fitness tracker.

[1443] (Claim 3)

[1444] The system according to claim 1, characterized in that the generating means generates an individual nutrition plan based on a generating AI model that learns the latest medical data and presents it to the user terminal via the information providing means.

[1445] "Application Example 1"

[1446] (Claim 1)

[1447] data collection means;

[1448] A pre-processing means;

[1449] generating means;

[1450] Means of providing information;

[1451] a feedback collection means;

[1452] Learning tools and

[1453] a means to view personalized nutrition plans in real time through devices such as smart glasses;

[1454] A system including:

[1455] (Claim 2)

[1456] The system according to claim 1, characterized in that the data collection means is a means for collecting physical data, training information, and lifestyle data, and automatically collects exercise data in cooperation with an activity meter or fitness tracker.

[1457] (Claim 3)

[1458] The system according to claim 1, characterized in that the generating means generates an individual nutrition plan based on a generative AI model that learns the latest medical data, and the generated nutrition plan is displayed on a device such as smart glasses.

[1459] "Example 2: Combining Emotion Engines"

[1460] (Claim 1)

[1461] data collection means;

[1462] A pre-processing means;

[1463] generating means;

[1464] Means of providing information;

[1465] a feedback collection means;

[1466] Learning tools and

[1467] A system that includes an emotion engine.

[1468] (Claim 2)

[1469] 2. The system according to claim 1, wherein the data collection means is means for collecting individual physical data, exercise information, lifestyle habit data, and emotion data.

[1470] (Claim 3)

[1471] The system according to claim 1, characterized in that the generating means is a means for generating an individual nutrition plan that takes into account the user's physical data, exercise information, lifestyle data, and emotional data based on a generating AI model that has learned the latest medical data.

[1472] "Application example 2 when combining emotion engines"

[1473] (Claim 1)

[1474] data collection means;

[1475] A pre-processing means;

[1476] generating means;

[1477] Means of providing information;

[1478] a feedback collection means;

[1479] Learning tools and

[1480] a service delivery method for providing meals based on a personalized nutrition plan;

[1481] A system including:

[1482] (Claim 2)

[1483] 2. The system of claim 1, wherein the data collection means is a means for collecting physical data, training information, lifestyle habits, and emotional data.

[1484] (Claim 3)

[1485] The system of claim 1, wherein the generating means is a means for generating an individualized nutrition plan based on a generative AI model that learns the latest medical data. [Explanation of symbols]

[1486] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. data collection means; A pre-processing means; generating means; Means of providing information; a feedback collection means; Learning tools and A system including:

2. 2. The system according to claim 1, wherein said data collection means is means for collecting physical data, training information, and lifestyle habit data.

3. The system according to claim 1, wherein the generating means is a means for generating an individual nutrition plan based on a generative AI model that learns the latest medical data.

4. 2. The system according to claim 1, wherein the information providing means is a means for presenting the nutrition plan generated by the generating means.

5. 2. The system according to claim 1, wherein the feedback collection means is a means for collecting feedback from users and updating the generative AI model in the learning means.

Images